diff --git a/.ipynb_checkpoints/[lab-customer-analysis-round-5] Fabiana-checkpoint.ipynb b/.ipynb_checkpoints/[lab-customer-analysis-round-5] Fabiana-checkpoint.ipynb
new file mode 100644
index 0000000..29150a4
--- /dev/null
+++ b/.ipynb_checkpoints/[lab-customer-analysis-round-5] Fabiana-checkpoint.ipynb	
@@ -0,0 +1,2637 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "58a989e2",
+   "metadata": {},
+   "source": [
+    "# Statistics Foundations"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5c269798",
+   "metadata": {},
+   "source": [
+    "# Show DataFrame info"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "00482570",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "\n",
+    "import warnings\n",
+    "warnings.filterwarnings ('ignore')\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "%matplotlib inline\n",
+    "\n",
+    "import seaborn as sns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "25c3936b",
+   "metadata": {
+    "scrolled": true
+   },
+   "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>Customer</th>\n",
+       "      <th>State</th>\n",
+       "      <th>Customer Lifetime Value</th>\n",
+       "      <th>Response</th>\n",
+       "      <th>Coverage</th>\n",
+       "      <th>Education</th>\n",
+       "      <th>Effective To Date</th>\n",
+       "      <th>EmploymentStatus</th>\n",
+       "      <th>Gender</th>\n",
+       "      <th>Income</th>\n",
+       "      <th>...</th>\n",
+       "      <th>Months Since Policy Inception</th>\n",
+       "      <th>Number of Open Complaints</th>\n",
+       "      <th>Number of Policies</th>\n",
+       "      <th>Policy Type</th>\n",
+       "      <th>Policy</th>\n",
+       "      <th>Renew Offer Type</th>\n",
+       "      <th>Sales Channel</th>\n",
+       "      <th>Total Claim Amount</th>\n",
+       "      <th>Vehicle Class</th>\n",
+       "      <th>Vehicle Size</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>BU79786</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>2763.519279</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2/24/11</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>56274</td>\n",
+       "      <td>...</td>\n",
+       "      <td>5</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>384.811147</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>QZ44356</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>6979.535903</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>1/31/11</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>42</td>\n",
+       "      <td>0</td>\n",
+       "      <td>8</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L3</td>\n",
+       "      <td>Offer3</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>1131.464935</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>AI49188</td>\n",
+       "      <td>Nevada</td>\n",
+       "      <td>12887.431650</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2/19/11</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>48767</td>\n",
+       "      <td>...</td>\n",
+       "      <td>38</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L3</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>566.472247</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>WW63253</td>\n",
+       "      <td>California</td>\n",
+       "      <td>7645.861827</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>1/20/11</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>65</td>\n",
+       "      <td>0</td>\n",
+       "      <td>7</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L2</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Call Center</td>\n",
+       "      <td>529.881344</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>HB64268</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>2813.692575</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2/3/11</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>43836</td>\n",
+       "      <td>...</td>\n",
+       "      <td>44</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L1</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>138.130879</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</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>9129</th>\n",
+       "      <td>LA72316</td>\n",
+       "      <td>California</td>\n",
+       "      <td>23405.987980</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2/10/11</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>71941</td>\n",
+       "      <td>...</td>\n",
+       "      <td>89</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L1</td>\n",
+       "      <td>Offer2</td>\n",
+       "      <td>Web</td>\n",
+       "      <td>198.234764</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9130</th>\n",
+       "      <td>PK87824</td>\n",
+       "      <td>California</td>\n",
+       "      <td>3096.511217</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2/12/11</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>21604</td>\n",
+       "      <td>...</td>\n",
+       "      <td>28</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>379.200000</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9131</th>\n",
+       "      <td>TD14365</td>\n",
+       "      <td>California</td>\n",
+       "      <td>8163.890428</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2/6/11</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>37</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L2</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>790.784983</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9132</th>\n",
+       "      <td>UP19263</td>\n",
+       "      <td>California</td>\n",
+       "      <td>7524.442436</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2/3/11</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>21941</td>\n",
+       "      <td>...</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L2</td>\n",
+       "      <td>Offer3</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>691.200000</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Large</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9133</th>\n",
+       "      <td>Y167826</td>\n",
+       "      <td>California</td>\n",
+       "      <td>2611.836866</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2/14/11</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>90</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer4</td>\n",
+       "      <td>Call Center</td>\n",
+       "      <td>369.600000</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>9134 rows × 24 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     Customer       State  Customer Lifetime Value Response  Coverage  \\\n",
+       "0     BU79786  Washington              2763.519279       No     Basic   \n",
+       "1     QZ44356     Arizona              6979.535903       No  Extended   \n",
+       "2     AI49188      Nevada             12887.431650       No   Premium   \n",
+       "3     WW63253  California              7645.861827       No     Basic   \n",
+       "4     HB64268  Washington              2813.692575       No     Basic   \n",
+       "...       ...         ...                      ...      ...       ...   \n",
+       "9129  LA72316  California             23405.987980       No     Basic   \n",
+       "9130  PK87824  California              3096.511217      Yes  Extended   \n",
+       "9131  TD14365  California              8163.890428       No  Extended   \n",
+       "9132  UP19263  California              7524.442436       No  Extended   \n",
+       "9133  Y167826  California              2611.836866       No  Extended   \n",
+       "\n",
+       "     Education Effective To Date EmploymentStatus Gender  Income  ...  \\\n",
+       "0     Bachelor           2/24/11         Employed      F   56274  ...   \n",
+       "1     Bachelor           1/31/11       Unemployed      F       0  ...   \n",
+       "2     Bachelor           2/19/11         Employed      F   48767  ...   \n",
+       "3     Bachelor           1/20/11       Unemployed      M       0  ...   \n",
+       "4     Bachelor            2/3/11         Employed      M   43836  ...   \n",
+       "...        ...               ...              ...    ...     ...  ...   \n",
+       "9129  Bachelor           2/10/11         Employed      M   71941  ...   \n",
+       "9130   College           2/12/11         Employed      F   21604  ...   \n",
+       "9131  Bachelor            2/6/11       Unemployed      M       0  ...   \n",
+       "9132   College            2/3/11         Employed      M   21941  ...   \n",
+       "9133   College           2/14/11       Unemployed      M       0  ...   \n",
+       "\n",
+       "     Months Since Policy Inception Number of Open Complaints  \\\n",
+       "0                                5                         0   \n",
+       "1                               42                         0   \n",
+       "2                               38                         0   \n",
+       "3                               65                         0   \n",
+       "4                               44                         0   \n",
+       "...                            ...                       ...   \n",
+       "9129                            89                         0   \n",
+       "9130                            28                         0   \n",
+       "9131                            37                         3   \n",
+       "9132                             3                         0   \n",
+       "9133                            90                         0   \n",
+       "\n",
+       "      Number of Policies     Policy Type        Policy  Renew Offer Type  \\\n",
+       "0                      1  Corporate Auto  Corporate L3            Offer1   \n",
+       "1                      8   Personal Auto   Personal L3            Offer3   \n",
+       "2                      2   Personal Auto   Personal L3            Offer1   \n",
+       "3                      7  Corporate Auto  Corporate L2            Offer1   \n",
+       "4                      1   Personal Auto   Personal L1            Offer1   \n",
+       "...                  ...             ...           ...               ...   \n",
+       "9129                   2   Personal Auto   Personal L1            Offer2   \n",
+       "9130                   1  Corporate Auto  Corporate L3            Offer1   \n",
+       "9131                   2  Corporate Auto  Corporate L2            Offer1   \n",
+       "9132                   3   Personal Auto   Personal L2            Offer3   \n",
+       "9133                   1  Corporate Auto  Corporate L3            Offer4   \n",
+       "\n",
+       "      Sales Channel Total Claim Amount  Vehicle Class Vehicle Size  \n",
+       "0             Agent         384.811147   Two-Door Car      Medsize  \n",
+       "1             Agent        1131.464935  Four-Door Car      Medsize  \n",
+       "2             Agent         566.472247   Two-Door Car      Medsize  \n",
+       "3       Call Center         529.881344            SUV      Medsize  \n",
+       "4             Agent         138.130879  Four-Door Car      Medsize  \n",
+       "...             ...                ...            ...          ...  \n",
+       "9129            Web         198.234764  Four-Door Car      Medsize  \n",
+       "9130         Branch         379.200000  Four-Door Car      Medsize  \n",
+       "9131         Branch         790.784983  Four-Door Car      Medsize  \n",
+       "9132         Branch         691.200000  Four-Door Car        Large  \n",
+       "9133    Call Center         369.600000   Two-Door Car      Medsize  \n",
+       "\n",
+       "[9134 rows x 24 columns]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Marketing Customer Analysis\n",
+    "df = pd.read_csv (r\"C:\\Users\\fabi_\\OneDrive\\Estudos e Cursos\\Data analytics\\Ironhack.Labs\\lab-customer-analysis-round-3\\files_for_lab\\csv_files\\marketing_customer_analysis.csv\")\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "fd945b48",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['customer', 'state', 'customer_lifetime_value', 'response', 'coverage',\n",
+       "       'education', 'effective_to_date', 'employmentstatus', 'gender',\n",
+       "       'income', 'location_code', 'marital_status', 'monthly_premium_auto',\n",
+       "       'months_since_last_claim', 'months_since_policy_inception',\n",
+       "       'number_of_open_complaints', 'number_of_policies', 'policy_type',\n",
+       "       'policy', 'renew_offer_type', 'sales_channel', 'total_claim_amount',\n",
+       "       'vehicle_class', 'vehicle_size'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.columns = df.columns.str.lower().str.replace(' ', '_')\n",
+    "df.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "2798c857",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                          object\n",
+       "state                             object\n",
+       "customer_lifetime_value          float64\n",
+       "response                          object\n",
+       "coverage                          object\n",
+       "education                         object\n",
+       "effective_to_date                 object\n",
+       "employmentstatus                  object\n",
+       "gender                            object\n",
+       "income                             int64\n",
+       "location_code                     object\n",
+       "marital_status                    object\n",
+       "monthly_premium_auto               int64\n",
+       "months_since_last_claim            int64\n",
+       "months_since_policy_inception      int64\n",
+       "number_of_open_complaints          int64\n",
+       "number_of_policies                 int64\n",
+       "policy_type                       object\n",
+       "policy                            object\n",
+       "renew_offer_type                  object\n",
+       "sales_channel                     object\n",
+       "total_claim_amount               float64\n",
+       "vehicle_class                     object\n",
+       "vehicle_size                      object\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "5d281ccc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0      2011-02-24\n",
+       "1      2011-01-31\n",
+       "2      2011-02-19\n",
+       "3      2011-01-20\n",
+       "4      2011-02-03\n",
+       "          ...    \n",
+       "9129   2011-02-10\n",
+       "9130   2011-02-12\n",
+       "9131   2011-02-06\n",
+       "9132   2011-02-03\n",
+       "9133   2011-02-14\n",
+       "Name: effective_to_date, Length: 9134, dtype: datetime64[ns]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['effective_to_date'] = pd.to_datetime(df['effective_to_date'])\n",
+    "df['effective_to_date']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "5dfbd78d",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                         9134\n",
+       "state                               5\n",
+       "customer_lifetime_value          8041\n",
+       "response                            2\n",
+       "coverage                            3\n",
+       "education                           5\n",
+       "effective_to_date                  59\n",
+       "employmentstatus                    5\n",
+       "gender                              2\n",
+       "income                           5694\n",
+       "location_code                       3\n",
+       "marital_status                      3\n",
+       "monthly_premium_auto              202\n",
+       "months_since_last_claim            36\n",
+       "months_since_policy_inception     100\n",
+       "number_of_open_complaints           6\n",
+       "number_of_policies                  9\n",
+       "policy_type                         3\n",
+       "policy                              9\n",
+       "renew_offer_type                    4\n",
+       "sales_channel                       4\n",
+       "total_claim_amount               5106\n",
+       "vehicle_class                       6\n",
+       "vehicle_size                        3\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.nunique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "d8437b8e",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                         0\n",
+       "state                            0\n",
+       "customer_lifetime_value          0\n",
+       "response                         0\n",
+       "coverage                         0\n",
+       "education                        0\n",
+       "effective_to_date                0\n",
+       "employmentstatus                 0\n",
+       "gender                           0\n",
+       "income                           0\n",
+       "location_code                    0\n",
+       "marital_status                   0\n",
+       "monthly_premium_auto             0\n",
+       "months_since_last_claim          0\n",
+       "months_since_policy_inception    0\n",
+       "number_of_open_complaints        0\n",
+       "number_of_policies               0\n",
+       "policy_type                      0\n",
+       "policy                           0\n",
+       "renew_offer_type                 0\n",
+       "sales_channel                    0\n",
+       "total_claim_amount               0\n",
+       "vehicle_class                    0\n",
+       "vehicle_size                     0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fc1cbb30",
+   "metadata": {},
+   "source": [
+    "# Numerical and categorical columns"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "185cc43c",
+   "metadata": {},
+   "source": [
+    "Check the data types of the columns. Get the numeric data into dataframe called numerical and categorical columns in a dataframe called categoricals. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "e671059f",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['customer_lifetime_value',\n",
+       " 'income',\n",
+       " 'monthly_premium_auto',\n",
+       " 'months_since_last_claim',\n",
+       " 'months_since_policy_inception',\n",
+       " 'number_of_open_complaints',\n",
+       " 'number_of_policies',\n",
+       " 'total_claim_amount']"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "numerical_columns = df.select_dtypes(include=['number']).columns.tolist()\n",
+    "numerical_columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "21d21dc2",
+   "metadata": {
+    "scrolled": true
+   },
+   "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>customer_lifetime_value</th>\n",
+       "      <th>income</th>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <th>months_since_last_claim</th>\n",
+       "      <th>months_since_policy_inception</th>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <th>number_of_policies</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2763.519279</td>\n",
+       "      <td>56274</td>\n",
+       "      <td>69</td>\n",
+       "      <td>32</td>\n",
+       "      <td>5</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>384.811147</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>6979.535903</td>\n",
+       "      <td>0</td>\n",
+       "      <td>94</td>\n",
+       "      <td>13</td>\n",
+       "      <td>42</td>\n",
+       "      <td>0</td>\n",
+       "      <td>8</td>\n",
+       "      <td>1131.464935</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>12887.431650</td>\n",
+       "      <td>48767</td>\n",
+       "      <td>108</td>\n",
+       "      <td>18</td>\n",
+       "      <td>38</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>566.472247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>7645.861827</td>\n",
+       "      <td>0</td>\n",
+       "      <td>106</td>\n",
+       "      <td>18</td>\n",
+       "      <td>65</td>\n",
+       "      <td>0</td>\n",
+       "      <td>7</td>\n",
+       "      <td>529.881344</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2813.692575</td>\n",
+       "      <td>43836</td>\n",
+       "      <td>73</td>\n",
+       "      <td>12</td>\n",
+       "      <td>44</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>138.130879</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9129</th>\n",
+       "      <td>23405.987980</td>\n",
+       "      <td>71941</td>\n",
+       "      <td>73</td>\n",
+       "      <td>18</td>\n",
+       "      <td>89</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>198.234764</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9130</th>\n",
+       "      <td>3096.511217</td>\n",
+       "      <td>21604</td>\n",
+       "      <td>79</td>\n",
+       "      <td>14</td>\n",
+       "      <td>28</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>379.200000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9131</th>\n",
+       "      <td>8163.890428</td>\n",
+       "      <td>0</td>\n",
+       "      <td>85</td>\n",
+       "      <td>9</td>\n",
+       "      <td>37</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>790.784983</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9132</th>\n",
+       "      <td>7524.442436</td>\n",
+       "      <td>21941</td>\n",
+       "      <td>96</td>\n",
+       "      <td>34</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>691.200000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9133</th>\n",
+       "      <td>2611.836866</td>\n",
+       "      <td>0</td>\n",
+       "      <td>77</td>\n",
+       "      <td>3</td>\n",
+       "      <td>90</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>369.600000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>9134 rows × 8 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      customer_lifetime_value  income  monthly_premium_auto  \\\n",
+       "0                 2763.519279   56274                    69   \n",
+       "1                 6979.535903       0                    94   \n",
+       "2                12887.431650   48767                   108   \n",
+       "3                 7645.861827       0                   106   \n",
+       "4                 2813.692575   43836                    73   \n",
+       "...                       ...     ...                   ...   \n",
+       "9129             23405.987980   71941                    73   \n",
+       "9130              3096.511217   21604                    79   \n",
+       "9131              8163.890428       0                    85   \n",
+       "9132              7524.442436   21941                    96   \n",
+       "9133              2611.836866       0                    77   \n",
+       "\n",
+       "      months_since_last_claim  months_since_policy_inception  \\\n",
+       "0                          32                              5   \n",
+       "1                          13                             42   \n",
+       "2                          18                             38   \n",
+       "3                          18                             65   \n",
+       "4                          12                             44   \n",
+       "...                       ...                            ...   \n",
+       "9129                       18                             89   \n",
+       "9130                       14                             28   \n",
+       "9131                        9                             37   \n",
+       "9132                       34                              3   \n",
+       "9133                        3                             90   \n",
+       "\n",
+       "      number_of_open_complaints  number_of_policies  total_claim_amount  \n",
+       "0                             0                   1          384.811147  \n",
+       "1                             0                   8         1131.464935  \n",
+       "2                             0                   2          566.472247  \n",
+       "3                             0                   7          529.881344  \n",
+       "4                             0                   1          138.130879  \n",
+       "...                         ...                 ...                 ...  \n",
+       "9129                          0                   2          198.234764  \n",
+       "9130                          0                   1          379.200000  \n",
+       "9131                          3                   2          790.784983  \n",
+       "9132                          0                   3          691.200000  \n",
+       "9133                          0                   1          369.600000  \n",
+       "\n",
+       "[9134 rows x 8 columns]"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_numerical = df[['customer_lifetime_value','income','monthly_premium_auto','months_since_last_claim','months_since_policy_inception','number_of_open_complaints','number_of_policies','total_claim_amount']]\n",
+    "df_numerical"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "ed419c65",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['customer',\n",
+       " 'state',\n",
+       " 'response',\n",
+       " 'coverage',\n",
+       " 'education',\n",
+       " 'effective_to_date',\n",
+       " 'employmentstatus',\n",
+       " 'gender',\n",
+       " 'location_code',\n",
+       " 'marital_status',\n",
+       " 'policy_type',\n",
+       " 'policy',\n",
+       " 'renew_offer_type',\n",
+       " 'sales_channel',\n",
+       " 'vehicle_class',\n",
+       " 'vehicle_size']"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "categorical_columns = df.select_dtypes(exclude=['number']).columns.tolist()\n",
+    "categorical_columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "44ad19bf",
+   "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>customer</th>\n",
+       "      <th>state</th>\n",
+       "      <th>response</th>\n",
+       "      <th>coverage</th>\n",
+       "      <th>education</th>\n",
+       "      <th>effective_to_date</th>\n",
+       "      <th>employmentstatus</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>location_code</th>\n",
+       "      <th>marital_status</th>\n",
+       "      <th>policy_type</th>\n",
+       "      <th>policy</th>\n",
+       "      <th>renew_offer_type</th>\n",
+       "      <th>sales_channel</th>\n",
+       "      <th>vehicle_class</th>\n",
+       "      <th>vehicle_size</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>BU79786</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-02-24</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>QZ44356</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-01-31</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Single</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L3</td>\n",
+       "      <td>Offer3</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>AI49188</td>\n",
+       "      <td>Nevada</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-02-19</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L3</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>WW63253</td>\n",
+       "      <td>California</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-01-20</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L2</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Call Center</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>HB64268</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-02-03</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Rural</td>\n",
+       "      <td>Single</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L1</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9129</th>\n",
+       "      <td>LA72316</td>\n",
+       "      <td>California</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-02-10</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Urban</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L1</td>\n",
+       "      <td>Offer2</td>\n",
+       "      <td>Web</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9130</th>\n",
+       "      <td>PK87824</td>\n",
+       "      <td>California</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2011-02-12</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Divorced</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9131</th>\n",
+       "      <td>TD14365</td>\n",
+       "      <td>California</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-02-06</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Single</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L2</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9132</th>\n",
+       "      <td>UP19263</td>\n",
+       "      <td>California</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2011-02-03</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L2</td>\n",
+       "      <td>Offer3</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Large</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9133</th>\n",
+       "      <td>Y167826</td>\n",
+       "      <td>California</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2011-02-14</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Single</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer4</td>\n",
+       "      <td>Call Center</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>9134 rows × 16 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     customer       state response  coverage education effective_to_date  \\\n",
+       "0     BU79786  Washington       No     Basic  Bachelor        2011-02-24   \n",
+       "1     QZ44356     Arizona       No  Extended  Bachelor        2011-01-31   \n",
+       "2     AI49188      Nevada       No   Premium  Bachelor        2011-02-19   \n",
+       "3     WW63253  California       No     Basic  Bachelor        2011-01-20   \n",
+       "4     HB64268  Washington       No     Basic  Bachelor        2011-02-03   \n",
+       "...       ...         ...      ...       ...       ...               ...   \n",
+       "9129  LA72316  California       No     Basic  Bachelor        2011-02-10   \n",
+       "9130  PK87824  California      Yes  Extended   College        2011-02-12   \n",
+       "9131  TD14365  California       No  Extended  Bachelor        2011-02-06   \n",
+       "9132  UP19263  California       No  Extended   College        2011-02-03   \n",
+       "9133  Y167826  California       No  Extended   College        2011-02-14   \n",
+       "\n",
+       "     employmentstatus gender location_code marital_status     policy_type  \\\n",
+       "0            Employed      F      Suburban        Married  Corporate Auto   \n",
+       "1          Unemployed      F      Suburban         Single   Personal Auto   \n",
+       "2            Employed      F      Suburban        Married   Personal Auto   \n",
+       "3          Unemployed      M      Suburban        Married  Corporate Auto   \n",
+       "4            Employed      M         Rural         Single   Personal Auto   \n",
+       "...               ...    ...           ...            ...             ...   \n",
+       "9129         Employed      M         Urban        Married   Personal Auto   \n",
+       "9130         Employed      F      Suburban       Divorced  Corporate Auto   \n",
+       "9131       Unemployed      M      Suburban         Single  Corporate Auto   \n",
+       "9132         Employed      M      Suburban        Married   Personal Auto   \n",
+       "9133       Unemployed      M      Suburban         Single  Corporate Auto   \n",
+       "\n",
+       "            policy renew_offer_type sales_channel  vehicle_class vehicle_size  \n",
+       "0     Corporate L3           Offer1         Agent   Two-Door Car      Medsize  \n",
+       "1      Personal L3           Offer3         Agent  Four-Door Car      Medsize  \n",
+       "2      Personal L3           Offer1         Agent   Two-Door Car      Medsize  \n",
+       "3     Corporate L2           Offer1   Call Center            SUV      Medsize  \n",
+       "4      Personal L1           Offer1         Agent  Four-Door Car      Medsize  \n",
+       "...            ...              ...           ...            ...          ...  \n",
+       "9129   Personal L1           Offer2           Web  Four-Door Car      Medsize  \n",
+       "9130  Corporate L3           Offer1        Branch  Four-Door Car      Medsize  \n",
+       "9131  Corporate L2           Offer1        Branch  Four-Door Car      Medsize  \n",
+       "9132   Personal L2           Offer3        Branch  Four-Door Car        Large  \n",
+       "9133  Corporate L3           Offer4   Call Center   Two-Door Car      Medsize  \n",
+       "\n",
+       "[9134 rows x 16 columns]"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_categorical = df [['customer','state','response','coverage','education','effective_to_date','employmentstatus','gender','location_code','marital_status','policy_type','policy','renew_offer_type','sales_channel','vehicle_class','vehicle_size']]\n",
+    "df_categorical"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0fa705d1",
+   "metadata": {},
+   "source": [
+    "# Visualizing distributions of the numerical data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "856334f0",
+   "metadata": {},
+   "source": [
+    "Use Seaborn or Matplot library to construct distribution plots for the numerical variables.\n",
+    "Do the distributions for different numerical variables and check which look like a normal distribution."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "4a3f5c52",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count     9134.000000\n",
+      "mean      8004.940475\n",
+      "std       6870.967608\n",
+      "min       1898.007675\n",
+      "25%       3994.251794\n",
+      "50%       5780.182197\n",
+      "75%       8962.167041\n",
+      "max      83325.381190\n",
+      "Name: customer_lifetime_value, dtype: float64\n",
+      "number of unique values:  8041\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['customer_lifetime_value'].describe())\n",
+    "print ('number of unique values: ', df_numerical['customer_lifetime_value'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "3987c080",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='customer_lifetime_value', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='customer_lifetime_value', kde=True)\n",
+    "# the plot is clearly right-skewed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "922ba108",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count     9134.000000\n",
+      "mean     37657.380009\n",
+      "std      30379.904734\n",
+      "min          0.000000\n",
+      "25%          0.000000\n",
+      "50%      33889.500000\n",
+      "75%      62320.000000\n",
+      "max      99981.000000\n",
+      "Name: income, dtype: float64\n",
+      "number of unique values:  5694\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['income'].describe())\n",
+    "print ('number of unique values: ', df_numerical['income'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "c908aa92",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='income', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='income',kde=True)\n",
+    "# there are many values at 0 so the distribution looks bimodal and somewhat right-skewed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "1c270f60",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count    9134.000000\n",
+      "mean       93.219291\n",
+      "std        34.407967\n",
+      "min        61.000000\n",
+      "25%        68.000000\n",
+      "50%        83.000000\n",
+      "75%       109.000000\n",
+      "max       298.000000\n",
+      "Name: monthly_premium_auto, dtype: float64\n",
+      "number of unique values:  202\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['monthly_premium_auto'].describe())\n",
+    "print ('number of unique values: ', df_numerical['monthly_premium_auto'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "8c6a4557",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='monthly_premium_auto', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='monthly_premium_auto',kde=True)\n",
+    "# there are 3 more noticeble peaks, so it loos like a multimodal distribution and it's right-skewed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "c51f8248",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count    9134.000000\n",
+      "mean       15.097000\n",
+      "std        10.073257\n",
+      "min         0.000000\n",
+      "25%         6.000000\n",
+      "50%        14.000000\n",
+      "75%        23.000000\n",
+      "max        35.000000\n",
+      "Name: months_since_last_claim, dtype: float64\n",
+      "number of unique values:  36\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['months_since_last_claim'].describe())\n",
+    "print ('number of unique values: ',df_numerical['months_since_last_claim'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "af65819b",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='months_since_last_claim', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjsAAAG2CAYAAACZEEfAAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8pXeV/AAAACXBIWXMAAA9hAAAPYQGoP6dpAABd7UlEQVR4nO3deXxU1f3/8dfNJJns+zIJCUlYFcImKIIiyCoWXCtarV+o1rpBS5HaorWiteDXb0UtKK39UVHRYhdR6w4qUEQUIrvsBBIgIQlZJutMlvv7IzJtNCGLSWYyeT8fj/uoc++5dz53Zmre3nvuOYZpmiYiIiIiXsrH3QWIiIiIdCSFHREREfFqCjsiIiLi1RR2RERExKsp7IiIiIhXU9gRERERr6awIyIiIl5NYUdERES8msKOiIiIeDWFHREREfFqHhN2Fi9ejGEYzJ0717XONE0WLlxIYmIigYGBjBs3jr179zbYz+FwMGfOHGJiYggODuaqq67ixIkTnVy9iIiIeCqPCDtbt27l+eefZ/DgwQ3WP/HEEyxZsoRly5axdetWbDYbkyZNorS01NVm7ty5rFmzhtWrV7Np0ybKysqYNm0atbW1nX0aIiIi4oHcHnbKysq45ZZb+POf/0xkZKRrvWmaPP300zz44INcd911pKen8+KLL1JRUcGrr74KQElJCStWrODJJ59k4sSJDBs2jFWrVrF7927WrVvnrlMSERERD+Lr7gLuvfdevve97zFx4kQee+wx1/rMzExyc3OZPHmya53VamXs2LFs3ryZO++8k4yMDKqrqxu0SUxMJD09nc2bNzNlypRG39PhcOBwOFyv6+rqKCwsJDo6GsMwOuAsRUREpL2ZpklpaSmJiYn4+DR9/catYWf16tV8+eWXbN269VvbcnNzAYiPj2+wPj4+nuPHj7va+Pv7N7gidLbN2f0bs3jxYh555JHvWr6IiIh4gOzsbJKSkprc7rawk52dzc9+9jM+/PBDAgICmmz3zSstpmk2e/WluTYLFixg3rx5rtclJSX07NmT7OxswsLCWngGIiIi4k52u53k5GRCQ0PP2c5tYScjI4O8vDyGDx/uWldbW8vGjRtZtmwZBw4cAOqv3iQkJLja5OXlua722Gw2nE4nRUVFDa7u5OXlMXr06Cbf22q1YrVav7U+LCxMYUdERKSLae4iiNs6KE+YMIHdu3ezY8cO1zJixAhuueUWduzYQa9evbDZbKxdu9a1j9PpZMOGDa4gM3z4cPz8/Bq0ycnJYc+ePecMOyIiItJ9uO3KTmhoKOnp6Q3WBQcHEx0d7Vo/d+5cFi1aRN++fenbty+LFi0iKCiIm2++GYDw8HBuv/127rvvPqKjo4mKimL+/PkMGjSIiRMndvo5iYiIiOdx+9NY53L//fdTWVnJPffcQ1FRESNHjuTDDz9scG/uqaeewtfXlxkzZlBZWcmECRNYuXIlFovFjZWLiIiIpzBM0zTdXYS72e12wsPDKSkpUZ8dERGRLqKlf7/dPqigiIiISEdS2BERERGvprAjIiIiXk1hR0RERLyawo6IiIh4NYUdERER8WoKOyIiIuLVFHZERETEqynsiIiIiFdT2BERERGv5tFzY0nHKSwsxG63t2qfsLAwoqKiOqgiERGRjqGw0w0VFhbSq3cfSoqLWrVfeEQkR48cVuAREZEuRWGnG7Lb7ZQUFzF7yStExNhatE9xQS7L5t2C3W5X2BERkS5FYacbi4ixEWVLcncZIiIiHUodlEVERMSrKeyIiIiIV1PYEREREa+msCMiIiJeTWFHREREvJrCjoiIiHg1hR0RERHxago7IiIi4tUUdkRERMSrKeyIiIiIV1PYEREREa+mubHEoxQWFmK321vcPiwsTBOTiojIOSnsiMcoLCykV+8+lBQXtXif8IhIjh45rMAjIiJNUtgRj2G32ykpLmL2kleIiLE12764IJdl827Bbrcr7IiISJMUdsTjRMTYiLIlubsMERHxEuqgLCIiIl5NYUdERES8msKOiIiIeDWFHREREfFqCjsiIiLi1RR2RERExKu5NewsX76cwYMHExYWRlhYGKNGjeK9995zbZ81axaGYTRYLr744gbHcDgczJkzh5iYGIKDg7nqqqs4ceJEZ5+KiIiIeCi3hp2kpCQef/xxtm3bxrZt2xg/fjxXX301e/fudbW54ooryMnJcS3vvvtug2PMnTuXNWvWsHr1ajZt2kRZWRnTpk2jtra2s09HREREPJBbBxWcPn16g9e/+93vWL58OVu2bGHgwIEAWK1WbLbGR9MtKSlhxYoVvPzyy0ycOBGAVatWkZyczLp165gyZUrHnoCIiIh4PI/ps1NbW8vq1aspLy9n1KhRrvXr168nLi6Ofv36cccdd5CXl+falpGRQXV1NZMnT3atS0xMJD09nc2bNzf5Xg6HA7vd3mARERER7+T2sLN7925CQkKwWq3cddddrFmzhgEDBgAwdepUXnnlFT7++GOefPJJtm7dyvjx43E4HADk5ubi7+9PZGRkg2PGx8eTm5vb5HsuXryY8PBw15KcnNxxJygiIiJu5fa5sfr378+OHTsoLi7mn//8JzNnzmTDhg0MGDCAG2+80dUuPT2dESNGkJKSwjvvvMN1113X5DFN08QwjCa3L1iwgHnz5rle2+12BR4REREv5faw4+/vT58+fQAYMWIEW7du5ZlnnuFPf/rTt9omJCSQkpLCoUOHALDZbDidToqKihpc3cnLy2P06NFNvqfVasVqtbbzmYiIiIgncvttrG8yTdN1m+qbzpw5Q3Z2NgkJCQAMHz4cPz8/1q5d62qTk5PDnj17zhl2REREpPtw65WdBx54gKlTp5KcnExpaSmrV69m/fr1vP/++5SVlbFw4UKuv/56EhISOHbsGA888AAxMTFce+21AISHh3P77bdz3333ER0dTVRUFPPnz2fQoEGup7O6osLCwlZ1mg4LCyMqKqoDKxIREem63Bp2Tp8+za233kpOTg7h4eEMHjyY999/n0mTJlFZWcnu3bt56aWXKC4uJiEhgcsvv5zXXnuN0NBQ1zGeeuopfH19mTFjBpWVlUyYMIGVK1disVjceGZtV1hYSK/efSgpLmrxPuERkRw9cliBR0REpBFuDTsrVqxocltgYCAffPBBs8cICAhg6dKlLF26tD1Lcxu73U5JcRGzl7xCREzj4wv9t+KCXJbNuwW73a6wIyIi0gi3d1CWxkXE2IiyJbm7DBERkS7P4zooi4iIiLQnhR0RERHxago7IiIi4tUUdkRERMSrKeyIiIiIV9PTWNIqJ06caHFbDXYoIiKeQGFHWqSyzA4YjBkzpsX7aLBDERHxBAo70ijTNKmtq5893uJj4KisAExmPfonklL7NLt/Zw522JqrTaArTiIi3Y3CjlDuqOF4YQUniiooKq+mqMKJs6YO8+vtFh8DX0KJv+UJDpsJ1DiCiQuzEh8WgJ/Ffd2+2nK1CXTFSUSku1HY6bYMTpbWsv7UCbKLKs/ZsrbOpBYfApIGkF0B2YcLALAYBgkRAaREBZESHUxMiD+GYXRG8QCtvtoEml5DRKQ7UtjphvbkVpDwoz/wcZbTtS4u1EpKdBCxIVYigvwJ8rfgazEwTXDW1HF43x5eX7mMMbf+gmprGKftDsocNZwoquREUSWfHjlDkL+FfvGhnGcLxdc0z1FB+wqLitPUGiIi0iSFHS/Rkn4rVdV1LP8slze/KsI/Lg0/HxiUFMGQpAjCAv2a3C/Az0KEXy0V+zfRP/w+UvslYpomxZXVHD9TwfEz5ZwoqqTCWcuO7GJ2ZBcT5m8QdvEN5JVVk9qO5ykiItJaCjtdXEv7rVhCooi97tdYE/oBULZrLTdfNYm03rFtel/DMIgM8icyyJ+hyRHU1NWRVVjBgZxSjhSUY3eaRI6dyU2vHGTa4DJ+PCaNwUkRbXovERGR70Jhp4trSb+Voqo6Pj7uoKIGrBboz0n+9d4zGN8b1251+Pr40CsmhF4xIThqatl5KJtPtnxJQM9BvLXzFG/tPMVFqVHcPiaNSefH4+PTeX17RESke1PY8RJN9VspqnDy0cETVNZAVJA/Vw1N5Mzhkg6txeproU+kL6v/uoAPt37Fe0ccvLXzFF8cK+SLY4Wk9wjjgannM7pPTIfWISIiApouwquVVdWwZvtJKqtriQ2xMmNEEuHn6JvTEfrGBLLkxqFs+uV47h7XmxCrL3tO2rn5/33OrBe+YH+uvVPrERGR7kdhx0vV1Nbx5s6TlFbVEBHoxzXDErH6WdxWjy08gF9ecR4bfjGOWaNT8fUxWH8gn6nP/Jtf/mMXReXO5g8iIiLSBgo7XmrDoXwKypwE+lm4dlgPgvw9445ldIiVhVcNZN28sXxvcAKmCa9ty2bikg2sO1Ts7vJERMQLKex4oYOnS9lzsv720JSB8ed8rNxdUmOCefbmC/jHXaPoFx/CmXInj310kphrFlBV03lj9IiIiPdT2PEypVXVfLQvD4ALUyNJiQ52c0XnNiI1irfnjGHepH5YfCC4/yW8faSKrMIKd5cmIiJeQmHHy2w8WICztg5bWAAXp0W7u5wW8ff14acT+rL82l44C7KorIE120/yRWYhZieOxCwiIt5JYceLHCso53B+GYYB48+L63Jj2fSLDST3xbn0iajvSP3Z0TP8a1cOjppaN1cmIiJdmcKOl6itg/UH8wEYmhxBbKjVzRW1jVnjZFQPfyaeH4fFxyCzoJy/bzuBvbLa3aWJiEgXpbDjJY6U+VBSWU2I1bfL3L46l4GJ4Xx/eBLB/hbOlDtZvTWbvNIqd5clIiJdkGc8j+zFCgsLsdtbPnBeSyb0/CbDP4jDpfW5dXTvaPx9vSPD2sICuOnCnry16xT5pQ7+mXGSq4Yk0iMy0N2liYhIF6Kw04EKCwvp1bsPJcVFrd63qqrlVzHCLrya6jqDqCB/+ttCW/1eHak14a2xtiEBvlx/QQ/+tTOHk8WVrNlxku8NSiAtxrOfMhMREc+hsNOB7HY7JcVFzF7yChExthbtk3VwNy89Nhens2UjCjvrDMIuvAaAkb2i8DE8o1NyS2djb8w3g57V18I1QxN5d08umQXlvL3rFJMH2PC80YNERMQTKex0gogYW6OTdDamOD+3Vcc+WuGPjzWAMD+TvnEhbSmvQ7RkNvZvOlfQ87X48L1BCazdd5oDuaW8vzeXwaGKOyIi0jyFnS6suraOY5X+APQPq8XwkKs6/62p2dgb01zQs/gYTBkQj9XXh10nSthVGkjwwPHtUaaIiHgx7+jJ2k3tzy2l2vShujiXhMDuMfieYRiM6xfL4KRwwCD6yp9xssLzQp6IiHgOhZ0uyjRNdmQVA1Ca8RYeeFGnw5wNPD0DnBg+FjLOWDiSX+buskRExEMp7HRRWYUVFFY48TVMynatdXc5nc4wDAaHVlK252NMDN7dncOxgnJ3lyUiIh5IfXa6qO3ZxQAkBzg54qx0bzFuYhhw5t2n6XfhOE5V+vD27hyuGZpIUmSQu0tr9fhKYWFhREVFdWBFIiLdl8JOF2Svqub4mfpZwdMCnax3bznuZdYxPLqWgKpQjhaU89bOU1x/QRLxYQFuK6kt4yuFR0Ry9MhhBR4RkQ7g1rCzfPlyli9fzrFjxwAYOHAgv/nNb5g6dSpQ3y/lkUce4fnnn6eoqIiRI0fy7LPPMnDgQNcxHA4H8+fP569//SuVlZVMmDCB5557jqSklj0B1BXtzykFICkykGDfEjdX434+BkxNt/HmzlOcKKrkjR0n+f4FSUSHuGd+sNaOr1RckMuyebdgt9sVdkREOoBb++wkJSXx+OOPs23bNrZt28b48eO5+uqr2bt3LwBPPPEES5YsYdmyZWzduhWbzcakSZMoLS11HWPu3LmsWbOG1atXs2nTJsrKypg2bRq1td45U7ZpmnyVU397ZEBCmJur8Ry+Fh+mD04kPsxKVXUda3acpMTNk4eeHV+puaWlA06KiEjbuDXsTJ8+nSuvvJJ+/frRr18/fve73xESEsKWLVswTZOnn36aBx98kOuuu4709HRefPFFKioqePXVVwEoKSlhxYoVPPnkk0ycOJFhw4axatUqdu/ezbp169x5ah3mVHEVJZXV+Ft86ONBgwh6An9fH64e2oPoYH/KHbWs2X6SckeNu8sSERE385insWpra1m9ejXl5eWMGjWKzMxMcnNzmTx5squN1Wpl7NixbN68GYCMjAyqq6sbtElMTCQ9Pd3VpjEOhwO73d5g6SrOXtXpGx+Cn8Vjvj6PEehn4ZphPQgP9KOkspo1209SVe2dV/lERKRl3P7Xcvfu3YSEhGC1WrnrrrtYs2YNAwYMIDe3fjTd+Pj4Bu3j4+Nd23Jzc/H39ycyMrLJNo1ZvHgx4eHhriU5Obmdz6pjOGvqOJRXfwvvfN3CalKI1Zdrh/Ug2GrhTLmTN3acxFlT5+6yRETETdwedvr378+OHTvYsmULd999NzNnzuSrr75ybf/mFAimaTY7LUJzbRYsWEBJSYlryc7O/m4n0UkyC8qprjUJD/QjMdx9Txt1BeGBflw7tAcBvj6ctjv4165T1NQq8IiIdEduf/Tc39+fPn3qJ4ocMWIEW7du5ZlnnuGXv/wlUH/1JiEhwdU+Ly/PdbXHZrPhdDopKipqcHUnLy+P0aNHN/meVqsVq9U9T+p8F2ev6vSNC/HIebA8TXSIlauH9eD1L09woqiS9/bkMirOc6fVOHHiRKvaa2weEZGWcXvY+SbTNHE4HKSlpWGz2Vi7di3Dhg0DwOl0smHDBv73f/8XgOHDh+Pn58fatWuZMWMGADk5OezZs4cnnnjCbefQEZw1dRz7emydvvHqmNxStrAArhqSyBs7TnG0oByqLYBnBcXKMjtgMGbMmFbtp7F5RERaxq1h54EHHmDq1KkkJydTWlrK6tWrWb9+Pe+//z6GYTB37lwWLVpE37596du3L4sWLSIoKIibb74ZgPDwcG6//Xbuu+8+oqOjiYqKYv78+QwaNIiJEye689Ta3bEz5dTW1d/CinXT+DFdVVJkEFcOsvHOrhyOltQSOfEnmKbnXOFxVFYAJrMe/RNJqX1atI83jc2j0aZFpKO5NeycPn2aW2+9lZycHMLDwxk8eDDvv/8+kyZNAuD++++nsrKSe+65xzWo4IcffkhoaKjrGE899RS+vr7MmDHDNajgypUrsVgs7jqtDnEor36iS93CapteMSFMGhDPB3tPEzZ8On/Zmsdv09LcXVYDYVFxRNm8dzDMxmi0aRHpDG4NOytWrDjndsMwWLhwIQsXLmyyTUBAAEuXLmXp0qXtXJ3nqK6tc01yqbF12u48WxhFhYV8kVPNy18WEBd9iNnj+yg8upFGmxaRzuBxfXbk244VlFNTZxIW4EtcqG5hfRf9o3z54K/PEznuRzy59iAV1bXcP6W/Ao+bnR1tWkSkI7j90XNp3tH/uqqjP8rfnf3zf3LPqPon+pavP8Jv3txLbZ3n9OEREZH2pbDj4epMk2Nn6sNOWkywm6vxHjOGxPDba9IxDHh5y3HueSVDIy2LiHgphR0Pd9peRVV1HVZfHxLCA91djle59eIUlv5gGP4WHz7Ye5qb/7yFPHuVu8sSEZF2prDj4TK/voWVEhWExUe3sNrbtMGJvHT7RYQF+PJlVjHTl21ie1bLnwwSERHPpw7KHu5s2EnVLawOc3GvaN6cfSl3vLSNw3ll3PinLdx/RX9uuyQNHwXMVmntmDmtHTVaRKQtFHY8WGlVNQVlTgBSoxV2OlJaTDBr7hnN/L/v5IO9p3nsnX1sOJjPE98f7DW3D1sbRKB1A/i1Zcycs6qqdPtQRDqOwo4HO1ZQPz1EQngAgf7eNUiiJwoN8OOPPxzOK59n8dg7X/HvQwVMfHIDP5/Uj1mjU/G1dN27vm0NIq0ZwK+1Y+YAZB3czUuPzcXpdLaqLhGR1lDY8WBnn8LSVZ3OYxgGP7w4hYt7RfOrf+5i2/EiHntnH3/9IoufT+rHlekJXfLWVluCSFsH8GvNmDnF+bktPq6ISFsp7HioOhNOFFUCkBId5OZqup8+cSH87c5R/D0jm8ff28+R/HJmv7qdfvGHmDU6jWuGJRLk3/X+76PB+0SkO+q61+W9XLHTwFlbR4CvD7EaNdktfHwMbrywJxvvv5y5E/sSYvXl4OkyHlizm5G/+4j7/raTT/bnaXweEREP1/X+07SbyK+qv1WSFBWEj0ZNdqvQAD/mTuzHj0an8feMbF767DhZhRX888sT/PPLE/j7+jC8ZyTDUyIZmBhGcK0Dw9ff3WWLiMjXFHY8VL6jPuAkR3rHk0CepjWPPJ99Iik8yI8fj+nFbZekse14EW/vOsUHe3M5bXfw2dEzfHb0jGufnve9zt/2VxKelUVogC9WXwtWXx/8/2uxWur/t6jagm9UEo5aqKszu2SfIBERT6aw44EMPyuFX4ednlHqr9OeKsvsgMGYMWNavM83n0jy8TG4KC2Ki9KieOSqgRwtKOezI2fYfaKEvTklHMkro7K6Dkct5JU6yCt1NPMOIfS444+8fwreP3UYq68PAX4WgvwthFh9CQnwJfTr/40I9CciyK/tH4CISDeksOOBrEkDMTEIDfAlPFB/2NqTo7ICMJn16J9ISu3TbPvmnkgyDIPesSH0jg1xrcvMzKT3+YO4Z+kbGCFRlFXV4Kipw1FTh/PrxVFTi7O2/p/LK6ooq6jAElB/jLNtSyqrm6wr2M8g7oZHWPppDsNy62voGx9CTIj6d4mIfJPCjgcKSBkCQHJkkGY57yBhUXEd9lSSYRiYjnIiA3yIiglptv3R3dtYdt8tzF66BltaP6qq66iqrqXcWUNZVQ1ljhpKq+qXogonjpo6yqtNAnsN55+7C/nn7kLXsaKC/ekbF0J/Wyh940PpFxdCv/jQDjlPEZGuQmHHA50NO7qF1b34GBDk70vQOfo2m6ZJZXUtWdkneXX577n7V49wxmHhcH4ZWYUVFJY7+TyzkM8zCxvsFxXkS9yNj7E1x0libQmRQX6EBfgRYvVVHyER8XoKOx7GWWfgH98LgCR1TpZvMAyDIH9f4oItlO36kKuSHyIpyQbEUlVdx/FiB8cKHRwrqiKz0EFmoYPTZdUUVtQQmDqU/YW17C/M+6/jQajVl7AAP8IC/QgL8CXY6kugv4Wailp8w+OpqK7FNE1dZRSRLkthx8MUVlswDB9CfE2Crfp6pHGt6Wht+AfiF52MX0xPRv9gLg5LECWV1ZRW1VBrmtirarBX1UBx5bf27XHXCq5csZ8Av4PEhFiJDrESE+xPbKiV2FArcV//b3xYAEZlTQecqYjId6e/ph6msLr+K4m2mm6uRDxZaztan52D6vw77yW1Xw+g/pZYuaMWe1U19srqr0NPNRXOWiqcNZRVOimtqMTHL4Cq6jpOFFW6RvVuSvLPVvPukSqiC3KICbFiCwsgPiwAf1+NXyoi7qOw42HOOOsn/Iy21rm5EukKWtrRurE5qAzDICSg/pH2xIhv3zItzD3BY//zPfYePExIVAIF5Q4KSh0UlDkpKHOQV1pFfqmD/FIHp4qryLVX4RMQwpkqkzNVZRw8XVb/PkB0iD8J4YGkRAfRMyoIvy48qaqIdD0KOx6kuraOkpqzYUdXdsQzBPlZ6BkdRM9m5mg7cPgog0Zdzs0L/x811jBO2+sDUGlVzdcBycnukyVYfAxSo4PoHx8K+pmLSCdQ2PEgOSVVmBjU2PMISo50dzkiQMtHm87PPUV1QRbJYRaibP/5/ZY5asgtqeJEUQWZBeXYq2o4kl/Okfxy/IxQIsb9iHJ19xGRDqSw40FOft1BtCp7Lwy81M3VSHfXltGmAaqqqhq8DrH60icuhD5xIYztZ1JQ5uTA6VIO5JZS5qghfOT1rMsxya7LZURqpAZGFJF2p7DjQU593fnTkb0HUNgR92prJ2in09lkG8MwXE9yje4dzZaMnWzccYDAtAvqA9DpUvrHhzKqd7RGDxeRdqOw4yFq60xy7PX/RVx1Yq+bqxH5j+/SCfpcfAwDm7WGvL/9hv9ZsoaTZiSH88o4cLqUw3llDOsZwci0KHzVmVlEviOFHQ+RV1pFbZ2Jv1FHzZmWz8gt4g0i/GFovwTy7FVsOlJAdmEl244XcSivjPHnxWk0cRH5ThR2PEROcf1VnUi/WjdXIuI+cWEBXDcsiSP5Zaw/kE9JZTVrtp/kfFsoY/rGutq1tNP0WWFhYY1O5Coi3YPCjoc4ewtLYUcEeseGkBQZyGdHzrDzRAn7cks5dqaCCyIctKXTdHhEJEePHFbgEemmFHY8RG7J2bCjZ3BFAKy+Fsb1j6O/LZSP9uVxptzJp/m+RI6/neljL6RnWvOdpgGKC3JZNu8W7Ha7wo5IN6Ww4wFKq6opc9RgGBChKzsiDSSEB3LTRcl8eugMO04UE3bhNeyoNkkJiyPyXFPEi4h8TY85eICzV3ViQqz4amJpkW/x9fFhbP9YLgwvp7aihJJqg79+kcWB3FJ3lyYiXYDCjgfI+TrsJIQFuLkSEc9ms9aQ88JPibbWUV1r8v7eXP59KJ+6Os07ISJNU9jxALlfd062hSvsiDSntuwMl8TWMiKlfkqKL7OKeXPnKaqqdQtYRBqnsONmNXV15NkdACQo7Ii0iGHAJX1iuDLdhq+PQVZhBau3ZlNQ5nB3aSLigRR23Cy/1EGtaRLoZ9Hw+CKt1Dc+lBkjkgkL8KWksprXtmZz6LT68YhIQ24NO4sXL+bCCy8kNDSUuLg4rrnmGg4cONCgzaxZszAMo8Fy8cUXN2jjcDiYM2cOMTExBAcHc9VVV7V60DF3Ods52RYegGGod7JIa8WGWrnpop4kRwZSU2fy7p5cNh8poM5UPx4RqefWsLNhwwbuvfdetmzZwtq1a6mpqWHy5MmUl5c3aHfFFVeQk5PjWt59990G2+fOncuaNWtYvXo1mzZtoqysjGnTplFb6/n38F39ddQ5WaTNAv0sXDO0Bxf0jABg67Ei/rXzFI4az/93gIh0PLeOs/P+++83eP3CCy8QFxdHRkYGl112mWu91WrFZrM1eoySkhJWrFjByy+/zMSJEwFYtWoVycnJrFu3jilTpnTcCbSD01/314kPs7q5EpGuzcfHYEzfWGJDrazbl8exMxW8tjWbMYm6Wy/S3XnUoIIlJSUA3xrldP369cTFxREREcHYsWP53e9+R1xcHAAZGRlUV1czefJkV/vExETS09PZvHlzo2HH4XDgcPynI6Pdbu+I02lWVXUtJZXVQP2cQOK5WnNbtKvcQvVW59nCiAzy5+1dORRVVPPeUQjoNcLdZYmIG3lM2DFNk3nz5nHppZeSnp7uWj916lRuuOEGUlJSyMzM5KGHHmL8+PFkZGRgtVrJzc3F39+fyMjIBseLj48nNze30fdavHgxjzzySIeeT0vkldYHrvBAPwL9LG6uRhpTWWanLXMxAVRVVbV/QdIi8WEB3HRhMu/sziGnpIq47/+GV7bn80BKivrGiXRDHhN2Zs+eza5du9i0aVOD9TfeeKPrn9PT0xkxYgQpKSm88847XHfddU0ezzTNJv+ltmDBAubNm+d6bbfbSU5O/o5n0Hqnv+6vEx+qW1ieylFZAZjMevRPJKW2bC6mrIO7eemxuTidzo4tTs4p2OrL9Rck8cGOTA4VwZ8/zyOncjv/9/0hBPrrPy5EuhOPCDtz5szhrbfeYuPGjSQlJZ2zbUJCAikpKRw6dAgAm82G0+mkqKiowdWdvLw8Ro8e3egxrFYrVqv7A8bZsKNbWJ4vLCqOKNu5f5tnFec3fkVROp/Fx+DiRH+2rP49cVPv5e1dORzNL+ePPxxOz+igJvcrLCxs9e3tsLAwTTQq4qHcGnZM02TOnDmsWbOG9evXk5aW1uw+Z86cITs7m4SEBACGDx+On58fa9euZcaMGQDk5OSwZ88ennjiiQ6t/7tS52SRzlG24z1eee7/eGTdKb7KsfO9pf/m9zcMYcrAbz/4UFhYSK/efSgpLmrVe4RHRHL0yGEFHhEP5Nawc++99/Lqq6/y5ptvEhoa6upjEx4eTmBgIGVlZSxcuJDrr7+ehIQEjh07xgMPPEBMTAzXXnutq+3tt9/OfffdR3R0NFFRUcyfP59Bgwa5ns7yROWOGsocNQDEherKjkhHG5wQzL/mXMrsV7/ky6xi7nw5gx9fmsYvp56Hn+U/T2zZ7XZKiouYveQVImIafwr0m4oLclk27xbsdrvCjogHcmvYWb58OQDjxo1rsP6FF15g1qxZWCwWdu/ezUsvvURxcTEJCQlcfvnlvPbaa4SGhrraP/XUU/j6+jJjxgwqKyuZMGECK1euxGLx3Pvyp0vrb2FFBfvj76tHY0U6Q2JEIK/dOYon3t/Pn/+dyf/blElGVhHLbr6AHhGBDdpGxNhafOtSRDyb229jnUtgYCAffPBBs8cJCAhg6dKlLF26tL1K63CuW1jqnCzSqfwsPjz4vQFcmBrF/L/vZHtWMVc8vZFHrx7INUN7uLs8EekAuqTgJnlnn8RS52QRt5g80MY7Px3D0OQISqtq+PlrO7l71ZcUV9a4uzQRaWcKO25ydoydOHVOFnGb5Kgg/nHXKOZP7oevj8H7e3P50d8OE9jnIneXJiLtyCMePe9uyh01VDhrMYCYEIUdEXfytfgwe3xfxvWP476/7eTA6VLirv8NG7OdTIioJjTAz90lfietfYxej9CLN1LYcYOzV3Uig/0bPAUiIu6T3iOct+ZcwsJ/bOXVL/M4boeXtxxnZFo0Q5MjsPh0vZGX2/IYvR6hF2+ksOMG+WdvYalzsohHsfpauPNiG0/+9GaGzH6W/Io6Nh0u4KtTdsb2j6VnVNMDEXqi1j5Gr0foxVsp7LhB3tePnccq7Ih4pOr8TKak+nOacDYdKqCwwsma7SdJjgxkdO8YbOFd68GCjn6MXrfKxNMp7LiBruyIeD7DMBhgC6NXTDCfHy1k18lisosqeW1bNr1ighnVO1p97tCtMukaFHY6WVV1Lfaq+kdbY/UvShGPF+BnYWz/WIb1jODzzEL25dg5WlDO0YJyesUEc0HPSAKaGTOsMd4y/5ZulUlXoLDTyc5e1QkP9MPq57kjPItIQ2GBfkwaEM/wlEi2HD3DobwyV+iJDjQIOu9SaupaFnq8cf4tjTgtnkxhp5OdfRJLV3VEuqaoYH+uHJRAYbmT7VlF7Mst5UylSezVv2LGS/uYPjCfK/pHkBDm3+QxTpw4ofm3RDqRwk4nO3tlJ1aDCYp0aVHB/kw4P55RvaPZtOswe3LKKCScFzPyWbntNFXHdlC2ay2Vhz/HrHE2eoyAkAhdDRHpBAo7nezsk1hxurIj0qlOnDjRru3OCvL3pY+1jPefm8XUB1dQ6BtDbjkEpl1AYNoF+PpAcqiFlDALiSE+WHwMsg7u5qXH5uJ0Nh6CRKR9Kex0ouraOooqqgE9di7SWSrL7IDBmDFjWrVfVVVV696otpq+caGk9utNSWU1X52ysy/XTmlVDZkltWSW1OLv60OvmGCCAxMw/LvWmD0iXZnCTic6U1b/X3FB/haCrfroRTqDo7ICMJn16J9ISu3TbPv2uOoSHujHqN7RXNwrilx7FQdPl3Eor5RyRy37c0uBYJJ/+iqf5vlQFFBEz6ggooL9MYyuN0qzSFegv7idqKCsvr+OxuYQ6XxhUXEt6h9TnJ/bbu9pGAYJ4YEkhAdyWd8YThVXcbSgjAMnz1COLwUO2HioAKj/j6CkyECSI4NIjgoiLMBX4UeknSjsdKL/hJ2mn9IQEe9kGAY9IgPrl6rj/PGxXzDl/uXYfUI5VVxJhbOWg6fLOHi6DIDQAF+SIgNJDA8kITwA2jCWj4jUU9jpRPlleuxcROrVFJ2id2gdqf16UFNXR25JFdlFlZworCDXXkVpVQ37ckrZl1MKgJ8PxN3wCCu35THeGczQnhGEdfEZ2UU6i8JOJzFNk4Kv++xEK+yIyH/x9fEhKTKIpMgg6BWNs6aOnJJKThRVkltSRa69iuo6k8Bew1m5LZ+V2/IxDOgdG8KQpAiG9oxgaFIE5yWE4mfxcffpiHgchZ1OUuqowVlTh49RPz6HiEhT/H19SIkOJiU6GIC6OpMjx7N5+Y9Pc+O9v+LAGSfZhZUczivjcF4Z//yy/nF5q68P6T3CXQEo1tCj7SKgsNNpCr4eTDAq2B+LjzodikjL+fgYRAf6ULb9HX49YRmpqakUlDnYmV3Mzuxitn/9v/aqGjKOF5FxvAg+rd83afYqPj7uILniDLbwAGzhAVh9NVWNdC8KO53k7C0sPYklIu0hJsTKhPPjmXB+PFB/9efYmXJ2ZBez4+vws/eUHYIjOFlWx8myQgAMIC7M+vVts/oO0P6+uvUl3q1NYadXr15s3bqV6OjoBuuLi4u54IILOHr0aLsU50302LmItIdzjfDsA1wQBRdEhcCQEI4ez2bqzXcw/Rd/oNQMINdeRUllNaftDk7bHWQcL8LHgKTIINJigoky6zrvREQ6UZvCzrFjx6itrf3WeofDwcmTJ79zUd5Ij52LyHfR1pGgAdKCa0hMrZ9wtLSqmhNFlWQXVXCiqJLSqhqyCivIKqwAIOG2ZbywNY9ZIbGkxQS35ymIuE2rws5bb73l+ucPPviA8PBw1+va2lo++ugjUlNT2604b1FTZ1L89TQRurIjIm3R2pGgofHRoEMD/Dg/wY/zE8IAKCp3crSgnMyCck4VV+Ifm8qLGfm8mLGeockRXDusB9MGJ+gpUunSWhV2rrnmGqB+cKyZM2c22Obn50dqaipPPvlkuxXnLUocJiYQ6GchyF8dA0Wk7Vo6EjS0bDToyGB/hgf7MzwlkpwT2Tz3+8f43j0L2XbyP/1/fvv2V0wdlMCs0Slc0DNSIztLl9OqsFNXV38/Ny0tja1btxITE9MhRXmboqr6zy0mRHPfiIjnsvoalH+1nv/9XgrB0Qn8a+cp1mw/ye6TJfxr5yn+tfMUg3qEM3N0KtMGJxDgp/94k66hTX12MjMz27sOr/afsKPLwCLSNcSGWrnt0jRuuzSNPSdLeHHzMd7ceYrdJ0uY//edPPH+fu4c25tL4jWNhXi+Nj96/tFHH/HRRx+Rl5fnuuJz1l/+8pfvXJg3Kaqq/5dBTKjCjoh0Pek9wvm/G4aw4Mrz+esXWazacpyckip++/ZXRAZaCLvoWqrrFHrEc7Up7DzyyCM8+uijjBgxgoSEBN2aaUaR4z+3sUREPN25Hm//Xpovk3um8cGBYlZtLyC3tJrIy29nzcEqLq4tZlCPcA2cKh6nTWHnj3/8IytXruTWW29t73q8jiUkGmctGAZEBSnsiIjnavXj7T4WggdeTvioGRCZyIaD+ezILuaS3tH0iQvRfwiLx2hT2HE6nYwePbq9a/FKfnFpQH3Q8dUEfSLiwdr8ePvv7uKqxWs4VO5PSWU17+7JJSE8gDF9Y0gID+zYokVaoE1h58c//jGvvvoqDz30UHvX43X8Y1MBiNYtLBHpIlr9eLtZR2pIHaMHp5KRVcSXx4vIKanib9tO0D8+lEv6RBMa4NfBVYs0rU1hp6qqiueff55169YxePBg/Pwa/oiXLFnSLsV5A/+4VEBPYomI9/P39WFUr2gG9Qhny9Ez7D1l58DpUo7kl3FhahQX9Ixwd4nnVFhYiN1ub3H7sLAwoqKiOrAiaS9tCju7du1i6NChAOzZs6fBNt2jbejsbSyFHRHpLkKsvkw8P57BPcJZfzCfnJIqPjt6hr2nShga65m38wsLC+nVuw8lxUUt3ic8IpKjRw4r8HQBbQo7n3zySXvX4ZUcNXX4RdVfCo5V2BGRbiYuLIAbhidx8HQZmw4XYK+qYWM2xN/0O46eqcKTZhey2+2UFBcxe8krRMTYmm1fXJDLsnm3YLfbFXa6ALdG7MWLF3PhhRcSGhpKXFwc11xzDQcOHGjQxjRNFi5cSGJiIoGBgYwbN469e/c2aONwOJgzZw4xMTEEBwdz1VVXnfPRyc6SVezA8LHgb4Fgq0YaFZHuxzAM+ttC+Z9RKVyUGoXFgICUIfz4H0d46I09FJU7mz9IJ4qIsRFlS2p2aUkgEs/RprBz+eWXM378+CaXltqwYQP33nsvW7ZsYe3atdTU1DB58mTKy8tdbZ544gmWLFnCsmXL2Lp1KzabjUmTJlFaWupqM3fuXNasWcPq1avZtGkTZWVlTJs2rdGZ2TvTkTP1M51HWn10e09EujU/iw+jekdzVR8r5fv/TZ0JL285zrjfr+fFzceoqa1r/iAibdSm21hn++ucVV1dzY4dO9izZ8+3Jgg9l/fff7/B6xdeeIG4uDgyMjK47LLLME2Tp59+mgcffJDrrrsOgBdffJH4+HheffVV7rzzTkpKSlixYgUvv/wyEydOBGDVqlUkJyezbt06pkyZ0pZTbBdHzlQBEBmgoCMiAhDi70PBm//L87+4lT9tPcP+3FIefmsvr3x+nIenD+SSPu0z52JrOxt7wt0A6ThtCjtPPfVUo+sXLlxIWVlZm4spKSkBcN3/zMzMJDc3l8mTJ7vaWK1Wxo4dy+bNm7nzzjvJyMigurq6QZvExETS09PZvHlzo2HH4XDgcDhcr1vzf4jWsFoMauz5RCYmdsjxRUS6qmE9gnn74vNZvTWbJz88wMHTZdzy/z5nysB4HrxyAD2jg9p87LZ0Nj6rqqqqze8rnqvNc2M15oc//CEXXXQRv//971u9r2mazJs3j0svvZT09HQAcnNzAYiPj2/QNj4+nuPHj7va+Pv7ExkZ+a02Z/f/psWLF/PII4+0usbW+vHIeH5308X0fnFdh7+XiEhX42vx4YcXpzBtcAJPrzvEy1uO88He03yyP58fj0nj3sv7EGxt/Z+p1nY2hq8HR3xsLk6nZ/UhkvbRrmHns88+IyAgoE37zp49m127drFp06ZvbftmfxfTNJvtA3OuNgsWLGDevHmu13a7neTk5DZU3TLqryMi0rSIIH8WXjWQm0f25NF/fcWmwwU8t/4Iq7dmc/ulafzPqJQ2DUp4trNxSxTnN/4fx+Id2hR2zvafOcs0TXJycti2bVubRlWeM2cOb731Fhs3biQp6T8/TJutPpHn5uaSkJDgWp+Xl+e62mOz2XA6nRQVFTW4upOXl9fklBZWqxWrVY+Ci4h4kn7xobx8+0Ws/eo0i97dx7EzFfzfBwf404YjzLokjdsuSSVCcwxKG7Tpaazw8PAGS1RUFOPGjePdd9/l4YcfbvFxTNNk9uzZvP7663z88cekpaU12J6WlobNZmPt2rWudU6nkw0bNriCzPDhw/Hz82vQJicnhz179mj+LhGRLsYwDCYPtLFu3lievnEofeJCsFfV8IePDjH68Y9Z8Ppu9pwscXeZ0sW06crOCy+80C5vfu+99/Lqq6/y5ptvEhoa6upjEx4eTmBgIIZhMHfuXBYtWkTfvn3p27cvixYtIigoiJtvvtnV9vbbb+e+++4jOjqaqKgo5s+fz6BBg1xPZ4mISNfia/HhmmE9uGpIIu/vzWXpx4fZl2Pnr19k8dcvshicFM4PLurJ9CGJhLShX490L9/pF5KRkcG+ffswDIMBAwYwbNiwVu2/fPlyAMaNG9dg/QsvvMCsWbMAuP/++6msrOSee+6hqKiIkSNH8uGHHxIaGupq/9RTT+Hr68uMGTOorKxkwoQJrFy5EotFA/mJiHRlPj4GVw5KYGq6jS1HC3n1iyze35PDrhMl7Dqxm4ff2sulfWKYPCCeiQPiNTWPNKpNYScvL4+bbrqJ9evXExERgWmalJSUcPnll7N69WpiY2NbdBzTNJttYxgGCxcuZOHChU22CQgIYOnSpSxdurSlpyAiIl2IYRiM6h3NqN7RnCkbwD+/PMHqrdkczS/n4/15fLw/D2PNbob3jOT8aAsBqcOorm3+b4x0D23qszNnzhzsdjt79+6lsLCQoqIi9uzZg91u56c//Wl71ygiIuISHWLlJ5f15qN5Y/nw55cxf3I/BieFY5qw7XgRL39ZQPyNv+W1/VX89YssPtmfx+6TJeSUVOKs0UjN3VGbruy8//77rFu3jvPPP9+1bsCAATz77LMNBvcTERHpKIZh0C8+lH7xocwe35dTxZVsPJjPJ3uyePuLA/hF2MgrdZBX6miwX3igHzEh/sSEWIkNtRITYqUFNxraRWtHdg4LC9NEo+2gTWGnrq4OP79vj3ng5+dHXZ1Ss4iIdL7EiEBuuqgnF8fV8fztY/j5inVU+EWQX+agoNRBQZmDcmctJZXVlFRWcyT/P/Mw+hphxN/8OLuKfCg7VUJsSH0Isvi03zhpbRnZOTwikqNHDivwfEdtCjvjx4/nZz/7GX/9619J/HoqhJMnT/Lzn/+cCRMmtGuBIiIibRHsZ5BsC6U//3mgpcJZQ0GZkwJXAHJyptxBjWkQkJxOZhlk7ssDwNfHICEigB4RgfSICMQWFoCvpU29P4DWj+xcXJDLsnm3YLfbFXa+ozaFnWXLlnH11VeTmppKcnIyhmGQlZXFoEGDWLVqVXvXKCIi0i6C/H3pGeVLz6j/zL1VW2eye+d2/vnS84z8wVycfiHk2x1U1dSRXVhJdmElUB9+UqKD6BMbQkRd2+97tWZkZ2kfbQo7ycnJfPnll6xdu5b9+/djmiYDBgzQuDYiItIirZ1lvCP7rlh8DMJ86yjf+wnpET8ltV8SpmlSWO7kZHElJ4sqOVFcSYWzliP55RzJL8cA4mY8yocHi/mfHrUE+GmoE0/WqrDz8ccfM3v2bLZs2UJYWBiTJk1i0qRJQP2M5QMHDuSPf/wjY8aM6ZBiRUSka6ssswNGq/9OdHbfFcMwiA6xEh1iZXBS/RAr+aUODueXcSS/nMJyJ4FpF7Do45M8+1ke11+QxM0jk+kTF9r8waXTtSrsPP3009xxxx2EhYV9a1t4eDh33nknS5YsUdgREZFGOSorAJNZj/6JpNQ+LdrHE/quGIZBXFgAcWEBjO4dw7HjWbz4wgr6T/0Rp8uq+cunmfzl00wu7hXF3eP6cFnfGE0C7UFaFXZ27tzJ//7v/za5ffLkyfz+97//zkWJiIh3C4uKa3W/lZbe+mrtLbK2CLP6ULJ5Nf/3+D2cqkvgX/uK+Ox4KVuOFrLl6Bf0jw3ghxfEcklqKD5fh57OqEsa16qwc/r06UYfOXcdzNeX/Pz871yUiIjIWW299VVVVdUxBfGfmsZedplrnSU0mrALryVk6BUcyIeHPsjGmX+Mkk2vUnFwc6fUJY1rVdjp0aMHu3fvpk+fxi897tq1i4SEhHYpTEREBFp/6yvr4G5eemwuTqfTLTVV1ZjsO1PDgcIaiE0l9toHiA30oYczizcX3dWhdUnjWhV2rrzySn7zm98wdepUAgICGmyrrKzk4YcfZtq0ae1aoIiICLT81ldxfm4nVFOvqZoSk+DS6lq+zCrmy6wi8ivryCeJmGsWUFbdsTVplOZva1XY+fWvf83rr79Ov379mD17Nv3798cwDPbt28ezzz5LbW0tDz74YEfVKiIi0mVY/SyM6h3NoKRwthw9w95TJQT3v4SPc02KrQVclBqFv2/bBylsjEZpblyrwk58fDybN2/m7rvvZsGCBa5Zyw3DYMqUKTz33HPEx8d3SKEiIiJdUYjVl4nnxxNbdZJ3t+4nqPeFZBwv4kBuKZf1jaFPXEi7PbmlUZob1+pBBVNSUnj33XcpKiri8OHDmKZJ3759iYyM7Ij6REREvEKobx35/3iEGf/3BvvKArBX1fDunlx6RgUxrl8skcH+7fZeGqW5oTaNoAwQGRnJhRde2J61iIiIeD1boMmI9BS2HS9i2/EisgorWPX5cYanRHJhahR+32H+LWmcPlEREZFO5mvx4eJe0fxwZE9SooOoM2HrsSJe3nKcYwXlzR9AWqXNV3ZERETku4kI8ufqIYkcLShnw8F8SqtqeHPnKfrFhzA4ou2TjUpDCjsiIiJuZBgGvWND6BkVxJajZ9ieVczB02UcK4DgQZNcDwNJ2+k2loiIiAfws/gwpm8sN16YTGyoFWctxFz5M37+r2MczS9zd3ldmq7siIiIeJD4sABuGpHM5q+OsTW7jB2n4Ipn/s2cy/tw59je7T42D7R+3q6uNhChwo6IiIiH8fExGBDjx1uP3Ms1v3uNrdllPLn2IG/tPMXj1w9ieEr7BI22zjvW1QYiVNgRERHxUDUlp3niyp7sKvHn0X99xaG8Mr7/x8+4ZWRP7r/iPMICmp6cuyVaO+8YdM2BCBV2REREPJhhGFw9tAeX9Y1l0bv7+HvGCVZtyWLtV6d55Kp0rkhvfqTk5rR03rGuSh2URUREuoDIYH/+74YhvPrjkaRGB3Ha7uCuVRn85KVtnLZXubs8j6awIyIi0oWM7hPD+3Mv497Le+PrY/DhV6eZ/NRG3txxUo+pN0FhR0REpIsJ8LPwiynn8fZPL2VQj3BKKqv52eodPLz2BD6BYe4uz+Mo7IiIiHRR59nCeP2e0fx8Yj98fQw2HrWTePuzZNtr3V2aR1HYERER6cL8LD78bGJf3rj3ElIjrViCI1mf7WTDwXxq63RbCxR2REREvEJ6j3Ce/34vSr54HYAd2cX888sTlFZVu7ky91PYERER8RL+Fh+KP/kL45L98ff1Iaekir9+kU1WYYW7S3MrhR0REREvkxxm4QcXJhMbYqWyupY120+y7Xhht31aS2FHRETEC0UE+TNjRBIDE+ufzvr08Bk+OZBPXTfsx6OwIyIi4qV8LT5MPD+esf1iAdh9soS3d+dQU1vn5so6l8KOiIiIlxuaHMH3BiVg8THILCjnrV2nqO5GgcetYWfjxo1Mnz6dxMREDMPgjTfeaLB91qxZGIbRYLn44osbtHE4HMyZM4eYmBiCg4O56qqrWj1VvYiIiLfrExfCNUMT8bMYZBdW8uaOU9R0kztabg075eXlDBkyhGXLljXZ5oorriAnJ8e1vPvuuw22z507lzVr1rB69Wo2bdpEWVkZ06ZNo7ZWAyqJiIj8t6TIIK4Z2gN/iw8niyvZVhIEPt4/J7hbz3Dq1KlMnTr1nG2sVis2W+MzupaUlLBixQpefvllJk6cCMCqVatITk5m3bp1TJkypd1rFhER6coSIwK5Zlgir395knynHzHT5uHtD2l5fJ+d9evXExcXR79+/bjjjjvIy8tzbcvIyKC6uprJkye71iUmJpKens7mzZubPKbD4cButzdYREREuouE8ECmDU7AwCT4/MvYW+zxceA78eizmzp1Kq+88goff/wxTz75JFu3bmX8+PE4HA4AcnNz8ff3JzIyssF+8fHx5ObmNnncxYsXEx4e7lqSk5M79DxEREQ8TUp0MMPCKgE4UmZh76kSN1fUcTw67Nx4441873vfIz09nenTp/Pee+9x8OBB3nnnnXPuZ5omhmE0uX3BggWUlJS4luzs7PYuXURExOP1CKimeNMrAHy8P4+TxZVurqhjeHTY+aaEhARSUlI4dOgQADabDafTSVFRUYN2eXl5xMfHN3kcq9VKWFhYg0VERKQ7Kvl0NYmBddSZ8N7uHCqcNe4uqd11qbBz5swZsrOzSUhIAGD48OH4+fmxdu1aV5ucnBz27NnD6NGj3VWmiIhIF2IyLKqWqCB/yp21fPjVaa+bVsKtYaesrIwdO3awY8cOADIzM9mxYwdZWVmUlZUxf/58PvvsM44dO8b69euZPn06MTExXHvttQCEh4dz++23c9999/HRRx+xfft2fvjDHzJo0CDX01kiIiJybr4+MHWQDYuPwfEzFXyZVezuktqVWx8937ZtG5dffrnr9bx58wCYOXMmy5cvZ/fu3bz00ksUFxeTkJDA5ZdfzmuvvUZoaKhrn6eeegpfX19mzJhBZWUlEyZMYOXKlVgslk4/HxERka4qJsTK2H6xfLw/j81HCugZFURsqNXdZbULt4adcePGnfNS2QcffNDsMQICAli6dClLly5tz9JERES6nfTEMI4VlHO0oJx1+05z44hkfHwaf+CnNbMVhIWFERUV1V5ltpr3D5soIiIiLWIYBuPPi+PkluPklTrIyCriwtSGIaWyzA4YjBkzpsXHDY+I5OiRw24LPAo7IiIi4hJs9WVsv1g+/Oo0nx8tpE9sCJHB/q7tjsoKwGTWo38iKbVPs8crLshl2bxbsNvtCjsiIiLiGc6zhXLgdCnHz1Sw/mA+1wxN/Nb4dWFRcUTZktxUYeso7IiIiHiw1vSNaU3bczEMg3H9Ylm1JYuswgqOFpTTOzakXY7tDgo7IiIiHqgtfWPOqqqq+s7vHxHkz/CUSL44VsiGg/mkRAXha+lSw/O5KOyIiIh4oNb2jQHIOriblx6bi9PpbJcaRqRG8lWOndKqGjKyihiZFt0ux+1sCjsiIiIerDV9Y4rzm54Euy38LD6M6RvDe3tyyThexKAe4e16/M7SNa9HiYiISKfoGxdCXKiV6lqTrZlFze/ggRR2REREpEmGYXBJnxgAdp0spqK28UEGPZnCjoiIiJxTz6ggekYFUWfC/rIAd5fTago7IiIi0qxLetd3Tj7p8MM3MtHN1bSOwo6IiIg0Ky4sgLSYYMAgfNQMd5fTKgo7IiIi0iIXpdVP9xA88HLKa9xcTCso7IiIiEiL2MICiPWvxvCxcMhucXc5LaawIyIiIi3WL9gBQFa5QWlVtZuraRmFHREREWmxKL9aqo7vwsRgZ3aJu8tpEYUdERERaRX7F68DsPtkCY6aWjdX0zyFHREREWmVyqMZhPiaOGvr2HvK7u5ymqWwIyIiIq1k0ie0/orO9qxiautMN9dzbgo7IiIi0mpJwSaBfhbKHDUczitzdznnpLAjIiIirWYxYHBS/SzoO08Uu7eYZijsiIiISJsM6hGOjwE5JVXklVa5u5wmKeyIiIhImwRbfekTFwLArhOe+xi6wo6IiIi02ZCkCAD255ZSVe2Zj6Er7IiIiEibJYQHEBtipbbO9NjH0BV2REREpM0Mw3B1VN5zqgTT9LzH0BV2RERE5DvpFx+Kn8WguKKaU8We11FZYUdERES+E39fH/rGhQKwN8fzOior7IiIiMh3NjAxDIBDp8s8br4shR0RERH5zhLCA4gM8qOmzuTgac8aUVlhR0RERL4zwzBIT6zvqLz3lGfdylLYERERkXZxXkIoPgactjsoKHO4uxwXhR0RERFpF0H+vqTFBAN41Jg7CjsiIiLSbgZ+fStrf46dmro6N1dTT2FHRERE2k1KdBAhVl+qauo4ml/u7nIAN4edjRs3Mn36dBITEzEMgzfeeKPBdtM0WbhwIYmJiQQGBjJu3Dj27t3boI3D4WDOnDnExMQQHBzMVVddxYkTJzrxLEREROQsH8NgQEL9Y+iecivLrWGnvLycIUOGsGzZska3P/HEEyxZsoRly5axdetWbDYbkyZNorS01NVm7ty5rFmzhtWrV7Np0ybKysqYNm0atbWe9Yy/iIhIdzHg6zF3sgorKHe6/1aWrzvffOrUqUydOrXRbaZp8vTTT/Pggw9y3XXXAfDiiy8SHx/Pq6++yp133klJSQkrVqzg5ZdfZuLEiQCsWrWK5ORk1q1bx5QpUzrtXERERKReeKAfSRGBnCiu5GiJ+y8+eGyfnczMTHJzc5k8ebJrndVqZezYsWzevBmAjIwMqqurG7RJTEwkPT3d1aYxDocDu93eYBEREZH2c15C/fQRmQo7TcvNzQUgPj6+wfr4+HjXttzcXPz9/YmMjGyyTWMWL15MeHi4a0lOTm7n6kVERLq3PnEhWHwMShwm/rY+bq3FY8POWYZhNHhtmua31n1Tc20WLFhASUmJa8nOzm6XWkVERKSe1ddC79j6MXeCB453ay0eG3ZsNhvAt67Q5OXlua722Gw2nE4nRUVFTbZpjNVqJSwsrMEiIiIi7et8W/3f1+DzL6Om1nRbHR4bdtLS0rDZbKxdu9a1zul0smHDBkaPHg3A8OHD8fPza9AmJyeHPXv2uNqIiIiIe/SMCiLAFyzBEXxxwn2Tg7r1aayysjIOHz7sep2ZmcmOHTuIioqiZ8+ezJ07l0WLFtG3b1/69u3LokWLCAoK4uabbwYgPDyc22+/nfvuu4/o6GiioqKYP38+gwYNcj2dJSIiIu7h42OQGmbhq9MV5NidbqvDrWFn27ZtXH755a7X8+bNA2DmzJmsXLmS+++/n8rKSu655x6KiooYOXIkH374IaGhoa59nnrqKXx9fZkxYwaVlZVMmDCBlStXYrFYOv18REREpKFBsX58+NAPuX7OV26rwa1hZ9y4cZhm0/fwDMNg4cKFLFy4sMk2AQEBLF26lKVLl3ZAhSIiIvJdBPgamM5Kt9bgsX12RERERNqDwo6IiIh4NYUdERER8WoKOyIiIuLVFHZERETEqynsiIiIiFdT2BERERGvprAjIiIiXk1hR0RERLyawo6IiIh4NYUdERER8WoKOyIiIuLVFHZERETEqynsiIiIiFdT2BERERGvprAjIiIiXk1hR0RERLyawo6IiIh4NYUdERER8WoKOyIiIuLVFHZERETEqynsiIiIiFdT2BERERGvprAjIiIiXk1hR0RERLyawo6IiIh4NYUdERER8WoKOyIiIuLVFHZERETEqynsiIiIiFdT2BERERGvprAjIiIiXk1hR0RERLyawo6IiIh4NYUdERER8WoeHXYWLlyIYRgNFpvN5tpumiYLFy4kMTGRwMBAxo0bx969e91YsYiIiHgajw47AAMHDiQnJ8e17N6927XtiSeeYMmSJSxbtoytW7dis9mYNGkSpaWlbqxYREREPInHhx1fX19sNptriY2NBeqv6jz99NM8+OCDXHfddaSnp/Piiy9SUVHBq6++6uaqRURExFN4fNg5dOgQiYmJpKWlcdNNN3H06FEAMjMzyc3NZfLkya62VquVsWPHsnnz5nMe0+FwYLfbGywiIiLinTw67IwcOZKXXnqJDz74gD//+c/k5uYyevRozpw5Q25uLgDx8fEN9omPj3dta8rixYsJDw93LcnJyR12DiIiIuJeHh12pk6dyvXXX8+gQYOYOHEi77zzDgAvvviiq41hGA32MU3zW+u+acGCBZSUlLiW7Ozs9i9eREREPIJHh51vCg4OZtCgQRw6dMj1VNY3r+Lk5eV962rPN1mtVsLCwhosIiIi4p26VNhxOBzs27ePhIQE0tLSsNlsrF271rXd6XSyYcMGRo8e7cYqRURExJP4uruAc5k/fz7Tp0+nZ8+e5OXl8dhjj2G325k5cyaGYTB37lwWLVpE37596du3L4sWLSIoKIibb77Z3aWLiIiIh/DosHPixAl+8IMfUFBQQGxsLBdffDFbtmwhJSUFgPvvv5/KykruueceioqKGDlyJB9++CGhoaFurlxEREQ8hUeHndWrV59zu2EYLFy4kIULF3ZOQSIiItLldKk+OyIiIiKtpbAjIiIiXk1hR0RERLyawo6IiIh4NYUdERER8WoKOyIiIuLVFHZERETEqynsiIiIiFdT2BERERGvprAjIiIiXk1hR0RERLyawo6IiIh4NYUdERER8WoKOyIiIuLVFHZERETEqynsiIiIiFdT2BERERGvprAjIiIiXk1hR0RERLyawo6IiIh4NYUdERER8WoKOyIiIuLVFHZERETEqynsiIiIiFdT2BERERGvprAjIiIiXk1hR0RERLyawo6IiIh4NYUdERER8WoKOyIiIuLVFHZERETEqynsiIiIiFdT2BERERGvprAjIiIiXk1hR0RERLyawo6IiIh4Na8JO8899xxpaWkEBAQwfPhw/v3vf7u7JBEREfEAXhF2XnvtNebOncuDDz7I9u3bGTNmDFOnTiUrK8vdpYmIiIibeUXYWbJkCbfffjs//vGPOf/883n66adJTk5m+fLl7i5NRERE3MzX3QV8V06nk4yMDH71q181WD958mQ2b97c6D4OhwOHw+F6XVJSAoDdbm/X2kpLSwHIO3EUR2V5i/YpyM2u/99Tx7H6Wdq9fWfto/fQe+g93PsenlqX3qP7vUfJmdNA/d/E9v47e/Z4pmmeu6HZxZ08edIEzE8//bTB+t/97ndmv379Gt3n4YcfNgEtWrRo0aJFixcs2dnZ58wKXf7KzlmGYTR4bZrmt9adtWDBAubNm+d6XVdXR2FhIdHR0U3u0xZ2u53k5GSys7MJCwtrt+N2Jd39M+ju5w/6DLr7+YM+A51/x52/aZqUlpaSmJh4znZdPuzExMRgsVjIzc1tsD4vL4/4+PhG97FarVit1gbrIiIiOqpEwsLCuuUP/L9198+gu58/6DPo7ucP+gx0/h1z/uHh4c226fIdlP39/Rk+fDhr165tsH7t2rWMHj3aTVWJiIiIp+jyV3YA5s2bx6233sqIESMYNWoUzz//PFlZWdx1113uLk1ERETczCvCzo033siZM2d49NFHycnJIT09nXfffZeUlBS31mW1Wnn44Ye/dcusO+nun0F3P3/QZ9Ddzx/0Gej83X/+hmk297yWiIiISNfV5fvsiIiIiJyLwo6IiIh4NYUdERER8WoKOyIiIuLVFHY60HPPPUdaWhoBAQEMHz6cf//73+4uqVMsXLgQwzAaLDabzd1ldaiNGzcyffp0EhMTMQyDN954o8F20zRZuHAhiYmJBAYGMm7cOPbu3eueYjtAc+c/a9asb/0mLr74YvcU2wEWL17MhRdeSGhoKHFxcVxzzTUcOHCgQRtv/w205DPw5t/B8uXLGTx4sGvgvFGjRvHee++5tnv79w/Nfwbu/P4VdjrIa6+9xty5c3nwwQfZvn07Y8aMYerUqWRlZbm7tE4xcOBAcnJyXMvu3bvdXVKHKi8vZ8iQISxbtqzR7U888QRLlixh2bJlbN26FZvNxqRJk1yTxXZ1zZ0/wBVXXNHgN/Huu+92YoUda8OGDdx7771s2bKFtWvXUlNTw+TJkykv/88EwN7+G2jJZwDe+ztISkri8ccfZ9u2bWzbto3x48dz9dVXuwKNt3//0PxnAG78/r/7VJzSmIsuusi86667Gqw777zzzF/96lduqqjzPPzww+aQIUPcXYbbAOaaNWtcr+vq6kybzWY+/vjjrnVVVVVmeHi4+cc//tENFXasb56/aZrmzJkzzauvvtot9bhDXl6eCZgbNmwwTbP7/QZM89ufgWl2v99BZGSk+f/+3//rlt//WWc/A9N07/evKzsdwOl0kpGRweTJkxusnzx5Mps3b3ZTVZ3r0KFDJCYmkpaWxk033cTRo0fdXZLbZGZmkpub2+D3YLVaGTt2bLf5PQCsX7+euLg4+vXrxx133EFeXp67S+owJSUlAERFRQHd8zfwzc/grO7wO6itrWX16tWUl5czatSobvn9f/MzOMtd379XjKDsaQoKCqitrf3WRKTx8fHfmrDUG40cOZKXXnqJfv36cfr0aR577DFGjx7N3r17iY6Odnd5ne7sd97Y7+H48ePuKKnTTZ06lRtuuIGUlBQyMzN56KGHGD9+PBkZGV43qqxpmsybN49LL72U9PR0oPv9Bhr7DMD7fwe7d+9m1KhRVFVVERISwpo1axgwYIAr0HSH77+pzwDc+/0r7HQgwzAavDZN81vrvNHUqVNd/zxo0CBGjRpF7969efHFF5k3b54bK3Ov7vp7gPopXc5KT09nxIgRpKSk8M4773Dddde5sbL2N3v2bHbt2sWmTZu+ta27/Aaa+gy8/XfQv39/duzYQXFxMf/85z+ZOXMmGzZscG3vDt9/U5/BgAED3Pr96zZWB4iJicFisXzrKk5eXt63kn13EBwczKBBgzh06JC7S3GLs0+i6ffwHwkJCaSkpHjdb2LOnDm89dZbfPLJJyQlJbnWd6ffQFOfQWO87Xfg7+9Pnz59GDFiBIsXL2bIkCE888wz3er7b+ozaExnfv8KOx3A39+f4cOHs3bt2gbr165dy+jRo91Ulfs4HA727dtHQkKCu0txi7S0NGw2W4Pfg9PpZMOGDd3y9wBw5swZsrOzveY3YZoms2fP5vXXX+fjjz8mLS2twfbu8Bto7jNojLf9Dr7JNE0cDke3+P6bcvYzaEynfv9u6RbdDaxevdr08/MzV6xYYX711Vfm3LlzzeDgYPPYsWPuLq3D3Xfffeb69evNo0ePmlu2bDGnTZtmhoaGevW5l5aWmtu3bze3b99uAuaSJUvM7du3m8ePHzdN0zQff/xxMzw83Hz99dfN3bt3mz/4wQ/MhIQE0263u7ny9nGu8y8tLTXvu+8+c/PmzWZmZqb5ySefmKNGjTJ79OjhNed/9913m+Hh4eb69evNnJwc11JRUeFq4+2/geY+A2//HSxYsMDcuHGjmZmZae7atct84IEHTB8fH/PDDz80TdP7v3/TPPdn4O7vX2GnAz377LNmSkqK6e/vb15wwQUNHsH0ZjfeeKOZkJBg+vn5mYmJieZ1111n7t27191ldahPPvnEBL61zJw50zTN+kePH374YdNms5lWq9W87LLLzN27d7u36HZ0rvOvqKgwJ0+ebMbGxpp+fn5mz549zZkzZ5pZWVnuLrvdNHbugPnCCy+42nj7b6C5z8Dbfwe33Xab69/3sbGx5oQJE1xBxzS9//s3zXN/Bu7+/g3TNM2Ov34kIiIi4h7qsyMiIiJeTWFHREREvJrCjoiIiHg1hR0RERHxago7IiIi4tUUdkRERMSrKeyIiIiIV1PYEZEmLVy4kKFDh3ab923KuHHjmDt3rrvLaJJhGLzxxhstbu9pn69IR1PYERGg9X8wO9L8+fP56KOP3F1Ghzh27BiGYbBjxw631eDNn69IY3zdXYCIyDeFhIQQEhLi7jK8lj5f6W50ZUfEw4wbN445c+Ywd+5cIiMjiY+P5/nnn6e8vJwf/ehHhIaG0rt3b9577z3XPhs2bOCiiy7CarWSkJDAr371K2pqahoc86c//Sn3338/UVFR2Gw2Fi5c6NqempoKwLXXXothGK7XZ7388sukpqYSHh7OTTfdRGlpqWvbP/7xDwYNGkRgYCDR0dFMnDiR8vLyZs9z/fr1XHTRRQQHBxMREcEll1zC8ePHgW/fZpk1axbXXHMNv//970lISCA6Opp7772X6upqVxuHw8H9999PcnIyVquVvn37smLFCtf2r776iiuvvJKQkBDi4+O59dZbKSgoaLbOxqxatYoRI0YQGhqKzWbj5ptvJi8vz7W9qKiIW265hdjYWAIDA+nbty8vvPACgGs28GHDhmEYBuPGjWvRe/7lL39h4MCBru949uzZTbb95S9/Sb9+/QgKCqJXr1489NBDDT6rpj7fRYsWER8fT0REBI888gg1NTX84he/ICoqiqSkJP7yl7+04lMS8RwKOyIe6MUXXyQmJoYvvviCOXPmcPfdd3PDDTcwevRovvzyS6ZMmcKtt95KRUUFJ0+e5Morr+TCCy9k586dLF++nBUrVvDYY49965jBwcF8/vnnPPHEEzz66KOsXbsWgK1btwLwwgsvkJOT43oNcOTIEd544w3efvtt3n77bTZs2MDjjz8OQE5ODj/4wQ+47bbb2LdvH+vXr+e6666juSn3ampquOaaaxg7diy7du3is88+4yc/+QmGYTS5zyeffMKRI0f45JNPePHFF1m5ciUrV650bf+f//kfVq9ezR/+8Af27dvHH//4R9fVi5ycHMaOHcvQoUPZtm0b77//PqdPn2bGjBkt/1L+i9Pp5Le//S07d+7kjTfeIDMzk1mzZrm2P/TQQ3z11Ve899577Nu3j+XLlxMTEwPAF198AcC6devIycnh9ddfb/b9li9fzr333stPfvITdu/ezVtvvUWfPn2abB8aGsrKlSv56quveOaZZ/jzn//MU089dc73+Pjjjzl16hQbN25kyZIlLFy4kGnTphEZGcnnn3/OXXfdxV133UV2dnYLPiERD9Mp042KSIuNHTvWvPTSS12va2pqzODgYPPWW291rcvJyTEB87PPPjMfeOABs3///mZdXZ1r+7PPPmuGhISYtbW1jR7TNE3zwgsvNH/5y1+6XgPmmjVrGrR5+OGHzaCgINNut7vW/eIXvzBHjhxpmqZpZmRkmIB57NixVp3jmTNnTMBcv359o9sffvhhc8iQIa7XM2fONFNSUsyamhrXuhtuuMG88cYbTdM0zQMHDpiAuXbt2kaP99BDD5mTJ09usC47O9sEzAMHDjRb79ixY82f/exnTW7/4osvTMAsLS01TdM0p0+fbv7oRz9qtG1mZqYJmNu3b2/2fc9KTEw0H3zwwSa3N/bd/bcnnnjCHD58uOt1U5/v2d+LaZpm//79zTFjxrhen/0d/vWvf21x3SKeQld2RDzQ4MGDXf9ssViIjo5m0KBBrnXx8fEA5OXlsW/fPkaNGtXgqsgll1xCWVkZJ06caPSYAAkJCQ1uvTQlNTWV0NDQRvcbMmQIEyZMYNCgQdxwww38+c9/pqioqNljRkVFMWvWLKZMmcL06dN55plnyMnJOec+AwcOxGKxNFrHjh07sFgsjB07ttF9MzIy+OSTT1x9VUJCQjjvvPOA+itXrbV9+3auvvpqUlJSCA0Ndd2KysrKAuDuu+9m9erVDB06lPvvv5/Nmze3+j3OysvL49SpU0yYMKHF+/zjH//g0ksvxWazERISwkMPPeSqrSkDBw7Ex+c/fxLi4+Mb/ObO/g5b8psR8TQKOyIeyM/Pr8FrwzAarDsbbOrq6jBN81u3f8yvbyP99/rGjllXV9emWs7uZ7FYWLt2Le+99x4DBgxg6dKl9O/fn8zMzGaP+8ILL/DZZ58xevRoXnvtNfr168eWLVvaVEdgYOA536uuro7p06ezY8eOBsuhQ4e47LLLmq31v5WXlzN58mRCQkJYtWoVW7duZc2aNUD97S2AqVOncvz4cebOnesKKvPnz2/V+5zV3Ll905YtW7jpppuYOnUqb7/9Ntu3b+fBBx901daU5n5zZ9e15Dcj4mkUdkS6uAEDBrB58+YG/WQ2b95MaGgoPXr0aPFx/Pz8qK2tbfX7G4bBJZdcwiOPPML27dvx9/d3/fFvzrBhw1iwYAGbN28mPT2dV199tdXvDzBo0CDq6urYsGFDo9svuOAC9u7dS2pqKn369GmwBAcHt+q99u/fT0FBAY8//jhjxozhvPPOa/RqR2xsLLNmzWLVqlU8/fTTPP/88wD4+/sDtPizDg0NJTU1tcWPin/66aekpKTw4IMPMmLECPr27evq+C3SXSnsiHRx99xzD9nZ2cyZM4f9+/fz5ptv8vDDDzNv3rwGtyWac/YPam5ubotuRQF8/vnnLFq0iG3btpGVlcXrr79Ofn4+559//jn3y8zMZMGCBXz22WccP36cDz/8kIMHDza737lqnzlzJrfddpurw/D69ev529/+BsC9995LYWEhP/jBD/jiiy84evQoH374IbfddlurA17Pnj3x9/dn6dKlHD16lLfeeovf/va3Ddr85je/4c033+Tw4cPs3buXt99+23VucXFxBAYGujpJl5SUNPueCxcu5Mknn+QPf/gDhw4d4ssvv2Tp0qWNtu3Tpw9ZWVmsXr2aI0eO8Ic//KHF4VPEWynsiHRxPXr04N133+WLL75gyJAh3HXXXdx+++38+te/btVxnnzySdauXUtycjLDhg1r0T5hYWFs3LiRK6+8kn79+vHrX/+aJ598kqlTp55zv6CgIPbv38/1119Pv379+MlPfsLs2bO58847W1Xzf1u+fDnf//73ueeeezjvvPO44447XI/AJyYm8umnn1JbW8uUKVNIT0/nZz/7GeHh4a0KhFB/xWblypX8/e9/Z8CAATz++OP8/ve/b9DG39+fBQsWMHjwYC677DIsFgurV68GwNfXlz/84Q/86U9/IjExkauvvrrZ95w5cyZPP/00zz33HAMHDmTatGkcOnSo0bZXX301P//5z5k9ezZDhw5l8+bNPPTQQ606RxFvY5hmM8+IioiIiHRhurIjIiIiXk1hR0Q6xH8/5v3N5d///re7y3PJyso6Z63NPbLdHrrKZyXSVek2loh0iMOHDze5rUePHq1+pLqj1NTUcOzYsSa3p6am4uvbsdMIdpXPSqSrUtgRERERr6bbWCIiIuLVFHZERETEqynsiIiIiFdT2BERERGvprAjIiIiXk1hR0RERLyawo6IiIh4NYUdERER8Wr/H7GpvzCH0ByAAAAAAElFTkSuQmCC",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='months_since_last_claim',bins= 36, kde=True)\n",
+    "# bins are irregular, but we can see a peak around 4 and then a decrease from left to right"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "a4826b7e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count    9134.000000\n",
+      "mean       48.064594\n",
+      "std        27.905991\n",
+      "min         0.000000\n",
+      "25%        24.000000\n",
+      "50%        48.000000\n",
+      "75%        71.000000\n",
+      "max        99.000000\n",
+      "Name: months_since_policy_inception, dtype: float64\n",
+      "number of unique values:  100\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['months_since_policy_inception'].describe())\n",
+    "print ('number of unique values: ',df_numerical['months_since_policy_inception'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "c5b92713",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='months_since_policy_inception', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='months_since_policy_inception', kde=True)\n",
+    "#bins are irregular and there are a couple of peaks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "19562ccd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count    9134.000000\n",
+      "mean        0.384388\n",
+      "std         0.910384\n",
+      "min         0.000000\n",
+      "25%         0.000000\n",
+      "50%         0.000000\n",
+      "75%         0.000000\n",
+      "max         5.000000\n",
+      "Name: number_of_open_complaints, dtype: float64\n",
+      "number of unique values:  6\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['number_of_open_complaints'].describe())\n",
+    "print ('number of unique values: ',df_numerical['number_of_open_complaints'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "6f3f38ac",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='number_of_open_complaints', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='number_of_open_complaints', bins=6, kde=True)\n",
+    "# plot is right skewed, most values are at zero"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "1e58676f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count    9134.000000\n",
+      "mean        2.966170\n",
+      "std         2.390182\n",
+      "min         1.000000\n",
+      "25%         1.000000\n",
+      "50%         2.000000\n",
+      "75%         4.000000\n",
+      "max         9.000000\n",
+      "Name: number_of_policies, dtype: float64\n",
+      "number of unique values:  9\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['number_of_policies'].describe())\n",
+    "print ('number of unique values: ',df_numerical['number_of_policies'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "5fd5179b",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='number_of_policies', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='number_of_policies', bins=9, kde=True)\n",
+    "# plot is right skewed, most values are at 1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "75600e89",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count    9134.000000\n",
+      "mean      434.088794\n",
+      "std       290.500092\n",
+      "min         0.099007\n",
+      "25%       272.258244\n",
+      "50%       383.945434\n",
+      "75%       547.514839\n",
+      "max      2893.239678\n",
+      "Name: total_claim_amount, dtype: float64\n",
+      "number of unique values:  5106\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['total_claim_amount'].describe())\n",
+    "print ('number of unique values: ',df_numerical['total_claim_amount'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "4ff3df2d",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='total_claim_amount', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='total_claim_amount', kde=True)\n",
+    "# plot is right-skewed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "8da7afd7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# None of the histograms displayed a normal distribution bell curve."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8412a487",
+   "metadata": {},
+   "source": [
+    "# Processing data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2d4b8cd0",
+   "metadata": {},
+   "source": [
+    "Normalize (numerical)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "632467dc",
+   "metadata": {
+    "scrolled": true
+   },
+   "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>customer_lifetime_value</th>\n",
+       "      <th>income</th>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <th>months_since_last_claim</th>\n",
+       "      <th>months_since_policy_inception</th>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <th>number_of_policies</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0.010629</td>\n",
+       "      <td>0.562847</td>\n",
+       "      <td>0.033755</td>\n",
+       "      <td>0.914286</td>\n",
+       "      <td>0.050505</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.132974</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0.062406</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.139241</td>\n",
+       "      <td>0.371429</td>\n",
+       "      <td>0.424242</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.875</td>\n",
+       "      <td>0.391051</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0.134960</td>\n",
+       "      <td>0.487763</td>\n",
+       "      <td>0.198312</td>\n",
+       "      <td>0.514286</td>\n",
+       "      <td>0.383838</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.125</td>\n",
+       "      <td>0.195764</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0.070589</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.189873</td>\n",
+       "      <td>0.514286</td>\n",
+       "      <td>0.656566</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.750</td>\n",
+       "      <td>0.183117</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0.011245</td>\n",
+       "      <td>0.438443</td>\n",
+       "      <td>0.050633</td>\n",
+       "      <td>0.342857</td>\n",
+       "      <td>0.444444</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.047710</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9129</th>\n",
+       "      <td>0.264137</td>\n",
+       "      <td>0.719547</td>\n",
+       "      <td>0.050633</td>\n",
+       "      <td>0.514286</td>\n",
+       "      <td>0.898990</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.125</td>\n",
+       "      <td>0.068485</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9130</th>\n",
+       "      <td>0.014719</td>\n",
+       "      <td>0.216081</td>\n",
+       "      <td>0.075949</td>\n",
+       "      <td>0.400000</td>\n",
+       "      <td>0.282828</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.131034</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9131</th>\n",
+       "      <td>0.076951</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.101266</td>\n",
+       "      <td>0.257143</td>\n",
+       "      <td>0.373737</td>\n",
+       "      <td>0.6</td>\n",
+       "      <td>0.125</td>\n",
+       "      <td>0.273297</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9132</th>\n",
+       "      <td>0.069098</td>\n",
+       "      <td>0.219452</td>\n",
+       "      <td>0.147679</td>\n",
+       "      <td>0.971429</td>\n",
+       "      <td>0.030303</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.250</td>\n",
+       "      <td>0.238876</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9133</th>\n",
+       "      <td>0.008766</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.067511</td>\n",
+       "      <td>0.085714</td>\n",
+       "      <td>0.909091</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.127716</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>9134 rows × 8 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      customer_lifetime_value    income  monthly_premium_auto  \\\n",
+       "0                    0.010629  0.562847              0.033755   \n",
+       "1                    0.062406  0.000000              0.139241   \n",
+       "2                    0.134960  0.487763              0.198312   \n",
+       "3                    0.070589  0.000000              0.189873   \n",
+       "4                    0.011245  0.438443              0.050633   \n",
+       "...                       ...       ...                   ...   \n",
+       "9129                 0.264137  0.719547              0.050633   \n",
+       "9130                 0.014719  0.216081              0.075949   \n",
+       "9131                 0.076951  0.000000              0.101266   \n",
+       "9132                 0.069098  0.219452              0.147679   \n",
+       "9133                 0.008766  0.000000              0.067511   \n",
+       "\n",
+       "      months_since_last_claim  months_since_policy_inception  \\\n",
+       "0                    0.914286                       0.050505   \n",
+       "1                    0.371429                       0.424242   \n",
+       "2                    0.514286                       0.383838   \n",
+       "3                    0.514286                       0.656566   \n",
+       "4                    0.342857                       0.444444   \n",
+       "...                       ...                            ...   \n",
+       "9129                 0.514286                       0.898990   \n",
+       "9130                 0.400000                       0.282828   \n",
+       "9131                 0.257143                       0.373737   \n",
+       "9132                 0.971429                       0.030303   \n",
+       "9133                 0.085714                       0.909091   \n",
+       "\n",
+       "      number_of_open_complaints  number_of_policies  total_claim_amount  \n",
+       "0                           0.0               0.000            0.132974  \n",
+       "1                           0.0               0.875            0.391051  \n",
+       "2                           0.0               0.125            0.195764  \n",
+       "3                           0.0               0.750            0.183117  \n",
+       "4                           0.0               0.000            0.047710  \n",
+       "...                         ...                 ...                 ...  \n",
+       "9129                        0.0               0.125            0.068485  \n",
+       "9130                        0.0               0.000            0.131034  \n",
+       "9131                        0.6               0.125            0.273297  \n",
+       "9132                        0.0               0.250            0.238876  \n",
+       "9133                        0.0               0.000            0.127716  \n",
+       "\n",
+       "[9134 rows x 8 columns]"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Normalization, in the context of data preprocessing, refers to the process of rescaling features to a range of [0, 1]. \n",
+    "#It's useful when the features have different ranges or units. Normalization ensures that all features are on a similar scale, preventing some features from dominating others.\n",
+    "\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "\n",
+    "scaler = MinMaxScaler()\n",
+    "normalized_data = scaler.fit_transform(df_numerical)\n",
+    "normalized_data = pd.DataFrame(normalized_data, columns=df_numerical.columns)\n",
+    "normalized_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "8a9c6497",
+   "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>customer_lifetime_value</th>\n",
+       "      <th>income</th>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <th>months_since_last_claim</th>\n",
+       "      <th>months_since_policy_inception</th>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <th>number_of_policies</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>-0.762878</td>\n",
+       "      <td>0.612827</td>\n",
+       "      <td>-0.703925</td>\n",
+       "      <td>1.678099</td>\n",
+       "      <td>-1.543287</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>-0.822648</td>\n",
+       "      <td>-0.169640</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>-0.149245</td>\n",
+       "      <td>-1.239617</td>\n",
+       "      <td>0.022691</td>\n",
+       "      <td>-0.208186</td>\n",
+       "      <td>-0.217334</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>2.106160</td>\n",
+       "      <td>2.400737</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0.710636</td>\n",
+       "      <td>0.365710</td>\n",
+       "      <td>0.429596</td>\n",
+       "      <td>0.288205</td>\n",
+       "      <td>-0.360680</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>-0.404247</td>\n",
+       "      <td>0.455734</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>-0.052263</td>\n",
+       "      <td>-1.239617</td>\n",
+       "      <td>0.371467</td>\n",
+       "      <td>0.288205</td>\n",
+       "      <td>0.606907</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>1.687759</td>\n",
+       "      <td>0.329769</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>-0.755575</td>\n",
+       "      <td>0.203390</td>\n",
+       "      <td>-0.587666</td>\n",
+       "      <td>-0.307465</td>\n",
+       "      <td>-0.145661</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>-0.822648</td>\n",
+       "      <td>-1.018843</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9129</th>\n",
+       "      <td>2.241590</td>\n",
+       "      <td>1.128558</td>\n",
+       "      <td>-0.587666</td>\n",
+       "      <td>0.288205</td>\n",
+       "      <td>1.466984</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>-0.404247</td>\n",
+       "      <td>-0.811934</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9130</th>\n",
+       "      <td>-0.714411</td>\n",
+       "      <td>-0.528450</td>\n",
+       "      <td>-0.413278</td>\n",
+       "      <td>-0.108908</td>\n",
+       "      <td>-0.719046</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>-0.822648</td>\n",
+       "      <td>-0.188956</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9131</th>\n",
+       "      <td>0.023135</td>\n",
+       "      <td>-1.239617</td>\n",
+       "      <td>-0.238891</td>\n",
+       "      <td>-0.605299</td>\n",
+       "      <td>-0.396517</td>\n",
+       "      <td>2.873245</td>\n",
+       "      <td>-0.404247</td>\n",
+       "      <td>1.227937</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9132</th>\n",
+       "      <td>-0.069935</td>\n",
+       "      <td>-0.517356</td>\n",
+       "      <td>0.080820</td>\n",
+       "      <td>1.876656</td>\n",
+       "      <td>-1.614960</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>0.014154</td>\n",
+       "      <td>0.885113</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9133</th>\n",
+       "      <td>-0.784955</td>\n",
+       "      <td>-1.239617</td>\n",
+       "      <td>-0.471408</td>\n",
+       "      <td>-1.200968</td>\n",
+       "      <td>1.502821</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>-0.822648</td>\n",
+       "      <td>-0.222004</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>9134 rows × 8 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      customer_lifetime_value    income  monthly_premium_auto  \\\n",
+       "0                   -0.762878  0.612827             -0.703925   \n",
+       "1                   -0.149245 -1.239617              0.022691   \n",
+       "2                    0.710636  0.365710              0.429596   \n",
+       "3                   -0.052263 -1.239617              0.371467   \n",
+       "4                   -0.755575  0.203390             -0.587666   \n",
+       "...                       ...       ...                   ...   \n",
+       "9129                 2.241590  1.128558             -0.587666   \n",
+       "9130                -0.714411 -0.528450             -0.413278   \n",
+       "9131                 0.023135 -1.239617             -0.238891   \n",
+       "9132                -0.069935 -0.517356              0.080820   \n",
+       "9133                -0.784955 -1.239617             -0.471408   \n",
+       "\n",
+       "      months_since_last_claim  months_since_policy_inception  \\\n",
+       "0                    1.678099                      -1.543287   \n",
+       "1                   -0.208186                      -0.217334   \n",
+       "2                    0.288205                      -0.360680   \n",
+       "3                    0.288205                       0.606907   \n",
+       "4                   -0.307465                      -0.145661   \n",
+       "...                       ...                            ...   \n",
+       "9129                 0.288205                       1.466984   \n",
+       "9130                -0.108908                      -0.719046   \n",
+       "9131                -0.605299                      -0.396517   \n",
+       "9132                 1.876656                      -1.614960   \n",
+       "9133                -1.200968                       1.502821   \n",
+       "\n",
+       "      number_of_open_complaints  number_of_policies  total_claim_amount  \n",
+       "0                     -0.422250           -0.822648           -0.169640  \n",
+       "1                     -0.422250            2.106160            2.400737  \n",
+       "2                     -0.422250           -0.404247            0.455734  \n",
+       "3                     -0.422250            1.687759            0.329769  \n",
+       "4                     -0.422250           -0.822648           -1.018843  \n",
+       "...                         ...                 ...                 ...  \n",
+       "9129                  -0.422250           -0.404247           -0.811934  \n",
+       "9130                  -0.422250           -0.822648           -0.188956  \n",
+       "9131                   2.873245           -0.404247            1.227937  \n",
+       "9132                  -0.422250            0.014154            0.885113  \n",
+       "9133                  -0.422250           -0.822648           -0.222004  \n",
+       "\n",
+       "[9134 rows x 8 columns]"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Standardization, also known as z-score normalization, involves rescaling features to have a mean of 0 and a standard deviation of 1. \n",
+    "# This is useful when your data might not follow a normal distribution, but you still want to make features comparable. \n",
+    "\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "\n",
+    "scaler = StandardScaler()\n",
+    "normalized_data = scaler.fit_transform(df_numerical)\n",
+    "normalized_data = pd.DataFrame(normalized_data, columns=df_numerical.columns)\n",
+    "normalized_data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "af12cb74",
+   "metadata": {},
+   "source": [
+    "X-y split"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "4b13050d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x800 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "correlations_matrix = df_numerical.corr()\n",
+    "\n",
+    "mask = np.zeros_like(correlations_matrix)\n",
+    "mask[np.triu_indices_from(mask)] = True\n",
+    "fig, ax = plt.subplots(figsize=(10, 8))\n",
+    "ax = sns.heatmap(correlations_matrix, mask=mask, annot=True)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "c1526a6e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"simpletable\">\n",
+       "<caption>OLS Regression Results</caption>\n",
+       "<tr>\n",
+       "  <th>Dep. Variable:</th>    <td>total_claim_amount</td> <th>  R-squared:         </th> <td>   0.519</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Model:</th>                    <td>OLS</td>        <th>  Adj. R-squared:    </th> <td>   0.518</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Method:</th>              <td>Least Squares</td>   <th>  F-statistic:       </th> <td>   1405.</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Date:</th>              <td>Wed, 03 Apr 2024</td>  <th>  Prob (F-statistic):</th>  <td>  0.00</td>  \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Time:</th>                  <td>16:58:20</td>      <th>  Log-Likelihood:    </th> <td> -61425.</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>No. Observations:</th>       <td>  9134</td>       <th>  AIC:               </th> <td>1.229e+05</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Df Residuals:</th>           <td>  9126</td>       <th>  BIC:               </th> <td>1.229e+05</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Df Model:</th>               <td>     7</td>       <th>                     </th>     <td> </td>    \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Covariance Type:</th>       <td>nonrobust</td>     <th>                     </th>     <td> </td>    \n",
+       "</tr>\n",
+       "</table>\n",
+       "<table class=\"simpletable\">\n",
+       "<tr>\n",
+       "                <td></td>                   <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>const</th>                         <td>   72.3910</td> <td>    8.744</td> <td>    8.279</td> <td> 0.000</td> <td>   55.252</td> <td>   89.530</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>customer_lifetime_value</th>       <td>   -0.0007</td> <td>    0.000</td> <td>   -2.014</td> <td> 0.044</td> <td>   -0.001</td> <td>-1.81e-05</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>income</th>                        <td>   -0.0033</td> <td> 6.95e-05</td> <td>  -47.370</td> <td> 0.000</td> <td>   -0.003</td> <td>   -0.003</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>monthly_premium_auto</th>          <td>    5.3425</td> <td>    0.067</td> <td>   79.934</td> <td> 0.000</td> <td>    5.212</td> <td>    5.474</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>months_since_last_claim</th>       <td>   -0.1457</td> <td>    0.210</td> <td>   -0.695</td> <td> 0.487</td> <td>   -0.557</td> <td>    0.265</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>months_since_policy_inception</th> <td>   -0.1023</td> <td>    0.076</td> <td>   -1.352</td> <td> 0.176</td> <td>   -0.251</td> <td>    0.046</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>number_of_open_complaints</th>     <td>   -1.3716</td> <td>    2.319</td> <td>   -0.591</td> <td> 0.554</td> <td>   -5.918</td> <td>    3.174</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>number_of_policies</th>            <td>    0.2486</td> <td>    0.883</td> <td>    0.281</td> <td> 0.778</td> <td>   -1.483</td> <td>    1.980</td>\n",
+       "</tr>\n",
+       "</table>\n",
+       "<table class=\"simpletable\">\n",
+       "<tr>\n",
+       "  <th>Omnibus:</th>       <td>994.270</td> <th>  Durbin-Watson:     </th> <td>   1.980</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Prob(Omnibus):</th> <td> 0.000</td>  <th>  Jarque-Bera (JB):  </th> <td>6389.170</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Skew:</th>          <td> 0.316</td>  <th>  Prob(JB):          </th> <td>    0.00</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Kurtosis:</th>      <td> 7.048</td>  <th>  Cond. No.          </th> <td>2.02e+05</td>\n",
+       "</tr>\n",
+       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.<br/>[2] The condition number is large, 2.02e+05. This might indicate that there are<br/>strong multicollinearity or other numerical problems."
+      ],
+      "text/latex": [
+       "\\begin{center}\n",
+       "\\begin{tabular}{lclc}\n",
+       "\\toprule\n",
+       "\\textbf{Dep. Variable:}                   & total\\_claim\\_amount & \\textbf{  R-squared:         } &     0.519   \\\\\n",
+       "\\textbf{Model:}                           &         OLS          & \\textbf{  Adj. R-squared:    } &     0.518   \\\\\n",
+       "\\textbf{Method:}                          &    Least Squares     & \\textbf{  F-statistic:       } &     1405.   \\\\\n",
+       "\\textbf{Date:}                            &   Wed, 03 Apr 2024   & \\textbf{  Prob (F-statistic):} &     0.00    \\\\\n",
+       "\\textbf{Time:}                            &       16:58:20       & \\textbf{  Log-Likelihood:    } &   -61425.   \\\\\n",
+       "\\textbf{No. Observations:}                &          9134        & \\textbf{  AIC:               } & 1.229e+05   \\\\\n",
+       "\\textbf{Df Residuals:}                    &          9126        & \\textbf{  BIC:               } & 1.229e+05   \\\\\n",
+       "\\textbf{Df Model:}                        &             7        & \\textbf{                     } &             \\\\\n",
+       "\\textbf{Covariance Type:}                 &      nonrobust       & \\textbf{                     } &             \\\\\n",
+       "\\bottomrule\n",
+       "\\end{tabular}\n",
+       "\\begin{tabular}{lcccccc}\n",
+       "                                          & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
+       "\\midrule\n",
+       "\\textbf{const}                            &      72.3910  &        8.744     &     8.279  &         0.000        &       55.252    &       89.530     \\\\\n",
+       "\\textbf{customer\\_lifetime\\_value}        &      -0.0007  &        0.000     &    -2.014  &         0.044        &       -0.001    &    -1.81e-05     \\\\\n",
+       "\\textbf{income}                           &      -0.0033  &     6.95e-05     &   -47.370  &         0.000        &       -0.003    &       -0.003     \\\\\n",
+       "\\textbf{monthly\\_premium\\_auto}           &       5.3425  &        0.067     &    79.934  &         0.000        &        5.212    &        5.474     \\\\\n",
+       "\\textbf{months\\_since\\_last\\_claim}       &      -0.1457  &        0.210     &    -0.695  &         0.487        &       -0.557    &        0.265     \\\\\n",
+       "\\textbf{months\\_since\\_policy\\_inception} &      -0.1023  &        0.076     &    -1.352  &         0.176        &       -0.251    &        0.046     \\\\\n",
+       "\\textbf{number\\_of\\_open\\_complaints}     &      -1.3716  &        2.319     &    -0.591  &         0.554        &       -5.918    &        3.174     \\\\\n",
+       "\\textbf{number\\_of\\_policies}             &       0.2486  &        0.883     &     0.281  &         0.778        &       -1.483    &        1.980     \\\\\n",
+       "\\bottomrule\n",
+       "\\end{tabular}\n",
+       "\\begin{tabular}{lclc}\n",
+       "\\textbf{Omnibus:}       & 994.270 & \\textbf{  Durbin-Watson:     } &    1.980  \\\\\n",
+       "\\textbf{Prob(Omnibus):} &   0.000 & \\textbf{  Jarque-Bera (JB):  } & 6389.170  \\\\\n",
+       "\\textbf{Skew:}          &   0.316 & \\textbf{  Prob(JB):          } &     0.00  \\\\\n",
+       "\\textbf{Kurtosis:}      &   7.048 & \\textbf{  Cond. No.          } & 2.02e+05  \\\\\n",
+       "\\bottomrule\n",
+       "\\end{tabular}\n",
+       "%\\caption{OLS Regression Results}\n",
+       "\\end{center}\n",
+       "\n",
+       "Notes: \\newline\n",
+       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified. \\newline\n",
+       " [2] The condition number is large, 2.02e+05. This might indicate that there are \\newline\n",
+       " strong multicollinearity or other numerical problems."
+      ],
+      "text/plain": [
+       "<class 'statsmodels.iolib.summary.Summary'>\n",
+       "\"\"\"\n",
+       "                            OLS Regression Results                            \n",
+       "==============================================================================\n",
+       "Dep. Variable:     total_claim_amount   R-squared:                       0.519\n",
+       "Model:                            OLS   Adj. R-squared:                  0.518\n",
+       "Method:                 Least Squares   F-statistic:                     1405.\n",
+       "Date:                Wed, 03 Apr 2024   Prob (F-statistic):               0.00\n",
+       "Time:                        16:58:20   Log-Likelihood:                -61425.\n",
+       "No. Observations:                9134   AIC:                         1.229e+05\n",
+       "Df Residuals:                    9126   BIC:                         1.229e+05\n",
+       "Df Model:                           7                                         \n",
+       "Covariance Type:            nonrobust                                         \n",
+       "=================================================================================================\n",
+       "                                    coef    std err          t      P>|t|      [0.025      0.975]\n",
+       "-------------------------------------------------------------------------------------------------\n",
+       "const                            72.3910      8.744      8.279      0.000      55.252      89.530\n",
+       "customer_lifetime_value          -0.0007      0.000     -2.014      0.044      -0.001   -1.81e-05\n",
+       "income                           -0.0033   6.95e-05    -47.370      0.000      -0.003      -0.003\n",
+       "monthly_premium_auto              5.3425      0.067     79.934      0.000       5.212       5.474\n",
+       "months_since_last_claim          -0.1457      0.210     -0.695      0.487      -0.557       0.265\n",
+       "months_since_policy_inception    -0.1023      0.076     -1.352      0.176      -0.251       0.046\n",
+       "number_of_open_complaints        -1.3716      2.319     -0.591      0.554      -5.918       3.174\n",
+       "number_of_policies                0.2486      0.883      0.281      0.778      -1.483       1.980\n",
+       "==============================================================================\n",
+       "Omnibus:                      994.270   Durbin-Watson:                   1.980\n",
+       "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             6389.170\n",
+       "Skew:                           0.316   Prob(JB):                         0.00\n",
+       "Kurtosis:                       7.048   Cond. No.                     2.02e+05\n",
+       "==============================================================================\n",
+       "\n",
+       "Notes:\n",
+       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
+       "[2] The condition number is large, 2.02e+05. This might indicate that there are\n",
+       "strong multicollinearity or other numerical problems.\n",
+       "\"\"\""
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# total claim amount have some of the strongest correlations\n",
+    "# let's see how it's imapcted by the other measurements\n",
+    "\n",
+    "from sklearn import linear_model\n",
+    "from sklearn.metrics import mean_squared_error, r2_score\n",
+    "\n",
+    "import statsmodels.api as sm\n",
+    "from statsmodels.formula.api import ols\n",
+    "\n",
+    "Y = df_numerical['total_claim_amount']\n",
+    "X = df_numerical.drop(['total_claim_amount'], axis=1)\n",
+    "\n",
+    "X = sm.add_constant(X)\n",
+    "model = sm.OLS(Y,X).fit()\n",
+    "\n",
+    "model.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "id": "927f1c54",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"simpletable\">\n",
+       "<caption>OLS Regression Results</caption>\n",
+       "<tr>\n",
+       "  <th>Dep. Variable:</th>    <td>total_claim_amount</td> <th>  R-squared:         </th> <td>   0.399</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Model:</th>                    <td>OLS</td>        <th>  Adj. R-squared:    </th> <td>   0.399</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Method:</th>              <td>Least Squares</td>   <th>  F-statistic:       </th> <td>   6074.</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Date:</th>              <td>Wed, 03 Apr 2024</td>  <th>  Prob (F-statistic):</th>  <td>  0.00</td>  \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Time:</th>                  <td>17:03:04</td>      <th>  Log-Likelihood:    </th> <td> -62436.</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>No. Observations:</th>       <td>  9134</td>       <th>  AIC:               </th> <td>1.249e+05</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Df Residuals:</th>           <td>  9132</td>       <th>  BIC:               </th> <td>1.249e+05</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Df Model:</th>               <td>     1</td>       <th>                     </th>     <td> </td>    \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Covariance Type:</th>       <td>nonrobust</td>     <th>                     </th>     <td> </td>    \n",
+       "</tr>\n",
+       "</table>\n",
+       "<table class=\"simpletable\">\n",
+       "<tr>\n",
+       "            <td></td>              <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>const</th>                <td>  -63.3293</td> <td>    6.803</td> <td>   -9.309</td> <td> 0.000</td> <td>  -76.665</td> <td>  -49.993</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>monthly_premium_auto</th> <td>    5.3360</td> <td>    0.068</td> <td>   77.935</td> <td> 0.000</td> <td>    5.202</td> <td>    5.470</td>\n",
+       "</tr>\n",
+       "</table>\n",
+       "<table class=\"simpletable\">\n",
+       "<tr>\n",
+       "  <th>Omnibus:</th>       <td>918.547</td> <th>  Durbin-Watson:     </th> <td>   1.984</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Prob(Omnibus):</th> <td> 0.000</td>  <th>  Jarque-Bera (JB):  </th> <td>4798.125</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Skew:</th>          <td> 0.348</td>  <th>  Prob(JB):          </th> <td>    0.00</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Kurtosis:</th>      <td> 6.482</td>  <th>  Cond. No.          </th> <td>    287.</td>\n",
+       "</tr>\n",
+       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
+      ],
+      "text/latex": [
+       "\\begin{center}\n",
+       "\\begin{tabular}{lclc}\n",
+       "\\toprule\n",
+       "\\textbf{Dep. Variable:}         & total\\_claim\\_amount & \\textbf{  R-squared:         } &     0.399   \\\\\n",
+       "\\textbf{Model:}                 &         OLS          & \\textbf{  Adj. R-squared:    } &     0.399   \\\\\n",
+       "\\textbf{Method:}                &    Least Squares     & \\textbf{  F-statistic:       } &     6074.   \\\\\n",
+       "\\textbf{Date:}                  &   Wed, 03 Apr 2024   & \\textbf{  Prob (F-statistic):} &     0.00    \\\\\n",
+       "\\textbf{Time:}                  &       17:03:04       & \\textbf{  Log-Likelihood:    } &   -62436.   \\\\\n",
+       "\\textbf{No. Observations:}      &          9134        & \\textbf{  AIC:               } & 1.249e+05   \\\\\n",
+       "\\textbf{Df Residuals:}          &          9132        & \\textbf{  BIC:               } & 1.249e+05   \\\\\n",
+       "\\textbf{Df Model:}              &             1        & \\textbf{                     } &             \\\\\n",
+       "\\textbf{Covariance Type:}       &      nonrobust       & \\textbf{                     } &             \\\\\n",
+       "\\bottomrule\n",
+       "\\end{tabular}\n",
+       "\\begin{tabular}{lcccccc}\n",
+       "                                & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
+       "\\midrule\n",
+       "\\textbf{const}                  &     -63.3293  &        6.803     &    -9.309  &         0.000        &      -76.665    &      -49.993     \\\\\n",
+       "\\textbf{monthly\\_premium\\_auto} &       5.3360  &        0.068     &    77.935  &         0.000        &        5.202    &        5.470     \\\\\n",
+       "\\bottomrule\n",
+       "\\end{tabular}\n",
+       "\\begin{tabular}{lclc}\n",
+       "\\textbf{Omnibus:}       & 918.547 & \\textbf{  Durbin-Watson:     } &    1.984  \\\\\n",
+       "\\textbf{Prob(Omnibus):} &   0.000 & \\textbf{  Jarque-Bera (JB):  } & 4798.125  \\\\\n",
+       "\\textbf{Skew:}          &   0.348 & \\textbf{  Prob(JB):          } &     0.00  \\\\\n",
+       "\\textbf{Kurtosis:}      &   6.482 & \\textbf{  Cond. No.          } &     287.  \\\\\n",
+       "\\bottomrule\n",
+       "\\end{tabular}\n",
+       "%\\caption{OLS Regression Results}\n",
+       "\\end{center}\n",
+       "\n",
+       "Notes: \\newline\n",
+       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
+      ],
+      "text/plain": [
+       "<class 'statsmodels.iolib.summary.Summary'>\n",
+       "\"\"\"\n",
+       "                            OLS Regression Results                            \n",
+       "==============================================================================\n",
+       "Dep. Variable:     total_claim_amount   R-squared:                       0.399\n",
+       "Model:                            OLS   Adj. R-squared:                  0.399\n",
+       "Method:                 Least Squares   F-statistic:                     6074.\n",
+       "Date:                Wed, 03 Apr 2024   Prob (F-statistic):               0.00\n",
+       "Time:                        17:03:04   Log-Likelihood:                -62436.\n",
+       "No. Observations:                9134   AIC:                         1.249e+05\n",
+       "Df Residuals:                    9132   BIC:                         1.249e+05\n",
+       "Df Model:                           1                                         \n",
+       "Covariance Type:            nonrobust                                         \n",
+       "========================================================================================\n",
+       "                           coef    std err          t      P>|t|      [0.025      0.975]\n",
+       "----------------------------------------------------------------------------------------\n",
+       "const                  -63.3293      6.803     -9.309      0.000     -76.665     -49.993\n",
+       "monthly_premium_auto     5.3360      0.068     77.935      0.000       5.202       5.470\n",
+       "==============================================================================\n",
+       "Omnibus:                      918.547   Durbin-Watson:                   1.984\n",
+       "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             4798.125\n",
+       "Skew:                           0.348   Prob(JB):                         0.00\n",
+       "Kurtosis:                       6.482   Cond. No.                         287.\n",
+       "==============================================================================\n",
+       "\n",
+       "Notes:\n",
+       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
+       "\"\"\""
+      ]
+     },
+     "execution_count": 37,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# the highest positive correlation was between total claim amount and monthly premium auto where the first seems to be dependant on the second\n",
+    "# coef: 5.3425, if we increase monthly premium auto by one unit, total claim amount will increase by 5.3425\n",
+    "Y = df_numerical['total_claim_amount']\n",
+    "X = df_numerical['monthly_premium_auto']\n",
+    "X = sm.add_constant(X)\n",
+    "model = sm.OLS(Y,X).fit()\n",
+    "\n",
+    "model.summary()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": 5
+}
diff --git a/[lab-customer-analysis-round-5] Fabiana.ipynb b/[lab-customer-analysis-round-5] Fabiana.ipynb
new file mode 100644
index 0000000..29150a4
--- /dev/null
+++ b/[lab-customer-analysis-round-5] Fabiana.ipynb	
@@ -0,0 +1,2637 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "58a989e2",
+   "metadata": {},
+   "source": [
+    "# Statistics Foundations"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5c269798",
+   "metadata": {},
+   "source": [
+    "# Show DataFrame info"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "00482570",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "\n",
+    "import warnings\n",
+    "warnings.filterwarnings ('ignore')\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "%matplotlib inline\n",
+    "\n",
+    "import seaborn as sns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "25c3936b",
+   "metadata": {
+    "scrolled": true
+   },
+   "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>Customer</th>\n",
+       "      <th>State</th>\n",
+       "      <th>Customer Lifetime Value</th>\n",
+       "      <th>Response</th>\n",
+       "      <th>Coverage</th>\n",
+       "      <th>Education</th>\n",
+       "      <th>Effective To Date</th>\n",
+       "      <th>EmploymentStatus</th>\n",
+       "      <th>Gender</th>\n",
+       "      <th>Income</th>\n",
+       "      <th>...</th>\n",
+       "      <th>Months Since Policy Inception</th>\n",
+       "      <th>Number of Open Complaints</th>\n",
+       "      <th>Number of Policies</th>\n",
+       "      <th>Policy Type</th>\n",
+       "      <th>Policy</th>\n",
+       "      <th>Renew Offer Type</th>\n",
+       "      <th>Sales Channel</th>\n",
+       "      <th>Total Claim Amount</th>\n",
+       "      <th>Vehicle Class</th>\n",
+       "      <th>Vehicle Size</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>BU79786</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>2763.519279</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2/24/11</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>56274</td>\n",
+       "      <td>...</td>\n",
+       "      <td>5</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>384.811147</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>QZ44356</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>6979.535903</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>1/31/11</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>42</td>\n",
+       "      <td>0</td>\n",
+       "      <td>8</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L3</td>\n",
+       "      <td>Offer3</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>1131.464935</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>AI49188</td>\n",
+       "      <td>Nevada</td>\n",
+       "      <td>12887.431650</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2/19/11</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>48767</td>\n",
+       "      <td>...</td>\n",
+       "      <td>38</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L3</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>566.472247</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>WW63253</td>\n",
+       "      <td>California</td>\n",
+       "      <td>7645.861827</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>1/20/11</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>65</td>\n",
+       "      <td>0</td>\n",
+       "      <td>7</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L2</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Call Center</td>\n",
+       "      <td>529.881344</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>HB64268</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>2813.692575</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2/3/11</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>43836</td>\n",
+       "      <td>...</td>\n",
+       "      <td>44</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L1</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>138.130879</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</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>9129</th>\n",
+       "      <td>LA72316</td>\n",
+       "      <td>California</td>\n",
+       "      <td>23405.987980</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2/10/11</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>71941</td>\n",
+       "      <td>...</td>\n",
+       "      <td>89</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L1</td>\n",
+       "      <td>Offer2</td>\n",
+       "      <td>Web</td>\n",
+       "      <td>198.234764</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9130</th>\n",
+       "      <td>PK87824</td>\n",
+       "      <td>California</td>\n",
+       "      <td>3096.511217</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2/12/11</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>21604</td>\n",
+       "      <td>...</td>\n",
+       "      <td>28</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>379.200000</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9131</th>\n",
+       "      <td>TD14365</td>\n",
+       "      <td>California</td>\n",
+       "      <td>8163.890428</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2/6/11</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>37</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L2</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>790.784983</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9132</th>\n",
+       "      <td>UP19263</td>\n",
+       "      <td>California</td>\n",
+       "      <td>7524.442436</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2/3/11</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>21941</td>\n",
+       "      <td>...</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L2</td>\n",
+       "      <td>Offer3</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>691.200000</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Large</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9133</th>\n",
+       "      <td>Y167826</td>\n",
+       "      <td>California</td>\n",
+       "      <td>2611.836866</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2/14/11</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>90</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer4</td>\n",
+       "      <td>Call Center</td>\n",
+       "      <td>369.600000</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>9134 rows × 24 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     Customer       State  Customer Lifetime Value Response  Coverage  \\\n",
+       "0     BU79786  Washington              2763.519279       No     Basic   \n",
+       "1     QZ44356     Arizona              6979.535903       No  Extended   \n",
+       "2     AI49188      Nevada             12887.431650       No   Premium   \n",
+       "3     WW63253  California              7645.861827       No     Basic   \n",
+       "4     HB64268  Washington              2813.692575       No     Basic   \n",
+       "...       ...         ...                      ...      ...       ...   \n",
+       "9129  LA72316  California             23405.987980       No     Basic   \n",
+       "9130  PK87824  California              3096.511217      Yes  Extended   \n",
+       "9131  TD14365  California              8163.890428       No  Extended   \n",
+       "9132  UP19263  California              7524.442436       No  Extended   \n",
+       "9133  Y167826  California              2611.836866       No  Extended   \n",
+       "\n",
+       "     Education Effective To Date EmploymentStatus Gender  Income  ...  \\\n",
+       "0     Bachelor           2/24/11         Employed      F   56274  ...   \n",
+       "1     Bachelor           1/31/11       Unemployed      F       0  ...   \n",
+       "2     Bachelor           2/19/11         Employed      F   48767  ...   \n",
+       "3     Bachelor           1/20/11       Unemployed      M       0  ...   \n",
+       "4     Bachelor            2/3/11         Employed      M   43836  ...   \n",
+       "...        ...               ...              ...    ...     ...  ...   \n",
+       "9129  Bachelor           2/10/11         Employed      M   71941  ...   \n",
+       "9130   College           2/12/11         Employed      F   21604  ...   \n",
+       "9131  Bachelor            2/6/11       Unemployed      M       0  ...   \n",
+       "9132   College            2/3/11         Employed      M   21941  ...   \n",
+       "9133   College           2/14/11       Unemployed      M       0  ...   \n",
+       "\n",
+       "     Months Since Policy Inception Number of Open Complaints  \\\n",
+       "0                                5                         0   \n",
+       "1                               42                         0   \n",
+       "2                               38                         0   \n",
+       "3                               65                         0   \n",
+       "4                               44                         0   \n",
+       "...                            ...                       ...   \n",
+       "9129                            89                         0   \n",
+       "9130                            28                         0   \n",
+       "9131                            37                         3   \n",
+       "9132                             3                         0   \n",
+       "9133                            90                         0   \n",
+       "\n",
+       "      Number of Policies     Policy Type        Policy  Renew Offer Type  \\\n",
+       "0                      1  Corporate Auto  Corporate L3            Offer1   \n",
+       "1                      8   Personal Auto   Personal L3            Offer3   \n",
+       "2                      2   Personal Auto   Personal L3            Offer1   \n",
+       "3                      7  Corporate Auto  Corporate L2            Offer1   \n",
+       "4                      1   Personal Auto   Personal L1            Offer1   \n",
+       "...                  ...             ...           ...               ...   \n",
+       "9129                   2   Personal Auto   Personal L1            Offer2   \n",
+       "9130                   1  Corporate Auto  Corporate L3            Offer1   \n",
+       "9131                   2  Corporate Auto  Corporate L2            Offer1   \n",
+       "9132                   3   Personal Auto   Personal L2            Offer3   \n",
+       "9133                   1  Corporate Auto  Corporate L3            Offer4   \n",
+       "\n",
+       "      Sales Channel Total Claim Amount  Vehicle Class Vehicle Size  \n",
+       "0             Agent         384.811147   Two-Door Car      Medsize  \n",
+       "1             Agent        1131.464935  Four-Door Car      Medsize  \n",
+       "2             Agent         566.472247   Two-Door Car      Medsize  \n",
+       "3       Call Center         529.881344            SUV      Medsize  \n",
+       "4             Agent         138.130879  Four-Door Car      Medsize  \n",
+       "...             ...                ...            ...          ...  \n",
+       "9129            Web         198.234764  Four-Door Car      Medsize  \n",
+       "9130         Branch         379.200000  Four-Door Car      Medsize  \n",
+       "9131         Branch         790.784983  Four-Door Car      Medsize  \n",
+       "9132         Branch         691.200000  Four-Door Car        Large  \n",
+       "9133    Call Center         369.600000   Two-Door Car      Medsize  \n",
+       "\n",
+       "[9134 rows x 24 columns]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Marketing Customer Analysis\n",
+    "df = pd.read_csv (r\"C:\\Users\\fabi_\\OneDrive\\Estudos e Cursos\\Data analytics\\Ironhack.Labs\\lab-customer-analysis-round-3\\files_for_lab\\csv_files\\marketing_customer_analysis.csv\")\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "fd945b48",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['customer', 'state', 'customer_lifetime_value', 'response', 'coverage',\n",
+       "       'education', 'effective_to_date', 'employmentstatus', 'gender',\n",
+       "       'income', 'location_code', 'marital_status', 'monthly_premium_auto',\n",
+       "       'months_since_last_claim', 'months_since_policy_inception',\n",
+       "       'number_of_open_complaints', 'number_of_policies', 'policy_type',\n",
+       "       'policy', 'renew_offer_type', 'sales_channel', 'total_claim_amount',\n",
+       "       'vehicle_class', 'vehicle_size'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.columns = df.columns.str.lower().str.replace(' ', '_')\n",
+    "df.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "2798c857",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                          object\n",
+       "state                             object\n",
+       "customer_lifetime_value          float64\n",
+       "response                          object\n",
+       "coverage                          object\n",
+       "education                         object\n",
+       "effective_to_date                 object\n",
+       "employmentstatus                  object\n",
+       "gender                            object\n",
+       "income                             int64\n",
+       "location_code                     object\n",
+       "marital_status                    object\n",
+       "monthly_premium_auto               int64\n",
+       "months_since_last_claim            int64\n",
+       "months_since_policy_inception      int64\n",
+       "number_of_open_complaints          int64\n",
+       "number_of_policies                 int64\n",
+       "policy_type                       object\n",
+       "policy                            object\n",
+       "renew_offer_type                  object\n",
+       "sales_channel                     object\n",
+       "total_claim_amount               float64\n",
+       "vehicle_class                     object\n",
+       "vehicle_size                      object\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "5d281ccc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0      2011-02-24\n",
+       "1      2011-01-31\n",
+       "2      2011-02-19\n",
+       "3      2011-01-20\n",
+       "4      2011-02-03\n",
+       "          ...    \n",
+       "9129   2011-02-10\n",
+       "9130   2011-02-12\n",
+       "9131   2011-02-06\n",
+       "9132   2011-02-03\n",
+       "9133   2011-02-14\n",
+       "Name: effective_to_date, Length: 9134, dtype: datetime64[ns]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['effective_to_date'] = pd.to_datetime(df['effective_to_date'])\n",
+    "df['effective_to_date']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "5dfbd78d",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                         9134\n",
+       "state                               5\n",
+       "customer_lifetime_value          8041\n",
+       "response                            2\n",
+       "coverage                            3\n",
+       "education                           5\n",
+       "effective_to_date                  59\n",
+       "employmentstatus                    5\n",
+       "gender                              2\n",
+       "income                           5694\n",
+       "location_code                       3\n",
+       "marital_status                      3\n",
+       "monthly_premium_auto              202\n",
+       "months_since_last_claim            36\n",
+       "months_since_policy_inception     100\n",
+       "number_of_open_complaints           6\n",
+       "number_of_policies                  9\n",
+       "policy_type                         3\n",
+       "policy                              9\n",
+       "renew_offer_type                    4\n",
+       "sales_channel                       4\n",
+       "total_claim_amount               5106\n",
+       "vehicle_class                       6\n",
+       "vehicle_size                        3\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.nunique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "d8437b8e",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "customer                         0\n",
+       "state                            0\n",
+       "customer_lifetime_value          0\n",
+       "response                         0\n",
+       "coverage                         0\n",
+       "education                        0\n",
+       "effective_to_date                0\n",
+       "employmentstatus                 0\n",
+       "gender                           0\n",
+       "income                           0\n",
+       "location_code                    0\n",
+       "marital_status                   0\n",
+       "monthly_premium_auto             0\n",
+       "months_since_last_claim          0\n",
+       "months_since_policy_inception    0\n",
+       "number_of_open_complaints        0\n",
+       "number_of_policies               0\n",
+       "policy_type                      0\n",
+       "policy                           0\n",
+       "renew_offer_type                 0\n",
+       "sales_channel                    0\n",
+       "total_claim_amount               0\n",
+       "vehicle_class                    0\n",
+       "vehicle_size                     0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fc1cbb30",
+   "metadata": {},
+   "source": [
+    "# Numerical and categorical columns"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "185cc43c",
+   "metadata": {},
+   "source": [
+    "Check the data types of the columns. Get the numeric data into dataframe called numerical and categorical columns in a dataframe called categoricals. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "e671059f",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['customer_lifetime_value',\n",
+       " 'income',\n",
+       " 'monthly_premium_auto',\n",
+       " 'months_since_last_claim',\n",
+       " 'months_since_policy_inception',\n",
+       " 'number_of_open_complaints',\n",
+       " 'number_of_policies',\n",
+       " 'total_claim_amount']"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "numerical_columns = df.select_dtypes(include=['number']).columns.tolist()\n",
+    "numerical_columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "21d21dc2",
+   "metadata": {
+    "scrolled": true
+   },
+   "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>customer_lifetime_value</th>\n",
+       "      <th>income</th>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <th>months_since_last_claim</th>\n",
+       "      <th>months_since_policy_inception</th>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <th>number_of_policies</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2763.519279</td>\n",
+       "      <td>56274</td>\n",
+       "      <td>69</td>\n",
+       "      <td>32</td>\n",
+       "      <td>5</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>384.811147</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>6979.535903</td>\n",
+       "      <td>0</td>\n",
+       "      <td>94</td>\n",
+       "      <td>13</td>\n",
+       "      <td>42</td>\n",
+       "      <td>0</td>\n",
+       "      <td>8</td>\n",
+       "      <td>1131.464935</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>12887.431650</td>\n",
+       "      <td>48767</td>\n",
+       "      <td>108</td>\n",
+       "      <td>18</td>\n",
+       "      <td>38</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>566.472247</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>7645.861827</td>\n",
+       "      <td>0</td>\n",
+       "      <td>106</td>\n",
+       "      <td>18</td>\n",
+       "      <td>65</td>\n",
+       "      <td>0</td>\n",
+       "      <td>7</td>\n",
+       "      <td>529.881344</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2813.692575</td>\n",
+       "      <td>43836</td>\n",
+       "      <td>73</td>\n",
+       "      <td>12</td>\n",
+       "      <td>44</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>138.130879</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9129</th>\n",
+       "      <td>23405.987980</td>\n",
+       "      <td>71941</td>\n",
+       "      <td>73</td>\n",
+       "      <td>18</td>\n",
+       "      <td>89</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>198.234764</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9130</th>\n",
+       "      <td>3096.511217</td>\n",
+       "      <td>21604</td>\n",
+       "      <td>79</td>\n",
+       "      <td>14</td>\n",
+       "      <td>28</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>379.200000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9131</th>\n",
+       "      <td>8163.890428</td>\n",
+       "      <td>0</td>\n",
+       "      <td>85</td>\n",
+       "      <td>9</td>\n",
+       "      <td>37</td>\n",
+       "      <td>3</td>\n",
+       "      <td>2</td>\n",
+       "      <td>790.784983</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9132</th>\n",
+       "      <td>7524.442436</td>\n",
+       "      <td>21941</td>\n",
+       "      <td>96</td>\n",
+       "      <td>34</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>691.200000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9133</th>\n",
+       "      <td>2611.836866</td>\n",
+       "      <td>0</td>\n",
+       "      <td>77</td>\n",
+       "      <td>3</td>\n",
+       "      <td>90</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>369.600000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>9134 rows × 8 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      customer_lifetime_value  income  monthly_premium_auto  \\\n",
+       "0                 2763.519279   56274                    69   \n",
+       "1                 6979.535903       0                    94   \n",
+       "2                12887.431650   48767                   108   \n",
+       "3                 7645.861827       0                   106   \n",
+       "4                 2813.692575   43836                    73   \n",
+       "...                       ...     ...                   ...   \n",
+       "9129             23405.987980   71941                    73   \n",
+       "9130              3096.511217   21604                    79   \n",
+       "9131              8163.890428       0                    85   \n",
+       "9132              7524.442436   21941                    96   \n",
+       "9133              2611.836866       0                    77   \n",
+       "\n",
+       "      months_since_last_claim  months_since_policy_inception  \\\n",
+       "0                          32                              5   \n",
+       "1                          13                             42   \n",
+       "2                          18                             38   \n",
+       "3                          18                             65   \n",
+       "4                          12                             44   \n",
+       "...                       ...                            ...   \n",
+       "9129                       18                             89   \n",
+       "9130                       14                             28   \n",
+       "9131                        9                             37   \n",
+       "9132                       34                              3   \n",
+       "9133                        3                             90   \n",
+       "\n",
+       "      number_of_open_complaints  number_of_policies  total_claim_amount  \n",
+       "0                             0                   1          384.811147  \n",
+       "1                             0                   8         1131.464935  \n",
+       "2                             0                   2          566.472247  \n",
+       "3                             0                   7          529.881344  \n",
+       "4                             0                   1          138.130879  \n",
+       "...                         ...                 ...                 ...  \n",
+       "9129                          0                   2          198.234764  \n",
+       "9130                          0                   1          379.200000  \n",
+       "9131                          3                   2          790.784983  \n",
+       "9132                          0                   3          691.200000  \n",
+       "9133                          0                   1          369.600000  \n",
+       "\n",
+       "[9134 rows x 8 columns]"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_numerical = df[['customer_lifetime_value','income','monthly_premium_auto','months_since_last_claim','months_since_policy_inception','number_of_open_complaints','number_of_policies','total_claim_amount']]\n",
+    "df_numerical"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "ed419c65",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['customer',\n",
+       " 'state',\n",
+       " 'response',\n",
+       " 'coverage',\n",
+       " 'education',\n",
+       " 'effective_to_date',\n",
+       " 'employmentstatus',\n",
+       " 'gender',\n",
+       " 'location_code',\n",
+       " 'marital_status',\n",
+       " 'policy_type',\n",
+       " 'policy',\n",
+       " 'renew_offer_type',\n",
+       " 'sales_channel',\n",
+       " 'vehicle_class',\n",
+       " 'vehicle_size']"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "categorical_columns = df.select_dtypes(exclude=['number']).columns.tolist()\n",
+    "categorical_columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "44ad19bf",
+   "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>customer</th>\n",
+       "      <th>state</th>\n",
+       "      <th>response</th>\n",
+       "      <th>coverage</th>\n",
+       "      <th>education</th>\n",
+       "      <th>effective_to_date</th>\n",
+       "      <th>employmentstatus</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>location_code</th>\n",
+       "      <th>marital_status</th>\n",
+       "      <th>policy_type</th>\n",
+       "      <th>policy</th>\n",
+       "      <th>renew_offer_type</th>\n",
+       "      <th>sales_channel</th>\n",
+       "      <th>vehicle_class</th>\n",
+       "      <th>vehicle_size</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>BU79786</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-02-24</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>QZ44356</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-01-31</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Single</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L3</td>\n",
+       "      <td>Offer3</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>AI49188</td>\n",
+       "      <td>Nevada</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-02-19</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L3</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>WW63253</td>\n",
+       "      <td>California</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-01-20</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L2</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Call Center</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>HB64268</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-02-03</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Rural</td>\n",
+       "      <td>Single</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L1</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9129</th>\n",
+       "      <td>LA72316</td>\n",
+       "      <td>California</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-02-10</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Urban</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L1</td>\n",
+       "      <td>Offer2</td>\n",
+       "      <td>Web</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9130</th>\n",
+       "      <td>PK87824</td>\n",
+       "      <td>California</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2011-02-12</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Divorced</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9131</th>\n",
+       "      <td>TD14365</td>\n",
+       "      <td>California</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-02-06</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Single</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L2</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9132</th>\n",
+       "      <td>UP19263</td>\n",
+       "      <td>California</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2011-02-03</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Married</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L2</td>\n",
+       "      <td>Offer3</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Large</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9133</th>\n",
+       "      <td>Y167826</td>\n",
+       "      <td>California</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2011-02-14</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>Suburban</td>\n",
+       "      <td>Single</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer4</td>\n",
+       "      <td>Call Center</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>9134 rows × 16 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     customer       state response  coverage education effective_to_date  \\\n",
+       "0     BU79786  Washington       No     Basic  Bachelor        2011-02-24   \n",
+       "1     QZ44356     Arizona       No  Extended  Bachelor        2011-01-31   \n",
+       "2     AI49188      Nevada       No   Premium  Bachelor        2011-02-19   \n",
+       "3     WW63253  California       No     Basic  Bachelor        2011-01-20   \n",
+       "4     HB64268  Washington       No     Basic  Bachelor        2011-02-03   \n",
+       "...       ...         ...      ...       ...       ...               ...   \n",
+       "9129  LA72316  California       No     Basic  Bachelor        2011-02-10   \n",
+       "9130  PK87824  California      Yes  Extended   College        2011-02-12   \n",
+       "9131  TD14365  California       No  Extended  Bachelor        2011-02-06   \n",
+       "9132  UP19263  California       No  Extended   College        2011-02-03   \n",
+       "9133  Y167826  California       No  Extended   College        2011-02-14   \n",
+       "\n",
+       "     employmentstatus gender location_code marital_status     policy_type  \\\n",
+       "0            Employed      F      Suburban        Married  Corporate Auto   \n",
+       "1          Unemployed      F      Suburban         Single   Personal Auto   \n",
+       "2            Employed      F      Suburban        Married   Personal Auto   \n",
+       "3          Unemployed      M      Suburban        Married  Corporate Auto   \n",
+       "4            Employed      M         Rural         Single   Personal Auto   \n",
+       "...               ...    ...           ...            ...             ...   \n",
+       "9129         Employed      M         Urban        Married   Personal Auto   \n",
+       "9130         Employed      F      Suburban       Divorced  Corporate Auto   \n",
+       "9131       Unemployed      M      Suburban         Single  Corporate Auto   \n",
+       "9132         Employed      M      Suburban        Married   Personal Auto   \n",
+       "9133       Unemployed      M      Suburban         Single  Corporate Auto   \n",
+       "\n",
+       "            policy renew_offer_type sales_channel  vehicle_class vehicle_size  \n",
+       "0     Corporate L3           Offer1         Agent   Two-Door Car      Medsize  \n",
+       "1      Personal L3           Offer3         Agent  Four-Door Car      Medsize  \n",
+       "2      Personal L3           Offer1         Agent   Two-Door Car      Medsize  \n",
+       "3     Corporate L2           Offer1   Call Center            SUV      Medsize  \n",
+       "4      Personal L1           Offer1         Agent  Four-Door Car      Medsize  \n",
+       "...            ...              ...           ...            ...          ...  \n",
+       "9129   Personal L1           Offer2           Web  Four-Door Car      Medsize  \n",
+       "9130  Corporate L3           Offer1        Branch  Four-Door Car      Medsize  \n",
+       "9131  Corporate L2           Offer1        Branch  Four-Door Car      Medsize  \n",
+       "9132   Personal L2           Offer3        Branch  Four-Door Car        Large  \n",
+       "9133  Corporate L3           Offer4   Call Center   Two-Door Car      Medsize  \n",
+       "\n",
+       "[9134 rows x 16 columns]"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_categorical = df [['customer','state','response','coverage','education','effective_to_date','employmentstatus','gender','location_code','marital_status','policy_type','policy','renew_offer_type','sales_channel','vehicle_class','vehicle_size']]\n",
+    "df_categorical"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0fa705d1",
+   "metadata": {},
+   "source": [
+    "# Visualizing distributions of the numerical data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "856334f0",
+   "metadata": {},
+   "source": [
+    "Use Seaborn or Matplot library to construct distribution plots for the numerical variables.\n",
+    "Do the distributions for different numerical variables and check which look like a normal distribution."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "4a3f5c52",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count     9134.000000\n",
+      "mean      8004.940475\n",
+      "std       6870.967608\n",
+      "min       1898.007675\n",
+      "25%       3994.251794\n",
+      "50%       5780.182197\n",
+      "75%       8962.167041\n",
+      "max      83325.381190\n",
+      "Name: customer_lifetime_value, dtype: float64\n",
+      "number of unique values:  8041\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['customer_lifetime_value'].describe())\n",
+    "print ('number of unique values: ', df_numerical['customer_lifetime_value'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "3987c080",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='customer_lifetime_value', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='customer_lifetime_value', kde=True)\n",
+    "# the plot is clearly right-skewed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "922ba108",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count     9134.000000\n",
+      "mean     37657.380009\n",
+      "std      30379.904734\n",
+      "min          0.000000\n",
+      "25%          0.000000\n",
+      "50%      33889.500000\n",
+      "75%      62320.000000\n",
+      "max      99981.000000\n",
+      "Name: income, dtype: float64\n",
+      "number of unique values:  5694\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['income'].describe())\n",
+    "print ('number of unique values: ', df_numerical['income'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "c908aa92",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='income', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='income',kde=True)\n",
+    "# there are many values at 0 so the distribution looks bimodal and somewhat right-skewed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "1c270f60",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count    9134.000000\n",
+      "mean       93.219291\n",
+      "std        34.407967\n",
+      "min        61.000000\n",
+      "25%        68.000000\n",
+      "50%        83.000000\n",
+      "75%       109.000000\n",
+      "max       298.000000\n",
+      "Name: monthly_premium_auto, dtype: float64\n",
+      "number of unique values:  202\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['monthly_premium_auto'].describe())\n",
+    "print ('number of unique values: ', df_numerical['monthly_premium_auto'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "8c6a4557",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='monthly_premium_auto', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='monthly_premium_auto',kde=True)\n",
+    "# there are 3 more noticeble peaks, so it loos like a multimodal distribution and it's right-skewed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "c51f8248",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count    9134.000000\n",
+      "mean       15.097000\n",
+      "std        10.073257\n",
+      "min         0.000000\n",
+      "25%         6.000000\n",
+      "50%        14.000000\n",
+      "75%        23.000000\n",
+      "max        35.000000\n",
+      "Name: months_since_last_claim, dtype: float64\n",
+      "number of unique values:  36\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['months_since_last_claim'].describe())\n",
+    "print ('number of unique values: ',df_numerical['months_since_last_claim'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "af65819b",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='months_since_last_claim', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='months_since_last_claim',bins= 36, kde=True)\n",
+    "# bins are irregular, but we can see a peak around 4 and then a decrease from left to right"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "a4826b7e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count    9134.000000\n",
+      "mean       48.064594\n",
+      "std        27.905991\n",
+      "min         0.000000\n",
+      "25%        24.000000\n",
+      "50%        48.000000\n",
+      "75%        71.000000\n",
+      "max        99.000000\n",
+      "Name: months_since_policy_inception, dtype: float64\n",
+      "number of unique values:  100\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['months_since_policy_inception'].describe())\n",
+    "print ('number of unique values: ',df_numerical['months_since_policy_inception'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "c5b92713",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='months_since_policy_inception', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='months_since_policy_inception', kde=True)\n",
+    "#bins are irregular and there are a couple of peaks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "19562ccd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count    9134.000000\n",
+      "mean        0.384388\n",
+      "std         0.910384\n",
+      "min         0.000000\n",
+      "25%         0.000000\n",
+      "50%         0.000000\n",
+      "75%         0.000000\n",
+      "max         5.000000\n",
+      "Name: number_of_open_complaints, dtype: float64\n",
+      "number of unique values:  6\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['number_of_open_complaints'].describe())\n",
+    "print ('number of unique values: ',df_numerical['number_of_open_complaints'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "6f3f38ac",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='number_of_open_complaints', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='number_of_open_complaints', bins=6, kde=True)\n",
+    "# plot is right skewed, most values are at zero"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "1e58676f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count    9134.000000\n",
+      "mean        2.966170\n",
+      "std         2.390182\n",
+      "min         1.000000\n",
+      "25%         1.000000\n",
+      "50%         2.000000\n",
+      "75%         4.000000\n",
+      "max         9.000000\n",
+      "Name: number_of_policies, dtype: float64\n",
+      "number of unique values:  9\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['number_of_policies'].describe())\n",
+    "print ('number of unique values: ',df_numerical['number_of_policies'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "5fd5179b",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='number_of_policies', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='number_of_policies', bins=9, kde=True)\n",
+    "# plot is right skewed, most values are at 1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "75600e89",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "count    9134.000000\n",
+      "mean      434.088794\n",
+      "std       290.500092\n",
+      "min         0.099007\n",
+      "25%       272.258244\n",
+      "50%       383.945434\n",
+      "75%       547.514839\n",
+      "max      2893.239678\n",
+      "Name: total_claim_amount, dtype: float64\n",
+      "number of unique values:  5106\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (df_numerical['total_claim_amount'].describe())\n",
+    "print ('number of unique values: ',df_numerical['total_claim_amount'].nunique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "4ff3df2d",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='total_claim_amount', ylabel='Count'>"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "sns.histplot(df_numerical, x='total_claim_amount', kde=True)\n",
+    "# plot is right-skewed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "8da7afd7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# None of the histograms displayed a normal distribution bell curve."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8412a487",
+   "metadata": {},
+   "source": [
+    "# Processing data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2d4b8cd0",
+   "metadata": {},
+   "source": [
+    "Normalize (numerical)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "632467dc",
+   "metadata": {
+    "scrolled": true
+   },
+   "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>customer_lifetime_value</th>\n",
+       "      <th>income</th>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <th>months_since_last_claim</th>\n",
+       "      <th>months_since_policy_inception</th>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <th>number_of_policies</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0.010629</td>\n",
+       "      <td>0.562847</td>\n",
+       "      <td>0.033755</td>\n",
+       "      <td>0.914286</td>\n",
+       "      <td>0.050505</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.132974</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0.062406</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.139241</td>\n",
+       "      <td>0.371429</td>\n",
+       "      <td>0.424242</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.875</td>\n",
+       "      <td>0.391051</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0.134960</td>\n",
+       "      <td>0.487763</td>\n",
+       "      <td>0.198312</td>\n",
+       "      <td>0.514286</td>\n",
+       "      <td>0.383838</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.125</td>\n",
+       "      <td>0.195764</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0.070589</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.189873</td>\n",
+       "      <td>0.514286</td>\n",
+       "      <td>0.656566</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.750</td>\n",
+       "      <td>0.183117</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0.011245</td>\n",
+       "      <td>0.438443</td>\n",
+       "      <td>0.050633</td>\n",
+       "      <td>0.342857</td>\n",
+       "      <td>0.444444</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.047710</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9129</th>\n",
+       "      <td>0.264137</td>\n",
+       "      <td>0.719547</td>\n",
+       "      <td>0.050633</td>\n",
+       "      <td>0.514286</td>\n",
+       "      <td>0.898990</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.125</td>\n",
+       "      <td>0.068485</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9130</th>\n",
+       "      <td>0.014719</td>\n",
+       "      <td>0.216081</td>\n",
+       "      <td>0.075949</td>\n",
+       "      <td>0.400000</td>\n",
+       "      <td>0.282828</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.131034</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9131</th>\n",
+       "      <td>0.076951</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.101266</td>\n",
+       "      <td>0.257143</td>\n",
+       "      <td>0.373737</td>\n",
+       "      <td>0.6</td>\n",
+       "      <td>0.125</td>\n",
+       "      <td>0.273297</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9132</th>\n",
+       "      <td>0.069098</td>\n",
+       "      <td>0.219452</td>\n",
+       "      <td>0.147679</td>\n",
+       "      <td>0.971429</td>\n",
+       "      <td>0.030303</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.250</td>\n",
+       "      <td>0.238876</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9133</th>\n",
+       "      <td>0.008766</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.067511</td>\n",
+       "      <td>0.085714</td>\n",
+       "      <td>0.909091</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.127716</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>9134 rows × 8 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      customer_lifetime_value    income  monthly_premium_auto  \\\n",
+       "0                    0.010629  0.562847              0.033755   \n",
+       "1                    0.062406  0.000000              0.139241   \n",
+       "2                    0.134960  0.487763              0.198312   \n",
+       "3                    0.070589  0.000000              0.189873   \n",
+       "4                    0.011245  0.438443              0.050633   \n",
+       "...                       ...       ...                   ...   \n",
+       "9129                 0.264137  0.719547              0.050633   \n",
+       "9130                 0.014719  0.216081              0.075949   \n",
+       "9131                 0.076951  0.000000              0.101266   \n",
+       "9132                 0.069098  0.219452              0.147679   \n",
+       "9133                 0.008766  0.000000              0.067511   \n",
+       "\n",
+       "      months_since_last_claim  months_since_policy_inception  \\\n",
+       "0                    0.914286                       0.050505   \n",
+       "1                    0.371429                       0.424242   \n",
+       "2                    0.514286                       0.383838   \n",
+       "3                    0.514286                       0.656566   \n",
+       "4                    0.342857                       0.444444   \n",
+       "...                       ...                            ...   \n",
+       "9129                 0.514286                       0.898990   \n",
+       "9130                 0.400000                       0.282828   \n",
+       "9131                 0.257143                       0.373737   \n",
+       "9132                 0.971429                       0.030303   \n",
+       "9133                 0.085714                       0.909091   \n",
+       "\n",
+       "      number_of_open_complaints  number_of_policies  total_claim_amount  \n",
+       "0                           0.0               0.000            0.132974  \n",
+       "1                           0.0               0.875            0.391051  \n",
+       "2                           0.0               0.125            0.195764  \n",
+       "3                           0.0               0.750            0.183117  \n",
+       "4                           0.0               0.000            0.047710  \n",
+       "...                         ...                 ...                 ...  \n",
+       "9129                        0.0               0.125            0.068485  \n",
+       "9130                        0.0               0.000            0.131034  \n",
+       "9131                        0.6               0.125            0.273297  \n",
+       "9132                        0.0               0.250            0.238876  \n",
+       "9133                        0.0               0.000            0.127716  \n",
+       "\n",
+       "[9134 rows x 8 columns]"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Normalization, in the context of data preprocessing, refers to the process of rescaling features to a range of [0, 1]. \n",
+    "#It's useful when the features have different ranges or units. Normalization ensures that all features are on a similar scale, preventing some features from dominating others.\n",
+    "\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "\n",
+    "scaler = MinMaxScaler()\n",
+    "normalized_data = scaler.fit_transform(df_numerical)\n",
+    "normalized_data = pd.DataFrame(normalized_data, columns=df_numerical.columns)\n",
+    "normalized_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "8a9c6497",
+   "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>customer_lifetime_value</th>\n",
+       "      <th>income</th>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <th>months_since_last_claim</th>\n",
+       "      <th>months_since_policy_inception</th>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <th>number_of_policies</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>-0.762878</td>\n",
+       "      <td>0.612827</td>\n",
+       "      <td>-0.703925</td>\n",
+       "      <td>1.678099</td>\n",
+       "      <td>-1.543287</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>-0.822648</td>\n",
+       "      <td>-0.169640</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>-0.149245</td>\n",
+       "      <td>-1.239617</td>\n",
+       "      <td>0.022691</td>\n",
+       "      <td>-0.208186</td>\n",
+       "      <td>-0.217334</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>2.106160</td>\n",
+       "      <td>2.400737</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0.710636</td>\n",
+       "      <td>0.365710</td>\n",
+       "      <td>0.429596</td>\n",
+       "      <td>0.288205</td>\n",
+       "      <td>-0.360680</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>-0.404247</td>\n",
+       "      <td>0.455734</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>-0.052263</td>\n",
+       "      <td>-1.239617</td>\n",
+       "      <td>0.371467</td>\n",
+       "      <td>0.288205</td>\n",
+       "      <td>0.606907</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>1.687759</td>\n",
+       "      <td>0.329769</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>-0.755575</td>\n",
+       "      <td>0.203390</td>\n",
+       "      <td>-0.587666</td>\n",
+       "      <td>-0.307465</td>\n",
+       "      <td>-0.145661</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>-0.822648</td>\n",
+       "      <td>-1.018843</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9129</th>\n",
+       "      <td>2.241590</td>\n",
+       "      <td>1.128558</td>\n",
+       "      <td>-0.587666</td>\n",
+       "      <td>0.288205</td>\n",
+       "      <td>1.466984</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>-0.404247</td>\n",
+       "      <td>-0.811934</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9130</th>\n",
+       "      <td>-0.714411</td>\n",
+       "      <td>-0.528450</td>\n",
+       "      <td>-0.413278</td>\n",
+       "      <td>-0.108908</td>\n",
+       "      <td>-0.719046</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>-0.822648</td>\n",
+       "      <td>-0.188956</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9131</th>\n",
+       "      <td>0.023135</td>\n",
+       "      <td>-1.239617</td>\n",
+       "      <td>-0.238891</td>\n",
+       "      <td>-0.605299</td>\n",
+       "      <td>-0.396517</td>\n",
+       "      <td>2.873245</td>\n",
+       "      <td>-0.404247</td>\n",
+       "      <td>1.227937</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9132</th>\n",
+       "      <td>-0.069935</td>\n",
+       "      <td>-0.517356</td>\n",
+       "      <td>0.080820</td>\n",
+       "      <td>1.876656</td>\n",
+       "      <td>-1.614960</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>0.014154</td>\n",
+       "      <td>0.885113</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9133</th>\n",
+       "      <td>-0.784955</td>\n",
+       "      <td>-1.239617</td>\n",
+       "      <td>-0.471408</td>\n",
+       "      <td>-1.200968</td>\n",
+       "      <td>1.502821</td>\n",
+       "      <td>-0.422250</td>\n",
+       "      <td>-0.822648</td>\n",
+       "      <td>-0.222004</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>9134 rows × 8 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      customer_lifetime_value    income  monthly_premium_auto  \\\n",
+       "0                   -0.762878  0.612827             -0.703925   \n",
+       "1                   -0.149245 -1.239617              0.022691   \n",
+       "2                    0.710636  0.365710              0.429596   \n",
+       "3                   -0.052263 -1.239617              0.371467   \n",
+       "4                   -0.755575  0.203390             -0.587666   \n",
+       "...                       ...       ...                   ...   \n",
+       "9129                 2.241590  1.128558             -0.587666   \n",
+       "9130                -0.714411 -0.528450             -0.413278   \n",
+       "9131                 0.023135 -1.239617             -0.238891   \n",
+       "9132                -0.069935 -0.517356              0.080820   \n",
+       "9133                -0.784955 -1.239617             -0.471408   \n",
+       "\n",
+       "      months_since_last_claim  months_since_policy_inception  \\\n",
+       "0                    1.678099                      -1.543287   \n",
+       "1                   -0.208186                      -0.217334   \n",
+       "2                    0.288205                      -0.360680   \n",
+       "3                    0.288205                       0.606907   \n",
+       "4                   -0.307465                      -0.145661   \n",
+       "...                       ...                            ...   \n",
+       "9129                 0.288205                       1.466984   \n",
+       "9130                -0.108908                      -0.719046   \n",
+       "9131                -0.605299                      -0.396517   \n",
+       "9132                 1.876656                      -1.614960   \n",
+       "9133                -1.200968                       1.502821   \n",
+       "\n",
+       "      number_of_open_complaints  number_of_policies  total_claim_amount  \n",
+       "0                     -0.422250           -0.822648           -0.169640  \n",
+       "1                     -0.422250            2.106160            2.400737  \n",
+       "2                     -0.422250           -0.404247            0.455734  \n",
+       "3                     -0.422250            1.687759            0.329769  \n",
+       "4                     -0.422250           -0.822648           -1.018843  \n",
+       "...                         ...                 ...                 ...  \n",
+       "9129                  -0.422250           -0.404247           -0.811934  \n",
+       "9130                  -0.422250           -0.822648           -0.188956  \n",
+       "9131                   2.873245           -0.404247            1.227937  \n",
+       "9132                  -0.422250            0.014154            0.885113  \n",
+       "9133                  -0.422250           -0.822648           -0.222004  \n",
+       "\n",
+       "[9134 rows x 8 columns]"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Standardization, also known as z-score normalization, involves rescaling features to have a mean of 0 and a standard deviation of 1. \n",
+    "# This is useful when your data might not follow a normal distribution, but you still want to make features comparable. \n",
+    "\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "\n",
+    "scaler = StandardScaler()\n",
+    "normalized_data = scaler.fit_transform(df_numerical)\n",
+    "normalized_data = pd.DataFrame(normalized_data, columns=df_numerical.columns)\n",
+    "normalized_data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "af12cb74",
+   "metadata": {},
+   "source": [
+    "X-y split"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "4b13050d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x800 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "correlations_matrix = df_numerical.corr()\n",
+    "\n",
+    "mask = np.zeros_like(correlations_matrix)\n",
+    "mask[np.triu_indices_from(mask)] = True\n",
+    "fig, ax = plt.subplots(figsize=(10, 8))\n",
+    "ax = sns.heatmap(correlations_matrix, mask=mask, annot=True)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "c1526a6e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"simpletable\">\n",
+       "<caption>OLS Regression Results</caption>\n",
+       "<tr>\n",
+       "  <th>Dep. Variable:</th>    <td>total_claim_amount</td> <th>  R-squared:         </th> <td>   0.519</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Model:</th>                    <td>OLS</td>        <th>  Adj. R-squared:    </th> <td>   0.518</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Method:</th>              <td>Least Squares</td>   <th>  F-statistic:       </th> <td>   1405.</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Date:</th>              <td>Wed, 03 Apr 2024</td>  <th>  Prob (F-statistic):</th>  <td>  0.00</td>  \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Time:</th>                  <td>16:58:20</td>      <th>  Log-Likelihood:    </th> <td> -61425.</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>No. Observations:</th>       <td>  9134</td>       <th>  AIC:               </th> <td>1.229e+05</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Df Residuals:</th>           <td>  9126</td>       <th>  BIC:               </th> <td>1.229e+05</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Df Model:</th>               <td>     7</td>       <th>                     </th>     <td> </td>    \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Covariance Type:</th>       <td>nonrobust</td>     <th>                     </th>     <td> </td>    \n",
+       "</tr>\n",
+       "</table>\n",
+       "<table class=\"simpletable\">\n",
+       "<tr>\n",
+       "                <td></td>                   <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>const</th>                         <td>   72.3910</td> <td>    8.744</td> <td>    8.279</td> <td> 0.000</td> <td>   55.252</td> <td>   89.530</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>customer_lifetime_value</th>       <td>   -0.0007</td> <td>    0.000</td> <td>   -2.014</td> <td> 0.044</td> <td>   -0.001</td> <td>-1.81e-05</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>income</th>                        <td>   -0.0033</td> <td> 6.95e-05</td> <td>  -47.370</td> <td> 0.000</td> <td>   -0.003</td> <td>   -0.003</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>monthly_premium_auto</th>          <td>    5.3425</td> <td>    0.067</td> <td>   79.934</td> <td> 0.000</td> <td>    5.212</td> <td>    5.474</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>months_since_last_claim</th>       <td>   -0.1457</td> <td>    0.210</td> <td>   -0.695</td> <td> 0.487</td> <td>   -0.557</td> <td>    0.265</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>months_since_policy_inception</th> <td>   -0.1023</td> <td>    0.076</td> <td>   -1.352</td> <td> 0.176</td> <td>   -0.251</td> <td>    0.046</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>number_of_open_complaints</th>     <td>   -1.3716</td> <td>    2.319</td> <td>   -0.591</td> <td> 0.554</td> <td>   -5.918</td> <td>    3.174</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>number_of_policies</th>            <td>    0.2486</td> <td>    0.883</td> <td>    0.281</td> <td> 0.778</td> <td>   -1.483</td> <td>    1.980</td>\n",
+       "</tr>\n",
+       "</table>\n",
+       "<table class=\"simpletable\">\n",
+       "<tr>\n",
+       "  <th>Omnibus:</th>       <td>994.270</td> <th>  Durbin-Watson:     </th> <td>   1.980</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Prob(Omnibus):</th> <td> 0.000</td>  <th>  Jarque-Bera (JB):  </th> <td>6389.170</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Skew:</th>          <td> 0.316</td>  <th>  Prob(JB):          </th> <td>    0.00</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Kurtosis:</th>      <td> 7.048</td>  <th>  Cond. No.          </th> <td>2.02e+05</td>\n",
+       "</tr>\n",
+       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.<br/>[2] The condition number is large, 2.02e+05. This might indicate that there are<br/>strong multicollinearity or other numerical problems."
+      ],
+      "text/latex": [
+       "\\begin{center}\n",
+       "\\begin{tabular}{lclc}\n",
+       "\\toprule\n",
+       "\\textbf{Dep. Variable:}                   & total\\_claim\\_amount & \\textbf{  R-squared:         } &     0.519   \\\\\n",
+       "\\textbf{Model:}                           &         OLS          & \\textbf{  Adj. R-squared:    } &     0.518   \\\\\n",
+       "\\textbf{Method:}                          &    Least Squares     & \\textbf{  F-statistic:       } &     1405.   \\\\\n",
+       "\\textbf{Date:}                            &   Wed, 03 Apr 2024   & \\textbf{  Prob (F-statistic):} &     0.00    \\\\\n",
+       "\\textbf{Time:}                            &       16:58:20       & \\textbf{  Log-Likelihood:    } &   -61425.   \\\\\n",
+       "\\textbf{No. Observations:}                &          9134        & \\textbf{  AIC:               } & 1.229e+05   \\\\\n",
+       "\\textbf{Df Residuals:}                    &          9126        & \\textbf{  BIC:               } & 1.229e+05   \\\\\n",
+       "\\textbf{Df Model:}                        &             7        & \\textbf{                     } &             \\\\\n",
+       "\\textbf{Covariance Type:}                 &      nonrobust       & \\textbf{                     } &             \\\\\n",
+       "\\bottomrule\n",
+       "\\end{tabular}\n",
+       "\\begin{tabular}{lcccccc}\n",
+       "                                          & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
+       "\\midrule\n",
+       "\\textbf{const}                            &      72.3910  &        8.744     &     8.279  &         0.000        &       55.252    &       89.530     \\\\\n",
+       "\\textbf{customer\\_lifetime\\_value}        &      -0.0007  &        0.000     &    -2.014  &         0.044        &       -0.001    &    -1.81e-05     \\\\\n",
+       "\\textbf{income}                           &      -0.0033  &     6.95e-05     &   -47.370  &         0.000        &       -0.003    &       -0.003     \\\\\n",
+       "\\textbf{monthly\\_premium\\_auto}           &       5.3425  &        0.067     &    79.934  &         0.000        &        5.212    &        5.474     \\\\\n",
+       "\\textbf{months\\_since\\_last\\_claim}       &      -0.1457  &        0.210     &    -0.695  &         0.487        &       -0.557    &        0.265     \\\\\n",
+       "\\textbf{months\\_since\\_policy\\_inception} &      -0.1023  &        0.076     &    -1.352  &         0.176        &       -0.251    &        0.046     \\\\\n",
+       "\\textbf{number\\_of\\_open\\_complaints}     &      -1.3716  &        2.319     &    -0.591  &         0.554        &       -5.918    &        3.174     \\\\\n",
+       "\\textbf{number\\_of\\_policies}             &       0.2486  &        0.883     &     0.281  &         0.778        &       -1.483    &        1.980     \\\\\n",
+       "\\bottomrule\n",
+       "\\end{tabular}\n",
+       "\\begin{tabular}{lclc}\n",
+       "\\textbf{Omnibus:}       & 994.270 & \\textbf{  Durbin-Watson:     } &    1.980  \\\\\n",
+       "\\textbf{Prob(Omnibus):} &   0.000 & \\textbf{  Jarque-Bera (JB):  } & 6389.170  \\\\\n",
+       "\\textbf{Skew:}          &   0.316 & \\textbf{  Prob(JB):          } &     0.00  \\\\\n",
+       "\\textbf{Kurtosis:}      &   7.048 & \\textbf{  Cond. No.          } & 2.02e+05  \\\\\n",
+       "\\bottomrule\n",
+       "\\end{tabular}\n",
+       "%\\caption{OLS Regression Results}\n",
+       "\\end{center}\n",
+       "\n",
+       "Notes: \\newline\n",
+       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified. \\newline\n",
+       " [2] The condition number is large, 2.02e+05. This might indicate that there are \\newline\n",
+       " strong multicollinearity or other numerical problems."
+      ],
+      "text/plain": [
+       "<class 'statsmodels.iolib.summary.Summary'>\n",
+       "\"\"\"\n",
+       "                            OLS Regression Results                            \n",
+       "==============================================================================\n",
+       "Dep. Variable:     total_claim_amount   R-squared:                       0.519\n",
+       "Model:                            OLS   Adj. R-squared:                  0.518\n",
+       "Method:                 Least Squares   F-statistic:                     1405.\n",
+       "Date:                Wed, 03 Apr 2024   Prob (F-statistic):               0.00\n",
+       "Time:                        16:58:20   Log-Likelihood:                -61425.\n",
+       "No. Observations:                9134   AIC:                         1.229e+05\n",
+       "Df Residuals:                    9126   BIC:                         1.229e+05\n",
+       "Df Model:                           7                                         \n",
+       "Covariance Type:            nonrobust                                         \n",
+       "=================================================================================================\n",
+       "                                    coef    std err          t      P>|t|      [0.025      0.975]\n",
+       "-------------------------------------------------------------------------------------------------\n",
+       "const                            72.3910      8.744      8.279      0.000      55.252      89.530\n",
+       "customer_lifetime_value          -0.0007      0.000     -2.014      0.044      -0.001   -1.81e-05\n",
+       "income                           -0.0033   6.95e-05    -47.370      0.000      -0.003      -0.003\n",
+       "monthly_premium_auto              5.3425      0.067     79.934      0.000       5.212       5.474\n",
+       "months_since_last_claim          -0.1457      0.210     -0.695      0.487      -0.557       0.265\n",
+       "months_since_policy_inception    -0.1023      0.076     -1.352      0.176      -0.251       0.046\n",
+       "number_of_open_complaints        -1.3716      2.319     -0.591      0.554      -5.918       3.174\n",
+       "number_of_policies                0.2486      0.883      0.281      0.778      -1.483       1.980\n",
+       "==============================================================================\n",
+       "Omnibus:                      994.270   Durbin-Watson:                   1.980\n",
+       "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             6389.170\n",
+       "Skew:                           0.316   Prob(JB):                         0.00\n",
+       "Kurtosis:                       7.048   Cond. No.                     2.02e+05\n",
+       "==============================================================================\n",
+       "\n",
+       "Notes:\n",
+       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
+       "[2] The condition number is large, 2.02e+05. This might indicate that there are\n",
+       "strong multicollinearity or other numerical problems.\n",
+       "\"\"\""
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# total claim amount have some of the strongest correlations\n",
+    "# let's see how it's imapcted by the other measurements\n",
+    "\n",
+    "from sklearn import linear_model\n",
+    "from sklearn.metrics import mean_squared_error, r2_score\n",
+    "\n",
+    "import statsmodels.api as sm\n",
+    "from statsmodels.formula.api import ols\n",
+    "\n",
+    "Y = df_numerical['total_claim_amount']\n",
+    "X = df_numerical.drop(['total_claim_amount'], axis=1)\n",
+    "\n",
+    "X = sm.add_constant(X)\n",
+    "model = sm.OLS(Y,X).fit()\n",
+    "\n",
+    "model.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "id": "927f1c54",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"simpletable\">\n",
+       "<caption>OLS Regression Results</caption>\n",
+       "<tr>\n",
+       "  <th>Dep. Variable:</th>    <td>total_claim_amount</td> <th>  R-squared:         </th> <td>   0.399</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Model:</th>                    <td>OLS</td>        <th>  Adj. R-squared:    </th> <td>   0.399</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Method:</th>              <td>Least Squares</td>   <th>  F-statistic:       </th> <td>   6074.</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Date:</th>              <td>Wed, 03 Apr 2024</td>  <th>  Prob (F-statistic):</th>  <td>  0.00</td>  \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Time:</th>                  <td>17:03:04</td>      <th>  Log-Likelihood:    </th> <td> -62436.</td> \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>No. Observations:</th>       <td>  9134</td>       <th>  AIC:               </th> <td>1.249e+05</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Df Residuals:</th>           <td>  9132</td>       <th>  BIC:               </th> <td>1.249e+05</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Df Model:</th>               <td>     1</td>       <th>                     </th>     <td> </td>    \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Covariance Type:</th>       <td>nonrobust</td>     <th>                     </th>     <td> </td>    \n",
+       "</tr>\n",
+       "</table>\n",
+       "<table class=\"simpletable\">\n",
+       "<tr>\n",
+       "            <td></td>              <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>const</th>                <td>  -63.3293</td> <td>    6.803</td> <td>   -9.309</td> <td> 0.000</td> <td>  -76.665</td> <td>  -49.993</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>monthly_premium_auto</th> <td>    5.3360</td> <td>    0.068</td> <td>   77.935</td> <td> 0.000</td> <td>    5.202</td> <td>    5.470</td>\n",
+       "</tr>\n",
+       "</table>\n",
+       "<table class=\"simpletable\">\n",
+       "<tr>\n",
+       "  <th>Omnibus:</th>       <td>918.547</td> <th>  Durbin-Watson:     </th> <td>   1.984</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Prob(Omnibus):</th> <td> 0.000</td>  <th>  Jarque-Bera (JB):  </th> <td>4798.125</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Skew:</th>          <td> 0.348</td>  <th>  Prob(JB):          </th> <td>    0.00</td>\n",
+       "</tr>\n",
+       "<tr>\n",
+       "  <th>Kurtosis:</th>      <td> 6.482</td>  <th>  Cond. No.          </th> <td>    287.</td>\n",
+       "</tr>\n",
+       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
+      ],
+      "text/latex": [
+       "\\begin{center}\n",
+       "\\begin{tabular}{lclc}\n",
+       "\\toprule\n",
+       "\\textbf{Dep. Variable:}         & total\\_claim\\_amount & \\textbf{  R-squared:         } &     0.399   \\\\\n",
+       "\\textbf{Model:}                 &         OLS          & \\textbf{  Adj. R-squared:    } &     0.399   \\\\\n",
+       "\\textbf{Method:}                &    Least Squares     & \\textbf{  F-statistic:       } &     6074.   \\\\\n",
+       "\\textbf{Date:}                  &   Wed, 03 Apr 2024   & \\textbf{  Prob (F-statistic):} &     0.00    \\\\\n",
+       "\\textbf{Time:}                  &       17:03:04       & \\textbf{  Log-Likelihood:    } &   -62436.   \\\\\n",
+       "\\textbf{No. Observations:}      &          9134        & \\textbf{  AIC:               } & 1.249e+05   \\\\\n",
+       "\\textbf{Df Residuals:}          &          9132        & \\textbf{  BIC:               } & 1.249e+05   \\\\\n",
+       "\\textbf{Df Model:}              &             1        & \\textbf{                     } &             \\\\\n",
+       "\\textbf{Covariance Type:}       &      nonrobust       & \\textbf{                     } &             \\\\\n",
+       "\\bottomrule\n",
+       "\\end{tabular}\n",
+       "\\begin{tabular}{lcccccc}\n",
+       "                                & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
+       "\\midrule\n",
+       "\\textbf{const}                  &     -63.3293  &        6.803     &    -9.309  &         0.000        &      -76.665    &      -49.993     \\\\\n",
+       "\\textbf{monthly\\_premium\\_auto} &       5.3360  &        0.068     &    77.935  &         0.000        &        5.202    &        5.470     \\\\\n",
+       "\\bottomrule\n",
+       "\\end{tabular}\n",
+       "\\begin{tabular}{lclc}\n",
+       "\\textbf{Omnibus:}       & 918.547 & \\textbf{  Durbin-Watson:     } &    1.984  \\\\\n",
+       "\\textbf{Prob(Omnibus):} &   0.000 & \\textbf{  Jarque-Bera (JB):  } & 4798.125  \\\\\n",
+       "\\textbf{Skew:}          &   0.348 & \\textbf{  Prob(JB):          } &     0.00  \\\\\n",
+       "\\textbf{Kurtosis:}      &   6.482 & \\textbf{  Cond. No.          } &     287.  \\\\\n",
+       "\\bottomrule\n",
+       "\\end{tabular}\n",
+       "%\\caption{OLS Regression Results}\n",
+       "\\end{center}\n",
+       "\n",
+       "Notes: \\newline\n",
+       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
+      ],
+      "text/plain": [
+       "<class 'statsmodels.iolib.summary.Summary'>\n",
+       "\"\"\"\n",
+       "                            OLS Regression Results                            \n",
+       "==============================================================================\n",
+       "Dep. Variable:     total_claim_amount   R-squared:                       0.399\n",
+       "Model:                            OLS   Adj. R-squared:                  0.399\n",
+       "Method:                 Least Squares   F-statistic:                     6074.\n",
+       "Date:                Wed, 03 Apr 2024   Prob (F-statistic):               0.00\n",
+       "Time:                        17:03:04   Log-Likelihood:                -62436.\n",
+       "No. Observations:                9134   AIC:                         1.249e+05\n",
+       "Df Residuals:                    9132   BIC:                         1.249e+05\n",
+       "Df Model:                           1                                         \n",
+       "Covariance Type:            nonrobust                                         \n",
+       "========================================================================================\n",
+       "                           coef    std err          t      P>|t|      [0.025      0.975]\n",
+       "----------------------------------------------------------------------------------------\n",
+       "const                  -63.3293      6.803     -9.309      0.000     -76.665     -49.993\n",
+       "monthly_premium_auto     5.3360      0.068     77.935      0.000       5.202       5.470\n",
+       "==============================================================================\n",
+       "Omnibus:                      918.547   Durbin-Watson:                   1.984\n",
+       "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             4798.125\n",
+       "Skew:                           0.348   Prob(JB):                         0.00\n",
+       "Kurtosis:                       6.482   Cond. No.                         287.\n",
+       "==============================================================================\n",
+       "\n",
+       "Notes:\n",
+       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
+       "\"\"\""
+      ]
+     },
+     "execution_count": 37,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# the highest positive correlation was between total claim amount and monthly premium auto where the first seems to be dependant on the second\n",
+    "# coef: 5.3425, if we increase monthly premium auto by one unit, total claim amount will increase by 5.3425\n",
+    "Y = df_numerical['total_claim_amount']\n",
+    "X = df_numerical['monthly_premium_auto']\n",
+    "X = sm.add_constant(X)\n",
+    "model = sm.OLS(Y,X).fit()\n",
+    "\n",
+    "model.summary()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": 5
+}