Strong typing

.pre-commit-config.yaml

@@ -45,7 +45,7 @@ repos:
     hooks:
       - id: yamllint
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.14.10
+    rev: v0.14.11
     hooks:
       - id: ruff-check
         types_or:
@@ -54,7 +54,6 @@ repos:
           - jupyter
         args:
           - --fix
-          # - --unsafe-fixes
       - id: ruff-format
         types_or:
           - python

.yamllint.yml

@@ -3,6 +3,8 @@ yaml-files:
   - '*.yaml'
   - '*.yml'
   - .yamllint
+ignore:
+  - src/skillmodels/test_data/simplest_augmented_model.yaml
 rules:
   braces: enable
   brackets: enable
@@ -34,3 +36,4 @@ rules:
   trailing-spaces: enable
   truthy:
     level: warning
+    check-keys: false

CLAUDE.md

@@ -86,10 +86,12 @@ The main package exports three functions:
 
 ## Code Style
 
-- Uses Ruff for linting (target: Python 3.13, line length: 88)
+- Require Python 3.14
+- Uses Ruff for linting (target: Python 3.14, line length: 88)
 - Google-style docstrings
 - Pre-commit hooks enforce formatting and linting
 - Type checking via `ty` with strict rules
+- Do not use `from __future__ import annotations`
 
 ## Testing
 

docs/source/conf.py

@@ -1,3 +1,5 @@
+"""Sphinx configuration file for skillmodels documentation."""
+
 #
 # Documentation build configuration file, created by sphinx-quickstart
 #
@@ -8,13 +10,13 @@
 #
 # All configuration values have a default; values that are commented out
 # serve to show the default.
-import os
 import sys
+from pathlib import Path
 
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the
-# documentation root, use os.path.abspath to make it absolute, like shown here.
-sys.path.insert(0, os.path.abspath("../.."))
+# documentation root, use Path.resolve() to make it absolute, like shown here.
+sys.path.insert(0, str(Path("../..").resolve()))
 
 
 # -- General configuration ----------------------------------------------------
@@ -61,7 +63,7 @@
 
 # General information about the project.
 project = "skillmodels"
-copyright = "2016-2021, Janos Gabler"
+copyright = "2016-, Janos Gabler"  # noqa: A001
 
 # The version info for the project you"re documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the

docs/source/getting_started/tutorial.ipynb

@@ -19,7 +19,7 @@
     "import pandas as pd\n",
     "import yaml\n",
     "\n",
-    "from skillmodels.config import TEST_DIR\n",
+    "from skillmodels.config import REGRESSION_VAULT, TEST_DATA_DIR\n",
     "from skillmodels.maximization_inputs import get_maximization_inputs"
    ]
   },
@@ -41,7 +41,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "with open(TEST_DIR / \"model2.yaml\") as y:\n",
+    "with (TEST_DATA_DIR / \"model2.yaml\").open() as y:\n",
     "    model_dict = yaml.load(y, Loader=yaml.SafeLoader)"
    ]
   },
@@ -51,7 +51,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "data = pd.read_stata(TEST_DIR / \"model2_simulated_data.dta\")\n",
+    "data = pd.read_stata(TEST_DATA_DIR / \"model2_simulated_data.dta\")\n",
     "data = data.set_index([\"caseid\", \"period\"])"
    ]
   },
@@ -110,7 +110,7 @@
    "outputs": [],
    "source": [
     "index_cols = [\"category\", \"period\", \"name1\", \"name2\"]\n",
-    "chs_path = TEST_DIR / \"regression_vault\" / \"chs_results.csv\"\n",
+    "chs_path = REGRESSION_VAULT / \"chs_results.csv\"\n",
     "chs_values = pd.read_csv(chs_path)\n",
     "chs_values = chs_values.set_index(index_cols)\n",
     "chs_values = chs_values[[\"chs_value\", \"good_start_value\", \"bad_start_value\"]]\n",
@@ -289,7 +289,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "pc, pp = om.process_constraints(constraints, params)\n",
     "params[\"group\"] = params.index.get_level_values(\"category\")\n",
     "params.loc[\"controls\", \"group\"] = params.loc[\"controls\"].index.get_level_values(\"name2\")\n",
     "\n",
@@ -299,8 +298,6 @@
     "    + params.index.get_level_values(\"period\").astype(str)\n",
     ")\n",
     "params[\"group\"] = params[\"group\"].str.replace(\"_\", \"-\")\n",
-    "params[\"group\"] = params[\"group\"].astype(\"O\")\n",
-    "params.loc[~pp[\"_internal_free\"], \"group\"] = None\n",
     "params"
    ]
   },

docs/source/how_to_guides/how_to_simulate_dataset.ipynb

@@ -9,7 +9,7 @@
     "import pandas as pd\n",
     "import yaml\n",
     "\n",
-    "from skillmodels.config import TEST_DIR\n",
+    "from skillmodels.config import REGRESSION_VAULT, TEST_DATA_DIR\n",
     "from skillmodels.simulate_data import simulate_dataset"
    ]
   },
@@ -34,13 +34,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "with open(TEST_DIR / \"model2.yaml\") as y:\n",
-    "    model_dict = yaml.load(y, Loader=yaml.FullLoader)\n",
+    "with (TEST_DATA_DIR / \"model2.yaml\").open() as y:\n",
+    "    model_dict = yaml.load(y, Loader=yaml.SafeLoader)\n",
     "\n",
-    "data = pd.read_stata(TEST_DIR / \"model2_simulated_data.dta\")\n",
+    "data = pd.read_stata(TEST_DATA_DIR / \"model2_simulated_data.dta\")\n",
     "data = data.set_index([\"caseid\", \"period\"])\n",
     "\n",
-    "params = pd.read_csv(TEST_DIR / \"regression_vault\" / \"one_stage_anchoring.csv\")\n",
+    "params = pd.read_csv(REGRESSION_VAULT / \"one_stage_anchoring.csv\")\n",
     "params = params.set_index([\"category\", \"period\", \"name1\", \"name2\"])"
    ]
   },

docs/source/how_to_guides/how_to_visualize_correlations.ipynb

@@ -16,7 +16,7 @@
     "import pandas as pd\n",
     "import yaml\n",
     "\n",
-    "from skillmodels.config import TEST_DIR\n",
+    "from skillmodels.config import REGRESSION_VAULT, TEST_DATA_DIR\n",
     "from skillmodels.correlation_heatmap import (\n",
     "    get_measurements_corr,\n",
     "    get_quasi_scores_corr,\n",
@@ -40,8 +40,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "with open(TEST_DIR / \"model2.yaml\") as y:\n",
-    "    model_dict = yaml.load(y, Loader=yaml.FullLoader)"
+    "with (TEST_DATA_DIR / \"model2.yaml\").open() as y:\n",
+    "    model_dict = yaml.load(y, Loader=yaml.SafeLoader)"
    ]
   },
   {
@@ -50,10 +50,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "params = pd.read_csv(TEST_DIR / \"regression_vault\" / \"one_stage_anchoring.csv\")\n",
+    "params = pd.read_csv(REGRESSION_VAULT / \"one_stage_anchoring.csv\")\n",
     "params = params.set_index([\"category\", \"period\", \"name1\", \"name2\"])\n",
     "\n",
-    "data = pd.read_stata(TEST_DIR / \"model2_simulated_data.dta\")\n",
+    "data = pd.read_stata(TEST_DATA_DIR / \"model2_simulated_data.dta\")\n",
     "data = data.set_index([\"caseid\", \"period\"])"
    ]
   },
@@ -170,7 +170,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from skillmodels.visualize_transition_equations import _get_pardict, _set_index_params"
+    "from skillmodels.visualize_transition_equations import (\n",
+    "    _get_parsed_params,\n",
+    "    _set_index_params,\n",
+    ")"
    ]
   },
   {
@@ -188,10 +191,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "_get_pardict(\n",
+    "_get_parsed_params(\n",
     "    params=_set_index_params(process_model(model_dict), params),\n",
     "    model=process_model(model_dict),\n",
-    ")[\"loadings\"]"
+    ").loadings"
    ]
   },
   {

docs/source/how_to_guides/how_to_visualize_pairwise_factor_distribution.ipynb

@@ -21,7 +21,7 @@
     "import pandas as pd\n",
     "import yaml\n",
     "\n",
-    "from skillmodels.config import TEST_DIR\n",
+    "from skillmodels.config import REGRESSION_VAULT, TEST_DATA_DIR\n",
     "from skillmodels.maximization_inputs import get_maximization_inputs\n",
     "from skillmodels.simulate_data import simulate_dataset\n",
     "from skillmodels.visualize_factor_distributions import (\n",
@@ -57,12 +57,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "with open(TEST_DIR / \"model2.yaml\") as y:\n",
-    "    model_dict = yaml.load(y, Loader=yaml.FullLoader)\n",
-    "params = pd.read_csv(TEST_DIR / \"regression_vault\" / \"one_stage_anchoring.csv\")\n",
+    "with (TEST_DATA_DIR / \"model2.yaml\").open() as y:\n",
+    "    model_dict = yaml.load(y, Loader=yaml.SafeLoader)\n",
+    "params = pd.read_csv(REGRESSION_VAULT / \"one_stage_anchoring.csv\")\n",
     "params = params.set_index([\"category\", \"period\", \"name1\", \"name2\"])\n",
     "\n",
-    "data = pd.read_stata(TEST_DIR / \"model2_simulated_data.dta\")\n",
+    "data = pd.read_stata(TEST_DATA_DIR / \"model2_simulated_data.dta\")\n",
     "data = data.set_index([\"caseid\", \"period\"])"
    ]
   },

docs/source/how_to_guides/how_to_visualize_transition_equations.ipynb

@@ -10,7 +10,7 @@
     "import pandas as pd\n",
     "import yaml\n",
     "\n",
-    "from skillmodels.config import TEST_DIR\n",
+    "from skillmodels.config import REGRESSION_VAULT, TEST_DATA_DIR\n",
     "from skillmodels.visualize_transition_equations import (\n",
     "    combine_transition_plots,\n",
     "    get_transition_plots,\n",
@@ -47,13 +47,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "with open(TEST_DIR / \"model2.yaml\") as y:\n",
-    "    model_dict = yaml.load(y, Loader=yaml.FullLoader)\n",
+    "with (TEST_DATA_DIR / \"model2.yaml\").open() as y:\n",
+    "    model_dict = yaml.load(y, Loader=yaml.SafeLoader)\n",
     "\n",
-    "params = pd.read_csv(TEST_DIR / \"regression_vault\" / \"one_stage_anchoring.csv\")\n",
+    "params = pd.read_csv(REGRESSION_VAULT / \"one_stage_anchoring.csv\")\n",
     "params = params.set_index([\"category\", \"period\", \"name1\", \"name2\"])\n",
     "\n",
-    "data = pd.read_stata(TEST_DIR / \"model2_simulated_data.dta\")\n",
+    "data = pd.read_stata(TEST_DATA_DIR / \"model2_simulated_data.dta\")\n",
     "data = data.set_index([\"caseid\", \"period\"])"
    ]
   },