From c0b5e732575c836564c50bef00ab25c031cefa44 Mon Sep 17 00:00:00 2001
From: xiaolongsun <95378566+xiaolong0728@users.noreply.github.com>
Date: Thu, 6 Mar 2025 10:37:14 +0100
Subject: [PATCH 1/2] delete notebooks

---
 .../blank_space/notebooks/notebook001.ipynb   |   59 -
 .../notebooks/ESCWA_model.ipynb               | 1712 -----------------
 .../notebooks/ESCWA_script_outputs.ipynb      |  831 --------
 .../orange_pasta/notebooks/notebook001.ipynb  |  242 ---
 models/orange_pasta/notebooks/test.ipynb      | 1263 ------------
 5 files changed, 4107 deletions(-)
 delete mode 100644 models/blank_space/notebooks/notebook001.ipynb
 delete mode 100644 models/electric_relaxation/notebooks/ESCWA_model.ipynb
 delete mode 100644 models/electric_relaxation/notebooks/ESCWA_script_outputs.ipynb
 delete mode 100644 models/orange_pasta/notebooks/notebook001.ipynb
 delete mode 100644 models/orange_pasta/notebooks/test.ipynb

diff --git a/models/blank_space/notebooks/notebook001.ipynb b/models/blank_space/notebooks/notebook001.ipynb
deleted file mode 100644
index 7353f17..0000000
--- a/models/blank_space/notebooks/notebook001.ipynb
+++ /dev/null
@@ -1,59 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-06-19T15:22:14.778930Z",
-     "start_time": "2024-06-19T15:22:14.386096Z"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": "                       step_pred_1  step_pred_2  step_pred_3  step_pred_4  \\\nmonth_id priogrid_gid                                                       \n530      62356            0.256551     0.227557     0.488913     0.209929   \n         79599            0.099671     0.146406     0.054649     0.092609   \n         79600            0.099671     0.170610     0.050000     0.178800   \n         79601            0.107438     0.146406     0.047399     0.089084   \n         80317            0.130778     0.185889     0.124451     0.135041   \n...                            ...          ...          ...          ...   \n         190496           0.058204     0.176467     0.041248     0.106065   \n         190507           0.069155     0.182948     0.038348     0.134397   \n         190508           0.063567     0.227789     0.097442     0.265889   \n         190510           0.071951     0.122570     0.012769     0.070929   \n         190511           0.069119     0.179973     0.032913     0.134397   \n\n                       step_pred_5  step_pred_6  step_pred_7  step_pred_8  \\\nmonth_id priogrid_gid                                                       \n530      62356            0.171139     0.152381     0.137336     0.382111   \n         79599            0.129852     0.136078     0.152552     0.173713   \n         79600            0.132606     0.136078     0.152559     0.170128   \n         79601            0.129982     0.145943     0.155419     0.179366   \n         80317            0.337237     0.437653     0.276352     0.213474   \n...                            ...          ...          ...          ...   \n         190496           0.118471     0.109181     0.114734     0.132791   \n         190507           0.067830     0.090494     0.094558     0.088219   \n         190508           0.436198     0.123455     0.169900     0.190923   \n         190510           0.068710     0.094915     0.070891     0.084737   \n         190511           0.072538     0.092565     0.093797     0.085655   \n\n                       step_pred_9  step_pred_10  ...  step_pred_27  \\\nmonth_id priogrid_gid                             ...                 \n530      62356            0.074186      0.521652  ...      0.144984   \n         79599            0.088084      0.124625  ...      0.054416   \n         79600            0.083449      0.128840  ...      0.060085   \n         79601            0.091251      0.152769  ...      0.055616   \n         80317            0.117918      0.288680  ...      2.309169   \n...                            ...           ...  ...           ...   \n         190496           0.070404      0.124292  ...      0.297846   \n         190507           0.173334      0.185612  ...      0.050816   \n         190508           0.239198      0.369074  ...      0.078425   \n         190510           0.064074      0.162256  ...      0.059743   \n         190511           0.173334      0.184369  ...      0.060692   \n\n                       step_pred_28  step_pred_29  step_pred_30  step_pred_31  \\\nmonth_id priogrid_gid                                                           \n530      62356             0.124197      0.134879      0.082405      0.138085   \n         79599             0.083813      0.107177      0.046228      0.081775   \n         79600             0.108221      0.095936      0.067836      0.105831   \n         79601             0.080253      0.106711      0.043890      0.079113   \n         80317             2.457354      2.063124      1.998081      1.867917   \n...                             ...           ...           ...           ...   \n         190496            0.263001      0.236426      0.124861      0.193002   \n         190507            0.048083      0.054207      0.043791      0.036109   \n         190508            0.091809      0.116149      0.054405      0.048250   \n         190510            0.057398      0.065735      0.047897      0.040076   \n         190511            0.055820      0.061413      0.046755      0.039636   \n\n                       step_pred_32  step_pred_33  step_pred_34  step_pred_35  \\\nmonth_id priogrid_gid                                                           \n530      62356             0.157001      0.109495      0.085181      0.134681   \n         79599             0.092314      0.095099      0.082592      0.082338   \n         79600             0.094867      0.094448      0.085848      0.082485   \n         79601             0.087037      0.093762      0.081972      0.078679   \n         80317             2.782171      3.282382      4.118517      0.753506   \n...                             ...           ...           ...           ...   \n         190496            0.302993      0.258323      0.212761      0.181067   \n         190507            0.059182      0.059286      0.060531      0.054909   \n         190508            0.109811      0.101721      0.121025      0.122890   \n         190510            0.064052      0.066666      0.064360      0.058652   \n         190511            0.064052      0.066666      0.064360      0.055670   \n\n                       step_pred_36  \nmonth_id priogrid_gid                \n530      62356             0.157107  \n         79599             0.061527  \n         79600             0.061588  \n         79601             0.061795  \n         80317             0.715522  \n...                             ...  \n         190496            0.365574  \n         190507            0.055392  \n         190508            0.146741  \n         190510            0.057022  \n         190511            0.058225  \n\n[13110 rows x 36 columns]",
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th></th>\n      <th>step_pred_1</th>\n      <th>step_pred_2</th>\n      <th>step_pred_3</th>\n      <th>step_pred_4</th>\n      <th>step_pred_5</th>\n      <th>step_pred_6</th>\n      <th>step_pred_7</th>\n      <th>step_pred_8</th>\n      <th>step_pred_9</th>\n      <th>step_pred_10</th>\n      <th>...</th>\n      <th>step_pred_27</th>\n      <th>step_pred_28</th>\n      <th>step_pred_29</th>\n      <th>step_pred_30</th>\n      <th>step_pred_31</th>\n      <th>step_pred_32</th>\n      <th>step_pred_33</th>\n      <th>step_pred_34</th>\n      <th>step_pred_35</th>\n      <th>step_pred_36</th>\n    </tr>\n    <tr>\n      <th>month_id</th>\n      <th>priogrid_gid</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th rowspan=\"11\" valign=\"top\">530</th>\n      <th>62356</th>\n      <td>0.256551</td>\n      <td>0.227557</td>\n      <td>0.488913</td>\n      <td>0.209929</td>\n      <td>0.171139</td>\n      <td>0.152381</td>\n      <td>0.137336</td>\n      <td>0.382111</td>\n      <td>0.074186</td>\n      <td>0.521652</td>\n      <td>...</td>\n      <td>0.144984</td>\n      <td>0.124197</td>\n      <td>0.134879</td>\n      <td>0.082405</td>\n      <td>0.138085</td>\n      <td>0.157001</td>\n      <td>0.109495</td>\n      <td>0.085181</td>\n      <td>0.134681</td>\n      <td>0.157107</td>\n    </tr>\n    <tr>\n      <th>79599</th>\n      <td>0.099671</td>\n      <td>0.146406</td>\n      <td>0.054649</td>\n      <td>0.092609</td>\n      <td>0.129852</td>\n      <td>0.136078</td>\n      <td>0.152552</td>\n      <td>0.173713</td>\n      <td>0.088084</td>\n      <td>0.124625</td>\n      <td>...</td>\n      <td>0.054416</td>\n      <td>0.083813</td>\n      <td>0.107177</td>\n      <td>0.046228</td>\n      <td>0.081775</td>\n      <td>0.092314</td>\n      <td>0.095099</td>\n      <td>0.082592</td>\n      <td>0.082338</td>\n      <td>0.061527</td>\n    </tr>\n    <tr>\n      <th>79600</th>\n      <td>0.099671</td>\n      <td>0.170610</td>\n      <td>0.050000</td>\n      <td>0.178800</td>\n      <td>0.132606</td>\n      <td>0.136078</td>\n      <td>0.152559</td>\n      <td>0.170128</td>\n      <td>0.083449</td>\n      <td>0.128840</td>\n      <td>...</td>\n      <td>0.060085</td>\n      <td>0.108221</td>\n      <td>0.095936</td>\n      <td>0.067836</td>\n      <td>0.105831</td>\n      <td>0.094867</td>\n      <td>0.094448</td>\n      <td>0.085848</td>\n      <td>0.082485</td>\n      <td>0.061588</td>\n    </tr>\n    <tr>\n      <th>79601</th>\n      <td>0.107438</td>\n      <td>0.146406</td>\n      <td>0.047399</td>\n      <td>0.089084</td>\n      <td>0.129982</td>\n      <td>0.145943</td>\n      <td>0.155419</td>\n      <td>0.179366</td>\n      <td>0.091251</td>\n      <td>0.152769</td>\n      <td>...</td>\n      <td>0.055616</td>\n      <td>0.080253</td>\n      <td>0.106711</td>\n      <td>0.043890</td>\n      <td>0.079113</td>\n      <td>0.087037</td>\n      <td>0.093762</td>\n      <td>0.081972</td>\n      <td>0.078679</td>\n      <td>0.061795</td>\n    </tr>\n    <tr>\n      <th>80317</th>\n      <td>0.130778</td>\n      <td>0.185889</td>\n      <td>0.124451</td>\n      <td>0.135041</td>\n      <td>0.337237</td>\n      <td>0.437653</td>\n      <td>0.276352</td>\n      <td>0.213474</td>\n      <td>0.117918</td>\n      <td>0.288680</td>\n      <td>...</td>\n      <td>2.309169</td>\n      <td>2.457354</td>\n      <td>2.063124</td>\n      <td>1.998081</td>\n      <td>1.867917</td>\n      <td>2.782171</td>\n      <td>3.282382</td>\n      <td>4.118517</td>\n      <td>0.753506</td>\n      <td>0.715522</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>190496</th>\n      <td>0.058204</td>\n      <td>0.176467</td>\n      <td>0.041248</td>\n      <td>0.106065</td>\n      <td>0.118471</td>\n      <td>0.109181</td>\n      <td>0.114734</td>\n      <td>0.132791</td>\n      <td>0.070404</td>\n      <td>0.124292</td>\n      <td>...</td>\n      <td>0.297846</td>\n      <td>0.263001</td>\n      <td>0.236426</td>\n      <td>0.124861</td>\n      <td>0.193002</td>\n      <td>0.302993</td>\n      <td>0.258323</td>\n      <td>0.212761</td>\n      <td>0.181067</td>\n      <td>0.365574</td>\n    </tr>\n    <tr>\n      <th>190507</th>\n      <td>0.069155</td>\n      <td>0.182948</td>\n      <td>0.038348</td>\n      <td>0.134397</td>\n      <td>0.067830</td>\n      <td>0.090494</td>\n      <td>0.094558</td>\n      <td>0.088219</td>\n      <td>0.173334</td>\n      <td>0.185612</td>\n      <td>...</td>\n      <td>0.050816</td>\n      <td>0.048083</td>\n      <td>0.054207</td>\n      <td>0.043791</td>\n      <td>0.036109</td>\n      <td>0.059182</td>\n      <td>0.059286</td>\n      <td>0.060531</td>\n      <td>0.054909</td>\n      <td>0.055392</td>\n    </tr>\n    <tr>\n      <th>190508</th>\n      <td>0.063567</td>\n      <td>0.227789</td>\n      <td>0.097442</td>\n      <td>0.265889</td>\n      <td>0.436198</td>\n      <td>0.123455</td>\n      <td>0.169900</td>\n      <td>0.190923</td>\n      <td>0.239198</td>\n      <td>0.369074</td>\n      <td>...</td>\n      <td>0.078425</td>\n      <td>0.091809</td>\n      <td>0.116149</td>\n      <td>0.054405</td>\n      <td>0.048250</td>\n      <td>0.109811</td>\n      <td>0.101721</td>\n      <td>0.121025</td>\n      <td>0.122890</td>\n      <td>0.146741</td>\n    </tr>\n    <tr>\n      <th>190510</th>\n      <td>0.071951</td>\n      <td>0.122570</td>\n      <td>0.012769</td>\n      <td>0.070929</td>\n      <td>0.068710</td>\n      <td>0.094915</td>\n      <td>0.070891</td>\n      <td>0.084737</td>\n      <td>0.064074</td>\n      <td>0.162256</td>\n      <td>...</td>\n      <td>0.059743</td>\n      <td>0.057398</td>\n      <td>0.065735</td>\n      <td>0.047897</td>\n      <td>0.040076</td>\n      <td>0.064052</td>\n      <td>0.066666</td>\n      <td>0.064360</td>\n      <td>0.058652</td>\n      <td>0.057022</td>\n    </tr>\n    <tr>\n      <th>190511</th>\n      <td>0.069119</td>\n      <td>0.179973</td>\n      <td>0.032913</td>\n      <td>0.134397</td>\n      <td>0.072538</td>\n      <td>0.092565</td>\n      <td>0.093797</td>\n      <td>0.085655</td>\n      <td>0.173334</td>\n      <td>0.184369</td>\n      <td>...</td>\n      <td>0.060692</td>\n      <td>0.055820</td>\n      <td>0.061413</td>\n      <td>0.046755</td>\n      <td>0.039636</td>\n      <td>0.064052</td>\n      <td>0.066666</td>\n      <td>0.064360</td>\n      <td>0.055670</td>\n      <td>0.058225</td>\n    </tr>\n  </tbody>\n</table>\n<p>13110 rows × 36 columns</p>\n</div>"
-     },
-     "execution_count": 1,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "import pandas as pd\n",
-    "pd.read_parquet(\"../data/generated/generated.parquet\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "outputs": [],
-   "source": [],
-   "metadata": {
-    "collapsed": false
-   }
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "viewser",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/models/electric_relaxation/notebooks/ESCWA_model.ipynb b/models/electric_relaxation/notebooks/ESCWA_model.ipynb
deleted file mode 100644
index 88709fd..0000000
--- a/models/electric_relaxation/notebooks/ESCWA_model.ipynb
+++ /dev/null
@@ -1,1712 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# ViEWS-ESCWA model respecified in VIEWS 3 form\n",
-    "-- without the Retrain and Retrieve wrapper"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Basics\n",
-    "import numpy as np\n",
-    "import pandas as pd\n",
-    "# Views 3\n",
-    "import views_runs\n",
-    "from viewser.operations import fetch\n",
-    "#from views_forecasts.extensions import *\n",
-    "from viewser import Queryset, Column\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "/Users/sarakallis/Documents/PRIO Local/views_pipeline/models/electric_relaxation/notebooks\n"
-     ]
-    }
-   ],
-   "source": [
-    "! pwd"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# turn into: src/dataloaders/get_forecasting_data.py"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      " .    "
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th>ged_sb_dep</th>\n",
-       "      <th>ged_sb_dummy_t0</th>\n",
-       "      <th>ged_os_dummy_t0</th>\n",
-       "      <th>ged_ns_dummy_t0</th>\n",
-       "      <th>ged_sb_dummy_t1</th>\n",
-       "      <th>ged_sb_dummy_t2</th>\n",
-       "      <th>ged_sb_dummy_t3</th>\n",
-       "      <th>_ged_sb_dummy_t3</th>\n",
-       "      <th>ged_sb_dummy_t4</th>\n",
-       "      <th>ged_sb_dummy_t5</th>\n",
-       "      <th>...</th>\n",
-       "      <th>decay_ged_ns_1</th>\n",
-       "      <th>decay_ged_ns_5</th>\n",
-       "      <th>decay_ged_ns_25</th>\n",
-       "      <th>decay_ged_ns_100</th>\n",
-       "      <th>splag_1_decay_ged_sb_25</th>\n",
-       "      <th>splag_1_decay_ged_sb_500</th>\n",
-       "      <th>splag_1_decay_ged_os_25</th>\n",
-       "      <th>splag_1_decay_ged_os_500</th>\n",
-       "      <th>splag_1_decay_ged_ns_25</th>\n",
-       "      <th>splag_1_decay_ged_ns_500</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>month_id</th>\n",
-       "      <th>country_id</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th rowspan=\"5\" valign=\"top\">1</th>\n",
-       "      <th>1</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>5 rows × 44 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                     ged_sb_dep  ged_sb_dummy_t0  ged_os_dummy_t0  \\\n",
-       "month_id country_id                                                 \n",
-       "1        1                  0.0              0.0              0.0   \n",
-       "         2                  0.0              0.0              0.0   \n",
-       "         3                  0.0              0.0              0.0   \n",
-       "         4                  0.0              0.0              0.0   \n",
-       "         5                  0.0              0.0              0.0   \n",
-       "\n",
-       "                     ged_ns_dummy_t0  ged_sb_dummy_t1  ged_sb_dummy_t2  \\\n",
-       "month_id country_id                                                      \n",
-       "1        1                       0.0              0.0              0.0   \n",
-       "         2                       0.0              0.0              0.0   \n",
-       "         3                       0.0              0.0              0.0   \n",
-       "         4                       0.0              0.0              0.0   \n",
-       "         5                       0.0              0.0              0.0   \n",
-       "\n",
-       "                     ged_sb_dummy_t3  _ged_sb_dummy_t3  ged_sb_dummy_t4  \\\n",
-       "month_id country_id                                                       \n",
-       "1        1                       0.0               0.0              0.0   \n",
-       "         2                       0.0               0.0              0.0   \n",
-       "         3                       0.0               0.0              0.0   \n",
-       "         4                       0.0               0.0              0.0   \n",
-       "         5                       0.0               0.0              0.0   \n",
-       "\n",
-       "                     ged_sb_dummy_t5  ...  decay_ged_ns_1  decay_ged_ns_5  \\\n",
-       "month_id country_id                   ...                                   \n",
-       "1        1                       0.0  ...             0.0             0.0   \n",
-       "         2                       0.0  ...             0.0             0.0   \n",
-       "         3                       0.0  ...             0.0             0.0   \n",
-       "         4                       0.0  ...             0.0             0.0   \n",
-       "         5                       0.0  ...             0.0             0.0   \n",
-       "\n",
-       "                     decay_ged_ns_25  decay_ged_ns_100  \\\n",
-       "month_id country_id                                      \n",
-       "1        1                       0.0               0.0   \n",
-       "         2                       0.0               0.0   \n",
-       "         3                       0.0               0.0   \n",
-       "         4                       0.0               0.0   \n",
-       "         5                       0.0               0.0   \n",
-       "\n",
-       "                     splag_1_decay_ged_sb_25  splag_1_decay_ged_sb_500  \\\n",
-       "month_id country_id                                                      \n",
-       "1        1                               0.0                       0.0   \n",
-       "         2                               0.0                       0.0   \n",
-       "         3                               0.0                       0.0   \n",
-       "         4                               0.0                       0.0   \n",
-       "         5                               0.0                       0.0   \n",
-       "\n",
-       "                     splag_1_decay_ged_os_25  splag_1_decay_ged_os_500  \\\n",
-       "month_id country_id                                                      \n",
-       "1        1                               0.0                       0.0   \n",
-       "         2                               0.0                       0.0   \n",
-       "         3                               0.0                       0.0   \n",
-       "         4                               0.0                       0.0   \n",
-       "         5                               0.0                       0.0   \n",
-       "\n",
-       "                     splag_1_decay_ged_ns_25  splag_1_decay_ged_ns_500  \n",
-       "month_id country_id                                                     \n",
-       "1        1                               0.0                       0.0  \n",
-       "         2                               0.0                       0.0  \n",
-       "         3                               0.0                       0.0  \n",
-       "         4                               0.0                       0.0  \n",
-       "         5                               0.0                       0.0  \n",
-       "\n",
-       "[5 rows x 44 columns]"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "qs_cm_cflong  = (Queryset(\"escwa001_cflong\", \"country_month\")\n",
-    "                # target variable\n",
-    "                .with_column(Column(\"ged_sb_dep\", from_table=\"ged2_cm\", from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                # timelag 0 of target variable\n",
-    "                .with_column(Column(\"ged_sb_dummy_t0\", from_table=\"ged2_cm\", from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                # further timelags of target variable\n",
-    "                # sb\n",
-    "                .with_column(Column(\"ged_sb_dummy_t1\", from_table=\"ged2_cm\", from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(1)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_sb_dummy_t2\", from_table=\"ged2_cm\", from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(2)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_sb_dummy_t3\", from_table=\"ged2_cm\", from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(1)\n",
-    "                            .transform.missing.fill()\n",
-    "                            ) \n",
-    "                .with_column(Column(\"ged_sb_dummy_t3\", from_table=\"ged2_cm\", from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(1)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )  \n",
-    "                .with_column(Column(\"ged_sb_dummy_t4\", from_table=\"ged2_cm\", from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(4)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_sb_dummy_t5\", from_table=\"ged2_cm\", from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(5)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_sb_dummy_t6\", from_table=\"ged2_cm\", from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(6)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                        \n",
-    "                # os\n",
-    "                .with_column(Column(\"ged_os_dummy_t0\", from_table=\"ged2_cm\", from_column=\"ged_os_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_os_dummy_t1\", from_table=\"ged2_cm\", from_column=\"ged_os_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(1)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_os_dummy_t2\", from_table=\"ged2_cm\", from_column=\"ged_os_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(2)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_os_dummy_t3\", from_table=\"ged2_cm\", from_column=\"ged_os_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(1)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_os_dummy_t3\", from_table=\"ged2_cm\", from_column=\"ged_os_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(1)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )                     \n",
-    "                .with_column(Column(\"ged_os_dummy_t4\", from_table=\"ged2_cm\", from_column=\"ged_os_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(4)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_os_dummy_t5\", from_table=\"ged2_cm\", from_column=\"ged_os_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(5)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_os_dummy_t6\", from_table=\"ged2_cm\", from_column=\"ged_os_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(6)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                # ns\n",
-    "                .with_column(Column(\"ged_ns_dummy_t0\", from_table=\"ged2_cm\", from_column=\"ged_ns_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_ns_dummy_t1\", from_table=\"ged2_cm\", from_column=\"ged_ns_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(1)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_ns_dummy_t2\", from_table=\"ged2_cm\", from_column=\"ged_ns_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(2)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_ns_dummy_t3\", from_table=\"ged2_cm\", from_column=\"ged_ns_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(1)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_ns_dummy_t3\", from_table=\"ged2_cm\", from_column=\"ged_ns_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(1)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )  \n",
-    "                .with_column(Column(\"ged_ns_dummy_t4\", from_table=\"ged2_cm\", from_column=\"ged_ns_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(4)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_ns_dummy_t5\", from_table=\"ged2_cm\", from_column=\"ged_ns_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(5)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                .with_column(Column(\"ged_ns_dummy_t6\", from_table=\"ged2_cm\", from_column=\"ged_ns_best_sum_nokgi\")\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.missing.fill()\n",
-    "                            .transform.temporal.tlag(6)\n",
-    "                            .transform.missing.fill()\n",
-    "                            )\n",
-    "                # Decay functions\n",
-    "                # sb\n",
-    "                .with_column(Column(\"decay_ged_sb_1\", from_table=\"ged2_cm\", from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(1)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                .with_column(Column(\"decay_ged_sb_5\", from_table=\"ged2_cm\", from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(5)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                .with_column(Column(\"decay_ged_sb_25\", from_table=\"ged2_cm\", from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                .with_column(Column(\"decay_ged_sb_100\", from_table=\"ged2_cm\", from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(100)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                .with_column(Column(\"decay_ged_sb_500\", from_table=\"ged2_cm\", from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(500)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                # os\n",
-    "                \n",
-    "                .with_column(Column(\"decay_ged_os_1\", from_table=\"ged2_cm\", from_column=\"ged_os_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(1)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                .with_column(Column(\"decay_ged_os_5\", from_table=\"ged2_cm\", from_column=\"ged_os_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(5)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                .with_column(Column(\"decay_ged_os_25\", from_table=\"ged2_cm\", from_column=\"ged_os_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                .with_column(Column(\"decay_ged_os_100\", from_table=\"ged2_cm\", from_column=\"ged_os_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(100)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )         \n",
-    "                        \n",
-    "                # ns\n",
-    "                .with_column(Column(\"decay_ged_ns_1\", from_table=\"ged2_cm\", from_column=\"ged_ns_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(1)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                .with_column(Column(\"decay_ged_ns_5\", from_table=\"ged2_cm\", from_column=\"ged_ns_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(5)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                .with_column(Column(\"decay_ged_ns_25\", from_table=\"ged2_cm\", from_column=\"ged_ns_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                .with_column(Column(\"decay_ged_ns_100\", from_table=\"ged2_cm\", from_column=\"ged_ns_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(100)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                        \n",
-    "                # Spatial lag decay functions\n",
-    "                        # sb\n",
-    "                .with_column(Column(\"splag_1_decay_ged_sb_25\", from_table=\"ged2_cm\",\n",
-    "                                    from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.spatial.countrylag(1, 1, 0, 0)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "\n",
-    "                .with_column(Column(\"splag_1_decay_ged_sb_500\", from_table=\"ged2_cm\",\n",
-    "                                    from_column=\"ged_sb_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(500)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.spatial.countrylag(1, 1, 0, 0)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                # os\n",
-    "                .with_column(Column(\"splag_1_decay_ged_os_25\", from_table=\"ged2_cm\",\n",
-    "                                    from_column=\"ged_os_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.spatial.countrylag(1, 1, 0, 0)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                .with_column(Column(\"splag_1_decay_ged_os_500\", from_table=\"ged2_cm\",\n",
-    "                                    from_column=\"ged_os_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(500)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.spatial.countrylag(1, 1, 0, 0)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                # ns\n",
-    "                .with_column(Column(\"splag_1_decay_ged_ns_25\", from_table=\"ged2_cm\",\n",
-    "                                    from_column=\"ged_ns_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(25)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.spatial.countrylag(1, 1, 0, 0)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "                .with_column(Column(\"splag_1_decay_ged_ns_500\", from_table=\"ged2_cm\",\n",
-    "                                    from_column=\"ged_ns_best_sum_nokgi\")\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            .transform.bool.gte(500)\n",
-    "                            .transform.temporal.time_since()\n",
-    "                            .transform.temporal.decay(24)\n",
-    "                            .transform.spatial.countrylag(1, 1, 0, 0)\n",
-    "                            .transform.missing.replace_na()\n",
-    "                            )\n",
-    "            \n",
-    "                .with_theme(\"views-escwa\")\n",
-    "                .describe(\"\"\"Views-escwa conflict history, cm level\n",
-    "\n",
-    "\n",
-    "                            \"\"\")\n",
-    "                )\n",
-    "\n",
-    "#data = qs_cm_cflong.publish().fetch()\n",
-    "data = qs_cm_cflong.fetch()\n",
-    "# Recast all columns to float because of an excessive assert in the stepshift library\n",
-    "data = data.astype(float)\n",
-    "data.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# configs/config_common or configs/config_partitioner"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor\n",
-    "from stepshift.views import StepshiftedModels\n",
-    "# Parameters for the model  \n",
-    "steps = [*range(1, 36+1, 1)] # Which steps to train and predict for\n",
-    "#steps = [1,3,6] # Shortened set of steps for the impatient\n",
-    "target = 'ged_sb_dep'\n",
-    "\n",
-    "calib_partitioner_dict = {\"train\":(121,396),\"predict\":(409,456)}\n",
-    "test_partitioner_dict = {\"train\":(121,456),\"predict\":(457,504)}\n",
-    "future_partitioner_dict = {\"train\":(121,504),\"predict\":(529,529)}\n",
-    "\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# src/training/train_forecasting_model.py"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "calib_partition = views_runs.DataPartitioner({'calib':calib_partitioner_dict}) #stepshifter implementation (views_runs is a class)\n",
-    "future_partition = views_runs.DataPartitioner({'future':future_partitioner_dict}) #stepshifter implementation \n",
-    "\n",
-    "# Fitting model\n",
-    "base_model = RandomForestClassifier(n_estimators=100, n_jobs=-2)\n",
-    "stepshifter_def = StepshiftedModels(base_model,steps,target)\n",
-    "\n",
-    "# Fitting for calibration run, calibration partition\n",
-    "stepshifter_model_calib = views_runs.ViewsRun(calib_partition,stepshifter_def)\n",
-    "stepshifter_model_calib.fit('calib','train',data)\n",
-    "\n",
-    "# Fitting for future run, future partition\n",
-    "stepshifter_model_future = views_runs.ViewsRun(future_partition,stepshifter_def)\n",
-    "stepshifter_model_future.fit('future','train',data)\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# src/forecasting/generate_forecast.py"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Predictions for test partition:\n",
-    "calib_predictions = stepshifter_model_calib.predict('calib','predict',data, proba=True)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th>ged_sb_dep</th>\n",
-       "      <th>ged_sb_dummy_t0</th>\n",
-       "      <th>ged_os_dummy_t0</th>\n",
-       "      <th>ged_ns_dummy_t0</th>\n",
-       "      <th>ged_sb_dummy_t1</th>\n",
-       "      <th>ged_sb_dummy_t2</th>\n",
-       "      <th>ged_sb_dummy_t3</th>\n",
-       "      <th>_ged_sb_dummy_t3</th>\n",
-       "      <th>ged_sb_dummy_t4</th>\n",
-       "      <th>ged_sb_dummy_t5</th>\n",
-       "      <th>...</th>\n",
-       "      <th>step_pred_33</th>\n",
-       "      <th>step_pred_34</th>\n",
-       "      <th>step_pred_35</th>\n",
-       "      <th>step_pred_36</th>\n",
-       "      <th>step_pred_4</th>\n",
-       "      <th>step_pred_5</th>\n",
-       "      <th>step_pred_6</th>\n",
-       "      <th>step_pred_7</th>\n",
-       "      <th>step_pred_8</th>\n",
-       "      <th>step_pred_9</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>month_id</th>\n",
-       "      <th>country_id</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th rowspan=\"5\" valign=\"top\">409</th>\n",
-       "      <th>1</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>5 rows × 80 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                     ged_sb_dep  ged_sb_dummy_t0  ged_os_dummy_t0  \\\n",
-       "month_id country_id                                                 \n",
-       "409      1                  0.0              0.0              0.0   \n",
-       "         2                  0.0              0.0              0.0   \n",
-       "         3                  0.0              0.0              0.0   \n",
-       "         4                  0.0              0.0              0.0   \n",
-       "         5                  0.0              0.0              0.0   \n",
-       "\n",
-       "                     ged_ns_dummy_t0  ged_sb_dummy_t1  ged_sb_dummy_t2  \\\n",
-       "month_id country_id                                                      \n",
-       "409      1                       0.0              0.0              0.0   \n",
-       "         2                       0.0              0.0              0.0   \n",
-       "         3                       0.0              0.0              0.0   \n",
-       "         4                       0.0              0.0              0.0   \n",
-       "         5                       0.0              0.0              0.0   \n",
-       "\n",
-       "                     ged_sb_dummy_t3  _ged_sb_dummy_t3  ged_sb_dummy_t4  \\\n",
-       "month_id country_id                                                       \n",
-       "409      1                       0.0               0.0              0.0   \n",
-       "         2                       0.0               0.0              0.0   \n",
-       "         3                       0.0               0.0              0.0   \n",
-       "         4                       0.0               0.0              0.0   \n",
-       "         5                       0.0               0.0              0.0   \n",
-       "\n",
-       "                     ged_sb_dummy_t5  ...  step_pred_33  step_pred_34  \\\n",
-       "month_id country_id                   ...                               \n",
-       "409      1                       0.0  ...           0.0           0.0   \n",
-       "         2                       0.0  ...           0.0           0.0   \n",
-       "         3                       0.0  ...           0.0           0.0   \n",
-       "         4                       0.0  ...           0.0           0.0   \n",
-       "         5                       0.0  ...           0.0           0.0   \n",
-       "\n",
-       "                     step_pred_35  step_pred_36  step_pred_4  step_pred_5  \\\n",
-       "month_id country_id                                                         \n",
-       "409      1                    0.0           0.0          0.0          0.0   \n",
-       "         2                    0.0           0.0          0.0          0.0   \n",
-       "         3                    0.0           0.0          0.0          0.0   \n",
-       "         4                    0.0           0.0          0.0          0.0   \n",
-       "         5                    0.0           0.0          0.0          0.0   \n",
-       "\n",
-       "                     step_pred_6  step_pred_7  step_pred_8  step_pred_9  \n",
-       "month_id country_id                                                      \n",
-       "409      1                   0.0          0.0          0.0          0.0  \n",
-       "         2                   0.0          0.0          0.0          0.0  \n",
-       "         3                   0.0          0.0          0.0          0.0  \n",
-       "         4                   0.0          0.0          0.0          0.0  \n",
-       "         5                   0.0          0.0          0.0          0.0  \n",
-       "\n",
-       "[5 rows x 80 columns]"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "calib_predictions.head()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>ged_sb_dep</th>\n",
-       "      <th>ged_sb_dummy_t0</th>\n",
-       "      <th>ged_os_dummy_t0</th>\n",
-       "      <th>ged_ns_dummy_t0</th>\n",
-       "      <th>ged_sb_dummy_t1</th>\n",
-       "      <th>ged_sb_dummy_t2</th>\n",
-       "      <th>ged_sb_dummy_t3</th>\n",
-       "      <th>_ged_sb_dummy_t3</th>\n",
-       "      <th>ged_sb_dummy_t4</th>\n",
-       "      <th>ged_sb_dummy_t5</th>\n",
-       "      <th>...</th>\n",
-       "      <th>step_pred_33</th>\n",
-       "      <th>step_pred_34</th>\n",
-       "      <th>step_pred_35</th>\n",
-       "      <th>step_pred_36</th>\n",
-       "      <th>step_pred_4</th>\n",
-       "      <th>step_pred_5</th>\n",
-       "      <th>step_pred_6</th>\n",
-       "      <th>step_pred_7</th>\n",
-       "      <th>step_pred_8</th>\n",
-       "      <th>step_pred_9</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>count</th>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>9168.0</td>\n",
-       "      <td>9168.0</td>\n",
-       "      <td>9168.0</td>\n",
-       "      <td>9168.0</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>mean</th>\n",
-       "      <td>0.075153</td>\n",
-       "      <td>0.075153</td>\n",
-       "      <td>0.033050</td>\n",
-       "      <td>0.036322</td>\n",
-       "      <td>0.075044</td>\n",
-       "      <td>0.074607</td>\n",
-       "      <td>0.075044</td>\n",
-       "      <td>0.075044</td>\n",
-       "      <td>0.073953</td>\n",
-       "      <td>0.073844</td>\n",
-       "      <td>...</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>0.074770</td>\n",
-       "      <td>0.074938</td>\n",
-       "      <td>0.075011</td>\n",
-       "      <td>0.074604</td>\n",
-       "      <td>0.074736</td>\n",
-       "      <td>0.074528</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>std</th>\n",
-       "      <td>0.263652</td>\n",
-       "      <td>0.263652</td>\n",
-       "      <td>0.178776</td>\n",
-       "      <td>0.187100</td>\n",
-       "      <td>0.263476</td>\n",
-       "      <td>0.262771</td>\n",
-       "      <td>0.263476</td>\n",
-       "      <td>0.263476</td>\n",
-       "      <td>0.261708</td>\n",
-       "      <td>0.261531</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.239002</td>\n",
-       "      <td>0.239331</td>\n",
-       "      <td>0.239643</td>\n",
-       "      <td>0.239266</td>\n",
-       "      <td>0.238990</td>\n",
-       "      <td>0.238090</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>min</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>25%</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>50%</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>75%</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>max</th>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>8 rows × 80 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "        ged_sb_dep  ged_sb_dummy_t0  ged_os_dummy_t0  ged_ns_dummy_t0  \\\n",
-       "count  9168.000000      9168.000000      9168.000000      9168.000000   \n",
-       "mean      0.075153         0.075153         0.033050         0.036322   \n",
-       "std       0.263652         0.263652         0.178776         0.187100   \n",
-       "min       0.000000         0.000000         0.000000         0.000000   \n",
-       "25%       0.000000         0.000000         0.000000         0.000000   \n",
-       "50%       0.000000         0.000000         0.000000         0.000000   \n",
-       "75%       0.000000         0.000000         0.000000         0.000000   \n",
-       "max       1.000000         1.000000         1.000000         1.000000   \n",
-       "\n",
-       "       ged_sb_dummy_t1  ged_sb_dummy_t2  ged_sb_dummy_t3  _ged_sb_dummy_t3  \\\n",
-       "count      9168.000000      9168.000000      9168.000000       9168.000000   \n",
-       "mean          0.075044         0.074607         0.075044          0.075044   \n",
-       "std           0.263476         0.262771         0.263476          0.263476   \n",
-       "min           0.000000         0.000000         0.000000          0.000000   \n",
-       "25%           0.000000         0.000000         0.000000          0.000000   \n",
-       "50%           0.000000         0.000000         0.000000          0.000000   \n",
-       "75%           0.000000         0.000000         0.000000          0.000000   \n",
-       "max           1.000000         1.000000         1.000000          1.000000   \n",
-       "\n",
-       "       ged_sb_dummy_t4  ged_sb_dummy_t5  ...  step_pred_33  step_pred_34  \\\n",
-       "count      9168.000000      9168.000000  ...        9168.0        9168.0   \n",
-       "mean          0.073953         0.073844  ...           inf           inf   \n",
-       "std           0.261708         0.261531  ...           NaN           NaN   \n",
-       "min           0.000000         0.000000  ...           0.0           0.0   \n",
-       "25%           0.000000         0.000000  ...           0.0           0.0   \n",
-       "50%           0.000000         0.000000  ...           0.0           0.0   \n",
-       "75%           0.000000         0.000000  ...           0.0           0.0   \n",
-       "max           1.000000         1.000000  ...           inf           inf   \n",
-       "\n",
-       "       step_pred_35  step_pred_36  step_pred_4  step_pred_5  step_pred_6  \\\n",
-       "count        9168.0        9168.0  9168.000000  9168.000000  9168.000000   \n",
-       "mean            inf           inf     0.074770     0.074938     0.075011   \n",
-       "std             NaN           NaN     0.239002     0.239331     0.239643   \n",
-       "min             0.0           0.0     0.000000     0.000000     0.000000   \n",
-       "25%             0.0           0.0     0.000000     0.000000     0.000000   \n",
-       "50%             0.0           0.0     0.000000     0.000000     0.000000   \n",
-       "75%             0.0           0.0     0.000000     0.000000     0.000000   \n",
-       "max             inf           inf     1.000000     1.000000     1.000000   \n",
-       "\n",
-       "       step_pred_7  step_pred_8  step_pred_9  \n",
-       "count  9168.000000  9168.000000  9168.000000  \n",
-       "mean      0.074604     0.074736     0.074528  \n",
-       "std       0.239266     0.238990     0.238090  \n",
-       "min       0.000000     0.000000     0.000000  \n",
-       "25%       0.000000     0.000000     0.000000  \n",
-       "50%       0.000000     0.000000     0.000000  \n",
-       "75%       0.000000     0.000000     0.000000  \n",
-       "max       1.000000     1.000000     1.000000  \n",
-       "\n",
-       "[8 rows x 80 columns]"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "calib_predictions.describe()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>feature</th>\n",
-       "      <th>step_combined</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>month_id</th>\n",
-       "      <th>country_id</th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th rowspan=\"20\" valign=\"top\">565</th>\n",
-       "      <th>205</th>\n",
-       "      <td>0.032541</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>206</th>\n",
-       "      <td>0.062064</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>209</th>\n",
-       "      <td>0.170000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>213</th>\n",
-       "      <td>0.230000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>214</th>\n",
-       "      <td>0.220000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>218</th>\n",
-       "      <td>0.430000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>220</th>\n",
-       "      <td>0.850000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>222</th>\n",
-       "      <td>0.340000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>223</th>\n",
-       "      <td>0.420000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>231</th>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>232</th>\n",
-       "      <td>0.030000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>233</th>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>234</th>\n",
-       "      <td>0.065739</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>235</th>\n",
-       "      <td>0.120000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>237</th>\n",
-       "      <td>0.200000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>242</th>\n",
-       "      <td>0.140000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>243</th>\n",
-       "      <td>0.125042</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>244</th>\n",
-       "      <td>0.070720</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>245</th>\n",
-       "      <td>0.690000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>246</th>\n",
-       "      <td>0.180000</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "feature              step_combined\n",
-       "month_id country_id               \n",
-       "565      205              0.032541\n",
-       "         206              0.062064\n",
-       "         209              0.170000\n",
-       "         213              0.230000\n",
-       "         214              0.220000\n",
-       "         218              0.430000\n",
-       "         220              0.850000\n",
-       "         222              0.340000\n",
-       "         223              0.420000\n",
-       "         231              0.000000\n",
-       "         232              0.030000\n",
-       "         233              0.000000\n",
-       "         234              0.065739\n",
-       "         235              0.120000\n",
-       "         237              0.200000\n",
-       "         242              0.140000\n",
-       "         243              0.125042\n",
-       "         244              0.070720\n",
-       "         245              0.690000\n",
-       "         246              0.180000"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Predictions for the future:\n",
-    "future_partition = views_runs.DataPartitioner({'future':future_partitioner_dict})\n",
-    "future_predictions = stepshifter_model_future.future_predict('future','predict',data)\n",
-    "# Predictions for the future, alternative method:\n",
-    "future_point_predictions = stepshifter_model_future.future_point_predict(time=529, data=data, proba=True)\n",
-    "future_point_predictions.tail(20)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th>feature</th>\n",
-       "      <th>step_combined</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>count</th>\n",
-       "      <td>6876.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>mean</th>\n",
-       "      <td>0.137513</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>std</th>\n",
-       "      <td>0.191055</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>min</th>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>25%</th>\n",
-       "      <td>0.023425</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>50%</th>\n",
-       "      <td>0.062464</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>75%</th>\n",
-       "      <td>0.160492</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>max</th>\n",
-       "      <td>0.970000</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "feature  step_combined\n",
-       "count      6876.000000\n",
-       "mean          0.137513\n",
-       "std           0.191055\n",
-       "min           0.000000\n",
-       "25%           0.023425\n",
-       "50%           0.062464\n",
-       "75%           0.160492\n",
-       "max           0.970000"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "future_point_predictions.describe()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[0;31mType:\u001b[0m        module\n",
-      "\u001b[0;31mString form:\u001b[0m <module 'views_runs' from '/Applications/anaconda3/envs/viewser/lib/python3.9/site-packages/views_runs/__init__.py'>\n",
-      "\u001b[0;31mFile:\u001b[0m        /Applications/anaconda3/envs/viewser/lib/python3.9/site-packages/views_runs/__init__.py\n",
-      "\u001b[0;31mDocstring:\u001b[0m  \n",
-      "views_runs\n",
-      "==========\n",
-      "\n",
-      "This package collects views related tools and utilities used when planning,\n",
-      "training and storing views \"runs\" of predictions.\n",
-      "\n",
-      "classes:\n",
-      "    ViewsRun:\n",
-      "        Class that encapsulates StepshiftedModels and DataPartitioner objects\n",
-      "        to provide a nice API for training and producing predictions.\n",
-      "    Storage:\n",
-      "        A class that exposes the viewser model_storage storage driver, used to\n",
-      "        save and load trained model objects.\n",
-      "    StepshiftedModels:\n",
-      "        Model class from the stepshift package that lets you train stepshifted\n",
-      "        models.\n",
-      "    DataPartitioner:\n",
-      "        Utility class for subsetting data in time, that lets you define\n",
-      "        tranining and testing periods, as well as do operations to ensure no\n",
-      "        overlap exists between these periods.\n",
-      "    ModelMetadata:\n",
-      "        Class used to specify metadata for trained model objects.\n",
-      "\n",
-      "modules:\n",
-      "    utilities: Various utility functions ported from views 2\n",
-      "    stats: Resampling functions\n",
-      "    run: Defines the ViewsRun class\n",
-      "    storage: Defines the Storage class\n",
-      "    validation: Functions used internally to validate data\n",
-      "\n",
-      "Each class and module mentioned here has more documentation. Use the help()\n",
-      "function."
-     ]
-    }
-   ],
-   "source": [
-    "# Docstrings: \n",
-    "views_runs?"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Help on package views_runs:\n",
-      "\n",
-      "NAME\n",
-      "    views_runs\n",
-      "\n",
-      "DESCRIPTION\n",
-      "    views_runs\n",
-      "    ==========\n",
-      "    \n",
-      "    This package collects views related tools and utilities used when planning,\n",
-      "    training and storing views \"runs\" of predictions.\n",
-      "    \n",
-      "    classes:\n",
-      "        ViewsRun:\n",
-      "            Class that encapsulates StepshiftedModels and DataPartitioner objects\n",
-      "            to provide a nice API for training and producing predictions.\n",
-      "        Storage:\n",
-      "            A class that exposes the viewser model_storage storage driver, used to\n",
-      "            save and load trained model objects.\n",
-      "        StepshiftedModels:\n",
-      "            Model class from the stepshift package that lets you train stepshifted\n",
-      "            models.\n",
-      "        DataPartitioner:\n",
-      "            Utility class for subsetting data in time, that lets you define\n",
-      "            tranining and testing periods, as well as do operations to ensure no\n",
-      "            overlap exists between these periods.\n",
-      "        ModelMetadata:\n",
-      "            Class used to specify metadata for trained model objects.\n",
-      "    \n",
-      "    modules:\n",
-      "        utilities: Various utility functions ported from views 2\n",
-      "        stats: Resampling functions\n",
-      "        run: Defines the ViewsRun class\n",
-      "        storage: Defines the Storage class\n",
-      "        validation: Functions used internally to validate data\n",
-      "    \n",
-      "    Each class and module mentioned here has more documentation. Use the help()\n",
-      "    function.\n",
-      "\n",
-      "PACKAGE CONTENTS\n",
-      "    operations\n",
-      "    run\n",
-      "    run_result\n",
-      "    stats\n",
-      "    storage\n",
-      "    utilities\n",
-      "    validation\n",
-      "    vendoring\n",
-      "\n",
-      "FILE\n",
-      "    /Applications/anaconda3/envs/viewser/lib/python3.9/site-packages/views_runs/__init__.py\n",
-      "\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Documentation:\n",
-    "help(views_runs)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Add:\n",
-    "- Drift detection\n",
-    "- wandb\n",
-    "- Hyperparameter testing"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.18"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/models/electric_relaxation/notebooks/ESCWA_script_outputs.ipynb b/models/electric_relaxation/notebooks/ESCWA_script_outputs.ipynb
deleted file mode 100644
index 8d89eaa..0000000
--- a/models/electric_relaxation/notebooks/ESCWA_script_outputs.ipynb
+++ /dev/null
@@ -1,831 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Inspect script output"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import pandas as pd\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "/Users/sarakallis/Documents/PRIO Local/views_pipeline/models/electric_relaxation/notebooks\n"
-     ]
-    }
-   ],
-   "source": [
-    "! pwd"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data_directory = \"/Users/sarakallis/Documents/PRIO Local/views_pipeline/models/electric_relaxation/data/generated\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Calibration predictions"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th>ged_sb_dep</th>\n",
-       "      <th>ged_sb_dummy_t0</th>\n",
-       "      <th>ged_os_dummy_t0</th>\n",
-       "      <th>ged_ns_dummy_t0</th>\n",
-       "      <th>ged_sb_dummy_t1</th>\n",
-       "      <th>ged_sb_dummy_t2</th>\n",
-       "      <th>ged_sb_dummy_t3</th>\n",
-       "      <th>_ged_sb_dummy_t3</th>\n",
-       "      <th>ged_sb_dummy_t4</th>\n",
-       "      <th>ged_sb_dummy_t5</th>\n",
-       "      <th>...</th>\n",
-       "      <th>step_pred_33</th>\n",
-       "      <th>step_pred_34</th>\n",
-       "      <th>step_pred_35</th>\n",
-       "      <th>step_pred_36</th>\n",
-       "      <th>step_pred_4</th>\n",
-       "      <th>step_pred_5</th>\n",
-       "      <th>step_pred_6</th>\n",
-       "      <th>step_pred_7</th>\n",
-       "      <th>step_pred_8</th>\n",
-       "      <th>step_pred_9</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>month_id</th>\n",
-       "      <th>country_id</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th rowspan=\"5\" valign=\"top\">409</th>\n",
-       "      <th>1</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>5 rows × 80 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                     ged_sb_dep  ged_sb_dummy_t0  ged_os_dummy_t0  \\\n",
-       "month_id country_id                                                 \n",
-       "409      1                  0.0              0.0              0.0   \n",
-       "         2                  0.0              0.0              0.0   \n",
-       "         3                  0.0              0.0              0.0   \n",
-       "         4                  0.0              0.0              0.0   \n",
-       "         5                  0.0              0.0              0.0   \n",
-       "\n",
-       "                     ged_ns_dummy_t0  ged_sb_dummy_t1  ged_sb_dummy_t2  \\\n",
-       "month_id country_id                                                      \n",
-       "409      1                       0.0              0.0              0.0   \n",
-       "         2                       0.0              0.0              0.0   \n",
-       "         3                       0.0              0.0              0.0   \n",
-       "         4                       0.0              0.0              0.0   \n",
-       "         5                       0.0              0.0              0.0   \n",
-       "\n",
-       "                     ged_sb_dummy_t3  _ged_sb_dummy_t3  ged_sb_dummy_t4  \\\n",
-       "month_id country_id                                                       \n",
-       "409      1                       0.0               0.0              0.0   \n",
-       "         2                       0.0               0.0              0.0   \n",
-       "         3                       0.0               0.0              0.0   \n",
-       "         4                       0.0               0.0              0.0   \n",
-       "         5                       0.0               0.0              0.0   \n",
-       "\n",
-       "                     ged_sb_dummy_t5  ...  step_pred_33  step_pred_34  \\\n",
-       "month_id country_id                   ...                               \n",
-       "409      1                       0.0  ...           0.0           0.0   \n",
-       "         2                       0.0  ...           0.0           0.0   \n",
-       "         3                       0.0  ...           0.0           0.0   \n",
-       "         4                       0.0  ...           0.0           0.0   \n",
-       "         5                       0.0  ...           0.0           0.0   \n",
-       "\n",
-       "                     step_pred_35  step_pred_36  step_pred_4  step_pred_5  \\\n",
-       "month_id country_id                                                         \n",
-       "409      1                    0.0           0.0          0.0          0.0   \n",
-       "         2                    0.0           0.0          0.0          0.0   \n",
-       "         3                    0.0           0.0          0.0          0.0   \n",
-       "         4                    0.0           0.0          0.0          0.0   \n",
-       "         5                    0.0           0.0          0.0          0.0   \n",
-       "\n",
-       "                     step_pred_6  step_pred_7  step_pred_8  step_pred_9  \n",
-       "month_id country_id                                                      \n",
-       "409      1                   0.0          0.0          0.0          0.0  \n",
-       "         2                   0.0          0.0          0.0          0.0  \n",
-       "         3                   0.0          0.0          0.0          0.0  \n",
-       "         4                   0.0          0.0          0.0          0.0  \n",
-       "         5                   0.0          0.0          0.0          0.0  \n",
-       "\n",
-       "[5 rows x 80 columns]"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "calib_predictions = pd.read_parquet(f\"{data_directory}/calib_predictions.parquet\")\n",
-    "calib_predictions.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>ged_sb_dep</th>\n",
-       "      <th>ged_sb_dummy_t0</th>\n",
-       "      <th>ged_os_dummy_t0</th>\n",
-       "      <th>ged_ns_dummy_t0</th>\n",
-       "      <th>ged_sb_dummy_t1</th>\n",
-       "      <th>ged_sb_dummy_t2</th>\n",
-       "      <th>ged_sb_dummy_t3</th>\n",
-       "      <th>_ged_sb_dummy_t3</th>\n",
-       "      <th>ged_sb_dummy_t4</th>\n",
-       "      <th>ged_sb_dummy_t5</th>\n",
-       "      <th>...</th>\n",
-       "      <th>step_pred_33</th>\n",
-       "      <th>step_pred_34</th>\n",
-       "      <th>step_pred_35</th>\n",
-       "      <th>step_pred_36</th>\n",
-       "      <th>step_pred_4</th>\n",
-       "      <th>step_pred_5</th>\n",
-       "      <th>step_pred_6</th>\n",
-       "      <th>step_pred_7</th>\n",
-       "      <th>step_pred_8</th>\n",
-       "      <th>step_pred_9</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>count</th>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>9168.0</td>\n",
-       "      <td>9168.0</td>\n",
-       "      <td>9168.0</td>\n",
-       "      <td>9168.0</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "      <td>9168.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>mean</th>\n",
-       "      <td>0.075153</td>\n",
-       "      <td>0.075153</td>\n",
-       "      <td>0.033050</td>\n",
-       "      <td>0.036322</td>\n",
-       "      <td>0.075044</td>\n",
-       "      <td>0.074607</td>\n",
-       "      <td>0.075044</td>\n",
-       "      <td>0.075044</td>\n",
-       "      <td>0.073953</td>\n",
-       "      <td>0.073844</td>\n",
-       "      <td>...</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>0.075143</td>\n",
-       "      <td>0.075019</td>\n",
-       "      <td>0.074955</td>\n",
-       "      <td>0.074634</td>\n",
-       "      <td>0.074712</td>\n",
-       "      <td>0.074912</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>std</th>\n",
-       "      <td>0.263652</td>\n",
-       "      <td>0.263652</td>\n",
-       "      <td>0.178776</td>\n",
-       "      <td>0.187100</td>\n",
-       "      <td>0.263476</td>\n",
-       "      <td>0.262771</td>\n",
-       "      <td>0.263476</td>\n",
-       "      <td>0.263476</td>\n",
-       "      <td>0.261708</td>\n",
-       "      <td>0.261531</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.240009</td>\n",
-       "      <td>0.239584</td>\n",
-       "      <td>0.239502</td>\n",
-       "      <td>0.238943</td>\n",
-       "      <td>0.239064</td>\n",
-       "      <td>0.238478</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>min</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>25%</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>50%</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>75%</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>max</th>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>inf</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>1.000000</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>8 rows × 80 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "        ged_sb_dep  ged_sb_dummy_t0  ged_os_dummy_t0  ged_ns_dummy_t0  \\\n",
-       "count  9168.000000      9168.000000      9168.000000      9168.000000   \n",
-       "mean      0.075153         0.075153         0.033050         0.036322   \n",
-       "std       0.263652         0.263652         0.178776         0.187100   \n",
-       "min       0.000000         0.000000         0.000000         0.000000   \n",
-       "25%       0.000000         0.000000         0.000000         0.000000   \n",
-       "50%       0.000000         0.000000         0.000000         0.000000   \n",
-       "75%       0.000000         0.000000         0.000000         0.000000   \n",
-       "max       1.000000         1.000000         1.000000         1.000000   \n",
-       "\n",
-       "       ged_sb_dummy_t1  ged_sb_dummy_t2  ged_sb_dummy_t3  _ged_sb_dummy_t3  \\\n",
-       "count      9168.000000      9168.000000      9168.000000       9168.000000   \n",
-       "mean          0.075044         0.074607         0.075044          0.075044   \n",
-       "std           0.263476         0.262771         0.263476          0.263476   \n",
-       "min           0.000000         0.000000         0.000000          0.000000   \n",
-       "25%           0.000000         0.000000         0.000000          0.000000   \n",
-       "50%           0.000000         0.000000         0.000000          0.000000   \n",
-       "75%           0.000000         0.000000         0.000000          0.000000   \n",
-       "max           1.000000         1.000000         1.000000          1.000000   \n",
-       "\n",
-       "       ged_sb_dummy_t4  ged_sb_dummy_t5  ...  step_pred_33  step_pred_34  \\\n",
-       "count      9168.000000      9168.000000  ...        9168.0        9168.0   \n",
-       "mean          0.073953         0.073844  ...           inf           inf   \n",
-       "std           0.261708         0.261531  ...           NaN           NaN   \n",
-       "min           0.000000         0.000000  ...           0.0           0.0   \n",
-       "25%           0.000000         0.000000  ...           0.0           0.0   \n",
-       "50%           0.000000         0.000000  ...           0.0           0.0   \n",
-       "75%           0.000000         0.000000  ...           0.0           0.0   \n",
-       "max           1.000000         1.000000  ...           inf           inf   \n",
-       "\n",
-       "       step_pred_35  step_pred_36  step_pred_4  step_pred_5  step_pred_6  \\\n",
-       "count        9168.0        9168.0  9168.000000  9168.000000  9168.000000   \n",
-       "mean            inf           inf     0.075143     0.075019     0.074955   \n",
-       "std             NaN           NaN     0.240009     0.239584     0.239502   \n",
-       "min             0.0           0.0     0.000000     0.000000     0.000000   \n",
-       "25%             0.0           0.0     0.000000     0.000000     0.000000   \n",
-       "50%             0.0           0.0     0.000000     0.000000     0.000000   \n",
-       "75%             0.0           0.0     0.000000     0.000000     0.000000   \n",
-       "max             inf           inf     1.000000     1.000000     1.000000   \n",
-       "\n",
-       "       step_pred_7  step_pred_8  step_pred_9  \n",
-       "count  9168.000000  9168.000000  9168.000000  \n",
-       "mean      0.074634     0.074712     0.074912  \n",
-       "std       0.238943     0.239064     0.238478  \n",
-       "min       0.000000     0.000000     0.000000  \n",
-       "25%       0.000000     0.000000     0.000000  \n",
-       "50%       0.000000     0.000000     0.000000  \n",
-       "75%       0.000000     0.000000     0.000000  \n",
-       "max       1.000000     1.000000     1.000000  \n",
-       "\n",
-       "[8 rows x 80 columns]"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "calib_predictions.describe()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Future predictions"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "future_predictions = pd.read_parquet(f\"{data_directory}/future_predictions.parquet\")\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>feature</th>\n",
-       "      <th>step_combined</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>month_id</th>\n",
-       "      <th>country_id</th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th rowspan=\"5\" valign=\"top\">530</th>\n",
-       "      <th>1</th>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5</th>\n",
-       "      <td>0.0</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "feature              step_combined\n",
-       "month_id country_id               \n",
-       "530      1                     0.0\n",
-       "         2                     0.0\n",
-       "         3                     0.0\n",
-       "         4                     0.0\n",
-       "         5                     0.0"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "future_predictions.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th>feature</th>\n",
-       "      <th>step_combined</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>count</th>\n",
-       "      <td>6876.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>mean</th>\n",
-       "      <td>0.077080</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>std</th>\n",
-       "      <td>0.266737</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>min</th>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>25%</th>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>50%</th>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>75%</th>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>max</th>\n",
-       "      <td>1.000000</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "feature  step_combined\n",
-       "count      6876.000000\n",
-       "mean          0.077080\n",
-       "std           0.266737\n",
-       "min           0.000000\n",
-       "25%           0.000000\n",
-       "50%           0.000000\n",
-       "75%           0.000000\n",
-       "max           1.000000"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "future_predictions.describe()"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "viewser",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.18"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/models/orange_pasta/notebooks/notebook001.ipynb b/models/orange_pasta/notebooks/notebook001.ipynb
deleted file mode 100644
index b428e1f..0000000
--- a/models/orange_pasta/notebooks/notebook001.ipynb
+++ /dev/null
@@ -1,242 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-06-19T14:45:24.635363Z",
-     "start_time": "2024-06-19T14:45:22.079967Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "from views_stepshift import *\n",
-    "import properscoring as ps\n",
-    "from sklearn.metrics import mean_squared_error, mean_absolute_error, mean_squared_log_error, brier_score_loss, average_precision_score, roc_auc_score\n",
-    "from views_forecasts.extensions import *\n",
-    "from common_utils.utils_evaluation_metrics import EvaluationMetrics\n",
-    "from common_utils.utils_model_outputs import ModelOutputs"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 52,
-   "outputs": [
-    {
-     "data": {
-      "text/plain": "           y_score y_score_prob y_var y_var_prob y_true y_true_binary   pg_id  \\\n0         0.062623          NaN   NaN        NaN    0.0           NaN   62356   \n1         0.062623          NaN   NaN        NaN    0.0           NaN   79599   \n2         0.062623          NaN   NaN        NaN    0.0           NaN   79600   \n3         0.062623          NaN   NaN        NaN    0.0           NaN   79601   \n4         0.062623          NaN   NaN        NaN    0.0           NaN   80317   \n...            ...          ...   ...        ...    ...           ...     ...   \n22654075  0.064958          NaN   NaN        NaN    0.0           NaN  190496   \n22654076  0.064958          NaN   NaN        NaN    0.0           NaN  190507   \n22654077  0.064958          NaN   NaN        NaN    0.0           NaN  190508   \n22654078  0.064958          NaN   NaN        NaN    0.0           NaN  190510   \n22654079  0.064958          NaN   NaN        NaN    0.0           NaN  190511   \n\n         c_id month_id  out_sample_month  \n0         NaN      445                 1  \n1         NaN      445                 1  \n2         NaN      445                 1  \n3         NaN      445                 1  \n4         NaN      445                 1  \n...       ...      ...               ...  \n22654075  NaN      492                36  \n22654076  NaN      492                36  \n22654077  NaN      492                36  \n22654078  NaN      492                36  \n22654079  NaN      492                36  \n\n[22654080 rows x 10 columns]",
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>y_score</th>\n      <th>y_score_prob</th>\n      <th>y_var</th>\n      <th>y_var_prob</th>\n      <th>y_true</th>\n      <th>y_true_binary</th>\n      <th>pg_id</th>\n      <th>c_id</th>\n      <th>month_id</th>\n      <th>out_sample_month</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>0.062623</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>0.0</td>\n      <td>NaN</td>\n      <td>62356</td>\n      <td>NaN</td>\n      <td>445</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>0.062623</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>0.0</td>\n      <td>NaN</td>\n      <td>79599</td>\n      <td>NaN</td>\n      <td>445</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>0.062623</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>0.0</td>\n      <td>NaN</td>\n      <td>79600</td>\n      <td>NaN</td>\n      <td>445</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>0.062623</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>0.0</td>\n      <td>NaN</td>\n      <td>79601</td>\n      <td>NaN</td>\n      <td>445</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>0.062623</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>0.0</td>\n      <td>NaN</td>\n      <td>80317</td>\n      <td>NaN</td>\n      <td>445</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>22654075</th>\n      <td>0.064958</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>0.0</td>\n      <td>NaN</td>\n      <td>190496</td>\n      <td>NaN</td>\n      <td>492</td>\n      <td>36</td>\n    </tr>\n    <tr>\n      <th>22654076</th>\n      <td>0.064958</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>0.0</td>\n      <td>NaN</td>\n      <td>190507</td>\n      <td>NaN</td>\n      <td>492</td>\n      <td>36</td>\n    </tr>\n    <tr>\n      <th>22654077</th>\n      <td>0.064958</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>0.0</td>\n      <td>NaN</td>\n      <td>190508</td>\n      <td>NaN</td>\n      <td>492</td>\n      <td>36</td>\n    </tr>\n    <tr>\n      <th>22654078</th>\n      <td>0.064958</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>0.0</td>\n      <td>NaN</td>\n      <td>190510</td>\n      <td>NaN</td>\n      <td>492</td>\n      <td>36</td>\n    </tr>\n    <tr>\n      <th>22654079</th>\n      <td>0.064958</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>0.0</td>\n      <td>NaN</td>\n      <td>190511</td>\n      <td>NaN</td>\n      <td>492</td>\n      <td>36</td>\n    </tr>\n  </tbody>\n</table>\n<p>22654080 rows × 10 columns</p>\n</div>"
-     },
-     "execution_count": 52,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df_output = pd.read_pickle('../data/generated/df_output_36_testing_20240618_155834.pkl')\n",
-    "df_output"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2024-06-19T14:13:59.953480Z",
-     "start_time": "2024-06-19T14:13:59.948609Z"
-    }
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 54,
-   "outputs": [
-    {
-     "data": {
-      "text/plain": "              MSE       MAE  MSLE   KLD Jeffreys      CRPS Brier    AP   AUC  \\\nstep01  33.787333  0.260264  None  None     None  0.260264  None  None  None   \nstep02  41.030356  0.281456  None  None     None  0.281456  None  None  None   \nstep03  48.388455  0.293722  None  None     None  0.293722  None  None  None   \nstep04  48.176262  0.282599  None  None     None  0.282599  None  None  None   \nstep05  56.285934  0.302974  None  None     None  0.302974  None  None  None   \nstep06  47.178029  0.288970  None  None     None  0.288970  None  None  None   \nstep07  47.613544  0.290899  None  None     None  0.290899  None  None  None   \nstep08  54.069031  0.305460  None  None     None  0.305460  None  None  None   \nstep09  55.087259  0.314131  None  None     None  0.314131  None  None  None   \nstep10  55.194927  0.314236  None  None     None  0.314236  None  None  None   \nstep11  65.340730  0.335363  None  None     None  0.335363  None  None  None   \nstep12  59.454320  0.318001  None  None     None  0.318001  None  None  None   \nstep13  53.123586  0.313850  None  None     None  0.313850  None  None  None   \nstep14  49.622333  0.302461  None  None     None  0.302461  None  None  None   \nstep15  52.879568  0.310318  None  None     None  0.310318  None  None  None   \nstep16  62.389715  0.325833  None  None     None  0.325833  None  None  None   \nstep17  61.386507  0.344998  None  None     None  0.344998  None  None  None   \nstep18  59.977352  0.340566  None  None     None  0.340566  None  None  None   \nstep19  53.626635  0.341182  None  None     None  0.341182  None  None  None   \nstep20  59.695450  0.333834  None  None     None  0.333834  None  None  None   \nstep21  51.908472  0.355539  None  None     None  0.355539  None  None  None   \nstep22  58.230838  0.371551  None  None     None  0.371551  None  None  None   \nstep23  60.724871  0.371524  None  None     None  0.371524  None  None  None   \nstep24  55.447345  0.386148  None  None     None  0.386148  None  None  None   \nstep25  55.070633  0.369498  None  None     None  0.369498  None  None  None   \nstep26  52.562588  0.372124  None  None     None  0.372124  None  None  None   \nstep27  69.148095  0.385292  None  None     None  0.385292  None  None  None   \nstep28  63.234910  0.373196  None  None     None  0.373196  None  None  None   \nstep29  59.858053  0.363831  None  None     None  0.363831  None  None  None   \nstep30  53.775858  0.352540  None  None     None  0.352540  None  None  None   \nstep31  64.640432  0.389636  None  None     None  0.389636  None  None  None   \nstep32  61.634035  0.405523  None  None     None  0.405523  None  None  None   \nstep33  59.013487  0.391181  None  None     None  0.391181  None  None  None   \nstep34  58.546634  0.379228  None  None     None  0.379228  None  None  None   \nstep35  58.752317  0.371496  None  None     None  0.371496  None  None  None   \nstep36  55.413118  0.372958  None  None     None  0.372958  None  None  None   \nmean    55.618584  0.339233  None  None     None  0.339233  None  None  None   \nstd      6.927444  0.038170  None  None     None  0.038170  None  None  None   \nmedian  55.430232  0.340874  None  None     None  0.340874  None  None  None   \n\n       ensemble_weight_reg ensemble_weight_class  \nstep01                None                  None  \nstep02                None                  None  \nstep03                None                  None  \nstep04                None                  None  \nstep05                None                  None  \nstep06                None                  None  \nstep07                None                  None  \nstep08                None                  None  \nstep09                None                  None  \nstep10                None                  None  \nstep11                None                  None  \nstep12                None                  None  \nstep13                None                  None  \nstep14                None                  None  \nstep15                None                  None  \nstep16                None                  None  \nstep17                None                  None  \nstep18                None                  None  \nstep19                None                  None  \nstep20                None                  None  \nstep21                None                  None  \nstep22                None                  None  \nstep23                None                  None  \nstep24                None                  None  \nstep25                None                  None  \nstep26                None                  None  \nstep27                None                  None  \nstep28                None                  None  \nstep29                None                  None  \nstep30                None                  None  \nstep31                None                  None  \nstep32                None                  None  \nstep33                None                  None  \nstep34                None                  None  \nstep35                None                  None  \nstep36                None                  None  \nmean                  None                  None  \nstd                   None                  None  \nmedian                None                  None  ",
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>MSE</th>\n      <th>MAE</th>\n      <th>MSLE</th>\n      <th>KLD</th>\n      <th>Jeffreys</th>\n      <th>CRPS</th>\n      <th>Brier</th>\n      <th>AP</th>\n      <th>AUC</th>\n      <th>ensemble_weight_reg</th>\n      <th>ensemble_weight_class</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>step01</th>\n      <td>33.787333</td>\n      <td>0.260264</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.260264</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step02</th>\n      <td>41.030356</td>\n      <td>0.281456</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.281456</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step03</th>\n      <td>48.388455</td>\n      <td>0.293722</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.293722</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step04</th>\n      <td>48.176262</td>\n      <td>0.282599</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.282599</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step05</th>\n      <td>56.285934</td>\n      <td>0.302974</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.302974</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step06</th>\n      <td>47.178029</td>\n      <td>0.288970</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.288970</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step07</th>\n      <td>47.613544</td>\n      <td>0.290899</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.290899</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step08</th>\n      <td>54.069031</td>\n      <td>0.305460</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.305460</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step09</th>\n      <td>55.087259</td>\n      <td>0.314131</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.314131</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step10</th>\n      <td>55.194927</td>\n      <td>0.314236</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.314236</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step11</th>\n      <td>65.340730</td>\n      <td>0.335363</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.335363</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step12</th>\n      <td>59.454320</td>\n      <td>0.318001</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.318001</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step13</th>\n      <td>53.123586</td>\n      <td>0.313850</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.313850</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step14</th>\n      <td>49.622333</td>\n      <td>0.302461</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.302461</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step15</th>\n      <td>52.879568</td>\n      <td>0.310318</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.310318</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step16</th>\n      <td>62.389715</td>\n      <td>0.325833</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.325833</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step17</th>\n      <td>61.386507</td>\n      <td>0.344998</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.344998</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step18</th>\n      <td>59.977352</td>\n      <td>0.340566</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.340566</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step19</th>\n      <td>53.626635</td>\n      <td>0.341182</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.341182</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step20</th>\n      <td>59.695450</td>\n      <td>0.333834</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.333834</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step21</th>\n      <td>51.908472</td>\n      <td>0.355539</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.355539</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step22</th>\n      <td>58.230838</td>\n      <td>0.371551</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.371551</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step23</th>\n      <td>60.724871</td>\n      <td>0.371524</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.371524</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step24</th>\n      <td>55.447345</td>\n      <td>0.386148</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.386148</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step25</th>\n      <td>55.070633</td>\n      <td>0.369498</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.369498</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step26</th>\n      <td>52.562588</td>\n      <td>0.372124</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.372124</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step27</th>\n      <td>69.148095</td>\n      <td>0.385292</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.385292</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step28</th>\n      <td>63.234910</td>\n      <td>0.373196</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.373196</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step29</th>\n      <td>59.858053</td>\n      <td>0.363831</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.363831</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step30</th>\n      <td>53.775858</td>\n      <td>0.352540</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.352540</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step31</th>\n      <td>64.640432</td>\n      <td>0.389636</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.389636</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step32</th>\n      <td>61.634035</td>\n      <td>0.405523</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.405523</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step33</th>\n      <td>59.013487</td>\n      <td>0.391181</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.391181</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step34</th>\n      <td>58.546634</td>\n      <td>0.379228</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.379228</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step35</th>\n      <td>58.752317</td>\n      <td>0.371496</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.371496</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>step36</th>\n      <td>55.413118</td>\n      <td>0.372958</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.372958</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>55.618584</td>\n      <td>0.339233</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.339233</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>std</th>\n      <td>6.927444</td>\n      <td>0.038170</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.038170</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n    <tr>\n      <th>median</th>\n      <td>55.430232</td>\n      <td>0.340874</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>0.340874</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n      <td>None</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
-     },
-     "execution_count": 54,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df_eval = pd.read_pickle('../data/generated/df_evaluation_36_testing_20240618_155834.pkl')\n",
-    "df_eval"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2024-06-19T14:14:48.935539Z",
-     "start_time": "2024-06-19T14:14:48.916520Z"
-    }
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "outputs": [],
-   "source": [
-    "df_forecast = pd.read_pickle(\"../data/generated/predictions_36_forecasting_20240619_172828.pkl\")"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2024-06-19T15:29:17.921430Z",
-     "start_time": "2024-06-19T15:29:17.914007Z"
-    }
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "outputs": [
-    {
-     "data": {
-      "text/plain": "Empty DataFrame\nColumns: [step_pred_1, step_pred_2, step_pred_3, step_pred_4, step_pred_5, step_pred_6, step_pred_7, step_pred_8, step_pred_9, step_pred_10, step_pred_11, step_pred_12, step_pred_13, step_pred_14, step_pred_15, step_pred_16, step_pred_17, step_pred_18, step_pred_19, step_pred_20, step_pred_21, step_pred_22, step_pred_23, step_pred_24, step_pred_25, step_pred_26, step_pred_27, step_pred_28, step_pred_29, step_pred_30, step_pred_31, step_pred_32, step_pred_33, step_pred_34, step_pred_35, step_pred_36]\nIndex: []\n\n[0 rows x 36 columns]",
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th></th>\n      <th>step_pred_1</th>\n      <th>step_pred_2</th>\n      <th>step_pred_3</th>\n      <th>step_pred_4</th>\n      <th>step_pred_5</th>\n      <th>step_pred_6</th>\n      <th>step_pred_7</th>\n      <th>step_pred_8</th>\n      <th>step_pred_9</th>\n      <th>step_pred_10</th>\n      <th>...</th>\n      <th>step_pred_27</th>\n      <th>step_pred_28</th>\n      <th>step_pred_29</th>\n      <th>step_pred_30</th>\n      <th>step_pred_31</th>\n      <th>step_pred_32</th>\n      <th>step_pred_33</th>\n      <th>step_pred_34</th>\n      <th>step_pred_35</th>\n      <th>step_pred_36</th>\n    </tr>\n    <tr>\n      <th>month_id</th>\n      <th>priogrid_gid</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n  </tbody>\n</table>\n<p>0 rows × 36 columns</p>\n</div>"
-     },
-     "execution_count": 19,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df_forecast"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2024-06-19T15:29:18.626134Z",
-     "start_time": "2024-06-19T15:29:18.622691Z"
-    }
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "outputs": [],
-   "source": [
-    "stepshift_model = pd.read_pickle(\"../artifacts/forecasting_model_20240618_173119.pkl\")\n",
-    "dataset = pd.read_parquet(\"../data/raw/raw_forecasting.parquet\")\n",
-    "run_type = 'forecasting'"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2024-06-20T07:20:03.452716Z",
-     "start_time": "2024-06-20T07:20:03.118062Z"
-    }
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 33,
-   "outputs": [],
-   "source": [
-    "from ingester3.ViewsMonth import ViewsMonth\n",
-    "\n",
-    "def get_partitioner_dict(partition, step=36):\n",
-    "\n",
-    "    \"\"\"Returns the partitioner_dict for the given partition.\"\"\"\n",
-    "\n",
-    "    if partition == 'calibration':\n",
-    "\n",
-    "        partitioner_dict = {\"train\":(121,396),\"predict\":(397,444)} # calib_partitioner_dict - (01/01/1990 - 12/31/2012) : (01/01/2013 - 31/12/2015)\n",
-    "\n",
-    "    if partition == 'testing':\n",
-    "\n",
-    "        partitioner_dict = {\"train\":(121,444),\"predict\":(445,492)} \n",
-    "\n",
-    "    if partition == 'forecasting':\n",
-    "\n",
-    "        month_last = ViewsMonth.now().id - 2 # minus 2 because the current month is not yet available. Verified but can be tested by chinging this and running the check_data notebook.\n",
-    "\n",
-    "        partitioner_dict = {\"train\":(121, month_last),\"predict\":(month_last +1, month_last + 1 + step)}  # is it even meaningful to have a predict partition for forecasting? if not you can remove steps\n",
-    "\n",
-    "    # print('partitioner_dict', partitioner_dict) \n",
-    "\n",
-    "    return partitioner_dict\n",
-    "    \n",
-    "def get_partition_data(df, run_type):\n",
-    "    partitioner_dict = get_partitioner_dict(run_type)\n",
-    "\n",
-    "    month_first = partitioner_dict['train'][0]\n",
-    "\n",
-    "    if run_type in ['calibration', 'testing', 'forecasting']:\n",
-    "        month_last = partitioner_dict['predict'][1] + 1 # forecasting also needs to get predict months even if they are empty\n",
-    "    else:\n",
-    "        raise ValueError('partition should be either \"calibration\", \"testing\" or \"forecasting\"')\n",
-    "    \n",
-    "    month_range = np.arange(month_first, month_last,1) # predict[1] is the last month to predict, so we need to add 1 to include it.\n",
-    "\n",
-    "    df = df[df.index.get_level_values(\"month_id\").isin(month_range)].copy() # temporal subset\n",
-    "\n",
-    "    return df"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2024-06-20T07:38:47.793724Z",
-     "start_time": "2024-06-20T07:38:47.787208Z"
-    }
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 34,
-   "outputs": [
-    {
-     "data": {
-      "text/plain": "                       ged_sb_dep  ln_ged_sb  ln_pop_gpw_sum  decay_ged_sb_1  \\\nmonth_id priogrid_gid                                                          \n533      62356                0.0        0.0        0.000000    2.124068e-07   \n         79599                0.0        0.0        9.145198    2.124068e-07   \n         79600                0.0        0.0        8.394584    2.124068e-07   \n         79601                0.0        0.0        9.903443    2.124068e-07   \n         80317                0.0        0.0       12.290978    2.124068e-07   \n...                           ...        ...             ...             ...   \n569      190496               0.0        0.0       10.408626    7.509715e-08   \n         190507               0.0        0.0        6.647283    7.509715e-08   \n         190508               0.0        0.0        4.562102    7.509715e-08   \n         190510               0.0        0.0        7.619576    7.509715e-08   \n         190511               0.0        0.0        7.596084    7.509715e-08   \n\n                       decay_ged_sb_25  decay_ged_os_1  splag_1_1_sb_1  \\\nmonth_id priogrid_gid                                                    \n533      62356            2.124068e-07    2.124068e-07    0.000000e+00   \n         79599            2.124068e-07    2.124068e-07    8.496272e-07   \n         79600            2.124068e-07    2.124068e-07    1.062034e-06   \n         79601            2.124068e-07    2.124068e-07    8.496272e-07   \n         80317            2.124068e-07    2.124068e-07    6.372204e-07   \n...                                ...             ...             ...   \n569      190496           7.509715e-08    7.509715e-08    3.003886e-07   \n         190507           7.509715e-08    7.509715e-08    3.003886e-07   \n         190508           7.509715e-08    7.509715e-08    3.003886e-07   \n         190510           7.509715e-08    7.509715e-08    3.003886e-07   \n         190511           7.509715e-08    7.509715e-08    3.003886e-07   \n\n                       splag_1_decay_ged_sb_1  step_pred_1  step_pred_10  ...  \\\nmonth_id priogrid_gid                                                     ...   \n533      62356                   0.000000e+00     0.075624      0.086838  ...   \n         79599                   8.496272e-07     0.075624      0.086838  ...   \n         79600                   1.062034e-06     0.075624      0.086838  ...   \n         79601                   8.496272e-07     0.075624      0.086838  ...   \n         80317                   6.372204e-07     0.075624      0.086838  ...   \n...                                       ...          ...           ...  ...   \n569      190496                  3.003886e-07     0.075624      0.086838  ...   \n         190507                  3.003886e-07     0.075624      0.086838  ...   \n         190508                  3.003886e-07     0.075624      0.086838  ...   \n         190510                  3.003886e-07     0.075624      0.086838  ...   \n         190511                  3.003886e-07     0.075624      0.086838  ...   \n\n                       step_pred_33  step_pred_34  step_pred_35  step_pred_36  \\\nmonth_id priogrid_gid                                                           \n533      62356             0.087995      0.085165      0.086579      0.087058   \n         79599             0.087995      0.085165      0.086579      0.087058   \n         79600             0.087995      0.085165      0.086579      0.087058   \n         79601             0.087995      0.085165      0.086579      0.087058   \n         80317             0.087995      0.085165      0.086579      0.087058   \n...                             ...           ...           ...           ...   \n569      190496            0.087995      0.085165      0.086579      0.087058   \n         190507            0.087995      0.085165      0.086579      0.087058   \n         190508            0.087995      0.085165      0.086579      0.087058   \n         190510            0.087995      0.085165      0.086579      0.087058   \n         190511            0.087995      0.085165      0.086579      0.087058   \n\n                       step_pred_4  step_pred_5  step_pred_6  step_pred_7  \\\nmonth_id priogrid_gid                                                       \n533      62356            0.078232     0.077486     0.077665     0.078307   \n         79599            0.078232     0.077486     0.077665     0.078307   \n         79600            0.078232     0.077486     0.077665     0.078307   \n         79601            0.078232     0.077486     0.077665     0.078307   \n         80317            0.078232     0.077486     0.077665     0.078307   \n...                            ...          ...          ...          ...   \n569      190496           0.078232     0.077486     0.077665     0.078307   \n         190507           0.078232     0.077486     0.077665     0.078307   \n         190508           0.078232     0.077486     0.077665     0.078307   \n         190510           0.078232     0.077486     0.077665     0.078307   \n         190511           0.078232     0.077486     0.077665     0.078307   \n\n                       step_pred_8  step_pred_9  \nmonth_id priogrid_gid                            \n533      62356            0.079862     0.081073  \n         79599            0.079862     0.081073  \n         79600            0.079862     0.081073  \n         79601            0.079862     0.081073  \n         80317            0.079862     0.081073  \n...                            ...          ...  \n569      190496           0.079862     0.081073  \n         190507           0.079862     0.081073  \n         190508           0.079862     0.081073  \n         190510           0.079862     0.081073  \n         190511           0.079862     0.081073  \n\n[485070 rows x 44 columns]",
-      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th></th>\n      <th>ged_sb_dep</th>\n      <th>ln_ged_sb</th>\n      <th>ln_pop_gpw_sum</th>\n      <th>decay_ged_sb_1</th>\n      <th>decay_ged_sb_25</th>\n      <th>decay_ged_os_1</th>\n      <th>splag_1_1_sb_1</th>\n      <th>splag_1_decay_ged_sb_1</th>\n      <th>step_pred_1</th>\n      <th>step_pred_10</th>\n      <th>...</th>\n      <th>step_pred_33</th>\n      <th>step_pred_34</th>\n      <th>step_pred_35</th>\n      <th>step_pred_36</th>\n      <th>step_pred_4</th>\n      <th>step_pred_5</th>\n      <th>step_pred_6</th>\n      <th>step_pred_7</th>\n      <th>step_pred_8</th>\n      <th>step_pred_9</th>\n    </tr>\n    <tr>\n      <th>month_id</th>\n      <th>priogrid_gid</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th rowspan=\"5\" valign=\"top\">533</th>\n      <th>62356</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.000000</td>\n      <td>2.124068e-07</td>\n      <td>2.124068e-07</td>\n      <td>2.124068e-07</td>\n      <td>0.000000e+00</td>\n      <td>0.000000e+00</td>\n      <td>0.075624</td>\n      <td>0.086838</td>\n      <td>...</td>\n      <td>0.087995</td>\n      <td>0.085165</td>\n      <td>0.086579</td>\n      <td>0.087058</td>\n      <td>0.078232</td>\n      <td>0.077486</td>\n      <td>0.077665</td>\n      <td>0.078307</td>\n      <td>0.079862</td>\n      <td>0.081073</td>\n    </tr>\n    <tr>\n      <th>79599</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>9.145198</td>\n      <td>2.124068e-07</td>\n      <td>2.124068e-07</td>\n      <td>2.124068e-07</td>\n      <td>8.496272e-07</td>\n      <td>8.496272e-07</td>\n      <td>0.075624</td>\n      <td>0.086838</td>\n      <td>...</td>\n      <td>0.087995</td>\n      <td>0.085165</td>\n      <td>0.086579</td>\n      <td>0.087058</td>\n      <td>0.078232</td>\n      <td>0.077486</td>\n      <td>0.077665</td>\n      <td>0.078307</td>\n      <td>0.079862</td>\n      <td>0.081073</td>\n    </tr>\n    <tr>\n      <th>79600</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>8.394584</td>\n      <td>2.124068e-07</td>\n      <td>2.124068e-07</td>\n      <td>2.124068e-07</td>\n      <td>1.062034e-06</td>\n      <td>1.062034e-06</td>\n      <td>0.075624</td>\n      <td>0.086838</td>\n      <td>...</td>\n      <td>0.087995</td>\n      <td>0.085165</td>\n      <td>0.086579</td>\n      <td>0.087058</td>\n      <td>0.078232</td>\n      <td>0.077486</td>\n      <td>0.077665</td>\n      <td>0.078307</td>\n      <td>0.079862</td>\n      <td>0.081073</td>\n    </tr>\n    <tr>\n      <th>79601</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>9.903443</td>\n      <td>2.124068e-07</td>\n      <td>2.124068e-07</td>\n      <td>2.124068e-07</td>\n      <td>8.496272e-07</td>\n      <td>8.496272e-07</td>\n      <td>0.075624</td>\n      <td>0.086838</td>\n      <td>...</td>\n      <td>0.087995</td>\n      <td>0.085165</td>\n      <td>0.086579</td>\n      <td>0.087058</td>\n      <td>0.078232</td>\n      <td>0.077486</td>\n      <td>0.077665</td>\n      <td>0.078307</td>\n      <td>0.079862</td>\n      <td>0.081073</td>\n    </tr>\n    <tr>\n      <th>80317</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>12.290978</td>\n      <td>2.124068e-07</td>\n      <td>2.124068e-07</td>\n      <td>2.124068e-07</td>\n      <td>6.372204e-07</td>\n      <td>6.372204e-07</td>\n      <td>0.075624</td>\n      <td>0.086838</td>\n      <td>...</td>\n      <td>0.087995</td>\n      <td>0.085165</td>\n      <td>0.086579</td>\n      <td>0.087058</td>\n      <td>0.078232</td>\n      <td>0.077486</td>\n      <td>0.077665</td>\n      <td>0.078307</td>\n      <td>0.079862</td>\n      <td>0.081073</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th rowspan=\"5\" valign=\"top\">569</th>\n      <th>190496</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>10.408626</td>\n      <td>7.509715e-08</td>\n      <td>7.509715e-08</td>\n      <td>7.509715e-08</td>\n      <td>3.003886e-07</td>\n      <td>3.003886e-07</td>\n      <td>0.075624</td>\n      <td>0.086838</td>\n      <td>...</td>\n      <td>0.087995</td>\n      <td>0.085165</td>\n      <td>0.086579</td>\n      <td>0.087058</td>\n      <td>0.078232</td>\n      <td>0.077486</td>\n      <td>0.077665</td>\n      <td>0.078307</td>\n      <td>0.079862</td>\n      <td>0.081073</td>\n    </tr>\n    <tr>\n      <th>190507</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>6.647283</td>\n      <td>7.509715e-08</td>\n      <td>7.509715e-08</td>\n      <td>7.509715e-08</td>\n      <td>3.003886e-07</td>\n      <td>3.003886e-07</td>\n      <td>0.075624</td>\n      <td>0.086838</td>\n      <td>...</td>\n      <td>0.087995</td>\n      <td>0.085165</td>\n      <td>0.086579</td>\n      <td>0.087058</td>\n      <td>0.078232</td>\n      <td>0.077486</td>\n      <td>0.077665</td>\n      <td>0.078307</td>\n      <td>0.079862</td>\n      <td>0.081073</td>\n    </tr>\n    <tr>\n      <th>190508</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>4.562102</td>\n      <td>7.509715e-08</td>\n      <td>7.509715e-08</td>\n      <td>7.509715e-08</td>\n      <td>3.003886e-07</td>\n      <td>3.003886e-07</td>\n      <td>0.075624</td>\n      <td>0.086838</td>\n      <td>...</td>\n      <td>0.087995</td>\n      <td>0.085165</td>\n      <td>0.086579</td>\n      <td>0.087058</td>\n      <td>0.078232</td>\n      <td>0.077486</td>\n      <td>0.077665</td>\n      <td>0.078307</td>\n      <td>0.079862</td>\n      <td>0.081073</td>\n    </tr>\n    <tr>\n      <th>190510</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>7.619576</td>\n      <td>7.509715e-08</td>\n      <td>7.509715e-08</td>\n      <td>7.509715e-08</td>\n      <td>3.003886e-07</td>\n      <td>3.003886e-07</td>\n      <td>0.075624</td>\n      <td>0.086838</td>\n      <td>...</td>\n      <td>0.087995</td>\n      <td>0.085165</td>\n      <td>0.086579</td>\n      <td>0.087058</td>\n      <td>0.078232</td>\n      <td>0.077486</td>\n      <td>0.077665</td>\n      <td>0.078307</td>\n      <td>0.079862</td>\n      <td>0.081073</td>\n    </tr>\n    <tr>\n      <th>190511</th>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>7.596084</td>\n      <td>7.509715e-08</td>\n      <td>7.509715e-08</td>\n      <td>7.509715e-08</td>\n      <td>3.003886e-07</td>\n      <td>3.003886e-07</td>\n      <td>0.075624</td>\n      <td>0.086838</td>\n      <td>...</td>\n      <td>0.087995</td>\n      <td>0.085165</td>\n      <td>0.086579</td>\n      <td>0.087058</td>\n      <td>0.078232</td>\n      <td>0.077486</td>\n      <td>0.077665</td>\n      <td>0.078307</td>\n      <td>0.079862</td>\n      <td>0.081073</td>\n    </tr>\n  </tbody>\n</table>\n<p>485070 rows × 44 columns</p>\n</div>"
-     },
-     "execution_count": 34,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "stepshift_model.predict(run_type, \"predict\", get_partition_data(dataset, run_type))"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2024-06-20T07:39:18.354405Z",
-     "start_time": "2024-06-20T07:38:48.115441Z"
-    }
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "outputs": [],
-   "source": [],
-   "metadata": {
-    "collapsed": false
-   }
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "viewser",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/models/orange_pasta/notebooks/test.ipynb b/models/orange_pasta/notebooks/test.ipynb
deleted file mode 100644
index 9fdf2a2..0000000
--- a/models/orange_pasta/notebooks/test.ipynb
+++ /dev/null
@@ -1,1263 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from common_utils.views_stepshifter_darts.stepshifter import *"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 103,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th>step_pred_combined</th>\n",
-       "      <th>ln_ged_sb_dep</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>month_id</th>\n",
-       "      <th>priogrid_gid</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th rowspan=\"5\" valign=\"top\">537</th>\n",
-       "      <th>62356.0</th>\n",
-       "      <td>0.000120</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79599.0</th>\n",
-       "      <td>0.000119</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79600.0</th>\n",
-       "      <td>0.000124</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79601.0</th>\n",
-       "      <td>0.000135</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>80317.0</th>\n",
-       "      <td>0.000417</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th rowspan=\"5\" valign=\"top\">572</th>\n",
-       "      <th>190496.0</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190507.0</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190508.0</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190510.0</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190511.0</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>471960 rows × 2 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                       step_pred_combined  ln_ged_sb_dep\n",
-       "month_id priogrid_gid                                   \n",
-       "537      62356.0                 0.000120            NaN\n",
-       "         79599.0                 0.000119            NaN\n",
-       "         79600.0                 0.000124            NaN\n",
-       "         79601.0                 0.000135            NaN\n",
-       "         80317.0                 0.000417            NaN\n",
-       "...                                   ...            ...\n",
-       "572      190496.0                0.000000            NaN\n",
-       "         190507.0                0.000000            NaN\n",
-       "         190508.0                0.000000            NaN\n",
-       "         190510.0                0.000000            NaN\n",
-       "         190511.0                0.000000            NaN\n",
-       "\n",
-       "[471960 rows x 2 columns]"
-      ]
-     },
-     "execution_count": 103,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "pd.read_pickle('models/old_money/data/generated/predictions_36_forecasting_20241009_153720.pkl')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 74,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th>step_pred_1</th>\n",
-       "      <th>step_pred_2</th>\n",
-       "      <th>step_pred_3</th>\n",
-       "      <th>step_pred_4</th>\n",
-       "      <th>step_pred_5</th>\n",
-       "      <th>step_pred_6</th>\n",
-       "      <th>step_pred_7</th>\n",
-       "      <th>step_pred_8</th>\n",
-       "      <th>step_pred_9</th>\n",
-       "      <th>step_pred_10</th>\n",
-       "      <th>...</th>\n",
-       "      <th>step_pred_27</th>\n",
-       "      <th>step_pred_28</th>\n",
-       "      <th>step_pred_29</th>\n",
-       "      <th>step_pred_30</th>\n",
-       "      <th>step_pred_31</th>\n",
-       "      <th>step_pred_32</th>\n",
-       "      <th>step_pred_33</th>\n",
-       "      <th>step_pred_34</th>\n",
-       "      <th>step_pred_35</th>\n",
-       "      <th>step_pred_36</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>month_id</th>\n",
-       "      <th>priogrid_gid</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th rowspan=\"5\" valign=\"top\">538</th>\n",
-       "      <th>62356.0</th>\n",
-       "      <td>0.000083</td>\n",
-       "      <td>0.000087</td>\n",
-       "      <td>0.000050</td>\n",
-       "      <td>0.000116</td>\n",
-       "      <td>0.000106</td>\n",
-       "      <td>0.000112</td>\n",
-       "      <td>0.000087</td>\n",
-       "      <td>0.000068</td>\n",
-       "      <td>0.000094</td>\n",
-       "      <td>0.000026</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.00000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000023</td>\n",
-       "      <td>0.000045</td>\n",
-       "      <td>0.000171</td>\n",
-       "      <td>0.000065</td>\n",
-       "      <td>0.000014</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79599.0</th>\n",
-       "      <td>0.000083</td>\n",
-       "      <td>0.000087</td>\n",
-       "      <td>0.000050</td>\n",
-       "      <td>0.000116</td>\n",
-       "      <td>0.000106</td>\n",
-       "      <td>0.000112</td>\n",
-       "      <td>0.000087</td>\n",
-       "      <td>0.000068</td>\n",
-       "      <td>0.000094</td>\n",
-       "      <td>0.000026</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.00000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000023</td>\n",
-       "      <td>0.000045</td>\n",
-       "      <td>0.000171</td>\n",
-       "      <td>0.000065</td>\n",
-       "      <td>0.000014</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79600.0</th>\n",
-       "      <td>0.000083</td>\n",
-       "      <td>0.000087</td>\n",
-       "      <td>0.000050</td>\n",
-       "      <td>0.000116</td>\n",
-       "      <td>0.000106</td>\n",
-       "      <td>0.000112</td>\n",
-       "      <td>0.000087</td>\n",
-       "      <td>0.000068</td>\n",
-       "      <td>0.000094</td>\n",
-       "      <td>0.000026</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.00000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000023</td>\n",
-       "      <td>0.000045</td>\n",
-       "      <td>0.000171</td>\n",
-       "      <td>0.000065</td>\n",
-       "      <td>0.000014</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79601.0</th>\n",
-       "      <td>0.000083</td>\n",
-       "      <td>0.000087</td>\n",
-       "      <td>0.000050</td>\n",
-       "      <td>0.000116</td>\n",
-       "      <td>0.000106</td>\n",
-       "      <td>0.000112</td>\n",
-       "      <td>0.000087</td>\n",
-       "      <td>0.000068</td>\n",
-       "      <td>0.000094</td>\n",
-       "      <td>0.000026</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.00000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000023</td>\n",
-       "      <td>0.000045</td>\n",
-       "      <td>0.000171</td>\n",
-       "      <td>0.000065</td>\n",
-       "      <td>0.000014</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>80317.0</th>\n",
-       "      <td>0.000372</td>\n",
-       "      <td>0.000540</td>\n",
-       "      <td>0.000613</td>\n",
-       "      <td>0.000722</td>\n",
-       "      <td>0.000815</td>\n",
-       "      <td>0.001095</td>\n",
-       "      <td>0.001092</td>\n",
-       "      <td>0.001170</td>\n",
-       "      <td>0.001545</td>\n",
-       "      <td>0.001709</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.001885</td>\n",
-       "      <td>0.002085</td>\n",
-       "      <td>0.00216</td>\n",
-       "      <td>0.003642</td>\n",
-       "      <td>0.002133</td>\n",
-       "      <td>0.002913</td>\n",
-       "      <td>0.002323</td>\n",
-       "      <td>0.003203</td>\n",
-       "      <td>0.003237</td>\n",
-       "      <td>0.003281</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th rowspan=\"5\" valign=\"top\">573</th>\n",
-       "      <th>190496.0</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190507.0</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190508.0</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190510.0</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190511.0</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>...</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>0.000000</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>471960 rows × 36 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                       step_pred_1  step_pred_2  step_pred_3  step_pred_4  \\\n",
-       "month_id priogrid_gid                                                       \n",
-       "538      62356.0          0.000083     0.000087     0.000050     0.000116   \n",
-       "         79599.0          0.000083     0.000087     0.000050     0.000116   \n",
-       "         79600.0          0.000083     0.000087     0.000050     0.000116   \n",
-       "         79601.0          0.000083     0.000087     0.000050     0.000116   \n",
-       "         80317.0          0.000372     0.000540     0.000613     0.000722   \n",
-       "...                            ...          ...          ...          ...   \n",
-       "573      190496.0              NaN          NaN          NaN          NaN   \n",
-       "         190507.0              NaN          NaN          NaN          NaN   \n",
-       "         190508.0              NaN          NaN          NaN          NaN   \n",
-       "         190510.0              NaN          NaN          NaN          NaN   \n",
-       "         190511.0              NaN          NaN          NaN          NaN   \n",
-       "\n",
-       "                       step_pred_5  step_pred_6  step_pred_7  step_pred_8  \\\n",
-       "month_id priogrid_gid                                                       \n",
-       "538      62356.0          0.000106     0.000112     0.000087     0.000068   \n",
-       "         79599.0          0.000106     0.000112     0.000087     0.000068   \n",
-       "         79600.0          0.000106     0.000112     0.000087     0.000068   \n",
-       "         79601.0          0.000106     0.000112     0.000087     0.000068   \n",
-       "         80317.0          0.000815     0.001095     0.001092     0.001170   \n",
-       "...                            ...          ...          ...          ...   \n",
-       "573      190496.0              NaN          NaN          NaN          NaN   \n",
-       "         190507.0              NaN          NaN          NaN          NaN   \n",
-       "         190508.0              NaN          NaN          NaN          NaN   \n",
-       "         190510.0              NaN          NaN          NaN          NaN   \n",
-       "         190511.0              NaN          NaN          NaN          NaN   \n",
-       "\n",
-       "                       step_pred_9  step_pred_10  ...  step_pred_27  \\\n",
-       "month_id priogrid_gid                             ...                 \n",
-       "538      62356.0          0.000094      0.000026  ...      0.000000   \n",
-       "         79599.0          0.000094      0.000026  ...      0.000000   \n",
-       "         79600.0          0.000094      0.000026  ...      0.000000   \n",
-       "         79601.0          0.000094      0.000026  ...      0.000000   \n",
-       "         80317.0          0.001545      0.001709  ...      0.001885   \n",
-       "...                            ...           ...  ...           ...   \n",
-       "573      190496.0              NaN           NaN  ...           NaN   \n",
-       "         190507.0              NaN           NaN  ...           NaN   \n",
-       "         190508.0              NaN           NaN  ...           NaN   \n",
-       "         190510.0              NaN           NaN  ...           NaN   \n",
-       "         190511.0              NaN           NaN  ...           NaN   \n",
-       "\n",
-       "                       step_pred_28  step_pred_29  step_pred_30  step_pred_31  \\\n",
-       "month_id priogrid_gid                                                           \n",
-       "538      62356.0           0.000000       0.00000      0.000000      0.000023   \n",
-       "         79599.0           0.000000       0.00000      0.000000      0.000023   \n",
-       "         79600.0           0.000000       0.00000      0.000000      0.000023   \n",
-       "         79601.0           0.000000       0.00000      0.000000      0.000023   \n",
-       "         80317.0           0.002085       0.00216      0.003642      0.002133   \n",
-       "...                             ...           ...           ...           ...   \n",
-       "573      190496.0               NaN           NaN           NaN           NaN   \n",
-       "         190507.0               NaN           NaN           NaN           NaN   \n",
-       "         190508.0               NaN           NaN           NaN           NaN   \n",
-       "         190510.0               NaN           NaN           NaN           NaN   \n",
-       "         190511.0               NaN           NaN           NaN           NaN   \n",
-       "\n",
-       "                       step_pred_32  step_pred_33  step_pred_34  step_pred_35  \\\n",
-       "month_id priogrid_gid                                                           \n",
-       "538      62356.0           0.000045      0.000171      0.000065      0.000014   \n",
-       "         79599.0           0.000045      0.000171      0.000065      0.000014   \n",
-       "         79600.0           0.000045      0.000171      0.000065      0.000014   \n",
-       "         79601.0           0.000045      0.000171      0.000065      0.000014   \n",
-       "         80317.0           0.002913      0.002323      0.003203      0.003237   \n",
-       "...                             ...           ...           ...           ...   \n",
-       "573      190496.0               NaN           NaN           NaN           NaN   \n",
-       "         190507.0               NaN           NaN           NaN           NaN   \n",
-       "         190508.0               NaN           NaN           NaN           NaN   \n",
-       "         190510.0               NaN           NaN           NaN           NaN   \n",
-       "         190511.0               NaN           NaN           NaN           NaN   \n",
-       "\n",
-       "                       step_pred_36  \n",
-       "month_id priogrid_gid                \n",
-       "538      62356.0           0.000000  \n",
-       "         79599.0           0.000000  \n",
-       "         79600.0           0.000000  \n",
-       "         79601.0           0.000000  \n",
-       "         80317.0           0.003281  \n",
-       "...                             ...  \n",
-       "573      190496.0          0.000000  \n",
-       "         190507.0          0.000000  \n",
-       "         190508.0          0.000000  \n",
-       "         190510.0          0.000000  \n",
-       "         190511.0          0.000000  \n",
-       "\n",
-       "[471960 rows x 36 columns]"
-      ]
-     },
-     "execution_count": 74,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df_forecast_old = pd.read_pickle('models/orange_pasta/data/generated/predictions_36_forecasting_20241108_162549_old.pkl')\n",
-    "df_forecast_old"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 72,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th>step_pred_combined</th>\n",
-       "      <th>ln_ged_sb_dep</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>month_id</th>\n",
-       "      <th>priogrid_gid</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th rowspan=\"5\" valign=\"top\">538</th>\n",
-       "      <th>62356.0</th>\n",
-       "      <td>0.000083</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79599.0</th>\n",
-       "      <td>0.000083</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79600.0</th>\n",
-       "      <td>0.000083</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79601.0</th>\n",
-       "      <td>0.000083</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>80317.0</th>\n",
-       "      <td>0.000372</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th rowspan=\"5\" valign=\"top\">573</th>\n",
-       "      <th>190496.0</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190507.0</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190508.0</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190510.0</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190511.0</th>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>NaN</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>471960 rows × 2 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                       step_pred_combined  ln_ged_sb_dep\n",
-       "month_id priogrid_gid                                   \n",
-       "538      62356.0                 0.000083            NaN\n",
-       "         79599.0                 0.000083            NaN\n",
-       "         79600.0                 0.000083            NaN\n",
-       "         79601.0                 0.000083            NaN\n",
-       "         80317.0                 0.000372            NaN\n",
-       "...                                   ...            ...\n",
-       "573      190496.0                0.000000            NaN\n",
-       "         190507.0                0.000000            NaN\n",
-       "         190508.0                0.000000            NaN\n",
-       "         190510.0                0.000000            NaN\n",
-       "         190511.0                0.000000            NaN\n",
-       "\n",
-       "[471960 rows x 2 columns]"
-      ]
-     },
-     "execution_count": 72,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df_forecast_new = pd.read_pickle('models/orange_pasta/data/generated/predictions_36_forecasting_20241108_162549.pkl')\n",
-    "df_forecast_new"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 100,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'ln_ged_sb_dep'"
-      ]
-     },
-     "execution_count": 100,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df_forecast_new.forecasts.target"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 87,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "month_id  priogrid_gid\n",
-       "539       62356.0         0.000087\n",
-       "          79599.0         0.000087\n",
-       "          79600.0         0.000087\n",
-       "          79601.0         0.000087\n",
-       "          80317.0         0.000540\n",
-       "                            ...   \n",
-       "          190496.0        0.000062\n",
-       "          190507.0        0.000000\n",
-       "          190508.0        0.000000\n",
-       "          190510.0        0.000000\n",
-       "          190511.0        0.000000\n",
-       "Name: step_pred_2, Length: 13110, dtype: float64"
-      ]
-     },
-     "execution_count": 87,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df_forecast_old.loc[df_forecast_old.index.get_level_values(0) == 539].iloc[:, 1]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 95,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for i in df_forecast_new.index.get_level_values(0).unique().tolist():\n",
-    "    if (df_forecast_new.loc[df_forecast_new.index.get_level_values(0) == i].iloc[:, 0] != \n",
-    "           df_forecast_old.loc[df_forecast_old.index.get_level_values(0) == i].iloc[:, i-538]).any():\n",
-    "        print(i)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "model = pd.read_pickle('models/orange_pasta/artifacts/forecasting_model_20241108_162549.pkl')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 31,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from ingester3.ViewsMonth import ViewsMonth\n",
-    "month_last = ViewsMonth.now().id - 2\n",
-    "partitioner_dict = {\"train\":(121, month_last),\"predict\":(month_last +1, month_last + 1 + 36)}\n",
-    "train_start, train_end = partitioner_dict[\"train\"]\n",
-    "test_start, test_end = partitioner_dict[\"predict\"]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 32,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "UserWarning: `time_col` was not set and `df` has a monotonically increasing (time) index. This results in time series groups with non-overlapping (time) index. You can ignore this warning if the index represents the actual index of each individual time series group.\n"
-     ]
-    }
-   ],
-   "source": [
-    "df = pd.read_pickle('models/orange_pasta/data/raw/forecasting_viewser_df.pkl')\n",
-    "level = df.index.names[1]\n",
-    "time = df.index.names[0]\n",
-    "independent_variables = [c for c in df.columns if c != 'ln_ged_sb_dep']\n",
-    "\n",
-    "df_reset = df.reset_index(level=[1])\n",
-    "series = TimeSeries.from_group_dataframe(df_reset, group_cols=level,\n",
-    "                                                       value_cols=independent_variables + ['ln_ged_sb_dep'])\n",
-    "target_train = [s.slice(train_start, train_end + 1)['ln_ged_sb_dep']\n",
-    "                              for s in series]  # ts.slice is different from df.slice\n",
-    "past_cov_train = [series.slice(train_start, train_end + 1)[independent_variables]\n",
-    "                                for series in series]\n",
-    "past_cov = [s[independent_variables] for s in series]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 34,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "model_1 = model.models[1]\n",
-    "pred = model_1.predict(n=2,\n",
-    "                series=target_train,\n",
-    "                # darts automatically locates the time period of past_covariates\n",
-    "                past_covariates=past_cov,\n",
-    "                show_warnings=False)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 57,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "index_tuples, df_list = [], []\n",
-    "for p in pred:\n",
-    "    # For forecasting only need to keep predictions with last-month-with-data, i.e., diagonal prediction\n",
-    "    df_pred = p.pd_dataframe().loc[[test_start + 1]]\n",
-    "    l = p.static_covariates.iat[0, 0]\n",
-    "    index_tuples.extend([(month, l) for month in df_pred.index])\n",
-    "    df_list.append(df_pred.values)\n",
-    "\n",
-    "df_preds = pd.DataFrame(\n",
-    "    data=np.concatenate(df_list),\n",
-    "    index=pd.MultiIndex.from_tuples(index_tuples, names=[time, level]),\n",
-    "    columns=[f\"step_pred_combined\"]\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 60,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th>step_pred_combined</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>month_id</th>\n",
-       "      <th>priogrid_gid</th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th rowspan=\"11\" valign=\"top\">539</th>\n",
-       "      <th>62356.0</th>\n",
-       "      <td>0.000087</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79599.0</th>\n",
-       "      <td>0.000087</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79600.0</th>\n",
-       "      <td>0.000087</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79601.0</th>\n",
-       "      <td>0.000087</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>80317.0</th>\n",
-       "      <td>0.000540</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190496.0</th>\n",
-       "      <td>0.000062</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190507.0</th>\n",
-       "      <td>-0.000260</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190508.0</th>\n",
-       "      <td>-0.000260</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190510.0</th>\n",
-       "      <td>-0.000260</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190511.0</th>\n",
-       "      <td>-0.000260</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>13110 rows × 1 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                       step_pred_combined\n",
-       "month_id priogrid_gid                    \n",
-       "539      62356.0                 0.000087\n",
-       "         79599.0                 0.000087\n",
-       "         79600.0                 0.000087\n",
-       "         79601.0                 0.000087\n",
-       "         80317.0                 0.000540\n",
-       "...                                   ...\n",
-       "         190496.0                0.000062\n",
-       "         190507.0               -0.000260\n",
-       "         190508.0               -0.000260\n",
-       "         190510.0               -0.000260\n",
-       "         190511.0               -0.000260\n",
-       "\n",
-       "[13110 rows x 1 columns]"
-      ]
-     },
-     "execution_count": 60,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df_preds"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 64,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "model_2 = model.models[2]\n",
-    "pred_2 = model_2.predict(n=3,\n",
-    "                series=target_train,\n",
-    "                # darts automatically locates the time period of past_covariates\n",
-    "                past_covariates=past_cov,\n",
-    "                show_warnings=False)\n",
-    "\n",
-    "index_tuples, df_list = [], []\n",
-    "for p in pred_2:\n",
-    "    # For forecasting only need to keep predictions with last-month-with-data, i.e., diagonal prediction\n",
-    "    df_pred = p.pd_dataframe().loc[[test_start + 2]]\n",
-    "    l = p.static_covariates.iat[0, 0]\n",
-    "    index_tuples.extend([(month, l) for month in df_pred.index])\n",
-    "    df_list.append(df_pred.values)\n",
-    "\n",
-    "df_preds_2 = pd.DataFrame(\n",
-    "    data=np.concatenate(df_list),\n",
-    "    index=pd.MultiIndex.from_tuples(index_tuples, names=[time, level]),\n",
-    "    columns=[f\"step_pred_combined\"]\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 65,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th>step_pred_combined</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>month_id</th>\n",
-       "      <th>priogrid_gid</th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th rowspan=\"11\" valign=\"top\">540</th>\n",
-       "      <th>62356.0</th>\n",
-       "      <td>0.000050</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79599.0</th>\n",
-       "      <td>0.000050</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79600.0</th>\n",
-       "      <td>0.000050</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79601.0</th>\n",
-       "      <td>0.000050</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>80317.0</th>\n",
-       "      <td>0.000613</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190496.0</th>\n",
-       "      <td>-0.000126</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190507.0</th>\n",
-       "      <td>-0.000385</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190508.0</th>\n",
-       "      <td>-0.000385</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190510.0</th>\n",
-       "      <td>-0.000385</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190511.0</th>\n",
-       "      <td>-0.000385</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>13110 rows × 1 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                       step_pred_combined\n",
-       "month_id priogrid_gid                    \n",
-       "540      62356.0                 0.000050\n",
-       "         79599.0                 0.000050\n",
-       "         79600.0                 0.000050\n",
-       "         79601.0                 0.000050\n",
-       "         80317.0                 0.000613\n",
-       "...                                   ...\n",
-       "         190496.0               -0.000126\n",
-       "         190507.0               -0.000385\n",
-       "         190508.0               -0.000385\n",
-       "         190510.0               -0.000385\n",
-       "         190511.0               -0.000385\n",
-       "\n",
-       "[13110 rows x 1 columns]"
-      ]
-     },
-     "execution_count": 65,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df_preds_2"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 68,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th>step_pred_combined</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>month_id</th>\n",
-       "      <th>priogrid_gid</th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th rowspan=\"5\" valign=\"top\">539</th>\n",
-       "      <th>62356.0</th>\n",
-       "      <td>0.000087</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79599.0</th>\n",
-       "      <td>0.000087</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79600.0</th>\n",
-       "      <td>0.000087</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>79601.0</th>\n",
-       "      <td>0.000087</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>80317.0</th>\n",
-       "      <td>0.000540</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th rowspan=\"5\" valign=\"top\">540</th>\n",
-       "      <th>190496.0</th>\n",
-       "      <td>-0.000126</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190507.0</th>\n",
-       "      <td>-0.000385</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190508.0</th>\n",
-       "      <td>-0.000385</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190510.0</th>\n",
-       "      <td>-0.000385</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>190511.0</th>\n",
-       "      <td>-0.000385</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>26220 rows × 1 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                       step_pred_combined\n",
-       "month_id priogrid_gid                    \n",
-       "539      62356.0                 0.000087\n",
-       "         79599.0                 0.000087\n",
-       "         79600.0                 0.000087\n",
-       "         79601.0                 0.000087\n",
-       "         80317.0                 0.000540\n",
-       "...                                   ...\n",
-       "540      190496.0               -0.000126\n",
-       "         190507.0               -0.000385\n",
-       "         190508.0               -0.000385\n",
-       "         190510.0               -0.000385\n",
-       "         190511.0               -0.000385\n",
-       "\n",
-       "[26220 rows x 1 columns]"
-      ]
-     },
-     "execution_count": 68,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "pd.concat([df_preds, df_preds_2])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "viewser",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

From 1869f614037fe7344ce2a40470986c7f438875ab Mon Sep 17 00:00:00 2001
From: xiaolongsun <95378566+xiaolong0728@users.noreply.github.com>
Date: Thu, 6 Mar 2025 13:45:37 +0100
Subject: [PATCH 2/2] rename target variables

---
 models/bad_blood/configs/config_queryset.py   |  34 +-
 .../configs/config_queryset.py                | 352 +++++++++---------
 models/blank_space/configs/config_queryset.py |  34 +-
 .../brown_cheese/configs/config_queryset.py   |   8 +-
 models/car_radio/configs/config_queryset.py   | 136 +++----
 models/caring_fish/configs/config_queryset.py |  12 +-
 models/chunky_cat/configs/config_queryset.py  |  34 +-
 .../counting_stars/configs/config_queryset.py |  80 ++--
 .../dark_paradise/configs/config_queryset.py  |  34 +-
 models/demon_days/configs/config_queryset.py  |  78 ++--
 .../configs/config_queryset.py                |  82 ++--
 models/fast_car/configs/config_queryset.py    | 124 +++---
 .../configs/config_queryset.py                |  54 +--
 .../good_riddance/configs/config_queryset.py  |  54 +--
 .../green_squirrel/configs/config_queryset.py | 132 +++----
 .../heavy_rotation/configs/config_queryset.py | 132 +++----
 models/high_hopes/configs/config_queryset.py  |  30 +-
 .../configs/config_queryset.py                |  36 +-
 .../lavender_haze/configs/config_queryset.py  |  36 +-
 models/little_lies/configs/config_queryset.py |  54 +--
 .../midnight_rain/configs/config_queryset.py  |  50 +--
 .../configs/config_queryset.py                |  64 ++--
 models/old_money/configs/config_queryset.py   |  50 +--
 models/ominous_ox/configs/config_queryset.py  |  30 +-
 .../orange_pasta/configs/config_queryset.py   |  10 +-
 .../plastic_beach/configs/config_queryset.py  |  30 +-
 .../configs/config_queryset.py                | 136 +++----
 models/teen_spirit/configs/config_queryset.py |  30 +-
 models/twin_flame/configs/config_queryset.py  | 136 +++----
 .../wildest_dream/configs/config_queryset.py  |  20 +-
 .../yellow_pikachu/configs/config_queryset.py |  14 +-
 .../configs/config_queryset.py                |  18 +-
 32 files changed, 1062 insertions(+), 1062 deletions(-)

diff --git a/models/bad_blood/configs/config_queryset.py b/models/bad_blood/configs/config_queryset.py
index 2d363b8..e80dc5d 100644
--- a/models/bad_blood/configs/config_queryset.py
+++ b/models/bad_blood/configs/config_queryset.py
@@ -14,57 +14,57 @@ def generate():
                     .transform.missing.fill()
                     )
 
-                .with_column(Column('imr_mean', from_loa='priogrid_year', from_column='imr_mean')
+                .with_column(Column('lr_imr_mean', from_loa='priogrid_year', from_column='imr_mean')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('mountains_mean', from_loa='priogrid_year', from_column='mountains_mean')
+                .with_column(Column('lr_mountains_mean', from_loa='priogrid_year', from_column='mountains_mean')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('dist_diamsec', from_loa='priogrid', from_column='dist_diamsec_s_wgs')
+                .with_column(Column('lr_dist_diamsec', from_loa='priogrid', from_column='dist_diamsec_s_wgs')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('dist_petroleum', from_loa='priogrid', from_column='dist_petroleum_s_wgs')
+                .with_column(Column('lr_dist_petroleum', from_loa='priogrid', from_column='dist_petroleum_s_wgs')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('agri_ih', from_loa='priogrid_year', from_column='agri_ih')
+                .with_column(Column('lr_agri_ih', from_loa='priogrid_year', from_column='agri_ih')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('barren_ih', from_loa='priogrid_year', from_column='barren_ih')
+                .with_column(Column('lr_barren_ih', from_loa='priogrid_year', from_column='barren_ih')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('forest_ih', from_loa='priogrid_year', from_column='forest_ih')
+                .with_column(Column('lr_forest_ih', from_loa='priogrid_year', from_column='forest_ih')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('pasture_ih', from_loa='priogrid_year', from_column='pasture_ih')
+                .with_column(Column('lr_pasture_ih', from_loa='priogrid_year', from_column='pasture_ih')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('savanna_ih', from_loa='priogrid_year', from_column='savanna_ih')
+                .with_column(Column('lr_savanna_ih', from_loa='priogrid_year', from_column='savanna_ih')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('shrub_ih', from_loa='priogrid_year', from_column='shrub_ih')
+                .with_column(Column('lr_shrub_ih', from_loa='priogrid_year', from_column='shrub_ih')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('urban_ih', from_loa='priogrid_year', from_column='urban_ih')
+                .with_column(Column('lr_urban_ih', from_loa='priogrid_year', from_column='urban_ih')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
@@ -99,13 +99,13 @@ def generate():
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('greq_1_excluded', from_loa='priogrid_year', from_column='excluded')
+                .with_column(Column('lr_greq_1_excluded', from_loa='priogrid_year', from_column='excluded')
                     .transform.bool.gte(1)
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                .with_column(Column('lr_decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.bool.gte(1)
                     .transform.temporal.time_since()
@@ -113,7 +113,7 @@ def generate():
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('decay_ged_sb_25', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                .with_column(Column('lr_decay_ged_sb_25', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.bool.gte(25)
                     .transform.temporal.time_since()
@@ -121,7 +121,7 @@ def generate():
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('decay_ged_os_1', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+                .with_column(Column('lr_decay_ged_os_1', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.bool.gte(1)
                     .transform.temporal.time_since()
@@ -129,7 +129,7 @@ def generate():
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('splag_1_1_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                .with_column(Column('lr_splag_1_1_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.bool.gte(1)
                     .transform.temporal.time_since()
@@ -138,7 +138,7 @@ def generate():
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('splag_1_decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                .with_column(Column('lr_splag_1_decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.bool.gte(1)
                     .transform.temporal.time_since()
diff --git a/models/bittersweet_symphony/configs/config_queryset.py b/models/bittersweet_symphony/configs/config_queryset.py
index 22678a7..5b5e7ba 100644
--- a/models/bittersweet_symphony/configs/config_queryset.py
+++ b/models/bittersweet_symphony/configs/config_queryset.py
@@ -18,9 +18,6 @@ def generate():
         .transform.ops.ln()
         .transform.missing.fill()
         )
-                     
-    .with_column(Column('gleditsch_ward', from_loa='country', from_column='gwcode')
-                 )
 
     .with_column(Column('ln_ged_sb', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.ops.ln()
@@ -36,6 +33,9 @@ def generate():
         .transform.ops.ln()
         .transform.missing.fill()
         )
+    
+    .with_column(Column('lr_lr_gleditsch_ward', from_loa='country', from_column='gwcode')
+                 )
 
     .with_column(Column('ln_acled_sb', from_loa='country_month', from_column='acled_sb_fat')
         .transform.ops.ln()
@@ -52,457 +52,457 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
+    .with_column(Column('lr_lr_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_dt_oda_odat_pc_zs', from_loa='country_year', from_column='wdi_dt_oda_odat_pc_zs')
+    .with_column(Column('lr_wdi_dt_oda_odat_pc_zs', from_loa='country_year', from_column='wdi_dt_oda_odat_pc_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_ms_mil_xpnd_gd_zs', from_loa='country_year', from_column='wdi_ms_mil_xpnd_gd_zs')
+    .with_column(Column('lr_wdi_ms_mil_xpnd_gd_zs', from_loa='country_year', from_column='wdi_ms_mil_xpnd_gd_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_ms_mil_xpnd_zs', from_loa='country_year', from_column='wdi_ms_mil_xpnd_zs')
+    .with_column(Column('lr_wdi_ms_mil_xpnd_zs', from_loa='country_year', from_column='wdi_ms_mil_xpnd_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_nv_agr_totl_kd', from_loa='country_year', from_column='wdi_nv_agr_totl_kd')
+    .with_column(Column('lr_wdi_nv_agr_totl_kd', from_loa='country_year', from_column='wdi_nv_agr_totl_kd')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_nv_agr_totl_kn', from_loa='country_year', from_column='wdi_nv_agr_totl_kn')
+    .with_column(Column('lr_wdi_nv_agr_totl_kn', from_loa='country_year', from_column='wdi_nv_agr_totl_kn')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_ny_gdp_pcap_kd', from_loa='country_year', from_column='wdi_ny_gdp_pcap_kd')
+    .with_column(Column('lr_wdi_ny_gdp_pcap_kd', from_loa='country_year', from_column='wdi_ny_gdp_pcap_kd')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_dyn_le00_in', from_loa='country_year', from_column='wdi_sp_dyn_le00_in')
+    .with_column(Column('lr_wdi_sp_dyn_le00_in', from_loa='country_year', from_column='wdi_sp_dyn_le00_in')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_se_enr_prim_fm_zs', from_loa='country_year', from_column='wdi_se_enr_prim_fm_zs')
+    .with_column(Column('lr_wdi_se_enr_prim_fm_zs', from_loa='country_year', from_column='wdi_se_enr_prim_fm_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_se_enr_prsc_fm_zs', from_loa='country_year', from_column='wdi_se_enr_prsc_fm_zs')
+    .with_column(Column('lr_wdi_se_enr_prsc_fm_zs', from_loa='country_year', from_column='wdi_se_enr_prsc_fm_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_se_prm_nenr', from_loa='country_year', from_column='wdi_se_prm_nenr')
+    .with_column(Column('lr_wdi_se_prm_nenr', from_loa='country_year', from_column='wdi_se_prm_nenr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sh_sta_maln_zs', from_loa='country_year', from_column='wdi_sh_sta_maln_zs')
+    .with_column(Column('lr_wdi_sh_sta_maln_zs', from_loa='country_year', from_column='wdi_sh_sta_maln_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sh_sta_stnt_zs', from_loa='country_year', from_column='wdi_sh_sta_stnt_zs')
+    .with_column(Column('lr_wdi_sh_sta_stnt_zs', from_loa='country_year', from_column='wdi_sh_sta_stnt_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
+    .with_column(Column('lr_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
+    .with_column(Column('lr_wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
+    .with_column(Column('lr_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sm_pop_totl_zs', from_loa='country_year', from_column='wdi_sm_pop_totl_zs')
+    .with_column(Column('lr_wdi_sm_pop_totl_zs', from_loa='country_year', from_column='wdi_sm_pop_totl_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_dyn_imrt_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_in')
+    .with_column(Column('lr_wdi_sp_dyn_imrt_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_in')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sh_dyn_mort_fe', from_loa='country_year', from_column='wdi_sh_dyn_mort_fe')
+    .with_column(Column('lr_wdi_sh_dyn_mort_fe', from_loa='country_year', from_column='wdi_sh_dyn_mort_fe')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_pop_14_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_0014_fe_zs')
+    .with_column(Column('lr_wdi_sp_pop_14_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_0014_fe_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_pop_1564_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_1564_fe_zs')
+    .with_column(Column('lr_wdi_sp_pop_1564_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_1564_fe_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_pop_65up_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_65up_fe_zs')
+    .with_column(Column('lr_wdi_sp_pop_65up_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_65up_fe_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_pop_grow', from_loa='country_year', from_column='wdi_sp_pop_grow')
+    .with_column(Column('lr_wdi_sp_pop_grow', from_loa='country_year', from_column='wdi_sp_pop_grow')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_urb_totl_in_zs', from_loa='country_year', from_column='wdi_sp_urb_totl_in_zs')
+    .with_column(Column('lr_wdi_sp_urb_totl_in_zs', from_loa='country_year', from_column='wdi_sp_urb_totl_in_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_delibdem', from_loa='country_year', from_column='vdem_v2x_delibdem')
+    .with_column(Column('lr_vdem_v2x_delibdem', from_loa='country_year', from_column='vdem_v2x_delibdem')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_egaldem', from_loa='country_year', from_column='vdem_v2x_egaldem')
+    .with_column(Column('lr_vdem_v2x_egaldem', from_loa='country_year', from_column='vdem_v2x_egaldem')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_libdem', from_loa='country_year', from_column='vdem_v2x_libdem')
+    .with_column(Column('lr_vdem_v2x_libdem', from_loa='country_year', from_column='vdem_v2x_libdem')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_libdem_48', from_loa='country_year', from_column='vdem_v2x_libdem')
+    .with_column(Column('lr_vdem_v2x_libdem_48', from_loa='country_year', from_column='vdem_v2x_libdem')
         .transform.missing.fill()
         .transform.temporal.tlag(60)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_partip', from_loa='country_year', from_column='vdem_v2x_partip')
+    .with_column(Column('lr_vdem_v2x_partip', from_loa='country_year', from_column='vdem_v2x_partip')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_partipdem', from_loa='country_year', from_column='vdem_v2x_partipdem')
+    .with_column(Column('lr_vdem_v2x_partipdem', from_loa='country_year', from_column='vdem_v2x_partipdem')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_accountability', from_loa='country_year', from_column='vdem_v2x_accountability')
+    .with_column(Column('lr_vdem_v2x_accountability', from_loa='country_year', from_column='vdem_v2x_accountability')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_civlib', from_loa='country_year', from_column='vdem_v2x_civlib')
+    .with_column(Column('lr_vdem_v2x_civlib', from_loa='country_year', from_column='vdem_v2x_civlib')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_clphy', from_loa='country_year', from_column='vdem_v2x_clphy')
+    .with_column(Column('lr_vdem_v2x_clphy', from_loa='country_year', from_column='vdem_v2x_clphy')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_cspart', from_loa='country_year', from_column='vdem_v2x_cspart')
+    .with_column(Column('lr_vdem_v2x_cspart', from_loa='country_year', from_column='vdem_v2x_cspart')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_divparctrl', from_loa='country_year', from_column='vdem_v2x_divparctrl')
+    .with_column(Column('lr_vdem_v2x_divparctrl', from_loa='country_year', from_column='vdem_v2x_divparctrl')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_edcomp_thick', from_loa='country_year', from_column='vdem_v2x_edcomp_thick')
+    .with_column(Column('lr_vdem_v2x_edcomp_thick', from_loa='country_year', from_column='vdem_v2x_edcomp_thick')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_egal', from_loa='country_year', from_column='vdem_v2x_egal')
+    .with_column(Column('lr_vdem_v2x_egal', from_loa='country_year', from_column='vdem_v2x_egal')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_execorr', from_loa='country_year', from_column='vdem_v2x_execorr')
+    .with_column(Column('lr_vdem_v2x_execorr', from_loa='country_year', from_column='vdem_v2x_execorr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_frassoc_thick', from_loa='country_year', from_column='vdem_v2x_frassoc_thick')
+    .with_column(Column('lr_vdem_v2x_frassoc_thick', from_loa='country_year', from_column='vdem_v2x_frassoc_thick')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_gencs', from_loa='country_year', from_column='vdem_v2x_gencs')
+    .with_column(Column('lr_vdem_v2x_gencs', from_loa='country_year', from_column='vdem_v2x_gencs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_gender', from_loa='country_year', from_column='vdem_v2x_gender')
+    .with_column(Column('lr_vdem_v2x_gender', from_loa='country_year', from_column='vdem_v2x_gender')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_genpp', from_loa='country_year', from_column='vdem_v2x_genpp')
+    .with_column(Column('lr_vdem_v2x_genpp', from_loa='country_year', from_column='vdem_v2x_genpp')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_horacc', from_loa='country_year', from_column='vdem_v2x_horacc')
+    .with_column(Column('lr_vdem_v2x_horacc', from_loa='country_year', from_column='vdem_v2x_horacc')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_neopat', from_loa='country_year', from_column='vdem_v2x_neopat')
+    .with_column(Column('lr_vdem_v2x_neopat', from_loa='country_year', from_column='vdem_v2x_neopat')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_pubcorr', from_loa='country_year', from_column='vdem_v2x_pubcorr')
+    .with_column(Column('lr_vdem_v2x_pubcorr', from_loa='country_year', from_column='vdem_v2x_pubcorr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_rule', from_loa='country_year', from_column='vdem_v2x_rule')
+    .with_column(Column('lr_vdem_v2x_rule', from_loa='country_year', from_column='vdem_v2x_rule')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_veracc', from_loa='country_year', from_column='vdem_v2x_veracc')
+    .with_column(Column('lr_vdem_v2x_veracc', from_loa='country_year', from_column='vdem_v2x_veracc')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_ex_military', from_loa='country_year', from_column='vdem_v2x_ex_military')
+    .with_column(Column('lr_vdem_v2x_ex_military', from_loa='country_year', from_column='vdem_v2x_ex_military')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_ex_party', from_loa='country_year', from_column='vdem_v2x_ex_party')
+    .with_column(Column('lr_vdem_v2x_ex_party', from_loa='country_year', from_column='vdem_v2x_ex_party')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_freexp', from_loa='country_year', from_column='vdem_v2x_freexp')
+    .with_column(Column('lr_vdem_v2x_freexp', from_loa='country_year', from_column='vdem_v2x_freexp')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xcl_acjst', from_loa='country_year', from_column='vdem_v2xcl_acjst')
+    .with_column(Column('lr_vdem_v2xcl_acjst', from_loa='country_year', from_column='vdem_v2xcl_acjst')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
+    .with_column(Column('lr_vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xcl_prpty', from_loa='country_year', from_column='vdem_v2xcl_prpty')
+    .with_column(Column('lr_vdem_v2xcl_prpty', from_loa='country_year', from_column='vdem_v2xcl_prpty')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
+    .with_column(Column('lr_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xcl_slave', from_loa='country_year', from_column='vdem_v2xcl_slave')
+    .with_column(Column('lr_vdem_v2xcl_slave', from_loa='country_year', from_column='vdem_v2xcl_slave')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xdd_dd', from_loa='country_year', from_column='vdem_v2xdd_dd')
+    .with_column(Column('lr_vdem_v2xdd_dd', from_loa='country_year', from_column='vdem_v2xdd_dd')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xdl_delib', from_loa='country_year', from_column='vdem_v2xdl_delib')
+    .with_column(Column('lr_vdem_v2xdl_delib', from_loa='country_year', from_column='vdem_v2xdl_delib')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xeg_eqdr', from_loa='country_year', from_column='vdem_v2xeg_eqdr')
+    .with_column(Column('lr_vdem_v2xeg_eqdr', from_loa='country_year', from_column='vdem_v2xeg_eqdr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xeg_eqprotec', from_loa='country_year', from_column='vdem_v2xeg_eqprotec')
+    .with_column(Column('lr_vdem_v2xeg_eqprotec', from_loa='country_year', from_column='vdem_v2xeg_eqprotec')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xel_frefair', from_loa='country_year', from_column='vdem_v2xel_frefair')
+    .with_column(Column('lr_vdem_v2xel_frefair', from_loa='country_year', from_column='vdem_v2xel_frefair')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xel_regelec', from_loa='country_year', from_column='vdem_v2xel_regelec')
+    .with_column(Column('lr_vdem_v2xel_regelec', from_loa='country_year', from_column='vdem_v2xel_regelec')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xme_altinf', from_loa='country_year', from_column='vdem_v2xme_altinf')
+    .with_column(Column('lr_vdem_v2xme_altinf', from_loa='country_year', from_column='vdem_v2xme_altinf')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xnp_client', from_loa='country_year', from_column='vdem_v2xnp_client')
+    .with_column(Column('lr_vdem_v2xnp_client', from_loa='country_year', from_column='vdem_v2xnp_client')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xnp_regcorr', from_loa='country_year', from_column='vdem_v2xnp_regcorr')
+    .with_column(Column('lr_vdem_v2xnp_regcorr', from_loa='country_year', from_column='vdem_v2xnp_regcorr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xpe_exlecon', from_loa='country_year', from_column='vdem_v2xpe_exlecon')
+    .with_column(Column('lr_vdem_v2xpe_exlecon', from_loa='country_year', from_column='vdem_v2xpe_exlecon')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xpe_exlpol', from_loa='country_year', from_column='vdem_v2xpe_exlpol')
+    .with_column(Column('lr_vdem_v2xpe_exlpol', from_loa='country_year', from_column='vdem_v2xpe_exlpol')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xpe_exlgeo', from_loa='country_year', from_column='vdem_v2xpe_exlgeo')
+    .with_column(Column('lr_vdem_v2xpe_exlgeo', from_loa='country_year', from_column='vdem_v2xpe_exlgeo')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xpe_exlgender', from_loa='country_year', from_column='vdem_v2xpe_exlgender')
+    .with_column(Column('lr_vdem_v2xpe_exlgender', from_loa='country_year', from_column='vdem_v2xpe_exlgender')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
+    .with_column(Column('lr_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xps_party', from_loa='country_year', from_column='vdem_v2xps_party')
+    .with_column(Column('lr_vdem_v2xps_party', from_loa='country_year', from_column='vdem_v2xps_party')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xcs_ccsi', from_loa='country_year', from_column='vdem_v2xcs_ccsi')
+    .with_column(Column('lr_vdem_v2xcs_ccsi', from_loa='country_year', from_column='vdem_v2xcs_ccsi')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xnp_pres', from_loa='country_year', from_column='vdem_v2xnp_pres')
+    .with_column(Column('lr_vdem_v2xnp_pres', from_loa='country_year', from_column='vdem_v2xnp_pres')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xeg_eqaccess', from_loa='country_year', from_column='vdem_v2xeg_eqaccess')
+    .with_column(Column('lr_vdem_v2xeg_eqaccess', from_loa='country_year', from_column='vdem_v2xeg_eqaccess')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2x_diagacc', from_loa='country_year', from_column='vdem_v2x_diagacc')
+    .with_column(Column('lr_vdem_v2x_diagacc', from_loa='country_year', from_column='vdem_v2x_diagacc')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2clrgunev', from_loa='country_year', from_column='vdem_v2clrgunev')
+    .with_column(Column('lr_vdem_v2clrgunev', from_loa='country_year', from_column='vdem_v2clrgunev')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+    .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
@@ -565,21 +565,21 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_tokens_t1', from_loa='country_month', from_column='topic_tokens')
+    .with_column(Column('lr_topic_tokens_t1', from_loa='country_month', from_column='topic_tokens')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_tokens_t2', from_loa='country_month', from_column='topic_tokens')
+    .with_column(Column('lr_topic_tokens_t2', from_loa='country_month', from_column='topic_tokens')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_tokens_t13', from_loa='country_month', from_column='topic_tokens')
+    .with_column(Column('lr_topic_tokens_t13', from_loa='country_month', from_column='topic_tokens')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -601,231 +601,231 @@ def generate():
         .transform.missing.fill()
         )
             
-    .with_column(Column('topic_ste_theta0_stock_t1', from_loa='country_month', from_column='topic_ste_theta0_stock')
+    .with_column(Column('lr_topic_ste_theta0_stock_t1', from_loa='country_month', from_column='topic_ste_theta0_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta0_stock_t2', from_loa='country_month', from_column='topic_ste_theta0_stock')
+    .with_column(Column('lr_topic_ste_theta0_stock_t2', from_loa='country_month', from_column='topic_ste_theta0_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta0_stock_t13', from_loa='country_month', from_column='topic_ste_theta0_stock')
+    .with_column(Column('lr_topic_ste_theta0_stock_t13', from_loa='country_month', from_column='topic_ste_theta0_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta1_stock_t1', from_loa='country_month', from_column='topic_ste_theta1_stock')
+    .with_column(Column('lr_topic_ste_theta1_stock_t1', from_loa='country_month', from_column='topic_ste_theta1_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta1_stock_t2', from_loa='country_month', from_column='topic_ste_theta1_stock')
+    .with_column(Column('lr_topic_ste_theta1_stock_t2', from_loa='country_month', from_column='topic_ste_theta1_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta1_stock_t13', from_loa='country_month', from_column='topic_ste_theta1_stock')
+    .with_column(Column('lr_topic_ste_theta1_stock_t13', from_loa='country_month', from_column='topic_ste_theta1_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta2_stock_t1', from_loa='country_month', from_column='topic_ste_theta2_stock')
+    .with_column(Column('lr_topic_ste_theta2_stock_t1', from_loa='country_month', from_column='topic_ste_theta2_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta2_stock_t2', from_loa='country_month', from_column='topic_ste_theta2_stock')
+    .with_column(Column('lr_topic_ste_theta2_stock_t2', from_loa='country_month', from_column='topic_ste_theta2_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta2_stock_t13', from_loa='country_month', from_column='topic_ste_theta2_stock')
+    .with_column(Column('lr_topic_ste_theta2_stock_t13', from_loa='country_month', from_column='topic_ste_theta2_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta3_stock_t1', from_loa='country_month', from_column='topic_ste_theta3_stock')
+    .with_column(Column('lr_topic_ste_theta3_stock_t1', from_loa='country_month', from_column='topic_ste_theta3_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta3_stock_t2', from_loa='country_month', from_column='topic_ste_theta3_stock')
+    .with_column(Column('lr_topic_ste_theta3_stock_t2', from_loa='country_month', from_column='topic_ste_theta3_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta3_stock_t13', from_loa='country_month', from_column='topic_ste_theta3_stock')
+    .with_column(Column('lr_topic_ste_theta3_stock_t13', from_loa='country_month', from_column='topic_ste_theta3_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta4_stock_t1', from_loa='country_month', from_column='topic_ste_theta4_stock')
+    .with_column(Column('lr_topic_ste_theta4_stock_t1', from_loa='country_month', from_column='topic_ste_theta4_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta4_stock_t2', from_loa='country_month', from_column='topic_ste_theta4_stock')
+    .with_column(Column('lr_topic_ste_theta4_stock_t2', from_loa='country_month', from_column='topic_ste_theta4_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta4_stock_t13', from_loa='country_month', from_column='topic_ste_theta4_stock')
+    .with_column(Column('lr_topic_ste_theta4_stock_t13', from_loa='country_month', from_column='topic_ste_theta4_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta5_stock_t1', from_loa='country_month', from_column='topic_ste_theta5_stock')
+    .with_column(Column('lr_topic_ste_theta5_stock_t1', from_loa='country_month', from_column='topic_ste_theta5_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta5_stock_t2', from_loa='country_month', from_column='topic_ste_theta5_stock')
+    .with_column(Column('lr_topic_ste_theta5_stock_t2', from_loa='country_month', from_column='topic_ste_theta5_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta5_stock_t13', from_loa='country_month', from_column='topic_ste_theta5_stock')
+    .with_column(Column('lr_topic_ste_theta5_stock_t13', from_loa='country_month', from_column='topic_ste_theta5_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta6_stock_t1', from_loa='country_month', from_column='topic_ste_theta6_stock')
+    .with_column(Column('lr_topic_ste_theta6_stock_t1', from_loa='country_month', from_column='topic_ste_theta6_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta6_stock_t2', from_loa='country_month', from_column='topic_ste_theta6_stock')
+    .with_column(Column('lr_topic_ste_theta6_stock_t2', from_loa='country_month', from_column='topic_ste_theta6_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta6_stock_t13', from_loa='country_month', from_column='topic_ste_theta6_stock')
+    .with_column(Column('lr_topic_ste_theta6_stock_t13', from_loa='country_month', from_column='topic_ste_theta6_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta7_stock_t1', from_loa='country_month', from_column='topic_ste_theta7_stock')
+    .with_column(Column('lr_topic_ste_theta7_stock_t1', from_loa='country_month', from_column='topic_ste_theta7_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta7_stock_t2', from_loa='country_month', from_column='topic_ste_theta7_stock')
+    .with_column(Column('lr_topic_ste_theta7_stock_t2', from_loa='country_month', from_column='topic_ste_theta7_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta7_stock_t13', from_loa='country_month', from_column='topic_ste_theta7_stock')
+    .with_column(Column('lr_topic_ste_theta7_stock_t13', from_loa='country_month', from_column='topic_ste_theta7_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta8_stock_t1', from_loa='country_month', from_column='topic_ste_theta8_stock')
+    .with_column(Column('lr_topic_ste_theta8_stock_t1', from_loa='country_month', from_column='topic_ste_theta8_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta8_stock_t2', from_loa='country_month', from_column='topic_ste_theta8_stock')
+    .with_column(Column('lr_topic_ste_theta8_stock_t2', from_loa='country_month', from_column='topic_ste_theta8_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta8_stock_t13', from_loa='country_month', from_column='topic_ste_theta8_stock')
+    .with_column(Column('lr_topic_ste_theta8_stock_t13', from_loa='country_month', from_column='topic_ste_theta8_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta9_stock_t1', from_loa='country_month', from_column='topic_ste_theta9_stock')
+    .with_column(Column('lr_topic_ste_theta9_stock_t1', from_loa='country_month', from_column='topic_ste_theta9_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta9_stock_t2', from_loa='country_month', from_column='topic_ste_theta9_stock')
+    .with_column(Column('lr_topic_ste_theta9_stock_t2', from_loa='country_month', from_column='topic_ste_theta9_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta9_stock_t13', from_loa='country_month', from_column='topic_ste_theta9_stock')
+    .with_column(Column('lr_topic_ste_theta9_stock_t13', from_loa='country_month', from_column='topic_ste_theta9_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta10_stock_t1', from_loa='country_month', from_column='topic_ste_theta10_stock')
+    .with_column(Column('lr_topic_ste_theta10_stock_t1', from_loa='country_month', from_column='topic_ste_theta10_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta10_stock_t2', from_loa='country_month', from_column='topic_ste_theta10_stock')
+    .with_column(Column('lr_topic_ste_theta10_stock_t2', from_loa='country_month', from_column='topic_ste_theta10_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta10_stock_t13', from_loa='country_month', from_column='topic_ste_theta10_stock')
+    .with_column(Column('lr_topic_ste_theta10_stock_t13', from_loa='country_month', from_column='topic_ste_theta10_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -833,231 +833,231 @@ def generate():
         )
 
     
-    .with_column(Column('topic_ste_theta11_stock_t1', from_loa='country_month', from_column='topic_ste_theta11_stock')
+    .with_column(Column('lr_topic_ste_theta11_stock_t1', from_loa='country_month', from_column='topic_ste_theta11_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta11_stock_t2', from_loa='country_month', from_column='topic_ste_theta11_stock')
+    .with_column(Column('lr_topic_ste_theta11_stock_t2', from_loa='country_month', from_column='topic_ste_theta11_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta11_stock_t13', from_loa='country_month', from_column='topic_ste_theta11_stock')
+    .with_column(Column('lr_topic_ste_theta11_stock_t13', from_loa='country_month', from_column='topic_ste_theta11_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta12_stock_t1', from_loa='country_month', from_column='topic_ste_theta12_stock')
+    .with_column(Column('lr_topic_ste_theta12_stock_t1', from_loa='country_month', from_column='topic_ste_theta12_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta12_stock_t2', from_loa='country_month', from_column='topic_ste_theta12_stock')
+    .with_column(Column('lr_topic_ste_theta12_stock_t2', from_loa='country_month', from_column='topic_ste_theta12_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta12_stock_t13', from_loa='country_month', from_column='topic_ste_theta12_stock')
+    .with_column(Column('lr_topic_ste_theta12_stock_t13', from_loa='country_month', from_column='topic_ste_theta12_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta13_stock_t1', from_loa='country_month', from_column='topic_ste_theta13_stock')
+    .with_column(Column('lr_topic_ste_theta13_stock_t1', from_loa='country_month', from_column='topic_ste_theta13_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta13_stock_t2', from_loa='country_month', from_column='topic_ste_theta13_stock')
+    .with_column(Column('lr_topic_ste_theta13_stock_t2', from_loa='country_month', from_column='topic_ste_theta13_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta13_stock_t13', from_loa='country_month', from_column='topic_ste_theta13_stock')
+    .with_column(Column('lr_topic_ste_theta13_stock_t13', from_loa='country_month', from_column='topic_ste_theta13_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta14_stock_t1', from_loa='country_month', from_column='topic_ste_theta14_stock')
+    .with_column(Column('lr_topic_ste_theta14_stock_t1', from_loa='country_month', from_column='topic_ste_theta14_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(1)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta14_stock_t2', from_loa='country_month', from_column='topic_ste_theta14_stock')
+    .with_column(Column('lr_topic_ste_theta14_stock_t2', from_loa='country_month', from_column='topic_ste_theta14_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(2)
         .transform.missing.fill()
         )
 
-    .with_column(Column('topic_ste_theta14_stock_t13', from_loa='country_month', from_column='topic_ste_theta14_stock')
+    .with_column(Column('lr_topic_ste_theta14_stock_t13', from_loa='country_month', from_column='topic_ste_theta14_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
         .transform.missing.fill()
         )
 
-    .with_column(Column('splag_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
+    .with_column(Column('lr_splag_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
+    .with_column(Column('lr_splag_wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
+    .with_column(Column('lr_splag_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
+    .with_column(Column('lr_splag_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_vdem_v2x_libdem', from_loa='country_year', from_column='vdem_v2x_libdem')
+    .with_column(Column('lr_splag_vdem_v2x_libdem', from_loa='country_year', from_column='vdem_v2x_libdem')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
+    .with_column(Column('lr_splag_vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_vdem_v2x_accountability', from_loa='country_year', from_column='vdem_v2x_accountability')
+    .with_column(Column('lr_splag_vdem_v2x_accountability', from_loa='country_year', from_column='vdem_v2x_accountability')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
+    .with_column(Column('lr_splag_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
+    .with_column(Column('lr_splag_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('agr_withdrawal_pct_t48', from_loa='country_year', from_column='agr_withdrawal_pct')
+    .with_column(Column('lr_agr_withdrawal_pct_t48', from_loa='country_year', from_column='agr_withdrawal_pct')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('dam_cap_pcap_t48', from_loa='country_year', from_column='dam_cap_pcap')
+    .with_column(Column('lr_dam_cap_pcap_t48', from_loa='country_year', from_column='dam_cap_pcap')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('groundwater_export_t48', from_loa='country_year', from_column='groundwater_export')
+    .with_column(Column('lr_groundwater_export_t48', from_loa='country_year', from_column='groundwater_export')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('fresh_withdrawal_pct_t48', from_loa='country_year', from_column='fresh_withdrawal_pct')
+    .with_column(Column('lr_fresh_withdrawal_pct_t48', from_loa='country_year', from_column='fresh_withdrawal_pct')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('ind_efficiency_t48', from_loa='country_year', from_column='ind_efficiency')
+    .with_column(Column('lr_ind_efficiency_t48', from_loa='country_year', from_column='ind_efficiency')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('irr_agr_efficiency_t48', from_loa='country_year', from_column='irr_agr_efficiency')
+    .with_column(Column('lr_irr_agr_efficiency_t48', from_loa='country_year', from_column='irr_agr_efficiency')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('services_efficiency_t48', from_loa='country_year', from_column='services_efficiency')
+    .with_column(Column('lr_services_efficiency_t48', from_loa='country_year', from_column='services_efficiency')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('general_efficiency_t48', from_loa='country_year', from_column='general_efficiency')
+    .with_column(Column('lr_general_efficiency_t48', from_loa='country_year', from_column='general_efficiency')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('water_stress_t48', from_loa='country_year', from_column='water_stress')
+    .with_column(Column('lr_water_stress_t48', from_loa='country_year', from_column='water_stress')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('renewable_internal_pcap_t48', from_loa='country_year', from_column='renewable_internal_pcap')
+    .with_column(Column('lr_renewable_internal_pcap_t48', from_loa='country_year', from_column='renewable_internal_pcap')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('renewable_pcap_t48', from_loa='country_year', from_column='renewable_pcap')
+    .with_column(Column('lr_renewable_pcap_t48', from_loa='country_year', from_column='renewable_pcap')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -1065,7 +1065,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -1073,7 +1073,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(100)
         .transform.temporal.time_since()
@@ -1081,7 +1081,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(500)
         .transform.temporal.time_since()
@@ -1089,7 +1089,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_os_100', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_os_100', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(100)
         .transform.temporal.time_since()
@@ -1097,7 +1097,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -1105,7 +1105,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_ns_100', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_ns_100', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(100)
         .transform.temporal.time_since()
@@ -1113,7 +1113,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_acled_sb_5', from_loa='country_month', from_column='acled_sb_fat')
+    .with_column(Column('lr_decay_acled_sb_5', from_loa='country_month', from_column='acled_sb_fat')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -1121,7 +1121,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
+    .with_column(Column('lr_decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -1129,7 +1129,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_acled_ns_5', from_loa='country_month', from_column='acled_ns_fat')
+    .with_column(Column('lr_decay_acled_ns_5', from_loa='country_month', from_column='acled_ns_fat')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -1137,7 +1137,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -1146,7 +1146,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_1_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+    .with_column(Column('lr_splag_1_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -1155,7 +1155,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_1_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+    .with_column(Column('lr_splag_1_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -1164,7 +1164,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_tokens_t1_splag', from_loa='country_month', from_column='topic_tokens')
+    .with_column(Column('lr_topic_tokens_t1_splag', from_loa='country_month', from_column='topic_tokens')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -1173,7 +1173,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_ste_theta0_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta0_stock')
+    .with_column(Column('lr_topic_ste_theta0_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta0_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -1182,7 +1182,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_ste_theta1_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta1_stock')
+    .with_column(Column('lr_topic_ste_theta1_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta1_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -1191,7 +1191,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_ste_theta2_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta2_stock')
+    .with_column(Column('lr_topic_ste_theta2_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta2_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -1200,7 +1200,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_ste_theta3_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta3_stock')
+    .with_column(Column('lr_topic_ste_theta3_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta3_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -1209,7 +1209,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_ste_theta4_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta4_stock')
+    .with_column(Column('lr_topic_ste_theta4_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta4_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -1218,7 +1218,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_ste_theta5_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta5_stock')
+    .with_column(Column('lr_topic_ste_theta5_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta5_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -1227,7 +1227,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_ste_theta6_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta6_stock')
+    .with_column(Column('lr_topic_ste_theta6_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta6_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -1236,7 +1236,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_ste_theta7_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta7_stock')
+    .with_column(Column('lr_topic_ste_theta7_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta7_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -1245,7 +1245,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_ste_theta8_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta8_stock')
+    .with_column(Column('lr_topic_ste_theta8_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta8_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -1254,7 +1254,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_ste_theta9_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta9_stock')
+    .with_column(Column('lr_topic_ste_theta9_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta9_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -1263,7 +1263,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_ste_theta10_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta10_stock')
+    .with_column(Column('lr_topic_ste_theta10_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta10_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -1272,7 +1272,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_ste_theta11_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta11_stock')
+    .with_column(Column('lr_topic_ste_theta11_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta11_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -1281,7 +1281,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_ste_theta12_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta12_stock')
+    .with_column(Column('lr_topic_ste_theta12_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta12_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -1290,7 +1290,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_ste_theta13_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta13_stock')
+    .with_column(Column('lr_topic_ste_theta13_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta13_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
@@ -1299,7 +1299,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('topic_ste_theta14_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta14_stock')
+    .with_column(Column('lr_topic_ste_theta14_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta14_stock')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(13)
diff --git a/models/blank_space/configs/config_queryset.py b/models/blank_space/configs/config_queryset.py
index 2d363b8..e80dc5d 100644
--- a/models/blank_space/configs/config_queryset.py
+++ b/models/blank_space/configs/config_queryset.py
@@ -14,57 +14,57 @@ def generate():
                     .transform.missing.fill()
                     )
 
-                .with_column(Column('imr_mean', from_loa='priogrid_year', from_column='imr_mean')
+                .with_column(Column('lr_imr_mean', from_loa='priogrid_year', from_column='imr_mean')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('mountains_mean', from_loa='priogrid_year', from_column='mountains_mean')
+                .with_column(Column('lr_mountains_mean', from_loa='priogrid_year', from_column='mountains_mean')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('dist_diamsec', from_loa='priogrid', from_column='dist_diamsec_s_wgs')
+                .with_column(Column('lr_dist_diamsec', from_loa='priogrid', from_column='dist_diamsec_s_wgs')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('dist_petroleum', from_loa='priogrid', from_column='dist_petroleum_s_wgs')
+                .with_column(Column('lr_dist_petroleum', from_loa='priogrid', from_column='dist_petroleum_s_wgs')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('agri_ih', from_loa='priogrid_year', from_column='agri_ih')
+                .with_column(Column('lr_agri_ih', from_loa='priogrid_year', from_column='agri_ih')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('barren_ih', from_loa='priogrid_year', from_column='barren_ih')
+                .with_column(Column('lr_barren_ih', from_loa='priogrid_year', from_column='barren_ih')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('forest_ih', from_loa='priogrid_year', from_column='forest_ih')
+                .with_column(Column('lr_forest_ih', from_loa='priogrid_year', from_column='forest_ih')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('pasture_ih', from_loa='priogrid_year', from_column='pasture_ih')
+                .with_column(Column('lr_pasture_ih', from_loa='priogrid_year', from_column='pasture_ih')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('savanna_ih', from_loa='priogrid_year', from_column='savanna_ih')
+                .with_column(Column('lr_savanna_ih', from_loa='priogrid_year', from_column='savanna_ih')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('shrub_ih', from_loa='priogrid_year', from_column='shrub_ih')
+                .with_column(Column('lr_shrub_ih', from_loa='priogrid_year', from_column='shrub_ih')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('urban_ih', from_loa='priogrid_year', from_column='urban_ih')
+                .with_column(Column('lr_urban_ih', from_loa='priogrid_year', from_column='urban_ih')
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
@@ -99,13 +99,13 @@ def generate():
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('greq_1_excluded', from_loa='priogrid_year', from_column='excluded')
+                .with_column(Column('lr_greq_1_excluded', from_loa='priogrid_year', from_column='excluded')
                     .transform.bool.gte(1)
                     .transform.missing.fill()
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                .with_column(Column('lr_decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.bool.gte(1)
                     .transform.temporal.time_since()
@@ -113,7 +113,7 @@ def generate():
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('decay_ged_sb_25', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                .with_column(Column('lr_decay_ged_sb_25', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.bool.gte(25)
                     .transform.temporal.time_since()
@@ -121,7 +121,7 @@ def generate():
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('decay_ged_os_1', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+                .with_column(Column('lr_decay_ged_os_1', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.bool.gte(1)
                     .transform.temporal.time_since()
@@ -129,7 +129,7 @@ def generate():
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('splag_1_1_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                .with_column(Column('lr_splag_1_1_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.bool.gte(1)
                     .transform.temporal.time_since()
@@ -138,7 +138,7 @@ def generate():
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('splag_1_decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                .with_column(Column('lr_splag_1_decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.bool.gte(1)
                     .transform.temporal.time_since()
diff --git a/models/brown_cheese/configs/config_queryset.py b/models/brown_cheese/configs/config_queryset.py
index 853185d..d5797e3 100644
--- a/models/brown_cheese/configs/config_queryset.py
+++ b/models/brown_cheese/configs/config_queryset.py
@@ -21,14 +21,14 @@ def generate():
             .transform.missing.fill()
             )
 
-        .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+        .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -36,7 +36,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -44,7 +44,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
diff --git a/models/car_radio/configs/config_queryset.py b/models/car_radio/configs/config_queryset.py
index ae9ed83..9e0f5f3 100644
--- a/models/car_radio/configs/config_queryset.py
+++ b/models/car_radio/configs/config_queryset.py
@@ -23,350 +23,350 @@ def generate():
             .transform.missing.fill()
             )
 
-        .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+        .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_tokens_t1', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t1', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_tokens_t2', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t2', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_tokens_t13', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t13', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta0_stock_t1', from_loa='country_month', from_column='topic_ste_theta0_stock')
+        .with_column(Column('lr_topic_ste_theta0_stock_t1', from_loa='country_month', from_column='topic_ste_theta0_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta0_stock_t2', from_loa='country_month', from_column='topic_ste_theta0_stock')
+        .with_column(Column('lr_topic_ste_theta0_stock_t2', from_loa='country_month', from_column='topic_ste_theta0_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta0_stock_t13', from_loa='country_month', from_column='topic_ste_theta0_stock')
+        .with_column(Column('lr_topic_ste_theta0_stock_t13', from_loa='country_month', from_column='topic_ste_theta0_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta1_stock_t1', from_loa='country_month', from_column='topic_ste_theta1_stock')
+        .with_column(Column('lr_topic_ste_theta1_stock_t1', from_loa='country_month', from_column='topic_ste_theta1_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta1_stock_t2', from_loa='country_month', from_column='topic_ste_theta1_stock')
+        .with_column(Column('lr_topic_ste_theta1_stock_t2', from_loa='country_month', from_column='topic_ste_theta1_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta1_stock_t13', from_loa='country_month', from_column='topic_ste_theta1_stock')
+        .with_column(Column('lr_topic_ste_theta1_stock_t13', from_loa='country_month', from_column='topic_ste_theta1_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t1', from_loa='country_month', from_column='topic_ste_theta2_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t1', from_loa='country_month', from_column='topic_ste_theta2_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t2', from_loa='country_month', from_column='topic_ste_theta2_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t2', from_loa='country_month', from_column='topic_ste_theta2_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t13', from_loa='country_month', from_column='topic_ste_theta2_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t13', from_loa='country_month', from_column='topic_ste_theta2_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta3_stock_t1', from_loa='country_month', from_column='topic_ste_theta3_stock')
+        .with_column(Column('lr_topic_ste_theta3_stock_t1', from_loa='country_month', from_column='topic_ste_theta3_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta3_stock_t2', from_loa='country_month', from_column='topic_ste_theta3_stock')
+        .with_column(Column('lr_topic_ste_theta3_stock_t2', from_loa='country_month', from_column='topic_ste_theta3_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta3_stock_t13', from_loa='country_month', from_column='topic_ste_theta3_stock')
+        .with_column(Column('lr_topic_ste_theta3_stock_t13', from_loa='country_month', from_column='topic_ste_theta3_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t1', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t1', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t2', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t2', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t13', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t13', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta5_stock_t1', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta5_stock_t1', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta5_stock_t2', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta5_stock_t2', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta5_stock_t13', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta5_stock_t13', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta6_stock_t1', from_loa='country_month', from_column='topic_ste_theta6_stock')
+        .with_column(Column('lr_topic_ste_theta6_stock_t1', from_loa='country_month', from_column='topic_ste_theta6_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta6_stock_t2', from_loa='country_month', from_column='topic_ste_theta6_stock')
+        .with_column(Column('lr_topic_ste_theta6_stock_t2', from_loa='country_month', from_column='topic_ste_theta6_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta6_stock_t13', from_loa='country_month', from_column='topic_ste_theta6_stock')
+        .with_column(Column('lr_topic_ste_theta6_stock_t13', from_loa='country_month', from_column='topic_ste_theta6_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta7_stock_t1', from_loa='country_month', from_column='topic_ste_theta7_stock')
+        .with_column(Column('lr_topic_ste_theta7_stock_t1', from_loa='country_month', from_column='topic_ste_theta7_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta7_stock_t2', from_loa='country_month', from_column='topic_ste_theta7_stock')
+        .with_column(Column('lr_topic_ste_theta7_stock_t2', from_loa='country_month', from_column='topic_ste_theta7_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta7_stock_t13', from_loa='country_month', from_column='topic_ste_theta7_stock')
+        .with_column(Column('lr_topic_ste_theta7_stock_t13', from_loa='country_month', from_column='topic_ste_theta7_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta8_stock_t1', from_loa='country_month', from_column='topic_ste_theta8_stock')
+        .with_column(Column('lr_topic_ste_theta8_stock_t1', from_loa='country_month', from_column='topic_ste_theta8_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta8_stock_t2', from_loa='country_month', from_column='topic_ste_theta8_stock')
+        .with_column(Column('lr_topic_ste_theta8_stock_t2', from_loa='country_month', from_column='topic_ste_theta8_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta8_stock_t13', from_loa='country_month', from_column='topic_ste_theta8_stock')
+        .with_column(Column('lr_topic_ste_theta8_stock_t13', from_loa='country_month', from_column='topic_ste_theta8_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta9_stock_t1', from_loa='country_month', from_column='topic_ste_theta9_stock')
+        .with_column(Column('lr_topic_ste_theta9_stock_t1', from_loa='country_month', from_column='topic_ste_theta9_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta9_stock_t2', from_loa='country_month', from_column='topic_ste_theta9_stock')
+        .with_column(Column('lr_topic_ste_theta9_stock_t2', from_loa='country_month', from_column='topic_ste_theta9_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta9_stock_t13', from_loa='country_month', from_column='topic_ste_theta9_stock')
+        .with_column(Column('lr_topic_ste_theta9_stock_t13', from_loa='country_month', from_column='topic_ste_theta9_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta10_stock_t1', from_loa='country_month', from_column='topic_ste_theta10_stock')
+        .with_column(Column('lr_topic_ste_theta10_stock_t1', from_loa='country_month', from_column='topic_ste_theta10_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta10_stock_t2', from_loa='country_month', from_column='topic_ste_theta10_stock')
+        .with_column(Column('lr_topic_ste_theta10_stock_t2', from_loa='country_month', from_column='topic_ste_theta10_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta10_stock_t13', from_loa='country_month', from_column='topic_ste_theta10_stock')
+        .with_column(Column('lr_topic_ste_theta10_stock_t13', from_loa='country_month', from_column='topic_ste_theta10_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta11_stock_t1', from_loa='country_month', from_column='topic_ste_theta11_stock')
+        .with_column(Column('lr_topic_ste_theta11_stock_t1', from_loa='country_month', from_column='topic_ste_theta11_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta11_stock_t2', from_loa='country_month', from_column='topic_ste_theta11_stock')
+        .with_column(Column('lr_topic_ste_theta11_stock_t2', from_loa='country_month', from_column='topic_ste_theta11_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta11_stock_t13', from_loa='country_month', from_column='topic_ste_theta11_stock')
+        .with_column(Column('lr_topic_ste_theta11_stock_t13', from_loa='country_month', from_column='topic_ste_theta11_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta12_stock_t1', from_loa='country_month', from_column='topic_ste_theta12_stock')
+        .with_column(Column('lr_topic_ste_theta12_stock_t1', from_loa='country_month', from_column='topic_ste_theta12_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta12_stock_t2', from_loa='country_month', from_column='topic_ste_theta12_stock')
+        .with_column(Column('lr_topic_ste_theta12_stock_t2', from_loa='country_month', from_column='topic_ste_theta12_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta12_stock_t13', from_loa='country_month', from_column='topic_ste_theta12_stock')
+        .with_column(Column('lr_topic_ste_theta12_stock_t13', from_loa='country_month', from_column='topic_ste_theta12_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta13_stock_t1', from_loa='country_month', from_column='topic_ste_theta13_stock')
+        .with_column(Column('lr_topic_ste_theta13_stock_t1', from_loa='country_month', from_column='topic_ste_theta13_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta13_stock_t2', from_loa='country_month', from_column='topic_ste_theta13_stock')
+        .with_column(Column('lr_topic_ste_theta13_stock_t2', from_loa='country_month', from_column='topic_ste_theta13_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta13_stock_t13', from_loa='country_month', from_column='topic_ste_theta13_stock')
+        .with_column(Column('lr_topic_ste_theta13_stock_t13', from_loa='country_month', from_column='topic_ste_theta13_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta14_stock_t1', from_loa='country_month', from_column='topic_ste_theta14_stock')
+        .with_column(Column('lr_topic_ste_theta14_stock_t1', from_loa='country_month', from_column='topic_ste_theta14_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta14_stock_t2', from_loa='country_month', from_column='topic_ste_theta14_stock')
+        .with_column(Column('lr_topic_ste_theta14_stock_t2', from_loa='country_month', from_column='topic_ste_theta14_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta14_stock_t13', from_loa='country_month', from_column='topic_ste_theta14_stock')
+        .with_column(Column('lr_topic_ste_theta14_stock_t13', from_loa='country_month', from_column='topic_ste_theta14_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -374,7 +374,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -382,7 +382,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -391,7 +391,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_tokens_t1_splag', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t1_splag', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -400,7 +400,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta0_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta0_stock')
+        .with_column(Column('lr_topic_ste_theta0_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta0_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -409,7 +409,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta1_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta1_stock')
+        .with_column(Column('lr_topic_ste_theta1_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta1_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -418,7 +418,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta2_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta2_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -427,7 +427,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta3_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta3_stock')
+        .with_column(Column('lr_topic_ste_theta3_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta3_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -436,7 +436,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -445,7 +445,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta5_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta5_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -454,7 +454,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta6_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta6_stock')
+        .with_column(Column('lr_topic_ste_theta6_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta6_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -463,7 +463,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta7_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta7_stock')
+        .with_column(Column('lr_topic_ste_theta7_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta7_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -472,7 +472,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta8_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta8_stock')
+        .with_column(Column('lr_topic_ste_theta8_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta8_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -481,7 +481,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta9_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta9_stock')
+        .with_column(Column('lr_topic_ste_theta9_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta9_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -490,7 +490,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta10_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta10_stock')
+        .with_column(Column('lr_topic_ste_theta10_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta10_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -499,7 +499,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta11_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta11_stock')
+        .with_column(Column('lr_topic_ste_theta11_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta11_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -508,7 +508,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta12_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta12_stock')
+        .with_column(Column('lr_topic_ste_theta12_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta12_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -517,7 +517,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta13_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta13_stock')
+        .with_column(Column('lr_topic_ste_theta13_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta13_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -526,7 +526,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta14_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta14_stock')
+        .with_column(Column('lr_topic_ste_theta14_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta14_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
diff --git a/models/caring_fish/configs/config_queryset.py b/models/caring_fish/configs/config_queryset.py
index cafe495..c329f8e 100644
--- a/models/caring_fish/configs/config_queryset.py
+++ b/models/caring_fish/configs/config_queryset.py
@@ -45,37 +45,37 @@ def generate():
                             .transform.missing.fill()
                             )
 
-                        .with_column(Column('mov_avg_6_ged_best_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                        .with_column(Column('ln_mov_avg_6_ged_best_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                             .transform.ops.ln()
                             .transform.missing.fill()
                             .transform.temporal.moving_average(6)
                             )
 
-                        .with_column(Column('mov_avg_12_ged_best_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                        .with_column(Column('ln_mov_avg_12_ged_best_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                             .transform.ops.ln()
                             .transform.missing.fill()
                             .transform.temporal.moving_average(12)
                             )
 
-                        .with_column(Column('mov_avg_36_ged_best_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                        .with_column(Column('ln_mov_avg_36_ged_best_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                             .transform.ops.ln()
                             .transform.missing.fill()
                             .transform.temporal.moving_average(36)
                             )
 
-                        .with_column(Column('mov_sum_6_ged_best_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                        .with_column(Column('ln_mov_sum_6_ged_best_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                             .transform.ops.ln()
                             .transform.missing.fill()
                             .transform.temporal.moving_sum(6)
                             )
 
-                        .with_column(Column('mov_sum_12_ged_best_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                        .with_column(Column('ln_mov_sum_12_ged_best_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                             .transform.ops.ln()
                             .transform.missing.fill()
                             .transform.temporal.moving_sum(12)
                             )
 
-                        .with_column(Column('mov_sum_36_ged_best_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                        .with_column(Column('ln_mov_sum_36_ged_best_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                             .transform.ops.ln()
                             .transform.missing.fill()
                             .transform.temporal.moving_sum(36)
diff --git a/models/chunky_cat/configs/config_queryset.py b/models/chunky_cat/configs/config_queryset.py
index 1a42751..87bc80f 100644
--- a/models/chunky_cat/configs/config_queryset.py
+++ b/models/chunky_cat/configs/config_queryset.py
@@ -8,17 +8,17 @@ def generate():
             .transform.ops.ln()
             )
 
-        .with_column(Column('ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('ged_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_ged_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('ged_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_ged_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
@@ -29,7 +29,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_5', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_5', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -37,7 +37,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_25', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_25', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(25)
             .transform.temporal.time_since()
@@ -45,7 +45,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_100', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_100', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -53,7 +53,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_500', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_500', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(500)
             .transform.temporal.time_since()
@@ -61,7 +61,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_5', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_5', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -69,7 +69,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_25', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_25', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(25)
             .transform.temporal.time_since()
@@ -77,7 +77,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_100', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_100', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -85,7 +85,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_500', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_500', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(500)
             .transform.temporal.time_since()
@@ -93,7 +93,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_5', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_5', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -101,7 +101,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_25', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_25', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(25)
             .transform.temporal.time_since()
@@ -109,7 +109,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_100', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_100', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -117,7 +117,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_500', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_500', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(500)
             .transform.temporal.time_since()
@@ -125,7 +125,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_1_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_1_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(1)
             .transform.temporal.time_since()
@@ -134,7 +134,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(1)
             .transform.temporal.time_since()
diff --git a/models/counting_stars/configs/config_queryset.py b/models/counting_stars/configs/config_queryset.py
index 1162af6..7b6b869 100644
--- a/models/counting_stars/configs/config_queryset.py
+++ b/models/counting_stars/configs/config_queryset.py
@@ -13,7 +13,17 @@ def generate():
     # VIEWSER 6, Example configuration. Modify as needed.
 
     queryset = (Queryset('fatalities003_conflict_history_long','country_month')
-        .with_column(Column('gleditsch_ward', from_loa='country', from_column='gwcode')
+        .with_column(Column('ln_ged_sb_dep', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+            .transform.ops.ln()
+            .transform.missing.fill()
+            )
+
+        .with_column(Column('ln_ged_sb', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+            .transform.ops.ln()
+            .transform.missing.fill()
+            )
+
+        .with_column(Column('lr_gleditsch_ward', from_loa='country', from_column='gwcode')
             )
 
         .with_column(Column('ln_ged_ns', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
@@ -41,22 +51,22 @@ def generate():
             .transform.missing.fill()
             )
 
-        .with_column(Column('splag_1_ged_sb', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_ged_sb', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.spatial.countrylag(1,1,0,0)
             )
 
-        .with_column(Column('splag_2_ged_sb', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_2_ged_sb', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.spatial.countrylag(1,2,0,0)
             )
 
-        .with_column(Column('splag_1_ged_os', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_ged_os', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.spatial.countrylag(1,1,0,0)
             )
 
-        .with_column(Column('splag_1_ged_ns', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_ged_ns', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.spatial.countrylag(1,1,0,0)
             )
@@ -91,17 +101,7 @@ def generate():
             .transform.missing.fill()
             )
 
-        .with_column(Column('ln_ged_sb_dep', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
-            .transform.ops.ln()
-            .transform.missing.fill()
-            )
-
-        .with_column(Column('ln_ged_sb', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
-            .transform.ops.ln()
-            .transform.missing.fill()
-            )
-
-        .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+        .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
@@ -241,7 +241,7 @@ def generate():
             .transform.missing.fill()
             )
 
-        .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -249,7 +249,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -257,7 +257,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -265,7 +265,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(500)
             .transform.temporal.time_since()
@@ -273,7 +273,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_100', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_100', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -281,7 +281,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -289,7 +289,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_100', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_100', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -297,7 +297,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_acled_sb_5', from_loa='country_month', from_column='acled_sb_fat')
+        .with_column(Column('lr_decay_acled_sb_5', from_loa='country_month', from_column='acled_sb_fat')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -305,7 +305,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
+        .with_column(Column('lr_decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -313,7 +313,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_acled_ns_5', from_loa='country_month', from_column='acled_ns_fat')
+        .with_column(Column('lr_decay_acled_ns_5', from_loa='country_month', from_column='acled_ns_fat')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -321,7 +321,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_1', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_1', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(1)
             .transform.temporal.time_since()
@@ -329,7 +329,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_25', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_25', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(25)
             .transform.temporal.time_since()
@@ -337,7 +337,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_1', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_1', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(1)
             .transform.temporal.time_since()
@@ -345,7 +345,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_25', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_25', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(25)
             .transform.temporal.time_since()
@@ -353,7 +353,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_500', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_500', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(500)
             .transform.temporal.time_since()
@@ -361,7 +361,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_1', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_1', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(1)
             .transform.temporal.time_since()
@@ -369,7 +369,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_25', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_25', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(25)
             .transform.temporal.time_since()
@@ -377,7 +377,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_500', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_500', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(500)
             .transform.temporal.time_since()
@@ -385,7 +385,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -394,7 +394,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -403,7 +403,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -412,7 +412,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -421,7 +421,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_os_100', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_os_100', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -430,7 +430,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_ns_100', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_ns_100', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
diff --git a/models/dark_paradise/configs/config_queryset.py b/models/dark_paradise/configs/config_queryset.py
index 7dedbf0..51fa8ec 100644
--- a/models/dark_paradise/configs/config_queryset.py
+++ b/models/dark_paradise/configs/config_queryset.py
@@ -9,17 +9,17 @@ def generate():
             .transform.ops.ln()
             )
 
-        .with_column(Column('ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('ged_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_ged_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('ged_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_ged_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
@@ -30,7 +30,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_5', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_5', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -38,7 +38,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_25', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_25', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(25)
             .transform.temporal.time_since()
@@ -46,7 +46,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_100', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_100', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -54,7 +54,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_500', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_500', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(500)
             .transform.temporal.time_since()
@@ -62,7 +62,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_5', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_5', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -70,7 +70,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_25', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_25', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(25)
             .transform.temporal.time_since()
@@ -78,7 +78,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_100', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_100', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -86,7 +86,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_500', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_500', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(500)
             .transform.temporal.time_since()
@@ -94,7 +94,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_5', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_5', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -102,7 +102,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_25', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_25', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(25)
             .transform.temporal.time_since()
@@ -110,7 +110,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_100', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_100', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -118,7 +118,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_500', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_500', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(500)
             .transform.temporal.time_since()
@@ -126,7 +126,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_1_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_1_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(1)
             .transform.temporal.time_since()
@@ -135,7 +135,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(1)
             .transform.temporal.time_since()
diff --git a/models/demon_days/configs/config_queryset.py b/models/demon_days/configs/config_queryset.py
index 27be9ee..ef3a4c0 100644
--- a/models/demon_days/configs/config_queryset.py
+++ b/models/demon_days/configs/config_queryset.py
@@ -23,223 +23,223 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('gleditsch_ward', from_loa='country', from_column='gwcode')
+    .with_column(Column('lr_gleditsch_ward', from_loa='country', from_column='gwcode')
         .transform.missing.fill()
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('consumer_prices_food_indices', from_loa='country_month', from_column='consumer_prices_food_indices')
+    .with_column(Column('lr_consumer_prices_food_indices', from_loa='country_month', from_column='consumer_prices_food_indices')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('consumer_prices_general_indices', from_loa='country_month', from_column='consumer_prices_general_indices')
+    .with_column(Column('lr_consumer_prices_general_indices', from_loa='country_month', from_column='consumer_prices_general_indices')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('food_price_inflation', from_loa='country_month', from_column='food_price_inflation')
+    .with_column(Column('lr_food_price_inflation', from_loa='country_month', from_column='food_price_inflation')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('avg_adequate_diet', from_loa='country_year', from_column='avg_adequate_diet')
+    .with_column(Column('lr_avg_adequate_diet', from_loa='country_year', from_column='avg_adequate_diet')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('avg_animalprotein_pcap_day', from_loa='country_year', from_column='avg_animalprotein_pcap_day')
+    .with_column(Column('lr_avg_animalprotein_pcap_day', from_loa='country_year', from_column='avg_animalprotein_pcap_day')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('avg_fprod_value', from_loa='country_year', from_column='avg_fprod_value')
+    .with_column(Column('lr_avg_fprod_value', from_loa='country_year', from_column='avg_fprod_value')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('avg_protein_pcap_day', from_loa='country_year', from_column='avg_protein_pcap_day')
+    .with_column(Column('lr_avg_protein_pcap_day', from_loa='country_year', from_column='avg_protein_pcap_day')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('gdp_pc_ppp', from_loa='country_year', from_column='gdp_pc_ppp')
+    .with_column(Column('lr_gdp_pc_ppp', from_loa='country_year', from_column='gdp_pc_ppp')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('kcal_pcap_day', from_loa='country_year', from_column='kcal_pcap_day')
+    .with_column(Column('lr_kcal_pcap_day', from_loa='country_year', from_column='kcal_pcap_day')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('kcal_pcap_day_cerotu', from_loa='country_year', from_column='kcal_pcap_day_cerotu')
+    .with_column(Column('lr_kcal_pcap_day_cerotu', from_loa='country_year', from_column='kcal_pcap_day_cerotu')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pcap_fprod_var', from_loa='country_year', from_column='pcap_fprod_var')
+    .with_column(Column('lr_pcap_fprod_var', from_loa='country_year', from_column='pcap_fprod_var')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pcap_fsupply_var', from_loa='country_year', from_column='pcap_fsupply_var')
+    .with_column(Column('lr_pcap_fsupply_var', from_loa='country_year', from_column='pcap_fsupply_var')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pct_arable_land', from_loa='country_year', from_column='pct_arable_land')
+    .with_column(Column('lr_pct_arable_land', from_loa='country_year', from_column='pct_arable_land')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pct_cereal_import', from_loa='country_year', from_column='pct_cereal_import')
+    .with_column(Column('lr_pct_cereal_import', from_loa='country_year', from_column='pct_cereal_import')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pct_fimport_merch', from_loa='country_year', from_column='pct_fimport_merch')
+    .with_column(Column('lr_pct_fimport_merch', from_loa='country_year', from_column='pct_fimport_merch')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pct_modsevere_finsecurity', from_loa='country_year', from_column='pct_modsevere_finsecurity')
+    .with_column(Column('lr_pct_modsevere_finsecurity', from_loa='country_year', from_column='pct_modsevere_finsecurity')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pct_pop_basicdrink', from_loa='country_year', from_column='pct_pop_basicdrink')
+    .with_column(Column('lr_pct_pop_basicdrink', from_loa='country_year', from_column='pct_pop_basicdrink')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pct_pop_basicsani', from_loa='country_year', from_column='pct_pop_basicsani')
+    .with_column(Column('lr_pct_pop_basicsani', from_loa='country_year', from_column='pct_pop_basicsani')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pct_pop_safedrink', from_loa='country_year', from_column='pct_pop_safedrink')
+    .with_column(Column('lr_pct_pop_safedrink', from_loa='country_year', from_column='pct_pop_safedrink')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pct_pop_safesani', from_loa='country_year', from_column='pct_pop_safesani')
+    .with_column(Column('lr_pct_pop_safesani', from_loa='country_year', from_column='pct_pop_safesani')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pct_severe_finsecurity', from_loa='country_year', from_column='pct_severe_finsecurity')
+    .with_column(Column('lr_pct_severe_finsecurity', from_loa='country_year', from_column='pct_severe_finsecurity')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pct_und5_overweight', from_loa='country_year', from_column='pct_und5_overweight')
+    .with_column(Column('lr_pct_und5_overweight', from_loa='country_year', from_column='pct_und5_overweight')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pct_und5_stunted', from_loa='country_year', from_column='pct_und5_stunted')
+    .with_column(Column('lr_pct_und5_stunted', from_loa='country_year', from_column='pct_und5_stunted')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pct_und5_wasting', from_loa='country_year', from_column='pct_und5_wasting')
+    .with_column(Column('lr_pct_und5_wasting', from_loa='country_year', from_column='pct_und5_wasting')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pct_undernourished', from_loa='country_year', from_column='pct_undernourished')
+    .with_column(Column('lr_pct_undernourished', from_loa='country_year', from_column='pct_undernourished')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pol_stability', from_loa='country_year', from_column='pol_stability')
+    .with_column(Column('lr_pol_stability', from_loa='country_year', from_column='pol_stability')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pop_modsevere_finsecurity', from_loa='country_year', from_column='pop_modsevere_finsecurity')
+    .with_column(Column('lr_pop_modsevere_finsecurity', from_loa='country_year', from_column='pop_modsevere_finsecurity')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pop_severe_finsecurity', from_loa='country_year', from_column='pop_severe_finsecurity')
+    .with_column(Column('lr_pop_severe_finsecurity', from_loa='country_year', from_column='pop_severe_finsecurity')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('pop_undernourished', from_loa='country_year', from_column='pop_undernourished')
+    .with_column(Column('lr_pop_undernourished', from_loa='country_year', from_column='pop_undernourished')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('prev_adult_obesity', from_loa='country_year', from_column='prev_adult_obesity')
+    .with_column(Column('lr_prev_adult_obesity', from_loa='country_year', from_column='prev_adult_obesity')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('prev_infant_bfeed', from_loa='country_year', from_column='prev_infant_bfeed')
+    .with_column(Column('lr_prev_infant_bfeed', from_loa='country_year', from_column='prev_infant_bfeed')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('prev_lowbweight', from_loa='country_year', from_column='prev_lowbweight')
+    .with_column(Column('lr_prev_lowbweight', from_loa='country_year', from_column='prev_lowbweight')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('prev_repr_anemia', from_loa='country_year', from_column='prev_repr_anemia')
+    .with_column(Column('lr_prev_repr_anemia', from_loa='country_year', from_column='prev_repr_anemia')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('rail_density', from_loa='country_year', from_column='rail_density')
+    .with_column(Column('lr_rail_density', from_loa='country_year', from_column='rail_density')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+    .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -247,7 +247,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -255,7 +255,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
diff --git a/models/electric_relaxation/configs/config_queryset.py b/models/electric_relaxation/configs/config_queryset.py
index af8ca51..d1c470c 100644
--- a/models/electric_relaxation/configs/config_queryset.py
+++ b/models/electric_relaxation/configs/config_queryset.py
@@ -11,48 +11,48 @@ def generate():
     
     qs_cm_cflong  = (Queryset("escwa001_cflong", "country_month")
                 # target variable
-                .with_column(Column("ged_sb_dep", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
+                .with_column(Column("lr_ged_sb_dep", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             )
                 # timelag 0 of target variable
-                .with_column(Column("ged_sb_dummy_t0", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
+                .with_column(Column("lr_ged_sb_dummy_t0", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             )
                 # further timelags of target variable
                 # sb
-                .with_column(Column("ged_sb_dummy_t1", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
+                .with_column(Column("lr_ged_sb_dummy_t1", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(1)
                             .transform.missing.fill()
                             )
-                .with_column(Column("ged_sb_dummy_t2", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
+                .with_column(Column("lr_ged_sb_dummy_t2", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(2)
                             .transform.missing.fill()
                             )
-                .with_column(Column("ged_sb_dummy_t3", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
+                .with_column(Column("lr_ged_sb_dummy_t3", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(3)
                             .transform.missing.fill()
                             ) 
-                .with_column(Column("ged_sb_dummy_t4", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
+                .with_column(Column("lr_ged_sb_dummy_t4", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(4)
                             .transform.missing.fill()
                             )
-                .with_column(Column("ged_sb_dummy_t5", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
+                .with_column(Column("lr_ged_sb_dummy_t5", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(5)
                             .transform.missing.fill()
                             )
-                .with_column(Column("ged_sb_dummy_t6", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
+                .with_column(Column("lr_ged_sb_dummy_t6", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(6)
@@ -60,82 +60,82 @@ def generate():
                             )
                         
                 # os
-                .with_column(Column("ged_os_dummy_t0", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
+                .with_column(Column("lr_ged_os_dummy_t0", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             )
-                .with_column(Column("ged_os_dummy_t1", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
+                .with_column(Column("lr_ged_os_dummy_t1", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(1)
                             .transform.missing.fill()
                             )
-                .with_column(Column("ged_os_dummy_t2", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
+                .with_column(Column("lr_ged_os_dummy_t2", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(2)
                             .transform.missing.fill()
                             )
-                .with_column(Column("ged_os_dummy_t3", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
+                .with_column(Column("lr_ged_os_dummy_t3", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(3)
                             .transform.missing.fill()
                             )                    
-                .with_column(Column("ged_os_dummy_t4", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
+                .with_column(Column("lr_ged_os_dummy_t4", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(4)
                             .transform.missing.fill()
                             )
-                .with_column(Column("ged_os_dummy_t5", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
+                .with_column(Column("lr_ged_os_dummy_t5", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(5)
                             .transform.missing.fill()
                             )
-                .with_column(Column("ged_os_dummy_t6", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
+                .with_column(Column("lr_ged_os_dummy_t6", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(6)
                             .transform.missing.fill()
                             )
                 # ns
-                .with_column(Column("ged_ns_dummy_t0", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
+                .with_column(Column("lr_ged_ns_dummy_t0", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             )
-                .with_column(Column("ged_ns_dummy_t1", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
+                .with_column(Column("lr_ged_ns_dummy_t1", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(1)
                             .transform.missing.fill()
                             )
-                .with_column(Column("ged_ns_dummy_t2", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
+                .with_column(Column("lr_ged_ns_dummy_t2", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(2)
                             .transform.missing.fill()
                             )
-                .with_column(Column("ged_ns_dummy_t3", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
+                .with_column(Column("lr_ged_ns_dummy_t3", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(3)
                             .transform.missing.fill()
                             )
-                .with_column(Column("ged_ns_dummy_t4", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
+                .with_column(Column("lr_ged_ns_dummy_t4", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(4)
                             .transform.missing.fill()
                             )
-                .with_column(Column("ged_ns_dummy_t5", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
+                .with_column(Column("lr_ged_ns_dummy_t5", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(5)
                             .transform.missing.fill()
                             )
-                .with_column(Column("ged_ns_dummy_t6", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
+                .with_column(Column("lr_ged_ns_dummy_t6", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
                             .transform.bool.gte(25)
                             .transform.missing.fill()
                             .transform.temporal.tlag(6)
@@ -143,35 +143,35 @@ def generate():
                             )
                 # Decay functions
                 # sb
-                .with_column(Column("decay_ged_sb_1", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
+                .with_column(Column("lr_decay_ged_sb_1", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(1)
                             .transform.temporal.time_since()
                             .transform.temporal.decay(24)
                             .transform.missing.replace_na()
                             )
-                .with_column(Column("decay_ged_sb_5", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
+                .with_column(Column("lr_decay_ged_sb_5", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(5)
                             .transform.temporal.time_since()
                             .transform.temporal.decay(24)
                             .transform.missing.replace_na()
                             )
-                .with_column(Column("decay_ged_sb_25", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
+                .with_column(Column("lr_decay_ged_sb_25", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(25)
                             .transform.temporal.time_since()
                             .transform.temporal.decay(24)
                             .transform.missing.replace_na()
                             )
-                .with_column(Column("decay_ged_sb_100", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
+                .with_column(Column("lr_decay_ged_sb_100", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(100)
                             .transform.temporal.time_since()
                             .transform.temporal.decay(24)
                             .transform.missing.replace_na()
                             )
-                .with_column(Column("decay_ged_sb_500", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
+                .with_column(Column("lr_decay_ged_sb_500", from_loa="country_month", from_column="ged_sb_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(500)
                             .transform.temporal.time_since()
@@ -180,28 +180,28 @@ def generate():
                             )
                 # os
                 
-                .with_column(Column("decay_ged_os_1", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
+                .with_column(Column("lr_decay_ged_os_1", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(1)
                             .transform.temporal.time_since()
                             .transform.temporal.decay(24)
                             .transform.missing.replace_na()
                             )
-                .with_column(Column("decay_ged_os_5", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
+                .with_column(Column("lr_decay_ged_os_5", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(5)
                             .transform.temporal.time_since()
                             .transform.temporal.decay(24)
                             .transform.missing.replace_na()
                             )
-                .with_column(Column("decay_ged_os_25", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
+                .with_column(Column("lr_decay_ged_os_25", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(25)
                             .transform.temporal.time_since()
                             .transform.temporal.decay(24)
                             .transform.missing.replace_na()
                             )
-                .with_column(Column("decay_ged_os_100", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
+                .with_column(Column("lr_decay_ged_os_100", from_loa="country_month", from_column="ged_os_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(100)
                             .transform.temporal.time_since()
@@ -210,28 +210,28 @@ def generate():
                             )         
                         
                 # ns
-                .with_column(Column("decay_ged_ns_1", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
+                .with_column(Column("lr_decay_ged_ns_1", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(1)
                             .transform.temporal.time_since()
                             .transform.temporal.decay(24)
                             .transform.missing.replace_na()
                             )
-                .with_column(Column("decay_ged_ns_5", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
+                .with_column(Column("lr_decay_ged_ns_5", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(5)
                             .transform.temporal.time_since()
                             .transform.temporal.decay(24)
                             .transform.missing.replace_na()
                             )
-                .with_column(Column("decay_ged_ns_25", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
+                .with_column(Column("lr_decay_ged_ns_25", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(25)
                             .transform.temporal.time_since()
                             .transform.temporal.decay(24)
                             .transform.missing.replace_na()
                             )
-                .with_column(Column("decay_ged_ns_100", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
+                .with_column(Column("lr_decay_ged_ns_100", from_loa="country_month", from_column="ged_ns_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(100)
                             .transform.temporal.time_since()
@@ -241,7 +241,7 @@ def generate():
                         
                 # Spatial lag decay functions
                         # sb
-                .with_column(Column("splag_1_decay_ged_sb_25", from_loa="country_month",
+                .with_column(Column("lr_splag_1_decay_ged_sb_25", from_loa="country_month",
                                     from_column="ged_sb_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(25)
@@ -251,7 +251,7 @@ def generate():
                             .transform.missing.replace_na()
                             )
 
-                .with_column(Column("splag_1_decay_ged_sb_500", from_loa="country_month",
+                .with_column(Column("lr_splag_1_decay_ged_sb_500", from_loa="country_month",
                                     from_column="ged_sb_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(500)
@@ -261,7 +261,7 @@ def generate():
                             .transform.missing.replace_na()
                             )
                 # os
-                .with_column(Column("splag_1_decay_ged_os_25", from_loa="country_month",
+                .with_column(Column("lr_splag_1_decay_ged_os_25", from_loa="country_month",
                                     from_column="ged_os_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(25)
@@ -270,7 +270,7 @@ def generate():
                             .transform.spatial.countrylag(1, 1, 0, 0)
                             .transform.missing.replace_na()
                             )
-                .with_column(Column("splag_1_decay_ged_os_500", from_loa="country_month",
+                .with_column(Column("lr_splag_1_decay_ged_os_500", from_loa="country_month",
                                     from_column="ged_os_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(500)
@@ -280,7 +280,7 @@ def generate():
                             .transform.missing.replace_na()
                             )
                 # ns
-                .with_column(Column("splag_1_decay_ged_ns_25", from_loa="country_month",
+                .with_column(Column("lr_splag_1_decay_ged_ns_25", from_loa="country_month",
                                     from_column="ged_ns_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(25)
@@ -289,7 +289,7 @@ def generate():
                             .transform.spatial.countrylag(1, 1, 0, 0)
                             .transform.missing.replace_na()
                             )
-                .with_column(Column("splag_1_decay_ged_ns_500", from_loa="country_month",
+                .with_column(Column("lr_splag_1_decay_ged_ns_500", from_loa="country_month",
                                     from_column="ged_ns_best_sum_nokgi")
                             .transform.missing.replace_na()
                             .transform.bool.gte(500)
diff --git a/models/fast_car/configs/config_queryset.py b/models/fast_car/configs/config_queryset.py
index fd651bb..3fad9d1 100644
--- a/models/fast_car/configs/config_queryset.py
+++ b/models/fast_car/configs/config_queryset.py
@@ -23,367 +23,367 @@ def generate():
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_delibdem', from_loa='country_year', from_column='vdem_v2x_delibdem')
+        .with_column(Column('lr_vdem_v2x_delibdem', from_loa='country_year', from_column='vdem_v2x_delibdem')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_egaldem', from_loa='country_year', from_column='vdem_v2x_egaldem')
+        .with_column(Column('lr_vdem_v2x_egaldem', from_loa='country_year', from_column='vdem_v2x_egaldem')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_libdem', from_loa='country_year', from_column='vdem_v2x_libdem')
+        .with_column(Column('lr_vdem_v2x_libdem', from_loa='country_year', from_column='vdem_v2x_libdem')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_libdem_48', from_loa='country_year', from_column='vdem_v2x_libdem')
+        .with_column(Column('lr_vdem_v2x_libdem_48', from_loa='country_year', from_column='vdem_v2x_libdem')
             .transform.missing.fill()
             .transform.temporal.tlag(60)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_partip', from_loa='country_year', from_column='vdem_v2x_partip')
+        .with_column(Column('lr_vdem_v2x_partip', from_loa='country_year', from_column='vdem_v2x_partip')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_partipdem', from_loa='country_year', from_column='vdem_v2x_partipdem')
+        .with_column(Column('lr_vdem_v2x_partipdem', from_loa='country_year', from_column='vdem_v2x_partipdem')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_accountability', from_loa='country_year', from_column='vdem_v2x_accountability')
+        .with_column(Column('lr_vdem_v2x_accountability', from_loa='country_year', from_column='vdem_v2x_accountability')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_civlib', from_loa='country_year', from_column='vdem_v2x_civlib')
+        .with_column(Column('lr_vdem_v2x_civlib', from_loa='country_year', from_column='vdem_v2x_civlib')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_clphy', from_loa='country_year', from_column='vdem_v2x_clphy')
+        .with_column(Column('lr_vdem_v2x_clphy', from_loa='country_year', from_column='vdem_v2x_clphy')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_cspart', from_loa='country_year', from_column='vdem_v2x_cspart')
+        .with_column(Column('lr_vdem_v2x_cspart', from_loa='country_year', from_column='vdem_v2x_cspart')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_divparctrl', from_loa='country_year', from_column='vdem_v2x_divparctrl')
+        .with_column(Column('lr_vdem_v2x_divparctrl', from_loa='country_year', from_column='vdem_v2x_divparctrl')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_edcomp_thick', from_loa='country_year', from_column='vdem_v2x_edcomp_thick')
+        .with_column(Column('lr_vdem_v2x_edcomp_thick', from_loa='country_year', from_column='vdem_v2x_edcomp_thick')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_egal', from_loa='country_year', from_column='vdem_v2x_egal')
+        .with_column(Column('lr_vdem_v2x_egal', from_loa='country_year', from_column='vdem_v2x_egal')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_execorr', from_loa='country_year', from_column='vdem_v2x_execorr')
+        .with_column(Column('lr_vdem_v2x_execorr', from_loa='country_year', from_column='vdem_v2x_execorr')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_frassoc_thick', from_loa='country_year', from_column='vdem_v2x_frassoc_thick')
+        .with_column(Column('lr_vdem_v2x_frassoc_thick', from_loa='country_year', from_column='vdem_v2x_frassoc_thick')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_gencs', from_loa='country_year', from_column='vdem_v2x_gencs')
+        .with_column(Column('lr_vdem_v2x_gencs', from_loa='country_year', from_column='vdem_v2x_gencs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_gender', from_loa='country_year', from_column='vdem_v2x_gender')
+        .with_column(Column('lr_vdem_v2x_gender', from_loa='country_year', from_column='vdem_v2x_gender')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_genpp', from_loa='country_year', from_column='vdem_v2x_genpp')
+        .with_column(Column('lr_vdem_v2x_genpp', from_loa='country_year', from_column='vdem_v2x_genpp')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_horacc', from_loa='country_year', from_column='vdem_v2x_horacc')
+        .with_column(Column('lr_vdem_v2x_horacc', from_loa='country_year', from_column='vdem_v2x_horacc')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_neopat', from_loa='country_year', from_column='vdem_v2x_neopat')
+        .with_column(Column('lr_vdem_v2x_neopat', from_loa='country_year', from_column='vdem_v2x_neopat')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_pubcorr', from_loa='country_year', from_column='vdem_v2x_pubcorr')
+        .with_column(Column('lr_vdem_v2x_pubcorr', from_loa='country_year', from_column='vdem_v2x_pubcorr')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_rule', from_loa='country_year', from_column='vdem_v2x_rule')
+        .with_column(Column('lr_vdem_v2x_rule', from_loa='country_year', from_column='vdem_v2x_rule')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_veracc', from_loa='country_year', from_column='vdem_v2x_veracc')
+        .with_column(Column('lr_vdem_v2x_veracc', from_loa='country_year', from_column='vdem_v2x_veracc')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_ex_military', from_loa='country_year', from_column='vdem_v2x_ex_military')
+        .with_column(Column('lr_vdem_v2x_ex_military', from_loa='country_year', from_column='vdem_v2x_ex_military')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_ex_party', from_loa='country_year', from_column='vdem_v2x_ex_party')
+        .with_column(Column('lr_vdem_v2x_ex_party', from_loa='country_year', from_column='vdem_v2x_ex_party')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_freexp', from_loa='country_year', from_column='vdem_v2x_freexp')
+        .with_column(Column('lr_vdem_v2x_freexp', from_loa='country_year', from_column='vdem_v2x_freexp')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xcl_acjst', from_loa='country_year', from_column='vdem_v2xcl_acjst')
+        .with_column(Column('lr_vdem_v2xcl_acjst', from_loa='country_year', from_column='vdem_v2xcl_acjst')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
+        .with_column(Column('lr_vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xcl_prpty', from_loa='country_year', from_column='vdem_v2xcl_prpty')
+        .with_column(Column('lr_vdem_v2xcl_prpty', from_loa='country_year', from_column='vdem_v2xcl_prpty')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
+        .with_column(Column('lr_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xcl_slave', from_loa='country_year', from_column='vdem_v2xcl_slave')
+        .with_column(Column('lr_vdem_v2xcl_slave', from_loa='country_year', from_column='vdem_v2xcl_slave')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xdd_dd', from_loa='country_year', from_column='vdem_v2xdd_dd')
+        .with_column(Column('lr_vdem_v2xdd_dd', from_loa='country_year', from_column='vdem_v2xdd_dd')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xdl_delib', from_loa='country_year', from_column='vdem_v2xdl_delib')
+        .with_column(Column('lr_vdem_v2xdl_delib', from_loa='country_year', from_column='vdem_v2xdl_delib')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xeg_eqdr', from_loa='country_year', from_column='vdem_v2xeg_eqdr')
+        .with_column(Column('lr_vdem_v2xeg_eqdr', from_loa='country_year', from_column='vdem_v2xeg_eqdr')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xeg_eqprotec', from_loa='country_year', from_column='vdem_v2xeg_eqprotec')
+        .with_column(Column('lr_vdem_v2xeg_eqprotec', from_loa='country_year', from_column='vdem_v2xeg_eqprotec')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xel_frefair', from_loa='country_year', from_column='vdem_v2xel_frefair')
+        .with_column(Column('lr_vdem_v2xel_frefair', from_loa='country_year', from_column='vdem_v2xel_frefair')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xel_regelec', from_loa='country_year', from_column='vdem_v2xel_regelec')
+        .with_column(Column('lr_vdem_v2xel_regelec', from_loa='country_year', from_column='vdem_v2xel_regelec')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xme_altinf', from_loa='country_year', from_column='vdem_v2xme_altinf')
+        .with_column(Column('lr_vdem_v2xme_altinf', from_loa='country_year', from_column='vdem_v2xme_altinf')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xnp_client', from_loa='country_year', from_column='vdem_v2xnp_client')
+        .with_column(Column('lr_vdem_v2xnp_client', from_loa='country_year', from_column='vdem_v2xnp_client')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xnp_regcorr', from_loa='country_year', from_column='vdem_v2xnp_regcorr')
+        .with_column(Column('lr_vdem_v2xnp_regcorr', from_loa='country_year', from_column='vdem_v2xnp_regcorr')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xpe_exlecon', from_loa='country_year', from_column='vdem_v2xpe_exlecon')
+        .with_column(Column('lr_vdem_v2xpe_exlecon', from_loa='country_year', from_column='vdem_v2xpe_exlecon')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xpe_exlpol', from_loa='country_year', from_column='vdem_v2xpe_exlpol')
+        .with_column(Column('lr_vdem_v2xpe_exlpol', from_loa='country_year', from_column='vdem_v2xpe_exlpol')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xpe_exlgeo', from_loa='country_year', from_column='vdem_v2xpe_exlgeo')
+        .with_column(Column('lr_vdem_v2xpe_exlgeo', from_loa='country_year', from_column='vdem_v2xpe_exlgeo')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xpe_exlgender', from_loa='country_year', from_column='vdem_v2xpe_exlgender')
+        .with_column(Column('lr_vdem_v2xpe_exlgender', from_loa='country_year', from_column='vdem_v2xpe_exlgender')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
+        .with_column(Column('lr_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xps_party', from_loa='country_year', from_column='vdem_v2xps_party')
+        .with_column(Column('lr_vdem_v2xps_party', from_loa='country_year', from_column='vdem_v2xps_party')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xcs_ccsi', from_loa='country_year', from_column='vdem_v2xcs_ccsi')
+        .with_column(Column('lr_vdem_v2xcs_ccsi', from_loa='country_year', from_column='vdem_v2xcs_ccsi')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xnp_pres', from_loa='country_year', from_column='vdem_v2xnp_pres')
+        .with_column(Column('lr_vdem_v2xnp_pres', from_loa='country_year', from_column='vdem_v2xnp_pres')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2xeg_eqaccess', from_loa='country_year', from_column='vdem_v2xeg_eqaccess')
+        .with_column(Column('lr_vdem_v2xeg_eqaccess', from_loa='country_year', from_column='vdem_v2xeg_eqaccess')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2x_diagacc', from_loa='country_year', from_column='vdem_v2x_diagacc')
+        .with_column(Column('lr_vdem_v2x_diagacc', from_loa='country_year', from_column='vdem_v2x_diagacc')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('vdem_v2clrgunev', from_loa='country_year', from_column='vdem_v2clrgunev')
+        .with_column(Column('lr_vdem_v2clrgunev', from_loa='country_year', from_column='vdem_v2clrgunev')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
+        .with_column(Column('lr_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('wdi_sp_dyn_imrt_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_in')
+        .with_column(Column('lr_wdi_sp_dyn_imrt_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_in')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             )
 
-        .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+        .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_vdem_v2x_libdem', from_loa='country_year', from_column='vdem_v2x_libdem')
+        .with_column(Column('lr_splag_vdem_v2x_libdem', from_loa='country_year', from_column='vdem_v2x_libdem')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
+        .with_column(Column('lr_splag_vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_vdem_v2x_accountability', from_loa='country_year', from_column='vdem_v2x_accountability')
+        .with_column(Column('lr_splag_vdem_v2x_accountability', from_loa='country_year', from_column='vdem_v2x_accountability')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
+        .with_column(Column('lr_splag_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
+        .with_column(Column('lr_splag_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -391,7 +391,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -399,7 +399,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
diff --git a/models/fluorescent_adolescent/configs/config_queryset.py b/models/fluorescent_adolescent/configs/config_queryset.py
index 46edf09..4e7f380 100644
--- a/models/fluorescent_adolescent/configs/config_queryset.py
+++ b/models/fluorescent_adolescent/configs/config_queryset.py
@@ -18,7 +18,7 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('gleditsch_ward', from_loa='country', from_column='gwcode')
+    .with_column(Column('lr_gleditsch_ward', from_loa='country', from_column='gwcode')
         .transform.missing.fill()
         .transform.missing.replace_na()
         )
@@ -28,90 +28,90 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('reign_tenure_months', from_loa='country_month', from_column='tenure_months')
+    .with_column(Column('lr_reign_tenure_months', from_loa='country_month', from_column='tenure_months')
         .transform.missing.fill()
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+    .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
+    .with_column(Column('lr_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_nv_agr_totl_kn', from_loa='country_year', from_column='wdi_nv_agr_totl_kn')
+    .with_column(Column('lr_wdi_nv_agr_totl_kn', from_loa='country_year', from_column='wdi_nv_agr_totl_kn')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sh_sta_maln_zs', from_loa='country_year', from_column='wdi_sh_sta_maln_zs')
+    .with_column(Column('lr_wdi_sh_sta_maln_zs', from_loa='country_year', from_column='wdi_sh_sta_maln_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
+    .with_column(Column('lr_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
+    .with_column(Column('lr_wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_dyn_imrt_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_in')
+    .with_column(Column('lr_wdi_sp_dyn_imrt_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_in')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_pop_14_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_0014_fe_zs')
+    .with_column(Column('lr_wdi_sp_pop_14_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_0014_fe_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_pop_grow', from_loa='country_year', from_column='wdi_sp_pop_grow')
+    .with_column(Column('lr_wdi_sp_pop_grow', from_loa='country_year', from_column='wdi_sp_pop_grow')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
+    .with_column(Column('lr_vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
+    .with_column(Column('lr_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xeg_eqdr', from_loa='country_year', from_column='vdem_v2xeg_eqdr')
+    .with_column(Column('lr_vdem_v2xeg_eqdr', from_loa='country_year', from_column='vdem_v2xeg_eqdr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xpe_exlpol', from_loa='country_year', from_column='vdem_v2xpe_exlpol')
+    .with_column(Column('lr_vdem_v2xpe_exlpol', from_loa='country_year', from_column='vdem_v2xpe_exlpol')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
+    .with_column(Column('lr_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
@@ -131,42 +131,42 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('splag_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
+    .with_column(Column('lr_splag_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
+    .with_column(Column('lr_splag_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
+    .with_column(Column('lr_splag_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
+    .with_column(Column('lr_splag_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
+    .with_column(Column('lr_splag_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -174,7 +174,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -182,7 +182,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
+    .with_column(Column('lr_decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -190,7 +190,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(100)
         .transform.temporal.time_since()
@@ -198,7 +198,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(500)
         .transform.temporal.time_since()
@@ -206,7 +206,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
diff --git a/models/good_riddance/configs/config_queryset.py b/models/good_riddance/configs/config_queryset.py
index 46edf09..4e7f380 100644
--- a/models/good_riddance/configs/config_queryset.py
+++ b/models/good_riddance/configs/config_queryset.py
@@ -18,7 +18,7 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('gleditsch_ward', from_loa='country', from_column='gwcode')
+    .with_column(Column('lr_gleditsch_ward', from_loa='country', from_column='gwcode')
         .transform.missing.fill()
         .transform.missing.replace_na()
         )
@@ -28,90 +28,90 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('reign_tenure_months', from_loa='country_month', from_column='tenure_months')
+    .with_column(Column('lr_reign_tenure_months', from_loa='country_month', from_column='tenure_months')
         .transform.missing.fill()
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+    .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
+    .with_column(Column('lr_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_nv_agr_totl_kn', from_loa='country_year', from_column='wdi_nv_agr_totl_kn')
+    .with_column(Column('lr_wdi_nv_agr_totl_kn', from_loa='country_year', from_column='wdi_nv_agr_totl_kn')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sh_sta_maln_zs', from_loa='country_year', from_column='wdi_sh_sta_maln_zs')
+    .with_column(Column('lr_wdi_sh_sta_maln_zs', from_loa='country_year', from_column='wdi_sh_sta_maln_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
+    .with_column(Column('lr_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
+    .with_column(Column('lr_wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_dyn_imrt_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_in')
+    .with_column(Column('lr_wdi_sp_dyn_imrt_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_in')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_pop_14_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_0014_fe_zs')
+    .with_column(Column('lr_wdi_sp_pop_14_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_0014_fe_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_pop_grow', from_loa='country_year', from_column='wdi_sp_pop_grow')
+    .with_column(Column('lr_wdi_sp_pop_grow', from_loa='country_year', from_column='wdi_sp_pop_grow')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
+    .with_column(Column('lr_vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
+    .with_column(Column('lr_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xeg_eqdr', from_loa='country_year', from_column='vdem_v2xeg_eqdr')
+    .with_column(Column('lr_vdem_v2xeg_eqdr', from_loa='country_year', from_column='vdem_v2xeg_eqdr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xpe_exlpol', from_loa='country_year', from_column='vdem_v2xpe_exlpol')
+    .with_column(Column('lr_vdem_v2xpe_exlpol', from_loa='country_year', from_column='vdem_v2xpe_exlpol')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
+    .with_column(Column('lr_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
@@ -131,42 +131,42 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('splag_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
+    .with_column(Column('lr_splag_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
+    .with_column(Column('lr_splag_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
+    .with_column(Column('lr_splag_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
+    .with_column(Column('lr_splag_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
+    .with_column(Column('lr_splag_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -174,7 +174,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -182,7 +182,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
+    .with_column(Column('lr_decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -190,7 +190,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(100)
         .transform.temporal.time_since()
@@ -198,7 +198,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(500)
         .transform.temporal.time_since()
@@ -206,7 +206,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
diff --git a/models/green_squirrel/configs/config_queryset.py b/models/green_squirrel/configs/config_queryset.py
index bb2497a..3c3b8fe 100644
--- a/models/green_squirrel/configs/config_queryset.py
+++ b/models/green_squirrel/configs/config_queryset.py
@@ -13,7 +13,7 @@ def generate():
     # VIEWSER 6, Example configuration. Modify as needed.
 
     queryset = (Queryset('fatalities003_joint_broad','country_month')
-        .with_column(Column('gleditsch_ward', from_loa='country', from_column='gwcode')
+        .with_column(Column('lr_gleditsch_ward', from_loa='country', from_column='gwcode')
             )
 
         .with_column(Column('ln_ged_sb_dep', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
@@ -58,231 +58,231 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
+        .with_column(Column('lr_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
+        .with_column(Column('lr_wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_dt_oda_odat_pc_zs', from_loa='country_year', from_column='wdi_dt_oda_odat_pc_zs')
+        .with_column(Column('lr_wdi_dt_oda_odat_pc_zs', from_loa='country_year', from_column='wdi_dt_oda_odat_pc_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_ms_mil_xpnd_gd_zs', from_loa='country_year', from_column='wdi_ms_mil_xpnd_gd_zs')
+        .with_column(Column('lr_wdi_ms_mil_xpnd_gd_zs', from_loa='country_year', from_column='wdi_ms_mil_xpnd_gd_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
+        .with_column(Column('lr_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_nv_agr_totl_kn', from_loa='country_year', from_column='wdi_nv_agr_totl_kn')
+        .with_column(Column('lr_wdi_nv_agr_totl_kn', from_loa='country_year', from_column='wdi_nv_agr_totl_kn')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_pop_grow', from_loa='country_year', from_column='wdi_sp_pop_grow')
+        .with_column(Column('lr_wdi_sp_pop_grow', from_loa='country_year', from_column='wdi_sp_pop_grow')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_se_enr_prim_fm_zs', from_loa='country_year', from_column='wdi_se_enr_prim_fm_zs')
+        .with_column(Column('lr_wdi_se_enr_prim_fm_zs', from_loa='country_year', from_column='wdi_se_enr_prim_fm_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_urb_totl_in_zs', from_loa='country_year', from_column='wdi_sp_urb_totl_in_zs')
+        .with_column(Column('lr_wdi_sp_urb_totl_in_zs', from_loa='country_year', from_column='wdi_sp_urb_totl_in_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sh_sta_maln_zs', from_loa='country_year', from_column='wdi_sh_sta_maln_zs')
+        .with_column(Column('lr_wdi_sh_sta_maln_zs', from_loa='country_year', from_column='wdi_sh_sta_maln_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_dyn_imrt_fe_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_fe_in')
+        .with_column(Column('lr_wdi_sp_dyn_imrt_fe_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_fe_in')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_ny_gdp_mktp_kd', from_loa='country_year', from_column='wdi_ny_gdp_mktp_kd')
+        .with_column(Column('lr_wdi_ny_gdp_mktp_kd', from_loa='country_year', from_column='wdi_ny_gdp_mktp_kd')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sh_sta_stnt_zs', from_loa='country_year', from_column='wdi_sh_sta_stnt_zs')
+        .with_column(Column('lr_wdi_sh_sta_stnt_zs', from_loa='country_year', from_column='wdi_sh_sta_stnt_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_horacc', from_loa='country_year', from_column='vdem_v2x_horacc')
+        .with_column(Column('lr_vdem_v2x_horacc', from_loa='country_year', from_column='vdem_v2x_horacc')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xnp_client', from_loa='country_year', from_column='vdem_v2xnp_client')
+        .with_column(Column('lr_vdem_v2xnp_client', from_loa='country_year', from_column='vdem_v2xnp_client')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_veracc', from_loa='country_year', from_column='vdem_v2x_veracc')
+        .with_column(Column('lr_vdem_v2x_veracc', from_loa='country_year', from_column='vdem_v2x_veracc')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_divparctrl', from_loa='country_year', from_column='vdem_v2x_divparctrl')
+        .with_column(Column('lr_vdem_v2x_divparctrl', from_loa='country_year', from_column='vdem_v2x_divparctrl')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xpe_exlpol', from_loa='country_year', from_column='vdem_v2xpe_exlpol')
+        .with_column(Column('lr_vdem_v2xpe_exlpol', from_loa='country_year', from_column='vdem_v2xpe_exlpol')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_diagacc', from_loa='country_year', from_column='vdem_v2x_diagacc')
+        .with_column(Column('lr_vdem_v2x_diagacc', from_loa='country_year', from_column='vdem_v2x_diagacc')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xpe_exlgeo', from_loa='country_year', from_column='vdem_v2xpe_exlgeo')
+        .with_column(Column('lr_vdem_v2xpe_exlgeo', from_loa='country_year', from_column='vdem_v2xpe_exlgeo')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xpe_exlgender', from_loa='country_year', from_column='vdem_v2xpe_exlgender')
+        .with_column(Column('lr_vdem_v2xpe_exlgender', from_loa='country_year', from_column='vdem_v2xpe_exlgender')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
+        .with_column(Column('lr_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_ex_party', from_loa='country_year', from_column='vdem_v2x_ex_party')
+        .with_column(Column('lr_vdem_v2x_ex_party', from_loa='country_year', from_column='vdem_v2x_ex_party')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_genpp', from_loa='country_year', from_column='vdem_v2x_genpp')
+        .with_column(Column('lr_vdem_v2x_genpp', from_loa='country_year', from_column='vdem_v2x_genpp')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xeg_eqdr', from_loa='country_year', from_column='vdem_v2xeg_eqdr')
+        .with_column(Column('lr_vdem_v2xeg_eqdr', from_loa='country_year', from_column='vdem_v2xeg_eqdr')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xcl_prpty', from_loa='country_year', from_column='vdem_v2xcl_prpty')
+        .with_column(Column('lr_vdem_v2xcl_prpty', from_loa='country_year', from_column='vdem_v2xcl_prpty')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xeg_eqprotec', from_loa='country_year', from_column='vdem_v2xeg_eqprotec')
+        .with_column(Column('lr_vdem_v2xeg_eqprotec', from_loa='country_year', from_column='vdem_v2xeg_eqprotec')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_ex_military', from_loa='country_year', from_column='vdem_v2x_ex_military')
+        .with_column(Column('lr_vdem_v2x_ex_military', from_loa='country_year', from_column='vdem_v2x_ex_military')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
+        .with_column(Column('lr_vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_clphy', from_loa='country_year', from_column='vdem_v2x_clphy')
+        .with_column(Column('lr_vdem_v2x_clphy', from_loa='country_year', from_column='vdem_v2x_clphy')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_hosabort', from_loa='country_year', from_column='vdem_v2x_hosabort')
+        .with_column(Column('lr_vdem_v2x_hosabort', from_loa='country_year', from_column='vdem_v2x_hosabort')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xnp_regcorr', from_loa='country_year', from_column='vdem_v2xnp_regcorr')
+        .with_column(Column('lr_vdem_v2xnp_regcorr', from_loa='country_year', from_column='vdem_v2xnp_regcorr')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+        .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
@@ -345,7 +345,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_tokens_t1', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t1', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
@@ -353,7 +353,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_tokens_t2', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t2', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
@@ -361,7 +361,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t1', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t1', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
@@ -369,7 +369,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t2', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t2', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
@@ -377,7 +377,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t13', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t13', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -385,7 +385,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t1', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t1', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
@@ -393,7 +393,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t2', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t2', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
@@ -401,7 +401,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t13', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t13', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -409,70 +409,70 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
+        .with_column(Column('lr_splag_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
+        .with_column(Column('lr_splag_wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
+        .with_column(Column('lr_splag_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
+        .with_column(Column('lr_splag_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_vdem_v2x_libdem', from_loa='country_year', from_column='vdem_v2x_libdem')
+        .with_column(Column('lr_splag_vdem_v2x_libdem', from_loa='country_year', from_column='vdem_v2x_libdem')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
+        .with_column(Column('lr_splag_vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_vdem_v2x_accountability', from_loa='country_year', from_column='vdem_v2x_accountability')
+        .with_column(Column('lr_splag_vdem_v2x_accountability', from_loa='country_year', from_column='vdem_v2x_accountability')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
+        .with_column(Column('lr_splag_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
+        .with_column(Column('lr_splag_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -480,7 +480,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -488,7 +488,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -496,7 +496,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(500)
             .transform.temporal.time_since()
@@ -504,7 +504,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_100', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_100', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -512,7 +512,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -520,7 +520,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_100', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_100', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -528,7 +528,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_acled_sb_5', from_loa='country_month', from_column='acled_sb_fat')
+        .with_column(Column('lr_decay_acled_sb_5', from_loa='country_month', from_column='acled_sb_fat')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -536,7 +536,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
+        .with_column(Column('lr_decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -544,7 +544,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_acled_ns_5', from_loa='country_month', from_column='acled_ns_fat')
+        .with_column(Column('lr_decay_acled_ns_5', from_loa='country_month', from_column='acled_ns_fat')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -552,7 +552,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -561,7 +561,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -570,7 +570,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -579,7 +579,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -588,7 +588,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
diff --git a/models/heavy_rotation/configs/config_queryset.py b/models/heavy_rotation/configs/config_queryset.py
index bb2497a..3c3b8fe 100644
--- a/models/heavy_rotation/configs/config_queryset.py
+++ b/models/heavy_rotation/configs/config_queryset.py
@@ -13,7 +13,7 @@ def generate():
     # VIEWSER 6, Example configuration. Modify as needed.
 
     queryset = (Queryset('fatalities003_joint_broad','country_month')
-        .with_column(Column('gleditsch_ward', from_loa='country', from_column='gwcode')
+        .with_column(Column('lr_gleditsch_ward', from_loa='country', from_column='gwcode')
             )
 
         .with_column(Column('ln_ged_sb_dep', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
@@ -58,231 +58,231 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
+        .with_column(Column('lr_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
+        .with_column(Column('lr_wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_dt_oda_odat_pc_zs', from_loa='country_year', from_column='wdi_dt_oda_odat_pc_zs')
+        .with_column(Column('lr_wdi_dt_oda_odat_pc_zs', from_loa='country_year', from_column='wdi_dt_oda_odat_pc_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_ms_mil_xpnd_gd_zs', from_loa='country_year', from_column='wdi_ms_mil_xpnd_gd_zs')
+        .with_column(Column('lr_wdi_ms_mil_xpnd_gd_zs', from_loa='country_year', from_column='wdi_ms_mil_xpnd_gd_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
+        .with_column(Column('lr_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_nv_agr_totl_kn', from_loa='country_year', from_column='wdi_nv_agr_totl_kn')
+        .with_column(Column('lr_wdi_nv_agr_totl_kn', from_loa='country_year', from_column='wdi_nv_agr_totl_kn')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_pop_grow', from_loa='country_year', from_column='wdi_sp_pop_grow')
+        .with_column(Column('lr_wdi_sp_pop_grow', from_loa='country_year', from_column='wdi_sp_pop_grow')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_se_enr_prim_fm_zs', from_loa='country_year', from_column='wdi_se_enr_prim_fm_zs')
+        .with_column(Column('lr_wdi_se_enr_prim_fm_zs', from_loa='country_year', from_column='wdi_se_enr_prim_fm_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_urb_totl_in_zs', from_loa='country_year', from_column='wdi_sp_urb_totl_in_zs')
+        .with_column(Column('lr_wdi_sp_urb_totl_in_zs', from_loa='country_year', from_column='wdi_sp_urb_totl_in_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sh_sta_maln_zs', from_loa='country_year', from_column='wdi_sh_sta_maln_zs')
+        .with_column(Column('lr_wdi_sh_sta_maln_zs', from_loa='country_year', from_column='wdi_sh_sta_maln_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_dyn_imrt_fe_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_fe_in')
+        .with_column(Column('lr_wdi_sp_dyn_imrt_fe_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_fe_in')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_ny_gdp_mktp_kd', from_loa='country_year', from_column='wdi_ny_gdp_mktp_kd')
+        .with_column(Column('lr_wdi_ny_gdp_mktp_kd', from_loa='country_year', from_column='wdi_ny_gdp_mktp_kd')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sh_sta_stnt_zs', from_loa='country_year', from_column='wdi_sh_sta_stnt_zs')
+        .with_column(Column('lr_wdi_sh_sta_stnt_zs', from_loa='country_year', from_column='wdi_sh_sta_stnt_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_horacc', from_loa='country_year', from_column='vdem_v2x_horacc')
+        .with_column(Column('lr_vdem_v2x_horacc', from_loa='country_year', from_column='vdem_v2x_horacc')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xnp_client', from_loa='country_year', from_column='vdem_v2xnp_client')
+        .with_column(Column('lr_vdem_v2xnp_client', from_loa='country_year', from_column='vdem_v2xnp_client')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_veracc', from_loa='country_year', from_column='vdem_v2x_veracc')
+        .with_column(Column('lr_vdem_v2x_veracc', from_loa='country_year', from_column='vdem_v2x_veracc')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_divparctrl', from_loa='country_year', from_column='vdem_v2x_divparctrl')
+        .with_column(Column('lr_vdem_v2x_divparctrl', from_loa='country_year', from_column='vdem_v2x_divparctrl')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xpe_exlpol', from_loa='country_year', from_column='vdem_v2xpe_exlpol')
+        .with_column(Column('lr_vdem_v2xpe_exlpol', from_loa='country_year', from_column='vdem_v2xpe_exlpol')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_diagacc', from_loa='country_year', from_column='vdem_v2x_diagacc')
+        .with_column(Column('lr_vdem_v2x_diagacc', from_loa='country_year', from_column='vdem_v2x_diagacc')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xpe_exlgeo', from_loa='country_year', from_column='vdem_v2xpe_exlgeo')
+        .with_column(Column('lr_vdem_v2xpe_exlgeo', from_loa='country_year', from_column='vdem_v2xpe_exlgeo')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xpe_exlgender', from_loa='country_year', from_column='vdem_v2xpe_exlgender')
+        .with_column(Column('lr_vdem_v2xpe_exlgender', from_loa='country_year', from_column='vdem_v2xpe_exlgender')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
+        .with_column(Column('lr_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_ex_party', from_loa='country_year', from_column='vdem_v2x_ex_party')
+        .with_column(Column('lr_vdem_v2x_ex_party', from_loa='country_year', from_column='vdem_v2x_ex_party')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_genpp', from_loa='country_year', from_column='vdem_v2x_genpp')
+        .with_column(Column('lr_vdem_v2x_genpp', from_loa='country_year', from_column='vdem_v2x_genpp')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xeg_eqdr', from_loa='country_year', from_column='vdem_v2xeg_eqdr')
+        .with_column(Column('lr_vdem_v2xeg_eqdr', from_loa='country_year', from_column='vdem_v2xeg_eqdr')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xcl_prpty', from_loa='country_year', from_column='vdem_v2xcl_prpty')
+        .with_column(Column('lr_vdem_v2xcl_prpty', from_loa='country_year', from_column='vdem_v2xcl_prpty')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xeg_eqprotec', from_loa='country_year', from_column='vdem_v2xeg_eqprotec')
+        .with_column(Column('lr_vdem_v2xeg_eqprotec', from_loa='country_year', from_column='vdem_v2xeg_eqprotec')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_ex_military', from_loa='country_year', from_column='vdem_v2x_ex_military')
+        .with_column(Column('lr_vdem_v2x_ex_military', from_loa='country_year', from_column='vdem_v2x_ex_military')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
+        .with_column(Column('lr_vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_clphy', from_loa='country_year', from_column='vdem_v2x_clphy')
+        .with_column(Column('lr_vdem_v2x_clphy', from_loa='country_year', from_column='vdem_v2x_clphy')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2x_hosabort', from_loa='country_year', from_column='vdem_v2x_hosabort')
+        .with_column(Column('lr_vdem_v2x_hosabort', from_loa='country_year', from_column='vdem_v2x_hosabort')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('vdem_v2xnp_regcorr', from_loa='country_year', from_column='vdem_v2xnp_regcorr')
+        .with_column(Column('lr_vdem_v2xnp_regcorr', from_loa='country_year', from_column='vdem_v2xnp_regcorr')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+        .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
@@ -345,7 +345,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_tokens_t1', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t1', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
@@ -353,7 +353,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_tokens_t2', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t2', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
@@ -361,7 +361,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t1', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t1', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
@@ -369,7 +369,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t2', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t2', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
@@ -377,7 +377,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t13', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t13', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -385,7 +385,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t1', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t1', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
@@ -393,7 +393,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t2', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t2', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
@@ -401,7 +401,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t13', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t13', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -409,70 +409,70 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
+        .with_column(Column('lr_splag_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
+        .with_column(Column('lr_splag_wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
+        .with_column(Column('lr_splag_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
+        .with_column(Column('lr_splag_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_vdem_v2x_libdem', from_loa='country_year', from_column='vdem_v2x_libdem')
+        .with_column(Column('lr_splag_vdem_v2x_libdem', from_loa='country_year', from_column='vdem_v2x_libdem')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
+        .with_column(Column('lr_splag_vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_vdem_v2x_accountability', from_loa='country_year', from_column='vdem_v2x_accountability')
+        .with_column(Column('lr_splag_vdem_v2x_accountability', from_loa='country_year', from_column='vdem_v2x_accountability')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
+        .with_column(Column('lr_splag_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
+        .with_column(Column('lr_splag_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -480,7 +480,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -488,7 +488,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -496,7 +496,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(500)
             .transform.temporal.time_since()
@@ -504,7 +504,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_100', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_100', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -512,7 +512,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -520,7 +520,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_100', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_100', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -528,7 +528,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_acled_sb_5', from_loa='country_month', from_column='acled_sb_fat')
+        .with_column(Column('lr_decay_acled_sb_5', from_loa='country_month', from_column='acled_sb_fat')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -536,7 +536,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
+        .with_column(Column('lr_decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -544,7 +544,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_acled_ns_5', from_loa='country_month', from_column='acled_ns_fat')
+        .with_column(Column('lr_decay_acled_ns_5', from_loa='country_month', from_column='acled_ns_fat')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -552,7 +552,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -561,7 +561,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -570,7 +570,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -579,7 +579,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -588,7 +588,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
diff --git a/models/high_hopes/configs/config_queryset.py b/models/high_hopes/configs/config_queryset.py
index 295f8fd..e200fde 100644
--- a/models/high_hopes/configs/config_queryset.py
+++ b/models/high_hopes/configs/config_queryset.py
@@ -13,7 +13,7 @@ def generate():
     # VIEWSER 6, Example configuration. Modify as needed.
 
     queryset = (Queryset('fatalities003_conflict_history','country_month')
-    .with_column(Column('gleditsch_ward', from_loa='country', from_column='gwcode')
+    .with_column(Column('lr_gleditsch_ward', from_loa='country', from_column='gwcode')
         )
 
     .with_column(Column('ln_ged_sb_dep', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
@@ -51,7 +51,7 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+    .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
@@ -114,7 +114,7 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -122,7 +122,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -130,7 +130,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(100)
         .transform.temporal.time_since()
@@ -138,7 +138,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(500)
         .transform.temporal.time_since()
@@ -146,7 +146,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_os_100', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_os_100', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(100)
         .transform.temporal.time_since()
@@ -154,7 +154,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -162,7 +162,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_ns_100', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_ns_100', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(100)
         .transform.temporal.time_since()
@@ -170,7 +170,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_acled_sb_5', from_loa='country_month', from_column='acled_sb_fat')
+    .with_column(Column('lr_decay_acled_sb_5', from_loa='country_month', from_column='acled_sb_fat')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -178,7 +178,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
+    .with_column(Column('lr_decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -186,7 +186,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_acled_ns_5', from_loa='country_month', from_column='acled_ns_fat')
+    .with_column(Column('lr_decay_acled_ns_5', from_loa='country_month', from_column='acled_ns_fat')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -194,7 +194,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -203,7 +203,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_1_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+    .with_column(Column('lr_splag_1_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -212,7 +212,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_1_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+    .with_column(Column('lr_splag_1_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
diff --git a/models/invisible_string/configs/config_queryset.py b/models/invisible_string/configs/config_queryset.py
index d2166a3..b76f604 100644
--- a/models/invisible_string/configs/config_queryset.py
+++ b/models/invisible_string/configs/config_queryset.py
@@ -4,19 +4,19 @@ def generate():
 
     qs_broad = (Queryset('fatalities003_pgm_broad','priogrid_month')
                 
-              .with_column(Column('tlag1_dr_mod_gs', from_loa='priogrid_month', from_column='tlag1_dr_mod_gs')
+              .with_column(Column('lr_tlag1_dr_mod_gs', from_loa='priogrid_month', from_column='tlag1_dr_mod_gs')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei1_gs_prev10_anom', from_loa='priogrid_month', from_column='spei1_gs_prev10_anom')
+              .with_column(Column('lr_spei1_gs_prev10_anom', from_loa='priogrid_month', from_column='spei1_gs_prev10_anom')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag_12_crop_sum', from_loa='priogrid_month', from_column='tlag_12_crop_sum')
+              .with_column(Column('lr_tlag_12_crop_sum', from_loa='priogrid_month', from_column='tlag_12_crop_sum')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei1gsy_lowermedian_count', from_loa='priogrid_month', from_column='spei1gsy_lowermedian_count')
+              .with_column(Column('lr_spei1gsy_lowermedian_count', from_loa='priogrid_month', from_column='spei1gsy_lowermedian_count')
                      .transform.missing.replace_na(0)
                      )
 
@@ -25,52 +25,52 @@ def generate():
                      .transform.ops.ln()
                      )
 
-              .with_column(Column('ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.fill()
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('ged_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+              .with_column(Column('lr_ged_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
                      .transform.missing.fill()
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('ged_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+              .with_column(Column('lr_ged_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
                      .transform.missing.fill()
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('treelag_1_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_treelag_1_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.spatial.treelag(0.7,1)
                      )
 
-              .with_column(Column('treelag_2_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_treelag_2_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.spatial.treelag(0.7,2)
                      )
 
-              .with_column(Column('sptime_dist_k1_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_sptime_dist_k1_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.spatial.sptime_dist('distances',1,1.0,0.0)
                      )
 
-              .with_column(Column('sptime_dist_k10_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_sptime_dist_k10_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.spatial.sptime_dist('distances',1,10.0,0.0)
                      )
 
-              .with_column(Column('sptime_dist_k001_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_sptime_dist_k001_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.spatial.sptime_dist('distances',1,0.01,0.0)
                      )
 
-              .with_column(Column('dist_diamsec', from_loa='priogrid', from_column='dist_diamsec_s_wgs')
+              .with_column(Column('lr_dist_diamsec', from_loa='priogrid', from_column='dist_diamsec_s_wgs')
                      .transform.missing.fill()
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('imr_mean', from_loa='priogrid_year', from_column='imr_mean')
+              .with_column(Column('lr_imr_mean', from_loa='priogrid_year', from_column='imr_mean')
                      .transform.missing.fill()
                      .transform.missing.replace_na()
                      )
@@ -99,7 +99,7 @@ def generate():
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('decay_ged_sb_5', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_decay_ged_sb_5', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.bool.gte(5)
                      .transform.temporal.time_since()
@@ -107,7 +107,7 @@ def generate():
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('decay_ged_os_5', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+              .with_column(Column('lr_decay_ged_os_5', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.bool.gte(5)
                      .transform.temporal.time_since()
@@ -115,7 +115,7 @@ def generate():
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('decay_ged_ns_5', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+              .with_column(Column('lr_decay_ged_ns_5', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.bool.gte(5)
                      .transform.temporal.time_since()
@@ -123,7 +123,7 @@ def generate():
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('splag_1_1_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_splag_1_1_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.bool.gte(1)
                      .transform.temporal.time_since()
diff --git a/models/lavender_haze/configs/config_queryset.py b/models/lavender_haze/configs/config_queryset.py
index d2166a3..b76f604 100644
--- a/models/lavender_haze/configs/config_queryset.py
+++ b/models/lavender_haze/configs/config_queryset.py
@@ -4,19 +4,19 @@ def generate():
 
     qs_broad = (Queryset('fatalities003_pgm_broad','priogrid_month')
                 
-              .with_column(Column('tlag1_dr_mod_gs', from_loa='priogrid_month', from_column='tlag1_dr_mod_gs')
+              .with_column(Column('lr_tlag1_dr_mod_gs', from_loa='priogrid_month', from_column='tlag1_dr_mod_gs')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei1_gs_prev10_anom', from_loa='priogrid_month', from_column='spei1_gs_prev10_anom')
+              .with_column(Column('lr_spei1_gs_prev10_anom', from_loa='priogrid_month', from_column='spei1_gs_prev10_anom')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag_12_crop_sum', from_loa='priogrid_month', from_column='tlag_12_crop_sum')
+              .with_column(Column('lr_tlag_12_crop_sum', from_loa='priogrid_month', from_column='tlag_12_crop_sum')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei1gsy_lowermedian_count', from_loa='priogrid_month', from_column='spei1gsy_lowermedian_count')
+              .with_column(Column('lr_spei1gsy_lowermedian_count', from_loa='priogrid_month', from_column='spei1gsy_lowermedian_count')
                      .transform.missing.replace_na(0)
                      )
 
@@ -25,52 +25,52 @@ def generate():
                      .transform.ops.ln()
                      )
 
-              .with_column(Column('ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.fill()
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('ged_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+              .with_column(Column('lr_ged_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
                      .transform.missing.fill()
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('ged_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+              .with_column(Column('lr_ged_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
                      .transform.missing.fill()
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('treelag_1_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_treelag_1_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.spatial.treelag(0.7,1)
                      )
 
-              .with_column(Column('treelag_2_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_treelag_2_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.spatial.treelag(0.7,2)
                      )
 
-              .with_column(Column('sptime_dist_k1_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_sptime_dist_k1_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.spatial.sptime_dist('distances',1,1.0,0.0)
                      )
 
-              .with_column(Column('sptime_dist_k10_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_sptime_dist_k10_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.spatial.sptime_dist('distances',1,10.0,0.0)
                      )
 
-              .with_column(Column('sptime_dist_k001_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_sptime_dist_k001_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.spatial.sptime_dist('distances',1,0.01,0.0)
                      )
 
-              .with_column(Column('dist_diamsec', from_loa='priogrid', from_column='dist_diamsec_s_wgs')
+              .with_column(Column('lr_dist_diamsec', from_loa='priogrid', from_column='dist_diamsec_s_wgs')
                      .transform.missing.fill()
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('imr_mean', from_loa='priogrid_year', from_column='imr_mean')
+              .with_column(Column('lr_imr_mean', from_loa='priogrid_year', from_column='imr_mean')
                      .transform.missing.fill()
                      .transform.missing.replace_na()
                      )
@@ -99,7 +99,7 @@ def generate():
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('decay_ged_sb_5', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_decay_ged_sb_5', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.bool.gte(5)
                      .transform.temporal.time_since()
@@ -107,7 +107,7 @@ def generate():
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('decay_ged_os_5', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+              .with_column(Column('lr_decay_ged_os_5', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.bool.gte(5)
                      .transform.temporal.time_since()
@@ -115,7 +115,7 @@ def generate():
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('decay_ged_ns_5', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+              .with_column(Column('lr_decay_ged_ns_5', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.bool.gte(5)
                      .transform.temporal.time_since()
@@ -123,7 +123,7 @@ def generate():
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('splag_1_1_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_splag_1_1_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.bool.gte(1)
                      .transform.temporal.time_since()
diff --git a/models/little_lies/configs/config_queryset.py b/models/little_lies/configs/config_queryset.py
index 46edf09..4e7f380 100644
--- a/models/little_lies/configs/config_queryset.py
+++ b/models/little_lies/configs/config_queryset.py
@@ -18,7 +18,7 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('gleditsch_ward', from_loa='country', from_column='gwcode')
+    .with_column(Column('lr_gleditsch_ward', from_loa='country', from_column='gwcode')
         .transform.missing.fill()
         .transform.missing.replace_na()
         )
@@ -28,90 +28,90 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('reign_tenure_months', from_loa='country_month', from_column='tenure_months')
+    .with_column(Column('lr_reign_tenure_months', from_loa='country_month', from_column='tenure_months')
         .transform.missing.fill()
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+    .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
+    .with_column(Column('lr_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_nv_agr_totl_kn', from_loa='country_year', from_column='wdi_nv_agr_totl_kn')
+    .with_column(Column('lr_wdi_nv_agr_totl_kn', from_loa='country_year', from_column='wdi_nv_agr_totl_kn')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sh_sta_maln_zs', from_loa='country_year', from_column='wdi_sh_sta_maln_zs')
+    .with_column(Column('lr_wdi_sh_sta_maln_zs', from_loa='country_year', from_column='wdi_sh_sta_maln_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
+    .with_column(Column('lr_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
+    .with_column(Column('lr_wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_dyn_imrt_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_in')
+    .with_column(Column('lr_wdi_sp_dyn_imrt_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_in')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_pop_14_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_0014_fe_zs')
+    .with_column(Column('lr_wdi_sp_pop_14_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_0014_fe_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_pop_grow', from_loa='country_year', from_column='wdi_sp_pop_grow')
+    .with_column(Column('lr_wdi_sp_pop_grow', from_loa='country_year', from_column='wdi_sp_pop_grow')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
+    .with_column(Column('lr_vdem_v2xcl_dmove', from_loa='country_year', from_column='vdem_v2xcl_dmove')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
+    .with_column(Column('lr_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xeg_eqdr', from_loa='country_year', from_column='vdem_v2xeg_eqdr')
+    .with_column(Column('lr_vdem_v2xeg_eqdr', from_loa='country_year', from_column='vdem_v2xeg_eqdr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xpe_exlpol', from_loa='country_year', from_column='vdem_v2xpe_exlpol')
+    .with_column(Column('lr_vdem_v2xpe_exlpol', from_loa='country_year', from_column='vdem_v2xpe_exlpol')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         )
 
-    .with_column(Column('vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
+    .with_column(Column('lr_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
@@ -131,42 +131,42 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('splag_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
+    .with_column(Column('lr_splag_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
+    .with_column(Column('lr_splag_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
+    .with_column(Column('lr_splag_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
+    .with_column(Column('lr_splag_vdem_v2xpe_exlsocgr', from_loa='country_year', from_column='vdem_v2xpe_exlsocgr')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
+    .with_column(Column('lr_splag_vdem_v2xcl_rol', from_loa='country_year', from_column='vdem_v2xcl_rol')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.spatial.countrylag(1,1,0,0)
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -174,7 +174,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -182,7 +182,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
+    .with_column(Column('lr_decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -190,7 +190,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(100)
         .transform.temporal.time_since()
@@ -198,7 +198,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(500)
         .transform.temporal.time_since()
@@ -206,7 +206,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
diff --git a/models/midnight_rain/configs/config_queryset.py b/models/midnight_rain/configs/config_queryset.py
index 7f9498e..e777ae8 100644
--- a/models/midnight_rain/configs/config_queryset.py
+++ b/models/midnight_rain/configs/config_queryset.py
@@ -12,83 +12,83 @@ def generate():
     
     qs_escwa_drought = (Queryset('fatalities003_pgm_escwa_drought','priogrid_month')
                         
-              .with_column(Column('pgd_nlights_calib_mean', from_loa='priogrid_year', from_column='nlights_calib_mean')
+              .with_column(Column('lr_pgd_nlights_calib_mean', from_loa='priogrid_year', from_column='nlights_calib_mean')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('pgd_imr_mean', from_loa='priogrid_year', from_column='imr_mean')
+              .with_column(Column('lr_pgd_imr_mean', from_loa='priogrid_year', from_column='imr_mean')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('pgd_urban_ih', from_loa='priogrid_year', from_column='urban_ih')
+              .with_column(Column('lr_pgd_urban_ih', from_loa='priogrid_year', from_column='urban_ih')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('count_moder_drought_prev10', from_loa='priogrid_month', from_column='count_moder_drought_prev10')
+              .with_column(Column('lr_count_moder_drought_prev10', from_loa='priogrid_month', from_column='count_moder_drought_prev10')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('cropprop', from_loa='priogrid_month', from_column='cropprop')
+              .with_column(Column('lr_cropprop', from_loa='priogrid_month', from_column='cropprop')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('growseasdummy', from_loa='priogrid_month', from_column='growseasdummy')
+              .with_column(Column('lr_growseasdummy', from_loa='priogrid_month', from_column='growseasdummy')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei1_gs_prev10', from_loa='priogrid_month', from_column='spei1_gs_prev10')
+              .with_column(Column('lr_spei1_gs_prev10', from_loa='priogrid_month', from_column='spei1_gs_prev10')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei1_gs_prev10_anom', from_loa='priogrid_month', from_column='spei1_gs_prev10_anom')
+              .with_column(Column('lr_spei1_gs_prev10_anom', from_loa='priogrid_month', from_column='spei1_gs_prev10_anom')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei1_gsm_cv_anom', from_loa='priogrid_month', from_column='spei1_gsm_cv_anom')
+              .with_column(Column('lr_spei1_gsm_cv_anom', from_loa='priogrid_month', from_column='spei1_gsm_cv_anom')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei1_gsm_detrend', from_loa='priogrid_month', from_column='spei1_gsm_detrend')
+              .with_column(Column('lr_spei1_gsm_detrend', from_loa='priogrid_month', from_column='spei1_gsm_detrend')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei1gsy_lowermedian_count', from_loa='priogrid_month', from_column='spei1gsy_lowermedian_count')
+              .with_column(Column('lr_spei1gsy_lowermedian_count', from_loa='priogrid_month', from_column='spei1gsy_lowermedian_count')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei_48_detrend', from_loa='priogrid_month', from_column='spei_48_detrend')
+              .with_column(Column('lr_spei_48_detrend', from_loa='priogrid_month', from_column='spei_48_detrend')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag1_dr_mod_gs', from_loa='priogrid_month', from_column='tlag1_dr_mod_gs')
+              .with_column(Column('lr_tlag1_dr_mod_gs', from_loa='priogrid_month', from_column='tlag1_dr_mod_gs')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag1_dr_moder_gs', from_loa='priogrid_month', from_column='tlag1_dr_moder_gs')
+              .with_column(Column('lr_tlag1_dr_moder_gs', from_loa='priogrid_month', from_column='tlag1_dr_moder_gs')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag1_dr_sev_gs', from_loa='priogrid_month', from_column='tlag1_dr_sev_gs')
+              .with_column(Column('lr_tlag1_dr_sev_gs', from_loa='priogrid_month', from_column='tlag1_dr_sev_gs')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag1_spei1_gsm', from_loa='priogrid_month', from_column='tlag1_spei1_gsm')
+              .with_column(Column('lr_tlag1_spei1_gsm', from_loa='priogrid_month', from_column='tlag1_spei1_gsm')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag_12_crop_sum', from_loa='priogrid_month', from_column='tlag_12_crop_sum')
+              .with_column(Column('lr_tlag_12_crop_sum', from_loa='priogrid_month', from_column='tlag_12_crop_sum')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag_12_harvarea_maincrops', from_loa='priogrid_month', from_column='tlag_12_harvarea_maincrops')
+              .with_column(Column('lr_tlag_12_harvarea_maincrops', from_loa='priogrid_month', from_column='tlag_12_harvarea_maincrops')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag_12_irr_maincrops', from_loa='priogrid_month', from_column='tlag_12_irr_maincrops')
+              .with_column(Column('lr_tlag_12_irr_maincrops', from_loa='priogrid_month', from_column='tlag_12_irr_maincrops')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag_12_rainf_maincrops', from_loa='priogrid_month', from_column='tlag_12_rainf_maincrops')
+              .with_column(Column('lr_tlag_12_rainf_maincrops', from_loa='priogrid_month', from_column='tlag_12_rainf_maincrops')
                      .transform.missing.replace_na(0)
                      )
 
@@ -102,7 +102,7 @@ def generate():
                      .transform.ops.ln()
                      )
 
-              .with_column(Column('greq_1_excluded', from_loa='priogrid_year', from_column='excluded')
+              .with_column(Column('lr_greq_1_excluded', from_loa='priogrid_year', from_column='excluded')
                      .transform.bool.gte(1)
                      .transform.missing.fill()
                      )
@@ -117,13 +117,13 @@ def generate():
                      .transform.ops.ln()
                      )
 
-              .with_column(Column('wdi_nv_agr_totl_kd', from_loa='country_year', from_column='wdi_nv_agr_totl_kd')
+              .with_column(Column('lr_wdi_nv_agr_totl_kd', from_loa='country_year', from_column='wdi_nv_agr_totl_kd')
                      .transform.missing.replace_na(0)
                      .transform.temporal.tlag(12)
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.bool.gte(1)
                      .transform.temporal.time_since()
@@ -131,7 +131,7 @@ def generate():
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('decay_ged_os_1', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+              .with_column(Column('lr_decay_ged_os_1', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.bool.gte(1)
                      .transform.temporal.time_since()
@@ -139,7 +139,7 @@ def generate():
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('decay_ged_ns_1', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+              .with_column(Column('lr_decay_ged_ns_1', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.bool.gte(1)
                      .transform.temporal.time_since()
diff --git a/models/national_anthem/configs/config_queryset.py b/models/national_anthem/configs/config_queryset.py
index 012b6cc..e6f6c47 100644
--- a/models/national_anthem/configs/config_queryset.py
+++ b/models/national_anthem/configs/config_queryset.py
@@ -25,210 +25,210 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
+        .with_column(Column('lr_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_dt_oda_odat_pc_zs', from_loa='country_year', from_column='wdi_dt_oda_odat_pc_zs')
+        .with_column(Column('lr_wdi_dt_oda_odat_pc_zs', from_loa='country_year', from_column='wdi_dt_oda_odat_pc_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_ms_mil_xpnd_gd_zs', from_loa='country_year', from_column='wdi_ms_mil_xpnd_gd_zs')
+        .with_column(Column('lr_wdi_ms_mil_xpnd_gd_zs', from_loa='country_year', from_column='wdi_ms_mil_xpnd_gd_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_ms_mil_xpnd_zs', from_loa='country_year', from_column='wdi_ms_mil_xpnd_zs')
+        .with_column(Column('lr_wdi_ms_mil_xpnd_zs', from_loa='country_year', from_column='wdi_ms_mil_xpnd_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_nv_agr_totl_kd', from_loa='country_year', from_column='wdi_nv_agr_totl_kd')
+        .with_column(Column('lr_wdi_nv_agr_totl_kd', from_loa='country_year', from_column='wdi_nv_agr_totl_kd')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_nv_agr_totl_kn', from_loa='country_year', from_column='wdi_nv_agr_totl_kn')
+        .with_column(Column('lr_wdi_nv_agr_totl_kn', from_loa='country_year', from_column='wdi_nv_agr_totl_kn')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_ny_gdp_pcap_kd', from_loa='country_year', from_column='wdi_ny_gdp_pcap_kd')
+        .with_column(Column('lr_wdi_ny_gdp_pcap_kd', from_loa='country_year', from_column='wdi_ny_gdp_pcap_kd')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_dyn_le00_in', from_loa='country_year', from_column='wdi_sp_dyn_le00_in')
+        .with_column(Column('lr_wdi_sp_dyn_le00_in', from_loa='country_year', from_column='wdi_sp_dyn_le00_in')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_se_enr_prim_fm_zs', from_loa='country_year', from_column='wdi_se_enr_prim_fm_zs')
+        .with_column(Column('lr_wdi_se_enr_prim_fm_zs', from_loa='country_year', from_column='wdi_se_enr_prim_fm_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_se_enr_prsc_fm_zs', from_loa='country_year', from_column='wdi_se_enr_prsc_fm_zs')
+        .with_column(Column('lr_wdi_se_enr_prsc_fm_zs', from_loa='country_year', from_column='wdi_se_enr_prsc_fm_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_se_prm_nenr', from_loa='country_year', from_column='wdi_se_prm_nenr')
+        .with_column(Column('lr_wdi_se_prm_nenr', from_loa='country_year', from_column='wdi_se_prm_nenr')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sh_sta_maln_zs', from_loa='country_year', from_column='wdi_sh_sta_maln_zs')
+        .with_column(Column('lr_wdi_sh_sta_maln_zs', from_loa='country_year', from_column='wdi_sh_sta_maln_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sh_sta_stnt_zs', from_loa='country_year', from_column='wdi_sh_sta_stnt_zs')
+        .with_column(Column('lr_wdi_sh_sta_stnt_zs', from_loa='country_year', from_column='wdi_sh_sta_stnt_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
+        .with_column(Column('lr_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
+        .with_column(Column('lr_wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
+        .with_column(Column('lr_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sm_pop_totl_zs', from_loa='country_year', from_column='wdi_sm_pop_totl_zs')
+        .with_column(Column('lr_wdi_sm_pop_totl_zs', from_loa='country_year', from_column='wdi_sm_pop_totl_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_dyn_imrt_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_in')
+        .with_column(Column('lr_wdi_sp_dyn_imrt_in', from_loa='country_year', from_column='wdi_sp_dyn_imrt_in')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sh_dyn_mort_fe', from_loa='country_year', from_column='wdi_sh_dyn_mort_fe')
+        .with_column(Column('lr_wdi_sh_dyn_mort_fe', from_loa='country_year', from_column='wdi_sh_dyn_mort_fe')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_pop_14_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_0014_fe_zs')
+        .with_column(Column('lr_wdi_sp_pop_14_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_0014_fe_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_pop_1564_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_1564_fe_zs')
+        .with_column(Column('lr_wdi_sp_pop_1564_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_1564_fe_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_pop_65up_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_65up_fe_zs')
+        .with_column(Column('lr_wdi_sp_pop_65up_fe_zs', from_loa='country_year', from_column='wdi_sp_pop_65up_fe_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_pop_grow', from_loa='country_year', from_column='wdi_sp_pop_grow')
+        .with_column(Column('lr_wdi_sp_pop_grow', from_loa='country_year', from_column='wdi_sp_pop_grow')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_urb_totl_in_zs', from_loa='country_year', from_column='wdi_sp_urb_totl_in_zs')
+        .with_column(Column('lr_wdi_sp_urb_totl_in_zs', from_loa='country_year', from_column='wdi_sp_urb_totl_in_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+        .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
+        .with_column(Column('lr_splag_wdi_sl_tlf_totl_fe_zs', from_loa='country_year', from_column='wdi_sl_tlf_totl_fe_zs')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
+        .with_column(Column('lr_splag_wdi_sm_pop_refg_or', from_loa='country_year', from_column='wdi_sm_pop_refg_or')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
+        .with_column(Column('lr_splag_wdi_sm_pop_netm', from_loa='country_year', from_column='wdi_sm_pop_netm')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
+        .with_column(Column('lr_splag_wdi_ag_lnd_frst_k2', from_loa='country_year', from_column='wdi_ag_lnd_frst_k2')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.spatial.countrylag(1,1,0,0)
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -236,7 +236,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -244,7 +244,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
diff --git a/models/old_money/configs/config_queryset.py b/models/old_money/configs/config_queryset.py
index 11cd459..31055a5 100644
--- a/models/old_money/configs/config_queryset.py
+++ b/models/old_money/configs/config_queryset.py
@@ -4,83 +4,83 @@ def generate():
     
     qs_escwa_drought = (Queryset('fatalities003_pgm_escwa_drought','priogrid_month')
                         
-              .with_column(Column('pgd_nlights_calib_mean', from_loa='priogrid_year', from_column='nlights_calib_mean')
+              .with_column(Column('lr_pgd_nlights_calib_mean', from_loa='priogrid_year', from_column='nlights_calib_mean')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('pgd_imr_mean', from_loa='priogrid_year', from_column='imr_mean')
+              .with_column(Column('lr_pgd_imr_mean', from_loa='priogrid_year', from_column='imr_mean')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('pgd_urban_ih', from_loa='priogrid_year', from_column='urban_ih')
+              .with_column(Column('lr_pgd_urban_ih', from_loa='priogrid_year', from_column='urban_ih')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('count_moder_drought_prev10', from_loa='priogrid_month', from_column='count_moder_drought_prev10')
+              .with_column(Column('lr_count_moder_drought_prev10', from_loa='priogrid_month', from_column='count_moder_drought_prev10')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('cropprop', from_loa='priogrid_month', from_column='cropprop')
+              .with_column(Column('lr_cropprop', from_loa='priogrid_month', from_column='cropprop')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('growseasdummy', from_loa='priogrid_month', from_column='growseasdummy')
+              .with_column(Column('lr_growseasdummy', from_loa='priogrid_month', from_column='growseasdummy')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei1_gs_prev10', from_loa='priogrid_month', from_column='spei1_gs_prev10')
+              .with_column(Column('lr_spei1_gs_prev10', from_loa='priogrid_month', from_column='spei1_gs_prev10')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei1_gs_prev10_anom', from_loa='priogrid_month', from_column='spei1_gs_prev10_anom')
+              .with_column(Column('lr_spei1_gs_prev10_anom', from_loa='priogrid_month', from_column='spei1_gs_prev10_anom')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei1_gsm_cv_anom', from_loa='priogrid_month', from_column='spei1_gsm_cv_anom')
+              .with_column(Column('lr_spei1_gsm_cv_anom', from_loa='priogrid_month', from_column='spei1_gsm_cv_anom')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei1_gsm_detrend', from_loa='priogrid_month', from_column='spei1_gsm_detrend')
+              .with_column(Column('lr_spei1_gsm_detrend', from_loa='priogrid_month', from_column='spei1_gsm_detrend')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei1gsy_lowermedian_count', from_loa='priogrid_month', from_column='spei1gsy_lowermedian_count')
+              .with_column(Column('lr_spei1gsy_lowermedian_count', from_loa='priogrid_month', from_column='spei1gsy_lowermedian_count')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('spei_48_detrend', from_loa='priogrid_month', from_column='spei_48_detrend')
+              .with_column(Column('lr_spei_48_detrend', from_loa='priogrid_month', from_column='spei_48_detrend')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag1_dr_mod_gs', from_loa='priogrid_month', from_column='tlag1_dr_mod_gs')
+              .with_column(Column('lr_tlag1_dr_mod_gs', from_loa='priogrid_month', from_column='tlag1_dr_mod_gs')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag1_dr_moder_gs', from_loa='priogrid_month', from_column='tlag1_dr_moder_gs')
+              .with_column(Column('lr_tlag1_dr_moder_gs', from_loa='priogrid_month', from_column='tlag1_dr_moder_gs')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag1_dr_sev_gs', from_loa='priogrid_month', from_column='tlag1_dr_sev_gs')
+              .with_column(Column('lr_tlag1_dr_sev_gs', from_loa='priogrid_month', from_column='tlag1_dr_sev_gs')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag1_spei1_gsm', from_loa='priogrid_month', from_column='tlag1_spei1_gsm')
+              .with_column(Column('lr_tlag1_spei1_gsm', from_loa='priogrid_month', from_column='tlag1_spei1_gsm')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag_12_crop_sum', from_loa='priogrid_month', from_column='tlag_12_crop_sum')
+              .with_column(Column('lr_tlag_12_crop_sum', from_loa='priogrid_month', from_column='tlag_12_crop_sum')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag_12_harvarea_maincrops', from_loa='priogrid_month', from_column='tlag_12_harvarea_maincrops')
+              .with_column(Column('lr_tlag_12_harvarea_maincrops', from_loa='priogrid_month', from_column='tlag_12_harvarea_maincrops')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag_12_irr_maincrops', from_loa='priogrid_month', from_column='tlag_12_irr_maincrops')
+              .with_column(Column('lr_tlag_12_irr_maincrops', from_loa='priogrid_month', from_column='tlag_12_irr_maincrops')
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('tlag_12_rainf_maincrops', from_loa='priogrid_month', from_column='tlag_12_rainf_maincrops')
+              .with_column(Column('lr_tlag_12_rainf_maincrops', from_loa='priogrid_month', from_column='tlag_12_rainf_maincrops')
                      .transform.missing.replace_na(0)
                      )
 
@@ -94,7 +94,7 @@ def generate():
                      .transform.ops.ln()
                      )
 
-              .with_column(Column('greq_1_excluded', from_loa='priogrid_year', from_column='excluded')
+              .with_column(Column('lr_greq_1_excluded', from_loa='priogrid_year', from_column='excluded')
                      .transform.bool.gte(1)
                      .transform.missing.fill()
                      )
@@ -109,13 +109,13 @@ def generate():
                      .transform.ops.ln()
                      )
 
-              .with_column(Column('wdi_nv_agr_totl_kd', from_loa='country_year', from_column='wdi_nv_agr_totl_kd')
+              .with_column(Column('lr_wdi_nv_agr_totl_kd', from_loa='country_year', from_column='wdi_nv_agr_totl_kd')
                      .transform.missing.replace_na(0)
                      .transform.temporal.tlag(12)
                      .transform.missing.replace_na(0)
                      )
 
-              .with_column(Column('decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+              .with_column(Column('lr_decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.bool.gte(1)
                      .transform.temporal.time_since()
@@ -123,7 +123,7 @@ def generate():
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('decay_ged_os_1', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+              .with_column(Column('lr_decay_ged_os_1', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.bool.gte(1)
                      .transform.temporal.time_since()
@@ -131,7 +131,7 @@ def generate():
                      .transform.missing.replace_na()
                      )
 
-              .with_column(Column('decay_ged_ns_1', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+              .with_column(Column('lr_decay_ged_ns_1', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
                      .transform.missing.replace_na()
                      .transform.bool.gte(1)
                      .transform.temporal.time_since()
diff --git a/models/ominous_ox/configs/config_queryset.py b/models/ominous_ox/configs/config_queryset.py
index 6fd9718..4040d16 100644
--- a/models/ominous_ox/configs/config_queryset.py
+++ b/models/ominous_ox/configs/config_queryset.py
@@ -13,7 +13,7 @@ def generate():
     # VIEWSER 6, Example configuration. Modify as needed.
 
     queryset = (Queryset('fatalities003_conflict_history','country_month')
-        .with_column(Column('gleditsch_ward', from_loa='country', from_column='gwcode')
+        .with_column(Column('lr_gleditsch_ward', from_loa='country', from_column='gwcode')
             )
 
         .with_column(Column('ln_ged_sb_dep', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
@@ -51,7 +51,7 @@ def generate():
             .transform.missing.fill()
             )
 
-        .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+        .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
@@ -114,7 +114,7 @@ def generate():
             .transform.missing.fill()
             )
 
-        .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -122,7 +122,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -130,7 +130,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_100', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -138,7 +138,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_500', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(500)
             .transform.temporal.time_since()
@@ -146,7 +146,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_100', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_100', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -154,7 +154,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -162,7 +162,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_ns_100', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_ns_100', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(100)
             .transform.temporal.time_since()
@@ -170,7 +170,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_acled_sb_5', from_loa='country_month', from_column='acled_sb_fat')
+        .with_column(Column('lr_decay_acled_sb_5', from_loa='country_month', from_column='acled_sb_fat')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -178,7 +178,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
+        .with_column(Column('lr_decay_acled_os_5', from_loa='country_month', from_column='acled_os_fat')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -186,7 +186,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_acled_ns_5', from_loa='country_month', from_column='acled_ns_fat')
+        .with_column(Column('lr_decay_acled_ns_5', from_loa='country_month', from_column='acled_ns_fat')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -194,7 +194,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -203,7 +203,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -212,7 +212,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_ns_5', from_loa='country_month', from_column='ged_ns_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
diff --git a/models/orange_pasta/configs/config_queryset.py b/models/orange_pasta/configs/config_queryset.py
index 1f9beb7..1d431f9 100644
--- a/models/orange_pasta/configs/config_queryset.py
+++ b/models/orange_pasta/configs/config_queryset.py
@@ -20,7 +20,7 @@ def generate():
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                .with_column(Column('lr_decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.bool.gte(1)
                     .transform.temporal.time_since()
@@ -28,7 +28,7 @@ def generate():
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('decay_ged_sb_25', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                .with_column(Column('lr_decay_ged_sb_25', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.bool.gte(25)
                     .transform.temporal.time_since()
@@ -36,7 +36,7 @@ def generate():
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('decay_ged_os_1', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+                .with_column(Column('lr_decay_ged_os_1', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.bool.gte(1)
                     .transform.temporal.time_since()
@@ -44,7 +44,7 @@ def generate():
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('splag_1_1_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                .with_column(Column('lr_splag_1_1_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.bool.gte(1)
                     .transform.temporal.time_since()
@@ -53,7 +53,7 @@ def generate():
                     .transform.missing.replace_na()
                     )
 
-                .with_column(Column('splag_1_decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                .with_column(Column('lr_splag_1_decay_ged_sb_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.bool.gte(1)
                     .transform.temporal.time_since()
diff --git a/models/plastic_beach/configs/config_queryset.py b/models/plastic_beach/configs/config_queryset.py
index cb85613..0830586 100644
--- a/models/plastic_beach/configs/config_queryset.py
+++ b/models/plastic_beach/configs/config_queryset.py
@@ -23,91 +23,91 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+    .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('agr_withdrawal_pct_t48', from_loa='country_year', from_column='agr_withdrawal_pct')
+    .with_column(Column('lr_agr_withdrawal_pct_t48', from_loa='country_year', from_column='agr_withdrawal_pct')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('dam_cap_pcap_t48', from_loa='country_year', from_column='dam_cap_pcap')
+    .with_column(Column('lr_dam_cap_pcap_t48', from_loa='country_year', from_column='dam_cap_pcap')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('groundwater_export_t48', from_loa='country_year', from_column='groundwater_export')
+    .with_column(Column('lr_groundwater_export_t48', from_loa='country_year', from_column='groundwater_export')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('fresh_withdrawal_pct_t48', from_loa='country_year', from_column='fresh_withdrawal_pct')
+    .with_column(Column('lr_fresh_withdrawal_pct_t48', from_loa='country_year', from_column='fresh_withdrawal_pct')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('ind_efficiency_t48', from_loa='country_year', from_column='ind_efficiency')
+    .with_column(Column('lr_ind_efficiency_t48', from_loa='country_year', from_column='ind_efficiency')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('irr_agr_efficiency_t48', from_loa='country_year', from_column='irr_agr_efficiency')
+    .with_column(Column('lr_irr_agr_efficiency_t48', from_loa='country_year', from_column='irr_agr_efficiency')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('services_efficiency_t48', from_loa='country_year', from_column='services_efficiency')
+    .with_column(Column('lr_services_efficiency_t48', from_loa='country_year', from_column='services_efficiency')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('general_efficiency_t48', from_loa='country_year', from_column='general_efficiency')
+    .with_column(Column('lr_general_efficiency_t48', from_loa='country_year', from_column='general_efficiency')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('water_stress_t48', from_loa='country_year', from_column='water_stress')
+    .with_column(Column('lr_water_stress_t48', from_loa='country_year', from_column='water_stress')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('renewable_internal_pcap_t48', from_loa='country_year', from_column='renewable_internal_pcap')
+    .with_column(Column('lr_renewable_internal_pcap_t48', from_loa='country_year', from_column='renewable_internal_pcap')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('renewable_pcap_t48', from_loa='country_year', from_column='renewable_pcap')
+    .with_column(Column('lr_renewable_pcap_t48', from_loa='country_year', from_column='renewable_pcap')
         .transform.missing.fill()
         .transform.missing.replace_na()
         .transform.temporal.tlag(48)
         .transform.missing.fill()
         )
 
-    .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -115,7 +115,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -123,7 +123,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
diff --git a/models/popular_monster/configs/config_queryset.py b/models/popular_monster/configs/config_queryset.py
index ae9ed83..9e0f5f3 100644
--- a/models/popular_monster/configs/config_queryset.py
+++ b/models/popular_monster/configs/config_queryset.py
@@ -23,350 +23,350 @@ def generate():
             .transform.missing.fill()
             )
 
-        .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+        .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_tokens_t1', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t1', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_tokens_t2', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t2', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_tokens_t13', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t13', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta0_stock_t1', from_loa='country_month', from_column='topic_ste_theta0_stock')
+        .with_column(Column('lr_topic_ste_theta0_stock_t1', from_loa='country_month', from_column='topic_ste_theta0_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta0_stock_t2', from_loa='country_month', from_column='topic_ste_theta0_stock')
+        .with_column(Column('lr_topic_ste_theta0_stock_t2', from_loa='country_month', from_column='topic_ste_theta0_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta0_stock_t13', from_loa='country_month', from_column='topic_ste_theta0_stock')
+        .with_column(Column('lr_topic_ste_theta0_stock_t13', from_loa='country_month', from_column='topic_ste_theta0_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta1_stock_t1', from_loa='country_month', from_column='topic_ste_theta1_stock')
+        .with_column(Column('lr_topic_ste_theta1_stock_t1', from_loa='country_month', from_column='topic_ste_theta1_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta1_stock_t2', from_loa='country_month', from_column='topic_ste_theta1_stock')
+        .with_column(Column('lr_topic_ste_theta1_stock_t2', from_loa='country_month', from_column='topic_ste_theta1_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta1_stock_t13', from_loa='country_month', from_column='topic_ste_theta1_stock')
+        .with_column(Column('lr_topic_ste_theta1_stock_t13', from_loa='country_month', from_column='topic_ste_theta1_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t1', from_loa='country_month', from_column='topic_ste_theta2_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t1', from_loa='country_month', from_column='topic_ste_theta2_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t2', from_loa='country_month', from_column='topic_ste_theta2_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t2', from_loa='country_month', from_column='topic_ste_theta2_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t13', from_loa='country_month', from_column='topic_ste_theta2_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t13', from_loa='country_month', from_column='topic_ste_theta2_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta3_stock_t1', from_loa='country_month', from_column='topic_ste_theta3_stock')
+        .with_column(Column('lr_topic_ste_theta3_stock_t1', from_loa='country_month', from_column='topic_ste_theta3_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta3_stock_t2', from_loa='country_month', from_column='topic_ste_theta3_stock')
+        .with_column(Column('lr_topic_ste_theta3_stock_t2', from_loa='country_month', from_column='topic_ste_theta3_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta3_stock_t13', from_loa='country_month', from_column='topic_ste_theta3_stock')
+        .with_column(Column('lr_topic_ste_theta3_stock_t13', from_loa='country_month', from_column='topic_ste_theta3_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t1', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t1', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t2', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t2', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t13', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t13', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta5_stock_t1', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta5_stock_t1', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta5_stock_t2', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta5_stock_t2', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta5_stock_t13', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta5_stock_t13', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta6_stock_t1', from_loa='country_month', from_column='topic_ste_theta6_stock')
+        .with_column(Column('lr_topic_ste_theta6_stock_t1', from_loa='country_month', from_column='topic_ste_theta6_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta6_stock_t2', from_loa='country_month', from_column='topic_ste_theta6_stock')
+        .with_column(Column('lr_topic_ste_theta6_stock_t2', from_loa='country_month', from_column='topic_ste_theta6_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta6_stock_t13', from_loa='country_month', from_column='topic_ste_theta6_stock')
+        .with_column(Column('lr_topic_ste_theta6_stock_t13', from_loa='country_month', from_column='topic_ste_theta6_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta7_stock_t1', from_loa='country_month', from_column='topic_ste_theta7_stock')
+        .with_column(Column('lr_topic_ste_theta7_stock_t1', from_loa='country_month', from_column='topic_ste_theta7_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta7_stock_t2', from_loa='country_month', from_column='topic_ste_theta7_stock')
+        .with_column(Column('lr_topic_ste_theta7_stock_t2', from_loa='country_month', from_column='topic_ste_theta7_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta7_stock_t13', from_loa='country_month', from_column='topic_ste_theta7_stock')
+        .with_column(Column('lr_topic_ste_theta7_stock_t13', from_loa='country_month', from_column='topic_ste_theta7_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta8_stock_t1', from_loa='country_month', from_column='topic_ste_theta8_stock')
+        .with_column(Column('lr_topic_ste_theta8_stock_t1', from_loa='country_month', from_column='topic_ste_theta8_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta8_stock_t2', from_loa='country_month', from_column='topic_ste_theta8_stock')
+        .with_column(Column('lr_topic_ste_theta8_stock_t2', from_loa='country_month', from_column='topic_ste_theta8_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta8_stock_t13', from_loa='country_month', from_column='topic_ste_theta8_stock')
+        .with_column(Column('lr_topic_ste_theta8_stock_t13', from_loa='country_month', from_column='topic_ste_theta8_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta9_stock_t1', from_loa='country_month', from_column='topic_ste_theta9_stock')
+        .with_column(Column('lr_topic_ste_theta9_stock_t1', from_loa='country_month', from_column='topic_ste_theta9_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta9_stock_t2', from_loa='country_month', from_column='topic_ste_theta9_stock')
+        .with_column(Column('lr_topic_ste_theta9_stock_t2', from_loa='country_month', from_column='topic_ste_theta9_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta9_stock_t13', from_loa='country_month', from_column='topic_ste_theta9_stock')
+        .with_column(Column('lr_topic_ste_theta9_stock_t13', from_loa='country_month', from_column='topic_ste_theta9_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta10_stock_t1', from_loa='country_month', from_column='topic_ste_theta10_stock')
+        .with_column(Column('lr_topic_ste_theta10_stock_t1', from_loa='country_month', from_column='topic_ste_theta10_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta10_stock_t2', from_loa='country_month', from_column='topic_ste_theta10_stock')
+        .with_column(Column('lr_topic_ste_theta10_stock_t2', from_loa='country_month', from_column='topic_ste_theta10_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta10_stock_t13', from_loa='country_month', from_column='topic_ste_theta10_stock')
+        .with_column(Column('lr_topic_ste_theta10_stock_t13', from_loa='country_month', from_column='topic_ste_theta10_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta11_stock_t1', from_loa='country_month', from_column='topic_ste_theta11_stock')
+        .with_column(Column('lr_topic_ste_theta11_stock_t1', from_loa='country_month', from_column='topic_ste_theta11_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta11_stock_t2', from_loa='country_month', from_column='topic_ste_theta11_stock')
+        .with_column(Column('lr_topic_ste_theta11_stock_t2', from_loa='country_month', from_column='topic_ste_theta11_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta11_stock_t13', from_loa='country_month', from_column='topic_ste_theta11_stock')
+        .with_column(Column('lr_topic_ste_theta11_stock_t13', from_loa='country_month', from_column='topic_ste_theta11_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta12_stock_t1', from_loa='country_month', from_column='topic_ste_theta12_stock')
+        .with_column(Column('lr_topic_ste_theta12_stock_t1', from_loa='country_month', from_column='topic_ste_theta12_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta12_stock_t2', from_loa='country_month', from_column='topic_ste_theta12_stock')
+        .with_column(Column('lr_topic_ste_theta12_stock_t2', from_loa='country_month', from_column='topic_ste_theta12_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta12_stock_t13', from_loa='country_month', from_column='topic_ste_theta12_stock')
+        .with_column(Column('lr_topic_ste_theta12_stock_t13', from_loa='country_month', from_column='topic_ste_theta12_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta13_stock_t1', from_loa='country_month', from_column='topic_ste_theta13_stock')
+        .with_column(Column('lr_topic_ste_theta13_stock_t1', from_loa='country_month', from_column='topic_ste_theta13_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta13_stock_t2', from_loa='country_month', from_column='topic_ste_theta13_stock')
+        .with_column(Column('lr_topic_ste_theta13_stock_t2', from_loa='country_month', from_column='topic_ste_theta13_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta13_stock_t13', from_loa='country_month', from_column='topic_ste_theta13_stock')
+        .with_column(Column('lr_topic_ste_theta13_stock_t13', from_loa='country_month', from_column='topic_ste_theta13_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta14_stock_t1', from_loa='country_month', from_column='topic_ste_theta14_stock')
+        .with_column(Column('lr_topic_ste_theta14_stock_t1', from_loa='country_month', from_column='topic_ste_theta14_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta14_stock_t2', from_loa='country_month', from_column='topic_ste_theta14_stock')
+        .with_column(Column('lr_topic_ste_theta14_stock_t2', from_loa='country_month', from_column='topic_ste_theta14_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta14_stock_t13', from_loa='country_month', from_column='topic_ste_theta14_stock')
+        .with_column(Column('lr_topic_ste_theta14_stock_t13', from_loa='country_month', from_column='topic_ste_theta14_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -374,7 +374,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -382,7 +382,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -391,7 +391,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_tokens_t1_splag', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t1_splag', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -400,7 +400,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta0_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta0_stock')
+        .with_column(Column('lr_topic_ste_theta0_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta0_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -409,7 +409,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta1_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta1_stock')
+        .with_column(Column('lr_topic_ste_theta1_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta1_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -418,7 +418,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta2_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta2_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -427,7 +427,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta3_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta3_stock')
+        .with_column(Column('lr_topic_ste_theta3_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta3_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -436,7 +436,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -445,7 +445,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta5_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta5_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -454,7 +454,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta6_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta6_stock')
+        .with_column(Column('lr_topic_ste_theta6_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta6_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -463,7 +463,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta7_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta7_stock')
+        .with_column(Column('lr_topic_ste_theta7_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta7_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -472,7 +472,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta8_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta8_stock')
+        .with_column(Column('lr_topic_ste_theta8_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta8_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -481,7 +481,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta9_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta9_stock')
+        .with_column(Column('lr_topic_ste_theta9_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta9_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -490,7 +490,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta10_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta10_stock')
+        .with_column(Column('lr_topic_ste_theta10_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta10_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -499,7 +499,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta11_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta11_stock')
+        .with_column(Column('lr_topic_ste_theta11_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta11_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -508,7 +508,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta12_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta12_stock')
+        .with_column(Column('lr_topic_ste_theta12_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta12_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -517,7 +517,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta13_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta13_stock')
+        .with_column(Column('lr_topic_ste_theta13_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta13_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -526,7 +526,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta14_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta14_stock')
+        .with_column(Column('lr_topic_ste_theta14_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta14_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
diff --git a/models/teen_spirit/configs/config_queryset.py b/models/teen_spirit/configs/config_queryset.py
index 3910ff7..32f8b1a 100644
--- a/models/teen_spirit/configs/config_queryset.py
+++ b/models/teen_spirit/configs/config_queryset.py
@@ -13,23 +13,23 @@ def generate():
     # VIEWSER 6, Example configuration. Modify as needed.
 
     queryset = (Queryset('fatalities003_faoprices','country_month')
-    .with_column(Column('fao_wheat_price', from_loa='country_month', from_column='wheat_price')
+    .with_column(Column('lr_fao_wheat_price', from_loa='country_month', from_column='wheat_price')
         .transform.missing.replace_na(0)
         )
 
-    .with_column(Column('fao_mp_price', from_loa='country_month', from_column='mp_price')
+    .with_column(Column('lr_fao_mp_price', from_loa='country_month', from_column='mp_price')
         .transform.missing.replace_na(0)
         )
 
-    .with_column(Column('fao_sugar_price', from_loa='country_month', from_column='sugar_price')
+    .with_column(Column('lr_fao_sugar_price', from_loa='country_month', from_column='sugar_price')
         .transform.missing.replace_na(0)
         )
 
-    .with_column(Column('fao_meat_price', from_loa='country_month', from_column='meat_price')
+    .with_column(Column('lr_fao_meat_price', from_loa='country_month', from_column='meat_price')
         .transform.missing.replace_na(0)
         )
 
-    .with_column(Column('fao_milk_price', from_loa='country_month', from_column='milk_price')
+    .with_column(Column('lr_fao_milk_price', from_loa='country_month', from_column='milk_price')
         .transform.missing.replace_na(0)
         )
 
@@ -43,44 +43,44 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('gleditsch_ward', from_loa='country', from_column='gwcode')
+    .with_column(Column('lr_gleditsch_ward', from_loa='country', from_column='gwcode')
         .transform.missing.fill()
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('delta_fao_wheat_price', from_loa='country_month', from_column='wheat_price')
+    .with_column(Column('lr_delta_fao_wheat_price', from_loa='country_month', from_column='wheat_price')
         .transform.temporal.delta(12)
         .transform.missing.replace_na(0)
         )
 
-    .with_column(Column('delta_fao_mp_price', from_loa='country_month', from_column='mp_price')
+    .with_column(Column('lr_delta_fao_mp_price', from_loa='country_month', from_column='mp_price')
         .transform.temporal.delta(12)
         .transform.missing.replace_na(0)
         )
 
-    .with_column(Column('delta_fao_sugar_price', from_loa='country_month', from_column='sugar_price')
+    .with_column(Column('lr_delta_fao_sugar_price', from_loa='country_month', from_column='sugar_price')
         .transform.temporal.delta(12)
         .transform.missing.replace_na(0)
         )
 
-    .with_column(Column('delta_fao_meat_price', from_loa='country_month', from_column='meat_price')
+    .with_column(Column('lr_delta_fao_meat_price', from_loa='country_month', from_column='meat_price')
         .transform.temporal.delta(12)
         .transform.missing.replace_na(0)
         )
 
-    .with_column(Column('delta_fao_milk_price', from_loa='country_month', from_column='milk_price')
+    .with_column(Column('lr_delta_fao_milk_price', from_loa='country_month', from_column='milk_price')
         .transform.temporal.delta(12)
         .transform.missing.replace_na(0)
         )
 
-    .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+    .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -88,7 +88,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -96,7 +96,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
diff --git a/models/twin_flame/configs/config_queryset.py b/models/twin_flame/configs/config_queryset.py
index ae9ed83..9e0f5f3 100644
--- a/models/twin_flame/configs/config_queryset.py
+++ b/models/twin_flame/configs/config_queryset.py
@@ -23,350 +23,350 @@ def generate():
             .transform.missing.fill()
             )
 
-        .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+        .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
             .transform.missing.fill()
             .transform.temporal.tlag(12)
             .transform.missing.fill()
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_tokens_t1', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t1', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_tokens_t2', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t2', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_tokens_t13', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t13', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta0_stock_t1', from_loa='country_month', from_column='topic_ste_theta0_stock')
+        .with_column(Column('lr_topic_ste_theta0_stock_t1', from_loa='country_month', from_column='topic_ste_theta0_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta0_stock_t2', from_loa='country_month', from_column='topic_ste_theta0_stock')
+        .with_column(Column('lr_topic_ste_theta0_stock_t2', from_loa='country_month', from_column='topic_ste_theta0_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta0_stock_t13', from_loa='country_month', from_column='topic_ste_theta0_stock')
+        .with_column(Column('lr_topic_ste_theta0_stock_t13', from_loa='country_month', from_column='topic_ste_theta0_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta1_stock_t1', from_loa='country_month', from_column='topic_ste_theta1_stock')
+        .with_column(Column('lr_topic_ste_theta1_stock_t1', from_loa='country_month', from_column='topic_ste_theta1_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta1_stock_t2', from_loa='country_month', from_column='topic_ste_theta1_stock')
+        .with_column(Column('lr_topic_ste_theta1_stock_t2', from_loa='country_month', from_column='topic_ste_theta1_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta1_stock_t13', from_loa='country_month', from_column='topic_ste_theta1_stock')
+        .with_column(Column('lr_topic_ste_theta1_stock_t13', from_loa='country_month', from_column='topic_ste_theta1_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t1', from_loa='country_month', from_column='topic_ste_theta2_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t1', from_loa='country_month', from_column='topic_ste_theta2_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t2', from_loa='country_month', from_column='topic_ste_theta2_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t2', from_loa='country_month', from_column='topic_ste_theta2_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t13', from_loa='country_month', from_column='topic_ste_theta2_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t13', from_loa='country_month', from_column='topic_ste_theta2_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta3_stock_t1', from_loa='country_month', from_column='topic_ste_theta3_stock')
+        .with_column(Column('lr_topic_ste_theta3_stock_t1', from_loa='country_month', from_column='topic_ste_theta3_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta3_stock_t2', from_loa='country_month', from_column='topic_ste_theta3_stock')
+        .with_column(Column('lr_topic_ste_theta3_stock_t2', from_loa='country_month', from_column='topic_ste_theta3_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta3_stock_t13', from_loa='country_month', from_column='topic_ste_theta3_stock')
+        .with_column(Column('lr_topic_ste_theta3_stock_t13', from_loa='country_month', from_column='topic_ste_theta3_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t1', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t1', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t2', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t2', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t13', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t13', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta5_stock_t1', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta5_stock_t1', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta5_stock_t2', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta5_stock_t2', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta5_stock_t13', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta5_stock_t13', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta6_stock_t1', from_loa='country_month', from_column='topic_ste_theta6_stock')
+        .with_column(Column('lr_topic_ste_theta6_stock_t1', from_loa='country_month', from_column='topic_ste_theta6_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta6_stock_t2', from_loa='country_month', from_column='topic_ste_theta6_stock')
+        .with_column(Column('lr_topic_ste_theta6_stock_t2', from_loa='country_month', from_column='topic_ste_theta6_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta6_stock_t13', from_loa='country_month', from_column='topic_ste_theta6_stock')
+        .with_column(Column('lr_topic_ste_theta6_stock_t13', from_loa='country_month', from_column='topic_ste_theta6_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta7_stock_t1', from_loa='country_month', from_column='topic_ste_theta7_stock')
+        .with_column(Column('lr_topic_ste_theta7_stock_t1', from_loa='country_month', from_column='topic_ste_theta7_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta7_stock_t2', from_loa='country_month', from_column='topic_ste_theta7_stock')
+        .with_column(Column('lr_topic_ste_theta7_stock_t2', from_loa='country_month', from_column='topic_ste_theta7_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta7_stock_t13', from_loa='country_month', from_column='topic_ste_theta7_stock')
+        .with_column(Column('lr_topic_ste_theta7_stock_t13', from_loa='country_month', from_column='topic_ste_theta7_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta8_stock_t1', from_loa='country_month', from_column='topic_ste_theta8_stock')
+        .with_column(Column('lr_topic_ste_theta8_stock_t1', from_loa='country_month', from_column='topic_ste_theta8_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta8_stock_t2', from_loa='country_month', from_column='topic_ste_theta8_stock')
+        .with_column(Column('lr_topic_ste_theta8_stock_t2', from_loa='country_month', from_column='topic_ste_theta8_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta8_stock_t13', from_loa='country_month', from_column='topic_ste_theta8_stock')
+        .with_column(Column('lr_topic_ste_theta8_stock_t13', from_loa='country_month', from_column='topic_ste_theta8_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta9_stock_t1', from_loa='country_month', from_column='topic_ste_theta9_stock')
+        .with_column(Column('lr_topic_ste_theta9_stock_t1', from_loa='country_month', from_column='topic_ste_theta9_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta9_stock_t2', from_loa='country_month', from_column='topic_ste_theta9_stock')
+        .with_column(Column('lr_topic_ste_theta9_stock_t2', from_loa='country_month', from_column='topic_ste_theta9_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta9_stock_t13', from_loa='country_month', from_column='topic_ste_theta9_stock')
+        .with_column(Column('lr_topic_ste_theta9_stock_t13', from_loa='country_month', from_column='topic_ste_theta9_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta10_stock_t1', from_loa='country_month', from_column='topic_ste_theta10_stock')
+        .with_column(Column('lr_topic_ste_theta10_stock_t1', from_loa='country_month', from_column='topic_ste_theta10_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta10_stock_t2', from_loa='country_month', from_column='topic_ste_theta10_stock')
+        .with_column(Column('lr_topic_ste_theta10_stock_t2', from_loa='country_month', from_column='topic_ste_theta10_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta10_stock_t13', from_loa='country_month', from_column='topic_ste_theta10_stock')
+        .with_column(Column('lr_topic_ste_theta10_stock_t13', from_loa='country_month', from_column='topic_ste_theta10_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta11_stock_t1', from_loa='country_month', from_column='topic_ste_theta11_stock')
+        .with_column(Column('lr_topic_ste_theta11_stock_t1', from_loa='country_month', from_column='topic_ste_theta11_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta11_stock_t2', from_loa='country_month', from_column='topic_ste_theta11_stock')
+        .with_column(Column('lr_topic_ste_theta11_stock_t2', from_loa='country_month', from_column='topic_ste_theta11_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta11_stock_t13', from_loa='country_month', from_column='topic_ste_theta11_stock')
+        .with_column(Column('lr_topic_ste_theta11_stock_t13', from_loa='country_month', from_column='topic_ste_theta11_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta12_stock_t1', from_loa='country_month', from_column='topic_ste_theta12_stock')
+        .with_column(Column('lr_topic_ste_theta12_stock_t1', from_loa='country_month', from_column='topic_ste_theta12_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta12_stock_t2', from_loa='country_month', from_column='topic_ste_theta12_stock')
+        .with_column(Column('lr_topic_ste_theta12_stock_t2', from_loa='country_month', from_column='topic_ste_theta12_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta12_stock_t13', from_loa='country_month', from_column='topic_ste_theta12_stock')
+        .with_column(Column('lr_topic_ste_theta12_stock_t13', from_loa='country_month', from_column='topic_ste_theta12_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta13_stock_t1', from_loa='country_month', from_column='topic_ste_theta13_stock')
+        .with_column(Column('lr_topic_ste_theta13_stock_t1', from_loa='country_month', from_column='topic_ste_theta13_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta13_stock_t2', from_loa='country_month', from_column='topic_ste_theta13_stock')
+        .with_column(Column('lr_topic_ste_theta13_stock_t2', from_loa='country_month', from_column='topic_ste_theta13_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta13_stock_t13', from_loa='country_month', from_column='topic_ste_theta13_stock')
+        .with_column(Column('lr_topic_ste_theta13_stock_t13', from_loa='country_month', from_column='topic_ste_theta13_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta14_stock_t1', from_loa='country_month', from_column='topic_ste_theta14_stock')
+        .with_column(Column('lr_topic_ste_theta14_stock_t1', from_loa='country_month', from_column='topic_ste_theta14_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(1)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta14_stock_t2', from_loa='country_month', from_column='topic_ste_theta14_stock')
+        .with_column(Column('lr_topic_ste_theta14_stock_t2', from_loa='country_month', from_column='topic_ste_theta14_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(2)
             .transform.missing.fill()
             )
 
-        .with_column(Column('topic_ste_theta14_stock_t13', from_loa='country_month', from_column='topic_ste_theta14_stock')
+        .with_column(Column('lr_topic_ste_theta14_stock_t13', from_loa='country_month', from_column='topic_ste_theta14_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
             .transform.missing.fill()
             )
 
-        .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -374,7 +374,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+        .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -382,7 +382,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+        .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
             .transform.missing.replace_na()
             .transform.bool.gte(5)
             .transform.temporal.time_since()
@@ -391,7 +391,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_tokens_t1_splag', from_loa='country_month', from_column='topic_tokens')
+        .with_column(Column('lr_topic_tokens_t1_splag', from_loa='country_month', from_column='topic_tokens')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -400,7 +400,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta0_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta0_stock')
+        .with_column(Column('lr_topic_ste_theta0_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta0_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -409,7 +409,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta1_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta1_stock')
+        .with_column(Column('lr_topic_ste_theta1_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta1_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -418,7 +418,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta2_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta2_stock')
+        .with_column(Column('lr_topic_ste_theta2_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta2_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -427,7 +427,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta3_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta3_stock')
+        .with_column(Column('lr_topic_ste_theta3_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta3_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -436,7 +436,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta4_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta4_stock')
+        .with_column(Column('lr_topic_ste_theta4_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta4_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -445,7 +445,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta5_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta5_stock')
+        .with_column(Column('lr_topic_ste_theta5_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta5_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -454,7 +454,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta6_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta6_stock')
+        .with_column(Column('lr_topic_ste_theta6_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta6_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -463,7 +463,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta7_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta7_stock')
+        .with_column(Column('lr_topic_ste_theta7_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta7_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -472,7 +472,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta8_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta8_stock')
+        .with_column(Column('lr_topic_ste_theta8_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta8_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -481,7 +481,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta9_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta9_stock')
+        .with_column(Column('lr_topic_ste_theta9_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta9_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -490,7 +490,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta10_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta10_stock')
+        .with_column(Column('lr_topic_ste_theta10_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta10_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -499,7 +499,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta11_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta11_stock')
+        .with_column(Column('lr_topic_ste_theta11_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta11_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -508,7 +508,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta12_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta12_stock')
+        .with_column(Column('lr_topic_ste_theta12_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta12_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -517,7 +517,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta13_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta13_stock')
+        .with_column(Column('lr_topic_ste_theta13_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta13_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
@@ -526,7 +526,7 @@ def generate():
             .transform.missing.replace_na()
             )
 
-        .with_column(Column('topic_ste_theta14_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta14_stock')
+        .with_column(Column('lr_topic_ste_theta14_stock_t1_splag', from_loa='country_month', from_column='topic_ste_theta14_stock')
             .transform.missing.fill()
             .transform.missing.replace_na()
             .transform.temporal.tlag(13)
diff --git a/models/wildest_dream/configs/config_queryset.py b/models/wildest_dream/configs/config_queryset.py
index 90884a3..395baaf 100644
--- a/models/wildest_dream/configs/config_queryset.py
+++ b/models/wildest_dream/configs/config_queryset.py
@@ -5,7 +5,7 @@ def generate():
 
     qs_sptime_dist = (Queryset('fatalities003_pgm_conflict_sptime_dist','priogrid_month')
                       
-                     .with_column(Column('ged_gte_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                     .with_column(Column('lr_ged_gte_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                             .transform.bool.gte(1)
                             )
 
@@ -14,47 +14,47 @@ def generate():
                             .transform.ops.ln()
                             )
 
-                     .with_column(Column('sptime_dist_k1_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                     .with_column(Column('lr_sptime_dist_k1_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                             .transform.missing.replace_na()
                             .transform.spatial.sptime_dist("distances",1,1.0,0.0)
                             )
 
-                     .with_column(Column('sptime_dist_k1_ged_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+                     .with_column(Column('lr_sptime_dist_k1_ged_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
                             .transform.missing.replace_na()
                             .transform.spatial.sptime_dist("distances",1,1.0,0.0)
                             )
 
-                     .with_column(Column('sptime_dist_k1_ged_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+                     .with_column(Column('lr_sptime_dist_k1_ged_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
                             .transform.missing.replace_na()
                             .transform.spatial.sptime_dist("distances",1,1.0,0.0)
                             )
 
-                     .with_column(Column('sptime_dist_k10_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                     .with_column(Column('lr_sptime_dist_k10_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                             .transform.missing.replace_na()
                             .transform.spatial.sptime_dist("distances",1,10.0,0.0)
                             )
 
-                     .with_column(Column('sptime_dist_k10_ged_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+                     .with_column(Column('lr_sptime_dist_k10_ged_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
                             .transform.missing.replace_na()
                             .transform.spatial.sptime_dist("distances",1,10.0,0.0)
                             )
 
-                     .with_column(Column('sptime_dist_k10_ged_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+                     .with_column(Column('lr_sptime_dist_k10_ged_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
                             .transform.missing.replace_na()
                             .transform.spatial.sptime_dist("distances",1,10.0,0.0)
                             )
 
-                     .with_column(Column('sptime_dist_k001_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                     .with_column(Column('lr_sptime_dist_k001_ged_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                             .transform.missing.replace_na()
                             .transform.spatial.sptime_dist("distances",1,0.01,0.0)
                             )
 
-                     .with_column(Column('sptime_dist_k001_ged_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+                     .with_column(Column('lr_sptime_dist_k001_ged_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
                             .transform.missing.replace_na()
                             .transform.spatial.sptime_dist("distances",1,0.01,0.0)
                             )
 
-                     .with_column(Column('sptime_dist_k001_ged_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+                     .with_column(Column('lr_sptime_dist_k001_ged_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
                             .transform.missing.replace_na()
                             .transform.spatial.sptime_dist("distances",1,0.01,0.0)
                             )
diff --git a/models/yellow_pikachu/configs/config_queryset.py b/models/yellow_pikachu/configs/config_queryset.py
index 29caf78..ad382c3 100644
--- a/models/yellow_pikachu/configs/config_queryset.py
+++ b/models/yellow_pikachu/configs/config_queryset.py
@@ -4,7 +4,7 @@ def generate():
 
     qs_treelag = (Queryset('fatalities003_pgm_conflict_treelag','priogrid_month')
                   
-                .with_column(Column('ged_gte_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                .with_column(Column('lr_ged_gte_1', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                     .transform.bool.gte(1)
                     )
 
@@ -13,32 +13,32 @@ def generate():
                     .transform.ops.ln()
                     )
 
-                .with_column(Column('treelag_1_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                .with_column(Column('lr_treelag_1_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.spatial.treelag(0.7,1)
                     )
 
-                .with_column(Column('treelag_1_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+                .with_column(Column('lr_treelag_1_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.spatial.treelag(0.7,1)
                     )
 
-                .with_column(Column('treelag_1_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+                .with_column(Column('lr_treelag_1_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.spatial.treelag(0.7,1)
                     )
 
-                .with_column(Column('treelag_2_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
+                .with_column(Column('lr_treelag_2_sb', from_loa='priogrid_month', from_column='ged_sb_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.spatial.treelag(0.7,2)
                     )
 
-                .with_column(Column('treelag_2_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
+                .with_column(Column('lr_treelag_2_ns', from_loa='priogrid_month', from_column='ged_ns_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.spatial.treelag(0.7,2)
                     )
 
-                .with_column(Column('treelag_2_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
+                .with_column(Column('lr_treelag_2_os', from_loa='priogrid_month', from_column='ged_os_best_sum_nokgi')
                     .transform.missing.replace_na()
                     .transform.spatial.treelag(0.7,2)
                     )
diff --git a/models/yellow_submarine/configs/config_queryset.py b/models/yellow_submarine/configs/config_queryset.py
index 9d2a4a8..90eb87a 100644
--- a/models/yellow_submarine/configs/config_queryset.py
+++ b/models/yellow_submarine/configs/config_queryset.py
@@ -13,19 +13,19 @@ def generate():
     # VIEWSER 6, Example configuration. Modify as needed.
 
     queryset = (Queryset('fatalities003_imfweo','country_month')
-    .with_column(Column('imfweo_ngdp_rpch_tcurrent', from_loa='country_month', from_column='ngdp_rpch_tcurrent')
+    .with_column(Column('lr_imfweo_ngdp_rpch_tcurrent', from_loa='country_month', from_column='ngdp_rpch_tcurrent')
         .transform.missing.replace_na(0)
         )
 
-    .with_column(Column('imfweo_ngdp_rpch_tmin1', from_loa='country_month', from_column='ngdp_rpch_tmin1')
+    .with_column(Column('lr_imfweo_ngdp_rpch_tmin1', from_loa='country_month', from_column='ngdp_rpch_tmin1')
         .transform.missing.replace_na(0)
         )
 
-    .with_column(Column('imfweo_ngdp_rpch_tplus1', from_loa='country_month', from_column='ngdp_rpch_tplus1')
+    .with_column(Column('lr_imfweo_ngdp_rpch_tplus1', from_loa='country_month', from_column='ngdp_rpch_tplus1')
         .transform.missing.replace_na(0)
         )
 
-    .with_column(Column('imfweo_ngdp_rpch_tplus2', from_loa='country_month', from_column='ngdp_rpch_tplus2')
+    .with_column(Column('lr_imfweo_ngdp_rpch_tplus2', from_loa='country_month', from_column='ngdp_rpch_tplus2')
         .transform.missing.replace_na(0)
         )
 
@@ -39,19 +39,19 @@ def generate():
         .transform.missing.fill()
         )
 
-    .with_column(Column('gleditsch_ward', from_loa='country', from_column='gwcode')
+    .with_column(Column('lr_gleditsch_ward', from_loa='country', from_column='gwcode')
         .transform.missing.fill()
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
+    .with_column(Column('lr_wdi_sp_pop_totl', from_loa='country_year', from_column='wdi_sp_pop_totl')
         .transform.missing.fill()
         .transform.temporal.tlag(12)
         .transform.missing.fill()
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -59,7 +59,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
+    .with_column(Column('lr_decay_ged_os_5', from_loa='country_month', from_column='ged_os_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()
@@ -67,7 +67,7 @@ def generate():
         .transform.missing.replace_na()
         )
 
-    .with_column(Column('splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
+    .with_column(Column('lr_splag_1_decay_ged_sb_5', from_loa='country_month', from_column='ged_sb_best_sum_nokgi')
         .transform.missing.replace_na()
         .transform.bool.gte(5)
         .transform.temporal.time_since()