age_dr.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "d3f579ef",
   "metadata": {},
   "source": [
    "# Outcome regression model for age"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "f32f347d",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "722096cc",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_raw = pd.read_csv('./stroke_data_dummies.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "51b04a63",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_r = df_raw[df_raw.Gender_Other == 0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "4a19270c",
   "metadata": {},
   "outputs": [],
   "source": [
    "def age_check(x):\n",
    "    if x >= 45:\n",
    "        return 1\n",
    "    else:\n",
    "        return 0\n",
    "    \n",
    "df_r['old'] = df_r.age.apply(age_check)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "99b37401",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df_r.drop(columns = ['Unnamed: 0','id','Obesity','Gender_Other','age'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "f695106a",
   "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>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>avg_glucose_level</th>\n",
       "      <th>bmi</th>\n",
       "      <th>stroke</th>\n",
       "      <th>marriage</th>\n",
       "      <th>Gender_Female</th>\n",
       "      <th>Gender_Male</th>\n",
       "      <th>Work_Govt_job</th>\n",
       "      <th>Work_Never_worked</th>\n",
       "      <th>Work_Private</th>\n",
       "      <th>Work_Self-employed</th>\n",
       "      <th>Work_children</th>\n",
       "      <th>smoking_Unknown</th>\n",
       "      <th>smoking_formerly smoked</th>\n",
       "      <th>smoking_never smoked</th>\n",
       "      <th>smoking_smokes</th>\n",
       "      <th>Residence_Rural</th>\n",
       "      <th>Residence_Urban</th>\n",
       "      <th>old</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>228.69</td>\n",
       "      <td>36.6</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>105.92</td>\n",
       "      <td>32.5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>171.23</td>\n",
       "      <td>34.4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>174.12</td>\n",
       "      <td>24.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>186.21</td>\n",
       "      <td>29.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   hypertension  heart_disease  avg_glucose_level   bmi  stroke  marriage  \\\n",
       "0             0              1             228.69  36.6       1         1   \n",
       "1             0              1             105.92  32.5       1         1   \n",
       "2             0              0             171.23  34.4       1         1   \n",
       "3             1              0             174.12  24.0       1         1   \n",
       "4             0              0             186.21  29.0       1         1   \n",
       "\n",
       "   Gender_Female  Gender_Male  Work_Govt_job  Work_Never_worked  Work_Private  \\\n",
       "0              0            1              0                  0             1   \n",
       "1              0            1              0                  0             1   \n",
       "2              1            0              0                  0             1   \n",
       "3              1            0              0                  0             0   \n",
       "4              0            1              0                  0             1   \n",
       "\n",
       "   Work_Self-employed  Work_children  smoking_Unknown  \\\n",
       "0                   0              0                0   \n",
       "1                   0              0                0   \n",
       "2                   0              0                0   \n",
       "3                   1              0                0   \n",
       "4                   0              0                0   \n",
       "\n",
       "   smoking_formerly smoked  smoking_never smoked  smoking_smokes  \\\n",
       "0                        1                     0               0   \n",
       "1                        0                     1               0   \n",
       "2                        0                     0               1   \n",
       "3                        0                     1               0   \n",
       "4                        1                     0               0   \n",
       "\n",
       "   Residence_Rural  Residence_Urban  old  \n",
       "0                0                1    1  \n",
       "1                1                0    1  \n",
       "2                0                1    1  \n",
       "3                1                0    1  \n",
       "4                0                1    1  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "195fcd68",
   "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>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>avg_glucose_level</th>\n",
       "      <th>bmi</th>\n",
       "      <th>marriage</th>\n",
       "      <th>Gender_Female</th>\n",
       "      <th>Gender_Male</th>\n",
       "      <th>Work_Govt_job</th>\n",
       "      <th>Work_Never_worked</th>\n",
       "      <th>Work_Private</th>\n",
       "      <th>Work_Self-employed</th>\n",
       "      <th>Work_children</th>\n",
       "      <th>smoking_Unknown</th>\n",
       "      <th>smoking_formerly smoked</th>\n",
       "      <th>smoking_never smoked</th>\n",
       "      <th>smoking_smokes</th>\n",
       "      <th>Residence_Rural</th>\n",
       "      <th>Residence_Urban</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>228.69</td>\n",
       "      <td>36.6</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>105.92</td>\n",
       "      <td>32.5</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>171.23</td>\n",
       "      <td>34.4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>174.12</td>\n",
       "      <td>24.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>186.21</td>\n",
       "      <td>29.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <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>4904</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>103.08</td>\n",
       "      <td>18.6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4905</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>125.20</td>\n",
       "      <td>40.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4906</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>82.99</td>\n",
       "      <td>30.6</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4907</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>166.29</td>\n",
       "      <td>25.6</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4908</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>85.28</td>\n",
       "      <td>26.2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4908 rows × 18 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      hypertension  heart_disease  avg_glucose_level   bmi  marriage  \\\n",
       "0                0              1             228.69  36.6         1   \n",
       "1                0              1             105.92  32.5         1   \n",
       "2                0              0             171.23  34.4         1   \n",
       "3                1              0             174.12  24.0         1   \n",
       "4                0              0             186.21  29.0         1   \n",
       "...            ...            ...                ...   ...       ...   \n",
       "4904             0              0             103.08  18.6         0   \n",
       "4905             0              0             125.20  40.0         1   \n",
       "4906             0              0              82.99  30.6         1   \n",
       "4907             0              0             166.29  25.6         1   \n",
       "4908             0              0              85.28  26.2         1   \n",
       "\n",
       "      Gender_Female  Gender_Male  Work_Govt_job  Work_Never_worked  \\\n",
       "0                 0            1              0                  0   \n",
       "1                 0            1              0                  0   \n",
       "2                 1            0              0                  0   \n",
       "3                 1            0              0                  0   \n",
       "4                 0            1              0                  0   \n",
       "...             ...          ...            ...                ...   \n",
       "4904              1            0              0                  0   \n",
       "4905              1            0              0                  0   \n",
       "4906              1            0              0                  0   \n",
       "4907              0            1              0                  0   \n",
       "4908              1            0              1                  0   \n",
       "\n",
       "      Work_Private  Work_Self-employed  Work_children  smoking_Unknown  \\\n",
       "0                1                   0              0                0   \n",
       "1                1                   0              0                0   \n",
       "2                1                   0              0                0   \n",
       "3                0                   1              0                0   \n",
       "4                1                   0              0                0   \n",
       "...            ...                 ...            ...              ...   \n",
       "4904             0                   0              1                1   \n",
       "4905             0                   1              0                0   \n",
       "4906             0                   1              0                0   \n",
       "4907             1                   0              0                0   \n",
       "4908             0                   0              0                1   \n",
       "\n",
       "      smoking_formerly smoked  smoking_never smoked  smoking_smokes  \\\n",
       "0                           1                     0               0   \n",
       "1                           0                     1               0   \n",
       "2                           0                     0               1   \n",
       "3                           0                     1               0   \n",
       "4                           1                     0               0   \n",
       "...                       ...                   ...             ...   \n",
       "4904                        0                     0               0   \n",
       "4905                        0                     1               0   \n",
       "4906                        0                     1               0   \n",
       "4907                        1                     0               0   \n",
       "4908                        0                     0               0   \n",
       "\n",
       "      Residence_Rural  Residence_Urban  \n",
       "0                   0                1  \n",
       "1                   1                0  \n",
       "2                   0                1  \n",
       "3                   1                0  \n",
       "4                   0                1  \n",
       "...               ...              ...  \n",
       "4904                1                0  \n",
       "4905                0                1  \n",
       "4906                1                0  \n",
       "4907                1                0  \n",
       "4908                0                1  \n",
       "\n",
       "[4908 rows x 18 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = df.drop(columns = ['stroke', 'old'])\n",
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "04acb475",
   "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>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>avg_glucose_level</th>\n",
       "      <th>bmi</th>\n",
       "      <th>stroke</th>\n",
       "      <th>marriage</th>\n",
       "      <th>Gender_Female</th>\n",
       "      <th>Gender_Male</th>\n",
       "      <th>Work_Govt_job</th>\n",
       "      <th>Work_Never_worked</th>\n",
       "      <th>Work_Private</th>\n",
       "      <th>Work_Self-employed</th>\n",
       "      <th>Work_children</th>\n",
       "      <th>smoking_Unknown</th>\n",
       "      <th>smoking_formerly smoked</th>\n",
       "      <th>smoking_never smoked</th>\n",
       "      <th>smoking_smokes</th>\n",
       "      <th>Residence_Rural</th>\n",
       "      <th>Residence_Urban</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>83.41</td>\n",
       "      <td>25.4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>58.09</td>\n",
       "      <td>39.2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>143.43</td>\n",
       "      <td>45.9</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>82.28</td>\n",
       "      <td>24.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>149</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>76.13</td>\n",
       "      <td>29.9</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4899</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>71.88</td>\n",
       "      <td>17.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4903</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>82.85</td>\n",
       "      <td>46.9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4904</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>103.08</td>\n",
       "      <td>18.6</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4906</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>82.99</td>\n",
       "      <td>30.6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4908</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>85.28</td>\n",
       "      <td>26.2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2464 rows × 19 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      hypertension  heart_disease  avg_glucose_level   bmi  stroke  marriage  \\\n",
       "25               0              0              83.41  25.4       1         1   \n",
       "41               1              0              58.09  39.2       1         1   \n",
       "64               0              0             143.43  45.9       1         1   \n",
       "99               0              0              82.28  24.0       1         0   \n",
       "149              0              0              76.13  29.9       1         1   \n",
       "...            ...            ...                ...   ...     ...       ...   \n",
       "4899             0              0              71.88  17.5       0         0   \n",
       "4903             0              0              82.85  46.9       0         0   \n",
       "4904             0              0             103.08  18.6       0         0   \n",
       "4906             0              0              82.99  30.6       0         1   \n",
       "4908             0              0              85.28  26.2       0         1   \n",
       "\n",
       "      Gender_Female  Gender_Male  Work_Govt_job  Work_Never_worked  \\\n",
       "25                0            1              0                  0   \n",
       "41                1            0              0                  0   \n",
       "64                0            1              0                  0   \n",
       "99                1            0              0                  0   \n",
       "149               1            0              0                  0   \n",
       "...             ...          ...            ...                ...   \n",
       "4899              0            1              0                  0   \n",
       "4903              1            0              0                  0   \n",
       "4904              1            0              0                  0   \n",
       "4906              1            0              0                  0   \n",
       "4908              1            0              1                  0   \n",
       "\n",
       "      Work_Private  Work_Self-employed  Work_children  smoking_Unknown  \\\n",
       "25               1                   0              0                1   \n",
       "41               1                   0              0                0   \n",
       "64               0                   1              0                1   \n",
       "99               0                   1              0                0   \n",
       "149              1                   0              0                0   \n",
       "...            ...                 ...            ...              ...   \n",
       "4899             0                   0              1                1   \n",
       "4903             1                   0              0                1   \n",
       "4904             0                   0              1                1   \n",
       "4906             0                   1              0                0   \n",
       "4908             0                   0              0                1   \n",
       "\n",
       "      smoking_formerly smoked  smoking_never smoked  smoking_smokes  \\\n",
       "25                          0                     0               0   \n",
       "41                          0                     0               1   \n",
       "64                          0                     0               0   \n",
       "99                          1                     0               0   \n",
       "149                         0                     0               1   \n",
       "...                       ...                   ...             ...   \n",
       "4899                        0                     0               0   \n",
       "4903                        0                     0               0   \n",
       "4904                        0                     0               0   \n",
       "4906                        0                     1               0   \n",
       "4908                        0                     0               0   \n",
       "\n",
       "      Residence_Rural  Residence_Urban  \n",
       "25                  1                0  \n",
       "41                  1                0  \n",
       "64                  0                1  \n",
       "99                  0                1  \n",
       "149                 1                0  \n",
       "...               ...              ...  \n",
       "4899                0                1  \n",
       "4903                0                1  \n",
       "4904                1                0  \n",
       "4906                1                0  \n",
       "4908                0                1  \n",
       "\n",
       "[2464 rows x 19 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_0 = df[df['old'] == 0]\n",
    "df_0 = df_0.drop(columns = ['old'])\n",
    "df_0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "47489de5",
   "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>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>avg_glucose_level</th>\n",
       "      <th>bmi</th>\n",
       "      <th>stroke</th>\n",
       "      <th>marriage</th>\n",
       "      <th>Gender_Female</th>\n",
       "      <th>Gender_Male</th>\n",
       "      <th>Work_Govt_job</th>\n",
       "      <th>Work_Never_worked</th>\n",
       "      <th>Work_Private</th>\n",
       "      <th>Work_Self-employed</th>\n",
       "      <th>Work_children</th>\n",
       "      <th>smoking_Unknown</th>\n",
       "      <th>smoking_formerly smoked</th>\n",
       "      <th>smoking_never smoked</th>\n",
       "      <th>smoking_smokes</th>\n",
       "      <th>Residence_Rural</th>\n",
       "      <th>Residence_Urban</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>228.69</td>\n",
       "      <td>36.6</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>105.92</td>\n",
       "      <td>32.5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>171.23</td>\n",
       "      <td>34.4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>174.12</td>\n",
       "      <td>24.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>186.21</td>\n",
       "      <td>29.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <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>4900</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>71.97</td>\n",
       "      <td>28.3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4901</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>97.95</td>\n",
       "      <td>24.5</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4902</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>77.93</td>\n",
       "      <td>21.7</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4905</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>125.20</td>\n",
       "      <td>40.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4907</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>166.29</td>\n",
       "      <td>25.6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2444 rows × 19 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      hypertension  heart_disease  avg_glucose_level   bmi  stroke  marriage  \\\n",
       "0                0              1             228.69  36.6       1         1   \n",
       "1                0              1             105.92  32.5       1         1   \n",
       "2                0              0             171.23  34.4       1         1   \n",
       "3                1              0             174.12  24.0       1         1   \n",
       "4                0              0             186.21  29.0       1         1   \n",
       "...            ...            ...                ...   ...     ...       ...   \n",
       "4900             1              0              71.97  28.3       0         1   \n",
       "4901             0              0              97.95  24.5       0         1   \n",
       "4902             0              0              77.93  21.7       0         1   \n",
       "4905             0              0             125.20  40.0       0         1   \n",
       "4907             0              0             166.29  25.6       0         1   \n",
       "\n",
       "      Gender_Female  Gender_Male  Work_Govt_job  Work_Never_worked  \\\n",
       "0                 0            1              0                  0   \n",
       "1                 0            1              0                  0   \n",
       "2                 1            0              0                  0   \n",
       "3                 1            0              0                  0   \n",
       "4                 0            1              0                  0   \n",
       "...             ...          ...            ...                ...   \n",
       "4900              0            1              0                  0   \n",
       "4901              1            0              0                  0   \n",
       "4902              1            0              0                  0   \n",
       "4905              1            0              0                  0   \n",
       "4907              0            1              0                  0   \n",
       "\n",
       "      Work_Private  Work_Self-employed  Work_children  smoking_Unknown  \\\n",
       "0                1                   0              0                0   \n",
       "1                1                   0              0                0   \n",
       "2                1                   0              0                0   \n",
       "3                0                   1              0                0   \n",
       "4                1                   0              0                0   \n",
       "...            ...                 ...            ...              ...   \n",
       "4900             0                   1              0                0   \n",
       "4901             1                   0              0                1   \n",
       "4902             1                   0              0                0   \n",
       "4905             0                   1              0                0   \n",
       "4907             1                   0              0                0   \n",
       "\n",
       "      smoking_formerly smoked  smoking_never smoked  smoking_smokes  \\\n",
       "0                           1                     0               0   \n",
       "1                           0                     1               0   \n",
       "2                           0                     0               1   \n",
       "3                           0                     1               0   \n",
       "4                           1                     0               0   \n",
       "...                       ...                   ...             ...   \n",
       "4900                        0                     1               0   \n",
       "4901                        0                     0               0   \n",
       "4902                        0                     1               0   \n",
       "4905                        0                     1               0   \n",
       "4907                        1                     0               0   \n",
       "\n",
       "      Residence_Rural  Residence_Urban  \n",
       "0                   0                1  \n",
       "1                   1                0  \n",
       "2                   0                1  \n",
       "3                   1                0  \n",
       "4                   0                1  \n",
       "...               ...              ...  \n",
       "4900                1                0  \n",
       "4901                0                1  \n",
       "4902                1                0  \n",
       "4905                0                1  \n",
       "4907                1                0  \n",
       "\n",
       "[2444 rows x 19 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_1 = df[df['old'] == 1]\n",
    "df_1 = df_1.drop(columns = ['old'])\n",
    "df_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "c2f2aae3",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_0 = df_0['stroke']\n",
    "x_0 = df_0.drop(columns = ['stroke'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "00b90cb6",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_1 = df_1['stroke']\n",
    "x_1 = df_1.drop(columns = ['stroke'])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b95d3694",
   "metadata": {},
   "source": [
    "# Model for controlled group"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "0a207234",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "from sklearn.model_selection import cross_val_score\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "4f2b7837",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9967537393426673"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rfc = RandomForestClassifier(random_state=60)\n",
    "score_pre_0 = cross_val_score(rfc,x_0,y_0,cv=5).mean()\n",
    "score_pre_0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "be7858f8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "nan 1\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "scorel = []\n",
    "for i in range(0,200,10):\n",
    "    rfc = RandomForestClassifier(n_estimators=i+1,\n",
    "                                 n_jobs=-1,\n",
    "                                random_state=60)\n",
    "    score = cross_val_score(rfc,x_0,y_0,cv=5).mean()\n",
    "    scorel.append(score)\n",
    "\n",
    "print(max(scorel),(scorel.index(max(scorel))*10)+1)\n",
    "plt.figure(figsize=[20,5])\n",
    "plt.plot(range(1,201,10),scorel)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "03826c0b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "nan 1\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 4320x1440 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "scorel = []\n",
    "for i in range(1,51):\n",
    "    rfc = RandomForestClassifier(n_estimators=i+1,\n",
    "                                 n_jobs=-1,\n",
    "                                random_state=60)\n",
    "    score = cross_val_score(rfc,x_0,y_0,cv=5).mean()\n",
    "    scorel.append(score)\n",
    "\n",
    "print(max(scorel),([*range(1,51)][scorel.index(max(scorel))]))\n",
    "plt.figure(figsize=[60,20])\n",
    "plt.plot(range(1,51),scorel)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "26e3a7c5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=5, random_state=60),\n",
       "             param_grid={'max_depth': array([ 1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16, 17,\n",
       "       18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29])})"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid = {'max_depth':np.arange(1, 30, 1)}\n",
    "rfc = RandomForestClassifier(n_estimators=5\n",
    "                             ,random_state=60\n",
    "                             )\n",
    "GS = GridSearchCV(rfc,param_grid,cv=5)\n",
    "GS.fit(x_0,y_0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "f0f12a76",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'max_depth': 1}"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "12ae353a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9967537393426673"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "3baf8e57",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=5, random_state=60),\n",
       "             param_grid={'max_features': array([ 1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16, 17,\n",
       "       18, 19])})"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid = {'max_features':np.arange(1,20,1)}\n",
    "rfc = RandomForestClassifier(n_estimators=5\n",
    "                             ,random_state=60\n",
    "                             )\n",
    "GS = GridSearchCV(rfc,param_grid,cv=5)\n",
    "GS.fit(x_0,y_0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "cab87a8c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'max_features': 1}"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "6dab1ac0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9967537393426673"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "a0b42e23",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=5, random_state=60),\n",
       "             param_grid={'min_samples_leaf': array([ 1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16, 17,\n",
       "       18, 19])})"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid={'min_samples_leaf':np.arange(1, 20, 1)}\n",
    "rfc = RandomForestClassifier(n_estimators=5\n",
    "                             ,random_state=60\n",
    "                             )\n",
    "GS = GridSearchCV(rfc,param_grid,cv=5)\n",
    "GS.fit(x_0,y_0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "021dad34",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'min_samples_leaf': 2}"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "0eecb4f8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9967537393426673"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "31d2a5e6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=5, random_state=60),\n",
       "             param_grid={'min_samples_split': array([ 2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16, 17, 18,\n",
       "       19, 20, 21])})"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid={'min_samples_split':np.arange(2, 2+20, 1)}\n",
    "rfc = RandomForestClassifier(n_estimators=5\n",
    "                             ,random_state=60\n",
    "                             )\n",
    "GS = GridSearchCV(rfc,param_grid,cv=5)\n",
    "GS.fit(x_0,y_0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "e9aa1131",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'min_samples_split': 3}"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "bbed554c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9967537393426673"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "8ba0d668",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9967537393426673"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rfc_0 = RandomForestClassifier(n_estimators=5,max_depth = 1,random_state=60)\n",
    "score_0 = cross_val_score(rfc_0,x_0,y_0,cv=5).mean()\n",
    "score_0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "92a79d34",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "score_0 - score_pre_0"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d1cefe9f",
   "metadata": {},
   "source": [
    "# Model for treatment group"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "5d76c53b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9144825505380669"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rfc = RandomForestClassifier(n_estimators=100,random_state=90)\n",
    "score_pre_1 = cross_val_score(rfc,x_1,y_1,cv=5).mean()\n",
    "score_pre_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "da9d8f0b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "nan 1\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "scorel = []\n",
    "for i in range(0,200,10):\n",
    "    rfc = RandomForestClassifier(n_estimators=i+1,\n",
    "                                 n_jobs=-1,\n",
    "                                random_state=80)\n",
    "    score = cross_val_score(rfc,x_1,y_1,cv=5).mean()\n",
    "    scorel.append(score)\n",
    "\n",
    "print(max(scorel),(scorel.index(max(scorel))*10)+1)\n",
    "plt.figure(figsize=[20,5])\n",
    "plt.plot(range(0,200,10),scorel)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "e5822dae",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "nan 21\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "scorel = []\n",
    "for i in range(21,81):\n",
    "    rfc = RandomForestClassifier(n_estimators=i+1,\n",
    "                                 n_jobs=-1,\n",
    "                                random_state=80)\n",
    "    score = cross_val_score(rfc,x_1,y_1,cv=5).mean()\n",
    "    scorel.append(score)\n",
    "\n",
    "print(max(scorel),([*range(21,81)][scorel.index(max(scorel))]))\n",
    "plt.figure(figsize=[20,5])\n",
    "plt.plot(range(21,81),scorel)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "04424108",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=27, random_state=80),\n",
       "             param_grid={'max_depth': array([ 1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16, 17,\n",
       "       18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29])})"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid = {'max_depth':np.arange(1, 30, 1)}\n",
    "rfc = RandomForestClassifier(n_estimators=27\n",
    "                             ,random_state=80\n",
    "                             )\n",
    "GS = GridSearchCV(rfc,param_grid,cv=5)\n",
    "GS.fit(x_1,y_1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "b4125355",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'max_depth': 7}"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "6745b688",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9177587247309665"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "0b7a1be2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=27, random_state=80),\n",
       "             param_grid={'max_features': array([ 1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16, 17,\n",
       "       18, 19])})"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid = {'max_features':np.arange(1,20,1)}\n",
    "rfc = RandomForestClassifier(n_estimators=27\n",
    "                             ,random_state=80\n",
    "                             )\n",
    "GS = GridSearchCV(rfc,param_grid,cv=5)\n",
    "GS.fit(x_1,y_1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "487f6d84",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'max_features': 8}"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "7512c907",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9136645546280466"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "3aef2b74",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=27, random_state=80),\n",
       "             param_grid={'min_samples_leaf': array([ 1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16, 17,\n",
       "       18, 19])})"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid={'min_samples_leaf':np.arange(1, 20, 1)}\n",
    "rfc = RandomForestClassifier(n_estimators=27\n",
    "                             ,random_state=80\n",
    "                             )\n",
    "GS = GridSearchCV(rfc,param_grid,cv=5)\n",
    "GS.fit(x_1,y_1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "d4bb5870",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'min_samples_leaf': 3}"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "dbb7ae8b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.917757886620403"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "3adf4de4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=27, random_state=80),\n",
       "             param_grid={'min_samples_split': array([ 2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16, 17, 18,\n",
       "       19, 20, 21])})"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid={'min_samples_split':np.arange(2, 2+20, 1)}\n",
    "rfc = RandomForestClassifier(n_estimators=27\n",
    "                             ,random_state=80\n",
    "                             )\n",
    "GS = GridSearchCV(rfc,param_grid,cv=5)\n",
    "GS.fit(x_1,y_1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "04aebe0a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'min_samples_split': 15}"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "9674e012",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.917757886620403"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "a8056d38",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9177587247309665"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rfc_1 = RandomForestClassifier(n_estimators=27,max_depth = 7,random_state=80)\n",
    "score_1 = cross_val_score(rfc_1,x_1,y_1,cv=5).mean()\n",
    "score_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "8a62b091",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0032761741928996058"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "score_1 - score_pre_1"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fa8c1df7",
   "metadata": {},
   "source": [
    "# Outcome modeling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "ccc99ff5",
   "metadata": {},
   "outputs": [],
   "source": [
    "from scipy import stats\n",
    "import scipy.stats"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "955d0f95",
   "metadata": {},
   "outputs": [],
   "source": [
    "rfc0 = rfc_0.fit(x_0, y_0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "1429ab21",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predict_0 = rfc0.predict(X)\n",
    "mean_0 = predict_0.mean()\n",
    "mean_0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "d0b74cde",
   "metadata": {},
   "outputs": [],
   "source": [
    "rfc1 = rfc_1.fit(x_1, y_1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "807519a4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0014262428687856561"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predict_1 = rfc1.predict(X)\n",
    "mean_1 = predict_1.mean()\n",
    "mean_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "cf7f14de",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0014262428687856561"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ATE_outcome = mean_1 - mean_0\n",
    "ATE_outcome"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "8dc5f9be",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-2.6473703329260934 0.004068989309135414\n"
     ]
    }
   ],
   "source": [
    "t,pval = scipy.stats.ttest_ind(predict_0,predict_1,equal_var=False,alternative='less')\n",
    "print(t,pval)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "446419b5",
   "metadata": {},
   "source": [
    "# IPW for age"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "c15e9939",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression as lr\n",
    "\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.neighbors import NearestNeighbors\n",
    "from sklearn import metrics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "361c4ac9",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Enabled to remove warnings for demo purposes.\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "753b28ee",
   "metadata": {},
   "outputs": [],
   "source": [
    "import math\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "# import scipy.stats as stats\n",
    "import statsmodels.api as sm\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "plt.style.use('classic')\n",
    "%matplotlib inline\n",
    "\n",
    "import seaborn as sns\n",
    "sns.set(rc={'figure.figsize':(16,10)}, font_scale=1.3)\n",
    "\n",
    "from scipy import stats"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "8190145a",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('./healthcare-dataset-stroke-data.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "063c5993",
   "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>id</th>\n",
       "      <th>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>ever_married</th>\n",
       "      <th>work_type</th>\n",
       "      <th>Residence_type</th>\n",
       "      <th>avg_glucose_level</th>\n",
       "      <th>bmi</th>\n",
       "      <th>smoking_status</th>\n",
       "      <th>stroke</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>9046</td>\n",
       "      <td>Male</td>\n",
       "      <td>67.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Private</td>\n",
       "      <td>Urban</td>\n",
       "      <td>228.69</td>\n",
       "      <td>36.6</td>\n",
       "      <td>formerly smoked</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>51676</td>\n",
       "      <td>Female</td>\n",
       "      <td>61.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Self-employed</td>\n",
       "      <td>Rural</td>\n",
       "      <td>202.21</td>\n",
       "      <td>NaN</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>31112</td>\n",
       "      <td>Male</td>\n",
       "      <td>80.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Private</td>\n",
       "      <td>Rural</td>\n",
       "      <td>105.92</td>\n",
       "      <td>32.5</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>60182</td>\n",
       "      <td>Female</td>\n",
       "      <td>49.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Private</td>\n",
       "      <td>Urban</td>\n",
       "      <td>171.23</td>\n",
       "      <td>34.4</td>\n",
       "      <td>smokes</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1665</td>\n",
       "      <td>Female</td>\n",
       "      <td>79.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Self-employed</td>\n",
       "      <td>Rural</td>\n",
       "      <td>174.12</td>\n",
       "      <td>24.0</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5105</th>\n",
       "      <td>18234</td>\n",
       "      <td>Female</td>\n",
       "      <td>80.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Private</td>\n",
       "      <td>Urban</td>\n",
       "      <td>83.75</td>\n",
       "      <td>NaN</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5106</th>\n",
       "      <td>44873</td>\n",
       "      <td>Female</td>\n",
       "      <td>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Self-employed</td>\n",
       "      <td>Urban</td>\n",
       "      <td>125.20</td>\n",
       "      <td>40.0</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5107</th>\n",
       "      <td>19723</td>\n",
       "      <td>Female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Self-employed</td>\n",
       "      <td>Rural</td>\n",
       "      <td>82.99</td>\n",
       "      <td>30.6</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5108</th>\n",
       "      <td>37544</td>\n",
       "      <td>Male</td>\n",
       "      <td>51.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Private</td>\n",
       "      <td>Rural</td>\n",
       "      <td>166.29</td>\n",
       "      <td>25.6</td>\n",
       "      <td>formerly smoked</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5109</th>\n",
       "      <td>44679</td>\n",
       "      <td>Female</td>\n",
       "      <td>44.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Govt_job</td>\n",
       "      <td>Urban</td>\n",
       "      <td>85.28</td>\n",
       "      <td>26.2</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5110 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         id  gender   age  hypertension  heart_disease ever_married  \\\n",
       "0      9046    Male  67.0             0              1          Yes   \n",
       "1     51676  Female  61.0             0              0          Yes   \n",
       "2     31112    Male  80.0             0              1          Yes   \n",
       "3     60182  Female  49.0             0              0          Yes   \n",
       "4      1665  Female  79.0             1              0          Yes   \n",
       "...     ...     ...   ...           ...            ...          ...   \n",
       "5105  18234  Female  80.0             1              0          Yes   \n",
       "5106  44873  Female  81.0             0              0          Yes   \n",
       "5107  19723  Female  35.0             0              0          Yes   \n",
       "5108  37544    Male  51.0             0              0          Yes   \n",
       "5109  44679  Female  44.0             0              0          Yes   \n",
       "\n",
       "          work_type Residence_type  avg_glucose_level   bmi   smoking_status  \\\n",
       "0           Private          Urban             228.69  36.6  formerly smoked   \n",
       "1     Self-employed          Rural             202.21   NaN     never smoked   \n",
       "2           Private          Rural             105.92  32.5     never smoked   \n",
       "3           Private          Urban             171.23  34.4           smokes   \n",
       "4     Self-employed          Rural             174.12  24.0     never smoked   \n",
       "...             ...            ...                ...   ...              ...   \n",
       "5105        Private          Urban              83.75   NaN     never smoked   \n",
       "5106  Self-employed          Urban             125.20  40.0     never smoked   \n",
       "5107  Self-employed          Rural              82.99  30.6     never smoked   \n",
       "5108        Private          Rural             166.29  25.6  formerly smoked   \n",
       "5109       Govt_job          Urban              85.28  26.2          Unknown   \n",
       "\n",
       "      stroke  \n",
       "0          1  \n",
       "1          1  \n",
       "2          1  \n",
       "3          1  \n",
       "4          1  \n",
       "...      ...  \n",
       "5105       0  \n",
       "5106       0  \n",
       "5107       0  \n",
       "5108       0  \n",
       "5109       0  \n",
       "\n",
       "[5110 rows x 12 columns]"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "94b8efcf",
   "metadata": {},
   "outputs": [],
   "source": [
    "# delete row with NA value\n",
    "df_na = df.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "2a9df117",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_na.reset_index(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "08f9e93b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "index                False\n",
       "id                   False\n",
       "gender               False\n",
       "age                  False\n",
       "hypertension         False\n",
       "heart_disease        False\n",
       "ever_married         False\n",
       "work_type            False\n",
       "Residence_type       False\n",
       "avg_glucose_level    False\n",
       "bmi                  False\n",
       "smoking_status       False\n",
       "stroke               False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.isnull(df_na).any()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "e98c9252",
   "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>index</th>\n",
       "      <th>id</th>\n",
       "      <th>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>ever_married</th>\n",
       "      <th>work_type</th>\n",
       "      <th>Residence_type</th>\n",
       "      <th>avg_glucose_level</th>\n",
       "      <th>bmi</th>\n",
       "      <th>smoking_status</th>\n",
       "      <th>stroke</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>9046</td>\n",
       "      <td>Male</td>\n",
       "      <td>67.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Private</td>\n",
       "      <td>Urban</td>\n",
       "      <td>228.69</td>\n",
       "      <td>36.6</td>\n",
       "      <td>formerly smoked</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>31112</td>\n",
       "      <td>Male</td>\n",
       "      <td>80.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Private</td>\n",
       "      <td>Rural</td>\n",
       "      <td>105.92</td>\n",
       "      <td>32.5</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>60182</td>\n",
       "      <td>Female</td>\n",
       "      <td>49.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Private</td>\n",
       "      <td>Urban</td>\n",
       "      <td>171.23</td>\n",
       "      <td>34.4</td>\n",
       "      <td>smokes</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1665</td>\n",
       "      <td>Female</td>\n",
       "      <td>79.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Self-employed</td>\n",
       "      <td>Rural</td>\n",
       "      <td>174.12</td>\n",
       "      <td>24.0</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>56669</td>\n",
       "      <td>Male</td>\n",
       "      <td>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Private</td>\n",
       "      <td>Urban</td>\n",
       "      <td>186.21</td>\n",
       "      <td>29.0</td>\n",
       "      <td>formerly smoked</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4904</th>\n",
       "      <td>5104</td>\n",
       "      <td>14180</td>\n",
       "      <td>Female</td>\n",
       "      <td>13.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>No</td>\n",
       "      <td>children</td>\n",
       "      <td>Rural</td>\n",
       "      <td>103.08</td>\n",
       "      <td>18.6</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4905</th>\n",
       "      <td>5106</td>\n",
       "      <td>44873</td>\n",
       "      <td>Female</td>\n",
       "      <td>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Self-employed</td>\n",
       "      <td>Urban</td>\n",
       "      <td>125.20</td>\n",
       "      <td>40.0</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4906</th>\n",
       "      <td>5107</td>\n",
       "      <td>19723</td>\n",
       "      <td>Female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Self-employed</td>\n",
       "      <td>Rural</td>\n",
       "      <td>82.99</td>\n",
       "      <td>30.6</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4907</th>\n",
       "      <td>5108</td>\n",
       "      <td>37544</td>\n",
       "      <td>Male</td>\n",
       "      <td>51.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Private</td>\n",
       "      <td>Rural</td>\n",
       "      <td>166.29</td>\n",
       "      <td>25.6</td>\n",
       "      <td>formerly smoked</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4908</th>\n",
       "      <td>5109</td>\n",
       "      <td>44679</td>\n",
       "      <td>Female</td>\n",
       "      <td>44.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Govt_job</td>\n",
       "      <td>Urban</td>\n",
       "      <td>85.28</td>\n",
       "      <td>26.2</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4909 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      index     id  gender   age  hypertension  heart_disease ever_married  \\\n",
       "0         0   9046    Male  67.0             0              1          Yes   \n",
       "1         2  31112    Male  80.0             0              1          Yes   \n",
       "2         3  60182  Female  49.0             0              0          Yes   \n",
       "3         4   1665  Female  79.0             1              0          Yes   \n",
       "4         5  56669    Male  81.0             0              0          Yes   \n",
       "...     ...    ...     ...   ...           ...            ...          ...   \n",
       "4904   5104  14180  Female  13.0             0              0           No   \n",
       "4905   5106  44873  Female  81.0             0              0          Yes   \n",
       "4906   5107  19723  Female  35.0             0              0          Yes   \n",
       "4907   5108  37544    Male  51.0             0              0          Yes   \n",
       "4908   5109  44679  Female  44.0             0              0          Yes   \n",
       "\n",
       "          work_type Residence_type  avg_glucose_level   bmi   smoking_status  \\\n",
       "0           Private          Urban             228.69  36.6  formerly smoked   \n",
       "1           Private          Rural             105.92  32.5     never smoked   \n",
       "2           Private          Urban             171.23  34.4           smokes   \n",
       "3     Self-employed          Rural             174.12  24.0     never smoked   \n",
       "4           Private          Urban             186.21  29.0  formerly smoked   \n",
       "...             ...            ...                ...   ...              ...   \n",
       "4904       children          Rural             103.08  18.6          Unknown   \n",
       "4905  Self-employed          Urban             125.20  40.0     never smoked   \n",
       "4906  Self-employed          Rural              82.99  30.6     never smoked   \n",
       "4907        Private          Rural             166.29  25.6  formerly smoked   \n",
       "4908       Govt_job          Urban              85.28  26.2          Unknown   \n",
       "\n",
       "      stroke  \n",
       "0          1  \n",
       "1          1  \n",
       "2          1  \n",
       "3          1  \n",
       "4          1  \n",
       "...      ...  \n",
       "4904       0  \n",
       "4905       0  \n",
       "4906       0  \n",
       "4907       0  \n",
       "4908       0  \n",
       "\n",
       "[4909 rows x 13 columns]"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_na"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "1d98e2ff",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_na['ever_married'] = df_na.ever_married.map({'Yes':1, 'No':0})\n",
    "# For gender, 1 means Male, 0 means Female\n",
    "df_na['gender'] = df_na.gender.map({'Male':1, 'Female':0})\n",
    "# For Residence_type, 1 means Urban, 0 means Rural\n",
    "df_na['Residence_type'] = df_na.Residence_type.map({'Urban':1, 'Rural':0})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "6e0d2d5d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "index                False\n",
       "id                   False\n",
       "gender                True\n",
       "age                  False\n",
       "hypertension         False\n",
       "heart_disease        False\n",
       "ever_married         False\n",
       "work_type            False\n",
       "Residence_type       False\n",
       "avg_glucose_level    False\n",
       "bmi                  False\n",
       "smoking_status       False\n",
       "stroke               False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.isnull(df_na).any()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "17b68ae8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "index                False\n",
       "id                   False\n",
       "gender               False\n",
       "age                  False\n",
       "hypertension         False\n",
       "heart_disease        False\n",
       "ever_married         False\n",
       "work_type            False\n",
       "Residence_type       False\n",
       "avg_glucose_level    False\n",
       "bmi                  False\n",
       "smoking_status       False\n",
       "stroke               False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_na = df_na.dropna()\n",
    "df_na.reset_index(drop=True,inplace=True)\n",
    "pd.isnull(df_na).any()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "72fc2c04",
   "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>index</th>\n",
       "      <th>id</th>\n",
       "      <th>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>ever_married</th>\n",
       "      <th>work_type</th>\n",
       "      <th>Residence_type</th>\n",
       "      <th>avg_glucose_level</th>\n",
       "      <th>bmi</th>\n",
       "      <th>smoking_status</th>\n",
       "      <th>stroke</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>9046</td>\n",
       "      <td>1.0</td>\n",
       "      <td>67.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Private</td>\n",
       "      <td>1</td>\n",
       "      <td>228.69</td>\n",
       "      <td>36.6</td>\n",
       "      <td>formerly smoked</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>31112</td>\n",
       "      <td>1.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Private</td>\n",
       "      <td>0</td>\n",
       "      <td>105.92</td>\n",
       "      <td>32.5</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>60182</td>\n",
       "      <td>0.0</td>\n",
       "      <td>49.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Private</td>\n",
       "      <td>1</td>\n",
       "      <td>171.23</td>\n",
       "      <td>34.4</td>\n",
       "      <td>smokes</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1665</td>\n",
       "      <td>0.0</td>\n",
       "      <td>79.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Self-employed</td>\n",
       "      <td>0</td>\n",
       "      <td>174.12</td>\n",
       "      <td>24.0</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>56669</td>\n",
       "      <td>1.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Private</td>\n",
       "      <td>1</td>\n",
       "      <td>186.21</td>\n",
       "      <td>29.0</td>\n",
       "      <td>formerly smoked</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4903</th>\n",
       "      <td>5104</td>\n",
       "      <td>14180</td>\n",
       "      <td>0.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>children</td>\n",
       "      <td>0</td>\n",
       "      <td>103.08</td>\n",
       "      <td>18.6</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4904</th>\n",
       "      <td>5106</td>\n",
       "      <td>44873</td>\n",
       "      <td>0.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Self-employed</td>\n",
       "      <td>1</td>\n",
       "      <td>125.20</td>\n",
       "      <td>40.0</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4905</th>\n",
       "      <td>5107</td>\n",
       "      <td>19723</td>\n",
       "      <td>0.0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Self-employed</td>\n",
       "      <td>0</td>\n",
       "      <td>82.99</td>\n",
       "      <td>30.6</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4906</th>\n",
       "      <td>5108</td>\n",
       "      <td>37544</td>\n",
       "      <td>1.0</td>\n",
       "      <td>51.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Private</td>\n",
       "      <td>0</td>\n",
       "      <td>166.29</td>\n",
       "      <td>25.6</td>\n",
       "      <td>formerly smoked</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4907</th>\n",
       "      <td>5109</td>\n",
       "      <td>44679</td>\n",
       "      <td>0.0</td>\n",
       "      <td>44.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Govt_job</td>\n",
       "      <td>1</td>\n",
       "      <td>85.28</td>\n",
       "      <td>26.2</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4908 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      index     id  gender   age  hypertension  heart_disease  ever_married  \\\n",
       "0         0   9046     1.0  67.0             0              1             1   \n",
       "1         2  31112     1.0  80.0             0              1             1   \n",
       "2         3  60182     0.0  49.0             0              0             1   \n",
       "3         4   1665     0.0  79.0             1              0             1   \n",
       "4         5  56669     1.0  81.0             0              0             1   \n",
       "...     ...    ...     ...   ...           ...            ...           ...   \n",
       "4903   5104  14180     0.0  13.0             0              0             0   \n",
       "4904   5106  44873     0.0  81.0             0              0             1   \n",
       "4905   5107  19723     0.0  35.0             0              0             1   \n",
       "4906   5108  37544     1.0  51.0             0              0             1   \n",
       "4907   5109  44679     0.0  44.0             0              0             1   \n",
       "\n",
       "          work_type  Residence_type  avg_glucose_level   bmi   smoking_status  \\\n",
       "0           Private               1             228.69  36.6  formerly smoked   \n",
       "1           Private               0             105.92  32.5     never smoked   \n",
       "2           Private               1             171.23  34.4           smokes   \n",
       "3     Self-employed               0             174.12  24.0     never smoked   \n",
       "4           Private               1             186.21  29.0  formerly smoked   \n",
       "...             ...             ...                ...   ...              ...   \n",
       "4903       children               0             103.08  18.6          Unknown   \n",
       "4904  Self-employed               1             125.20  40.0     never smoked   \n",
       "4905  Self-employed               0              82.99  30.6     never smoked   \n",
       "4906        Private               0             166.29  25.6  formerly smoked   \n",
       "4907       Govt_job               1              85.28  26.2          Unknown   \n",
       "\n",
       "      stroke  \n",
       "0          1  \n",
       "1          1  \n",
       "2          1  \n",
       "3          1  \n",
       "4          1  \n",
       "...      ...  \n",
       "4903       0  \n",
       "4904       0  \n",
       "4905       0  \n",
       "4906       0  \n",
       "4907       0  \n",
       "\n",
       "[4908 rows x 13 columns]"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_na"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "101c6e10",
   "metadata": {},
   "outputs": [],
   "source": [
    "def AGE_check(x):\n",
    "    if x >= 45:\n",
    "        return 1\n",
    "    else:\n",
    "        return 0\n",
    "    \n",
    "df_na['treatment_age'] = df_na.age.apply(AGE_check)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "d12286e7",
   "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>gender</th>\n",
       "      <th>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>ever_married</th>\n",
       "      <th>work_type</th>\n",
       "      <th>Residence_type</th>\n",
       "      <th>avg_glucose_level</th>\n",
       "      <th>bmi</th>\n",
       "      <th>smoking_status</th>\n",
       "      <th>stroke</th>\n",
       "      <th>treatment_age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Private</td>\n",
       "      <td>1</td>\n",
       "      <td>228.69</td>\n",
       "      <td>36.6</td>\n",
       "      <td>formerly smoked</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Private</td>\n",
       "      <td>0</td>\n",
       "      <td>105.92</td>\n",
       "      <td>32.5</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Private</td>\n",
       "      <td>1</td>\n",
       "      <td>171.23</td>\n",
       "      <td>34.4</td>\n",
       "      <td>smokes</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Self-employed</td>\n",
       "      <td>0</td>\n",
       "      <td>174.12</td>\n",
       "      <td>24.0</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Private</td>\n",
       "      <td>1</td>\n",
       "      <td>186.21</td>\n",
       "      <td>29.0</td>\n",
       "      <td>formerly smoked</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4903</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>children</td>\n",
       "      <td>0</td>\n",
       "      <td>103.08</td>\n",
       "      <td>18.6</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4904</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Self-employed</td>\n",
       "      <td>1</td>\n",
       "      <td>125.20</td>\n",
       "      <td>40.0</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4905</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Self-employed</td>\n",
       "      <td>0</td>\n",
       "      <td>82.99</td>\n",
       "      <td>30.6</td>\n",
       "      <td>never smoked</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4906</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Private</td>\n",
       "      <td>0</td>\n",
       "      <td>166.29</td>\n",
       "      <td>25.6</td>\n",
       "      <td>formerly smoked</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4907</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Govt_job</td>\n",
       "      <td>1</td>\n",
       "      <td>85.28</td>\n",
       "      <td>26.2</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4908 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      gender  hypertension  heart_disease  ever_married      work_type  \\\n",
       "0        1.0             0              1             1        Private   \n",
       "1        1.0             0              1             1        Private   \n",
       "2        0.0             0              0             1        Private   \n",
       "3        0.0             1              0             1  Self-employed   \n",
       "4        1.0             0              0             1        Private   \n",
       "...      ...           ...            ...           ...            ...   \n",
       "4903     0.0             0              0             0       children   \n",
       "4904     0.0             0              0             1  Self-employed   \n",
       "4905     0.0             0              0             1  Self-employed   \n",
       "4906     1.0             0              0             1        Private   \n",
       "4907     0.0             0              0             1       Govt_job   \n",
       "\n",
       "      Residence_type  avg_glucose_level   bmi   smoking_status  stroke  \\\n",
       "0                  1             228.69  36.6  formerly smoked       1   \n",
       "1                  0             105.92  32.5     never smoked       1   \n",
       "2                  1             171.23  34.4           smokes       1   \n",
       "3                  0             174.12  24.0     never smoked       1   \n",
       "4                  1             186.21  29.0  formerly smoked       1   \n",
       "...              ...                ...   ...              ...     ...   \n",
       "4903               0             103.08  18.6          Unknown       0   \n",
       "4904               1             125.20  40.0     never smoked       0   \n",
       "4905               0              82.99  30.6     never smoked       0   \n",
       "4906               0             166.29  25.6  formerly smoked       0   \n",
       "4907               1              85.28  26.2          Unknown       0   \n",
       "\n",
       "      treatment_age  \n",
       "0                 1  \n",
       "1                 1  \n",
       "2                 1  \n",
       "3                 1  \n",
       "4                 1  \n",
       "...             ...  \n",
       "4903              0  \n",
       "4904              1  \n",
       "4905              0  \n",
       "4906              1  \n",
       "4907              0  \n",
       "\n",
       "[4908 rows x 11 columns]"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_data = df_na.drop(columns = ['index','id','age'])\n",
    "df_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "c98550f9",
   "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>gender</th>\n",
       "      <th>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>ever_married</th>\n",
       "      <th>Residence_type</th>\n",
       "      <th>avg_glucose_level</th>\n",
       "      <th>bmi</th>\n",
       "      <th>stroke</th>\n",
       "      <th>treatment_age</th>\n",
       "      <th>work_type_Govt_job</th>\n",
       "      <th>work_type_Never_worked</th>\n",
       "      <th>work_type_Private</th>\n",
       "      <th>work_type_Self-employed</th>\n",
       "      <th>work_type_children</th>\n",
       "      <th>smoking_status_Unknown</th>\n",
       "      <th>smoking_status_formerly smoked</th>\n",
       "      <th>smoking_status_never smoked</th>\n",
       "      <th>smoking_status_smokes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>228.69</td>\n",
       "      <td>36.6</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>105.92</td>\n",
       "      <td>32.5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>171.23</td>\n",
       "      <td>34.4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>174.12</td>\n",
       "      <td>24.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>186.21</td>\n",
       "      <td>29.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4903</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>103.08</td>\n",
       "      <td>18.6</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4904</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>125.20</td>\n",
       "      <td>40.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4905</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>82.99</td>\n",
       "      <td>30.6</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4906</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>166.29</td>\n",
       "      <td>25.6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4907</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>85.28</td>\n",
       "      <td>26.2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4908 rows × 18 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      gender  hypertension  heart_disease  ever_married  Residence_type  \\\n",
       "0        1.0             0              1             1               1   \n",
       "1        1.0             0              1             1               0   \n",
       "2        0.0             0              0             1               1   \n",
       "3        0.0             1              0             1               0   \n",
       "4        1.0             0              0             1               1   \n",
       "...      ...           ...            ...           ...             ...   \n",
       "4903     0.0             0              0             0               0   \n",
       "4904     0.0             0              0             1               1   \n",
       "4905     0.0             0              0             1               0   \n",
       "4906     1.0             0              0             1               0   \n",
       "4907     0.0             0              0             1               1   \n",
       "\n",
       "      avg_glucose_level   bmi  stroke  treatment_age  work_type_Govt_job  \\\n",
       "0                228.69  36.6       1              1                   0   \n",
       "1                105.92  32.5       1              1                   0   \n",
       "2                171.23  34.4       1              1                   0   \n",
       "3                174.12  24.0       1              1                   0   \n",
       "4                186.21  29.0       1              1                   0   \n",
       "...                 ...   ...     ...            ...                 ...   \n",
       "4903             103.08  18.6       0              0                   0   \n",
       "4904             125.20  40.0       0              1                   0   \n",
       "4905              82.99  30.6       0              0                   0   \n",
       "4906             166.29  25.6       0              1                   0   \n",
       "4907              85.28  26.2       0              0                   1   \n",
       "\n",
       "      work_type_Never_worked  work_type_Private  work_type_Self-employed  \\\n",
       "0                          0                  1                        0   \n",
       "1                          0                  1                        0   \n",
       "2                          0                  1                        0   \n",
       "3                          0                  0                        1   \n",
       "4                          0                  1                        0   \n",
       "...                      ...                ...                      ...   \n",
       "4903                       0                  0                        0   \n",
       "4904                       0                  0                        1   \n",
       "4905                       0                  0                        1   \n",
       "4906                       0                  1                        0   \n",
       "4907                       0                  0                        0   \n",
       "\n",
       "      work_type_children  smoking_status_Unknown  \\\n",
       "0                      0                       0   \n",
       "1                      0                       0   \n",
       "2                      0                       0   \n",
       "3                      0                       0   \n",
       "4                      0                       0   \n",
       "...                  ...                     ...   \n",
       "4903                   1                       1   \n",
       "4904                   0                       0   \n",
       "4905                   0                       0   \n",
       "4906                   0                       0   \n",
       "4907                   0                       1   \n",
       "\n",
       "      smoking_status_formerly smoked  smoking_status_never smoked  \\\n",
       "0                                  1                            0   \n",
       "1                                  0                            1   \n",
       "2                                  0                            0   \n",
       "3                                  0                            1   \n",
       "4                                  1                            0   \n",
       "...                              ...                          ...   \n",
       "4903                               0                            0   \n",
       "4904                               0                            1   \n",
       "4905                               0                            1   \n",
       "4906                               1                            0   \n",
       "4907                               0                            0   \n",
       "\n",
       "      smoking_status_smokes  \n",
       "0                         0  \n",
       "1                         0  \n",
       "2                         1  \n",
       "3                         0  \n",
       "4                         0  \n",
       "...                     ...  \n",
       "4903                      0  \n",
       "4904                      0  \n",
       "4905                      0  \n",
       "4906                      0  \n",
       "4907                      0  \n",
       "\n",
       "[4908 rows x 18 columns]"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_encoded = pd.get_dummies(df_data, columns = ['work_type','smoking_status'], \\\n",
    "                           prefix = {'work_type':'work_type', 'smoking_status' : 'smoking_status'}, drop_first=False)\n",
    "df_encoded"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "6e2aeb5d",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_treatment = df_encoded[df_encoded['treatment_age']==1]\n",
    "df_control = df_encoded[df_encoded['treatment_age']==0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "2737d4f9",
   "metadata": {},
   "outputs": [],
   "source": [
    "treat_mean = df_treatment.mean()\n",
    "treat_std = df_treatment.std()\n",
    "control_mean = df_control.mean()\n",
    "control_std = df_control.std()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "d91abdfb",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_list = ['gender','hypertension','heart_disease','ever_married','Residence_type','avg_glucose_level','bmi','work_type_Govt_job',\n",
    "          'work_type_Never_worked','work_type_Private','work_type_Self-employed','work_type_children','smoking_status_Unknown',\n",
    "          'smoking_status_formerly smoked','smoking_status_never smoked','smoking_status_smokes']\n",
    "X_descrip = ['0 to Female and 1 to Male','observation of hypertension','observation of heart_disease',\n",
    "             'Marriage states','0 to Rural and 1 to Urban','average glucose level','bmi','Whether is government job',\n",
    "             'Whether is never worked','Whether job is private','Whether job is self-employed','Whether job is children',\n",
    "             'Whether smoking status is unknown','Whether is formerly smoked','Whether is never smoked','Whether is smokes']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "5ad18a81",
   "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>Label</th>\n",
       "      <th>Variable Description</th>\n",
       "      <th>Controls Mean</th>\n",
       "      <th>Controls STD</th>\n",
       "      <th>Treated Mean</th>\n",
       "      <th>Treated STD</th>\n",
       "      <th>t-Statistics</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>gender</td>\n",
       "      <td>0 to Female and 1 to Male</td>\n",
       "      <td>0.403815</td>\n",
       "      <td>0.490761</td>\n",
       "      <td>0.415712</td>\n",
       "      <td>0.492945</td>\n",
       "      <td>-0.847259</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>hypertension</td>\n",
       "      <td>observation of hypertension</td>\n",
       "      <td>0.019886</td>\n",
       "      <td>0.139638</td>\n",
       "      <td>0.164484</td>\n",
       "      <td>0.370790</td>\n",
       "      <td>-18.051112</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>heart_disease</td>\n",
       "      <td>observation of heart_disease</td>\n",
       "      <td>0.002435</td>\n",
       "      <td>0.049296</td>\n",
       "      <td>0.096972</td>\n",
       "      <td>0.295980</td>\n",
       "      <td>-15.577435</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ever_married</td>\n",
       "      <td>Marriage states</td>\n",
       "      <td>0.385552</td>\n",
       "      <td>0.486824</td>\n",
       "      <td>0.922259</td>\n",
       "      <td>0.267819</td>\n",
       "      <td>-47.902598</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Residence_type</td>\n",
       "      <td>0 to Rural and 1 to Urban</td>\n",
       "      <td>0.497565</td>\n",
       "      <td>0.500096</td>\n",
       "      <td>0.517185</td>\n",
       "      <td>0.499807</td>\n",
       "      <td>-1.374646</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>avg_glucose_level</td>\n",
       "      <td>average glucose level</td>\n",
       "      <td>95.613389</td>\n",
       "      <td>30.794491</td>\n",
       "      <td>115.060663</td>\n",
       "      <td>53.086851</td>\n",
       "      <td>-15.681360</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>bmi</td>\n",
       "      <td>bmi</td>\n",
       "      <td>27.026177</td>\n",
       "      <td>8.367229</td>\n",
       "      <td>30.778232</td>\n",
       "      <td>6.801232</td>\n",
       "      <td>-17.244675</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>work_type_Govt_job</td>\n",
       "      <td>Whether is government job</td>\n",
       "      <td>0.090503</td>\n",
       "      <td>0.286960</td>\n",
       "      <td>0.166530</td>\n",
       "      <td>0.372632</td>\n",
       "      <td>-8.003549</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>work_type_Never_worked</td>\n",
       "      <td>Whether is never worked</td>\n",
       "      <td>0.008929</td>\n",
       "      <td>0.094087</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>4.710540</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>work_type_Private</td>\n",
       "      <td>Whether job is private</td>\n",
       "      <td>0.566558</td>\n",
       "      <td>0.495651</td>\n",
       "      <td>0.578560</td>\n",
       "      <td>0.493891</td>\n",
       "      <td>-0.849660</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>work_type_Self-employed</td>\n",
       "      <td>Whether job is self-employed</td>\n",
       "      <td>0.061688</td>\n",
       "      <td>0.240637</td>\n",
       "      <td>0.254910</td>\n",
       "      <td>0.435900</td>\n",
       "      <td>-19.202913</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>work_type_children</td>\n",
       "      <td>Whether job is children</td>\n",
       "      <td>0.272321</td>\n",
       "      <td>0.445245</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>30.360109</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>smoking_status_Unknown</td>\n",
       "      <td>Whether smoking status is unknown</td>\n",
       "      <td>0.419237</td>\n",
       "      <td>0.493534</td>\n",
       "      <td>0.184124</td>\n",
       "      <td>0.387665</td>\n",
       "      <td>18.567278</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>smoking_status_formerly smoked</td>\n",
       "      <td>Whether is formerly smoked</td>\n",
       "      <td>0.092127</td>\n",
       "      <td>0.289263</td>\n",
       "      <td>0.249182</td>\n",
       "      <td>0.432628</td>\n",
       "      <td>-14.937960</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>smoking_status_never smoked</td>\n",
       "      <td>Whether is never smoked</td>\n",
       "      <td>0.355114</td>\n",
       "      <td>0.478645</td>\n",
       "      <td>0.399755</td>\n",
       "      <td>0.489948</td>\n",
       "      <td>-3.228418</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>smoking_status_smokes</td>\n",
       "      <td>Whether is smokes</td>\n",
       "      <td>0.133523</td>\n",
       "      <td>0.340208</td>\n",
       "      <td>0.166939</td>\n",
       "      <td>0.372998</td>\n",
       "      <td>-3.278369</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                             Label               Variable Description  \\\n",
       "0                           gender          0 to Female and 1 to Male   \n",
       "1                     hypertension        observation of hypertension   \n",
       "2                    heart_disease       observation of heart_disease   \n",
       "3                     ever_married                    Marriage states   \n",
       "4                   Residence_type          0 to Rural and 1 to Urban   \n",
       "5                avg_glucose_level              average glucose level   \n",
       "6                              bmi                                bmi   \n",
       "7               work_type_Govt_job          Whether is government job   \n",
       "8           work_type_Never_worked            Whether is never worked   \n",
       "9                work_type_Private             Whether job is private   \n",
       "10         work_type_Self-employed       Whether job is self-employed   \n",
       "11              work_type_children            Whether job is children   \n",
       "12          smoking_status_Unknown  Whether smoking status is unknown   \n",
       "13  smoking_status_formerly smoked         Whether is formerly smoked   \n",
       "14     smoking_status_never smoked            Whether is never smoked   \n",
       "15           smoking_status_smokes                  Whether is smokes   \n",
       "\n",
       "    Controls Mean  Controls STD  Treated Mean  Treated STD  t-Statistics  \n",
       "0        0.403815      0.490761      0.415712     0.492945     -0.847259  \n",
       "1        0.019886      0.139638      0.164484     0.370790    -18.051112  \n",
       "2        0.002435      0.049296      0.096972     0.295980    -15.577435  \n",
       "3        0.385552      0.486824      0.922259     0.267819    -47.902598  \n",
       "4        0.497565      0.500096      0.517185     0.499807     -1.374646  \n",
       "5       95.613389     30.794491    115.060663    53.086851    -15.681360  \n",
       "6       27.026177      8.367229     30.778232     6.801232    -17.244675  \n",
       "7        0.090503      0.286960      0.166530     0.372632     -8.003549  \n",
       "8        0.008929      0.094087      0.000000     0.000000      4.710540  \n",
       "9        0.566558      0.495651      0.578560     0.493891     -0.849660  \n",
       "10       0.061688      0.240637      0.254910     0.435900    -19.202913  \n",
       "11       0.272321      0.445245      0.000000     0.000000     30.360109  \n",
       "12       0.419237      0.493534      0.184124     0.387665     18.567278  \n",
       "13       0.092127      0.289263      0.249182     0.432628    -14.937960  \n",
       "14       0.355114      0.478645      0.399755     0.489948     -3.228418  \n",
       "15       0.133523      0.340208      0.166939     0.372998     -3.278369  "
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "summary_list = []\n",
    "\n",
    "for i in range(0, len(X_list)):\n",
    "    summary_list.append([X_list[i],X_descrip[i],control_mean[X_list[i]],control_std[X_list[i]],treat_mean[X_list[i]],treat_std[X_list[i]],\n",
    "                    stats.ttest_ind(df_control[X_list[i]], df_treatment[X_list[i]], equal_var=False)[0]])\n",
    "\n",
    "summary_df = pd.DataFrame(summary_list,columns=\n",
    "                          ['Label', 'Variable Description','Controls Mean','Controls STD','Treated Mean','Treated STD','t-Statistics'])\n",
    "summary_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "896f9d1f",
   "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>gender</th>\n",
       "      <th>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>ever_married</th>\n",
       "      <th>Residence_type</th>\n",
       "      <th>avg_glucose_level</th>\n",
       "      <th>bmi</th>\n",
       "      <th>stroke</th>\n",
       "      <th>treatment_age</th>\n",
       "      <th>work_type_Govt_job</th>\n",
       "      <th>work_type_Never_worked</th>\n",
       "      <th>work_type_Private</th>\n",
       "      <th>work_type_Self-employed</th>\n",
       "      <th>work_type_children</th>\n",
       "      <th>smoking_status_Unknown</th>\n",
       "      <th>smoking_status_formerly smoked</th>\n",
       "      <th>smoking_status_never smoked</th>\n",
       "      <th>smoking_status_smokes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>228.69</td>\n",
       "      <td>36.6</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>105.92</td>\n",
       "      <td>32.5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>171.23</td>\n",
       "      <td>34.4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>174.12</td>\n",
       "      <td>24.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>186.21</td>\n",
       "      <td>29.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4903</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>103.08</td>\n",
       "      <td>18.6</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4904</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>125.20</td>\n",
       "      <td>40.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4905</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>82.99</td>\n",
       "      <td>30.6</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4906</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>166.29</td>\n",
       "      <td>25.6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4907</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>85.28</td>\n",
       "      <td>26.2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4908 rows × 18 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      gender  hypertension  heart_disease  ever_married  Residence_type  \\\n",
       "0        1.0             0              1             1               1   \n",
       "1        1.0             0              1             1               0   \n",
       "2        0.0             0              0             1               1   \n",
       "3        0.0             1              0             1               0   \n",
       "4        1.0             0              0             1               1   \n",
       "...      ...           ...            ...           ...             ...   \n",
       "4903     0.0             0              0             0               0   \n",
       "4904     0.0             0              0             1               1   \n",
       "4905     0.0             0              0             1               0   \n",
       "4906     1.0             0              0             1               0   \n",
       "4907     0.0             0              0             1               1   \n",
       "\n",
       "      avg_glucose_level   bmi  stroke  treatment_age  work_type_Govt_job  \\\n",
       "0                228.69  36.6       1              1                   0   \n",
       "1                105.92  32.5       1              1                   0   \n",
       "2                171.23  34.4       1              1                   0   \n",
       "3                174.12  24.0       1              1                   0   \n",
       "4                186.21  29.0       1              1                   0   \n",
       "...                 ...   ...     ...            ...                 ...   \n",
       "4903             103.08  18.6       0              0                   0   \n",
       "4904             125.20  40.0       0              1                   0   \n",
       "4905              82.99  30.6       0              0                   0   \n",
       "4906             166.29  25.6       0              1                   0   \n",
       "4907              85.28  26.2       0              0                   1   \n",
       "\n",
       "      work_type_Never_worked  work_type_Private  work_type_Self-employed  \\\n",
       "0                          0                  1                        0   \n",
       "1                          0                  1                        0   \n",
       "2                          0                  1                        0   \n",
       "3                          0                  0                        1   \n",
       "4                          0                  1                        0   \n",
       "...                      ...                ...                      ...   \n",
       "4903                       0                  0                        0   \n",
       "4904                       0                  0                        1   \n",
       "4905                       0                  0                        1   \n",
       "4906                       0                  1                        0   \n",
       "4907                       0                  0                        0   \n",
       "\n",
       "      work_type_children  smoking_status_Unknown  \\\n",
       "0                      0                       0   \n",
       "1                      0                       0   \n",
       "2                      0                       0   \n",
       "3                      0                       0   \n",
       "4                      0                       0   \n",
       "...                  ...                     ...   \n",
       "4903                   1                       1   \n",
       "4904                   0                       0   \n",
       "4905                   0                       0   \n",
       "4906                   0                       0   \n",
       "4907                   0                       1   \n",
       "\n",
       "      smoking_status_formerly smoked  smoking_status_never smoked  \\\n",
       "0                                  1                            0   \n",
       "1                                  0                            1   \n",
       "2                                  0                            0   \n",
       "3                                  0                            1   \n",
       "4                                  1                            0   \n",
       "...                              ...                          ...   \n",
       "4903                               0                            0   \n",
       "4904                               0                            1   \n",
       "4905                               0                            1   \n",
       "4906                               1                            0   \n",
       "4907                               0                            0   \n",
       "\n",
       "      smoking_status_smokes  \n",
       "0                         0  \n",
       "1                         0  \n",
       "2                         1  \n",
       "3                         0  \n",
       "4                         0  \n",
       "...                     ...  \n",
       "4903                      0  \n",
       "4904                      0  \n",
       "4905                      0  \n",
       "4906                      0  \n",
       "4907                      0  \n",
       "\n",
       "[4908 rows x 18 columns]"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = df_encoded\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "6dafa01c",
   "metadata": {},
   "outputs": [],
   "source": [
    "Y = df.stroke\n",
    "\n",
    "df_data = df.loc[:,df.columns !='stroke']\n",
    "T = df_data.treatment_age\n",
    "X = df_data.loc[:,df_data.columns !='treatment_age']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "7760098d",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_a = ['hypertension','heart_disease','avg_glucose_level','bmi']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "14702273",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.4979625101874491"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "T.mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "id": "acbd2a21",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.6483\n",
      "\n",
      "Confusion matrix:\n",
      "[[1053 1411]\n",
      " [ 315 2129]]\n",
      "\n",
      "F1 score is: 0.7116\n"
     ]
    }
   ],
   "source": [
    "# weighted based on size ratio of treatment group and control group\n",
    "model_initial = Pipeline([('scaler', StandardScaler()),('logistic_classifier', lr(class_weight={0:1,1:1.8}))])\n",
    "model_initial.fit(X.loc[:,X_a], T)\n",
    "\n",
    "predictions_binary = model_initial.predict(X.loc[:,X_a])\n",
    "print('Accuracy: {:.4f}\\n'.format(metrics.accuracy_score(T, predictions_binary)))\n",
    "print('Confusion matrix:\\n{}\\n'.format(metrics.confusion_matrix(T, predictions_binary)))\n",
    "print('F1 score is: {:.4f}'.format(metrics.f1_score(T, predictions_binary)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "6e222b8b",
   "metadata": {},
   "outputs": [],
   "source": [
    "likelihood_ratio_table = []\n",
    "X_l = X_a.copy()\n",
    "\n",
    "while not likelihood_ratio_table or max([x for x in likelihood_ratio_table[-1].values() if x != '-']) >= 1:\n",
    "    if likelihood_ratio_table:\n",
    "        max_likelihood_ratio = max([x for x in likelihood_ratio_table[-1].values() if x != '-'])\n",
    "        next_label = [key for key in likelihood_ratio_table[-1] if likelihood_ratio_table[-1][key] == max_likelihood_ratio][0]\n",
    "        X_l.append(next_label)\n",
    "    model = Pipeline([('scaler', StandardScaler()),('logistic_classifier', lr(class_weight={0:1,1:1.8}))])\n",
    "    model.fit(X.loc[:,X_l], T)\n",
    "    step = {}\n",
    "    for x in X.columns:\n",
    "        if x in X_l:\n",
    "            step[x] = '-'\n",
    "        else:\n",
    "            X_new = X_l.copy()\n",
    "            X_new.append(x)\n",
    "            model_new = Pipeline([('scaler', StandardScaler()),('logistic_classifier', lr(class_weight={0:1,1:1.8}))])\n",
    "            model_new.fit(X.loc[:,X_new], T)\n",
    "            \n",
    "            step[x] = -2*((-metrics.log_loss(T, model.predict_proba(X.loc[:,X_l]))*len(T))\n",
    "                      -(-metrics.log_loss(T, model_new.predict_proba(X.loc[:,X_new]))*len(T)))\n",
    "    likelihood_ratio_table.append(step)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "dc25557f",
   "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>Label</th>\n",
       "      <th>Step 1</th>\n",
       "      <th>Step 2</th>\n",
       "      <th>Step 3</th>\n",
       "      <th>Step 4</th>\n",
       "      <th>Step 5</th>\n",
       "      <th>Step 6</th>\n",
       "      <th>Step 7</th>\n",
       "      <th>Step 8</th>\n",
       "      <th>Step 9</th>\n",
       "      <th>Step 10</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>gender</td>\n",
       "      <td>0.426998</td>\n",
       "      <td>1.399362</td>\n",
       "      <td>3.895933</td>\n",
       "      <td>5.558384</td>\n",
       "      <td>4.212808</td>\n",
       "      <td>4.370331</td>\n",
       "      <td>4.516161</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>hypertension</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>2</th>\n",
       "      <td>heart_disease</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>3</th>\n",
       "      <td>ever_married</td>\n",
       "      <td>1371.404411</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>4</th>\n",
       "      <td>Residence_type</td>\n",
       "      <td>2.87283</td>\n",
       "      <td>2.67131</td>\n",
       "      <td>2.708461</td>\n",
       "      <td>2.15928</td>\n",
       "      <td>2.471772</td>\n",
       "      <td>2.229507</td>\n",
       "      <td>2.337096</td>\n",
       "      <td>2.382211</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>avg_glucose_level</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>6</th>\n",
       "      <td>bmi</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>7</th>\n",
       "      <td>work_type_Govt_job</td>\n",
       "      <td>52.248799</td>\n",
       "      <td>8.963068</td>\n",
       "      <td>5.294081</td>\n",
       "      <td>20.801019</td>\n",
       "      <td>20.456227</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>work_type_Never_worked</td>\n",
       "      <td>24.194315</td>\n",
       "      <td>4.398252</td>\n",
       "      <td>7.760698</td>\n",
       "      <td>6.658812</td>\n",
       "      <td>6.094552</td>\n",
       "      <td>5.719204</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>work_type_Private</td>\n",
       "      <td>4.211225</td>\n",
       "      <td>43.742427</td>\n",
       "      <td>110.161818</td>\n",
       "      <td>17.689519</td>\n",
       "      <td>17.578046</td>\n",
       "      <td>5.133531</td>\n",
       "      <td>0.107287</td>\n",
       "      <td>0.122075</td>\n",
       "      <td>0.13468</td>\n",
       "      <td>0.166491</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>work_type_Self-employed</td>\n",
       "      <td>285.085128</td>\n",
       "      <td>151.916279</td>\n",
       "      <td>130.006746</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>11</th>\n",
       "      <td>work_type_children</td>\n",
       "      <td>718.311425</td>\n",
       "      <td>173.797997</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>12</th>\n",
       "      <td>smoking_status_Unknown</td>\n",
       "      <td>150.803763</td>\n",
       "      <td>14.116796</td>\n",
       "      <td>0.371167</td>\n",
       "      <td>0.137026</td>\n",
       "      <td>2.07055</td>\n",
       "      <td>2.233903</td>\n",
       "      <td>2.292349</td>\n",
       "      <td>2.127247</td>\n",
       "      <td>2.155724</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>smoking_status_formerly smoked</td>\n",
       "      <td>161.259622</td>\n",
       "      <td>72.177894</td>\n",
       "      <td>60.643752</td>\n",
       "      <td>52.731336</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>14</th>\n",
       "      <td>smoking_status_never smoked</td>\n",
       "      <td>0.683427</td>\n",
       "      <td>2.919084</td>\n",
       "      <td>12.090347</td>\n",
       "      <td>12.268279</td>\n",
       "      <td>0.343682</td>\n",
       "      <td>0.432973</td>\n",
       "      <td>0.398158</td>\n",
       "      <td>0.266571</td>\n",
       "      <td>0.21974</td>\n",
       "      <td>0.302054</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>smoking_status_smokes</td>\n",
       "      <td>1.077049</td>\n",
       "      <td>3.792116</td>\n",
       "      <td>7.773212</td>\n",
       "      <td>5.807484</td>\n",
       "      <td>0.666031</td>\n",
       "      <td>0.619041</td>\n",
       "      <td>0.717424</td>\n",
       "      <td>0.874988</td>\n",
       "      <td>0.982649</td>\n",
       "      <td>0.307767</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                             Label       Step 1      Step 2      Step 3  \\\n",
       "0                           gender     0.426998    1.399362    3.895933   \n",
       "1                     hypertension            -           -           -   \n",
       "2                    heart_disease            -           -           -   \n",
       "3                     ever_married  1371.404411           -           -   \n",
       "4                   Residence_type      2.87283     2.67131    2.708461   \n",
       "5                avg_glucose_level            -           -           -   \n",
       "6                              bmi            -           -           -   \n",
       "7               work_type_Govt_job    52.248799    8.963068    5.294081   \n",
       "8           work_type_Never_worked    24.194315    4.398252    7.760698   \n",
       "9                work_type_Private     4.211225   43.742427  110.161818   \n",
       "10         work_type_Self-employed   285.085128  151.916279  130.006746   \n",
       "11              work_type_children   718.311425  173.797997           -   \n",
       "12          smoking_status_Unknown   150.803763   14.116796    0.371167   \n",
       "13  smoking_status_formerly smoked   161.259622   72.177894   60.643752   \n",
       "14     smoking_status_never smoked     0.683427    2.919084   12.090347   \n",
       "15           smoking_status_smokes     1.077049    3.792116    7.773212   \n",
       "\n",
       "       Step 4     Step 5    Step 6    Step 7    Step 8    Step 9   Step 10  \n",
       "0    5.558384   4.212808  4.370331  4.516161         -         -         -  \n",
       "1           -          -         -         -         -         -         -  \n",
       "2           -          -         -         -         -         -         -  \n",
       "3           -          -         -         -         -         -         -  \n",
       "4     2.15928   2.471772  2.229507  2.337096  2.382211         -         -  \n",
       "5           -          -         -         -         -         -         -  \n",
       "6           -          -         -         -         -         -         -  \n",
       "7   20.801019  20.456227         -         -         -         -         -  \n",
       "8    6.658812   6.094552  5.719204         -         -         -         -  \n",
       "9   17.689519  17.578046  5.133531  0.107287  0.122075   0.13468  0.166491  \n",
       "10          -          -         -         -         -         -         -  \n",
       "11          -          -         -         -         -         -         -  \n",
       "12   0.137026    2.07055  2.233903  2.292349  2.127247  2.155724         -  \n",
       "13  52.731336          -         -         -         -         -         -  \n",
       "14  12.268279   0.343682  0.432973  0.398158  0.266571   0.21974  0.302054  \n",
       "15   5.807484   0.666031  0.619041  0.717424  0.874988  0.982649  0.307767  "
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "linear_terms_list = []\n",
    "for x in X.columns:\n",
    "    row = [step[x] for step in likelihood_ratio_table]\n",
    "    row.insert(0, x)\n",
    "    linear_terms_list.append(row)\n",
    "    \n",
    "columns = ['Label']\n",
    "for i in range(0,len(likelihood_ratio_table)):\n",
    "    step = 'Step ' + str(i+1)\n",
    "    columns.append(step)\n",
    "    \n",
    "linear_terms_df = pd.DataFrame(linear_terms_list,columns = columns)\n",
    "linear_terms_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "efebc2f5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['hypertension',\n",
       " 'heart_disease',\n",
       " 'avg_glucose_level',\n",
       " 'bmi',\n",
       " 'ever_married',\n",
       " 'work_type_children',\n",
       " 'work_type_Self-employed',\n",
       " 'smoking_status_formerly smoked',\n",
       " 'work_type_Govt_job',\n",
       " 'work_type_Never_worked',\n",
       " 'gender',\n",
       " 'Residence_type',\n",
       " 'smoking_status_Unknown']"
      ]
     },
     "execution_count": 81,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_l"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "ae7c4190",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.7765\n",
      "\n",
      "Confusion matrix:\n",
      "[[1490  974]\n",
      " [ 123 2321]]\n",
      "\n",
      "F1 score is: 0.8089\n"
     ]
    }
   ],
   "source": [
    "model_linear = Pipeline([('scaler', StandardScaler()),('logistic_classifier', lr(class_weight={0:1,1:1.8}))])\n",
    "model_linear.fit(X.loc[:,X_l], T)\n",
    "\n",
    "predictions_binary = model_linear.predict(X.loc[:,X_l])\n",
    "print('Accuracy: {:.4f}\\n'.format(metrics.accuracy_score(T, predictions_binary)))\n",
    "print('Confusion matrix:\\n{}\\n'.format(metrics.confusion_matrix(T, predictions_binary)))\n",
    "print('F1 score is: {:.4f}'.format(metrics.f1_score(T, predictions_binary)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "c2317969",
   "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>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>avg_glucose_level</th>\n",
       "      <th>bmi</th>\n",
       "      <th>ever_married</th>\n",
       "      <th>work_type_children</th>\n",
       "      <th>work_type_Self-employed</th>\n",
       "      <th>smoking_status_formerly smoked</th>\n",
       "      <th>work_type_Govt_job</th>\n",
       "      <th>work_type_Never_worked</th>\n",
       "      <th>...</th>\n",
       "      <th>work_type_Never_worked*work_type_Never_worked</th>\n",
       "      <th>work_type_Never_worked*gender</th>\n",
       "      <th>work_type_Never_worked*Residence_type</th>\n",
       "      <th>work_type_Never_worked*smoking_status_Unknown</th>\n",
       "      <th>gender*gender</th>\n",
       "      <th>gender*Residence_type</th>\n",
       "      <th>gender*smoking_status_Unknown</th>\n",
       "      <th>Residence_type*Residence_type</th>\n",
       "      <th>Residence_type*smoking_status_Unknown</th>\n",
       "      <th>smoking_status_Unknown*smoking_status_Unknown</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>228.69</td>\n",
       "      <td>36.6</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>105.92</td>\n",
       "      <td>32.5</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>171.23</td>\n",
       "      <td>34.4</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>174.12</td>\n",
       "      <td>24.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>186.21</td>\n",
       "      <td>29.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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>4903</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>103.08</td>\n",
       "      <td>18.6</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4904</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>125.20</td>\n",
       "      <td>40.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4905</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>82.99</td>\n",
       "      <td>30.6</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4906</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>166.29</td>\n",
       "      <td>25.6</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4907</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>85.28</td>\n",
       "      <td>26.2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4908 rows × 104 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      hypertension  heart_disease  avg_glucose_level   bmi  ever_married  \\\n",
       "0                0              1             228.69  36.6             1   \n",
       "1                0              1             105.92  32.5             1   \n",
       "2                0              0             171.23  34.4             1   \n",
       "3                1              0             174.12  24.0             1   \n",
       "4                0              0             186.21  29.0             1   \n",
       "...            ...            ...                ...   ...           ...   \n",
       "4903             0              0             103.08  18.6             0   \n",
       "4904             0              0             125.20  40.0             1   \n",
       "4905             0              0              82.99  30.6             1   \n",
       "4906             0              0             166.29  25.6             1   \n",
       "4907             0              0              85.28  26.2             1   \n",
       "\n",
       "      work_type_children  work_type_Self-employed  \\\n",
       "0                      0                        0   \n",
       "1                      0                        0   \n",
       "2                      0                        0   \n",
       "3                      0                        1   \n",
       "4                      0                        0   \n",
       "...                  ...                      ...   \n",
       "4903                   1                        0   \n",
       "4904                   0                        1   \n",
       "4905                   0                        1   \n",
       "4906                   0                        0   \n",
       "4907                   0                        0   \n",
       "\n",
       "      smoking_status_formerly smoked  work_type_Govt_job  \\\n",
       "0                                  1                   0   \n",
       "1                                  0                   0   \n",
       "2                                  0                   0   \n",
       "3                                  0                   0   \n",
       "4                                  1                   0   \n",
       "...                              ...                 ...   \n",
       "4903                               0                   0   \n",
       "4904                               0                   0   \n",
       "4905                               0                   0   \n",
       "4906                               1                   0   \n",
       "4907                               0                   1   \n",
       "\n",
       "      work_type_Never_worked  ...  \\\n",
       "0                          0  ...   \n",
       "1                          0  ...   \n",
       "2                          0  ...   \n",
       "3                          0  ...   \n",
       "4                          0  ...   \n",
       "...                      ...  ...   \n",
       "4903                       0  ...   \n",
       "4904                       0  ...   \n",
       "4905                       0  ...   \n",
       "4906                       0  ...   \n",
       "4907                       0  ...   \n",
       "\n",
       "      work_type_Never_worked*work_type_Never_worked  \\\n",
       "0                                                 0   \n",
       "1                                                 0   \n",
       "2                                                 0   \n",
       "3                                                 0   \n",
       "4                                                 0   \n",
       "...                                             ...   \n",
       "4903                                              0   \n",
       "4904                                              0   \n",
       "4905                                              0   \n",
       "4906                                              0   \n",
       "4907                                              0   \n",
       "\n",
       "      work_type_Never_worked*gender  work_type_Never_worked*Residence_type  \\\n",
       "0                               0.0                                      0   \n",
       "1                               0.0                                      0   \n",
       "2                               0.0                                      0   \n",
       "3                               0.0                                      0   \n",
       "4                               0.0                                      0   \n",
       "...                             ...                                    ...   \n",
       "4903                            0.0                                      0   \n",
       "4904                            0.0                                      0   \n",
       "4905                            0.0                                      0   \n",
       "4906                            0.0                                      0   \n",
       "4907                            0.0                                      0   \n",
       "\n",
       "      work_type_Never_worked*smoking_status_Unknown  gender*gender  \\\n",
       "0                                                 0            1.0   \n",
       "1                                                 0            1.0   \n",
       "2                                                 0            0.0   \n",
       "3                                                 0            0.0   \n",
       "4                                                 0            1.0   \n",
       "...                                             ...            ...   \n",
       "4903                                              0            0.0   \n",
       "4904                                              0            0.0   \n",
       "4905                                              0            0.0   \n",
       "4906                                              0            1.0   \n",
       "4907                                              0            0.0   \n",
       "\n",
       "      gender*Residence_type  gender*smoking_status_Unknown  \\\n",
       "0                       1.0                            0.0   \n",
       "1                       0.0                            0.0   \n",
       "2                       0.0                            0.0   \n",
       "3                       0.0                            0.0   \n",
       "4                       1.0                            0.0   \n",
       "...                     ...                            ...   \n",
       "4903                    0.0                            0.0   \n",
       "4904                    0.0                            0.0   \n",
       "4905                    0.0                            0.0   \n",
       "4906                    0.0                            0.0   \n",
       "4907                    0.0                            0.0   \n",
       "\n",
       "      Residence_type*Residence_type  Residence_type*smoking_status_Unknown  \\\n",
       "0                                 1                                      0   \n",
       "1                                 0                                      0   \n",
       "2                                 1                                      0   \n",
       "3                                 0                                      0   \n",
       "4                                 1                                      0   \n",
       "...                             ...                                    ...   \n",
       "4903                              0                                      0   \n",
       "4904                              1                                      0   \n",
       "4905                              0                                      0   \n",
       "4906                              0                                      0   \n",
       "4907                              1                                      1   \n",
       "\n",
       "      smoking_status_Unknown*smoking_status_Unknown  \n",
       "0                                                 0  \n",
       "1                                                 0  \n",
       "2                                                 0  \n",
       "3                                                 0  \n",
       "4                                                 0  \n",
       "...                                             ...  \n",
       "4903                                              1  \n",
       "4904                                              0  \n",
       "4905                                              0  \n",
       "4906                                              0  \n",
       "4907                                              1  \n",
       "\n",
       "[4908 rows x 104 columns]"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_copy = X.loc[:,X_l]\n",
    "\n",
    "for i in range(0, len(X_l)):\n",
    "    j = i\n",
    "    while j < len(X_l):\n",
    "        X_copy[X_l[i]+'*'+X_l[j]] = X_copy[X_l[i]] * X_copy[X_l[j]]\n",
    "        j += 1\n",
    "\n",
    "X_copy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "df1b304d",
   "metadata": {},
   "outputs": [],
   "source": [
    "likelihood_ratio_table = []\n",
    "X_2 = X_l.copy()\n",
    "\n",
    "while not likelihood_ratio_table or max([x for x in likelihood_ratio_table[-1].values() if x != '-']) >= 2.71:\n",
    "    if likelihood_ratio_table:\n",
    "        max_likelihood_ratio = max([x for x in likelihood_ratio_table[-1].values() if x != '-'])\n",
    "        next_label = [key for key in likelihood_ratio_table[-1] if likelihood_ratio_table[-1][key] == max_likelihood_ratio][0]\n",
    "        X_2.append(next_label)\n",
    "    model = Pipeline([('scaler', StandardScaler()),('logistic_classifier', lr(class_weight={0:1,1:1.8}))])\n",
    "    model.fit(X_copy.loc[:,X_2], T)\n",
    "    step = {}\n",
    "    for x in X_copy.columns:\n",
    "        if x in X_2:\n",
    "            step[x] = '-'\n",
    "        else:\n",
    "            X_new = X_2.copy()\n",
    "            X_new.append(x)\n",
    "            model_new = Pipeline([('scaler', StandardScaler()),('logistic_classifier', lr(class_weight={0:1,1:1.8}))])\n",
    "            model_new.fit(X_copy.loc[:,X_new], T)\n",
    "            \n",
    "            step[x] = -2*((-metrics.log_loss(T, model.predict_proba(X_copy.loc[:,X_2]))*len(T))\n",
    "                      -(-metrics.log_loss(T, model_new.predict_proba(X_copy.loc[:,X_new]))*len(T)))\n",
    "    likelihood_ratio_table.append(step)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "f49a1736",
   "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>Label</th>\n",
       "      <th>Step 1</th>\n",
       "      <th>Step 2</th>\n",
       "      <th>Step 3</th>\n",
       "      <th>Step 4</th>\n",
       "      <th>Step 5</th>\n",
       "      <th>Step 6</th>\n",
       "      <th>Step 7</th>\n",
       "      <th>Step 8</th>\n",
       "      <th>Step 9</th>\n",
       "      <th>Step 10</th>\n",
       "      <th>Step 11</th>\n",
       "      <th>Step 12</th>\n",
       "      <th>Step 13</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>hypertension</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>1</th>\n",
       "      <td>heart_disease</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>2</th>\n",
       "      <td>avg_glucose_level</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>3</th>\n",
       "      <td>bmi</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>4</th>\n",
       "      <td>ever_married</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>...</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>gender*Residence_type</td>\n",
       "      <td>0.429994</td>\n",
       "      <td>0.403544</td>\n",
       "      <td>0.558156</td>\n",
       "      <td>0.683972</td>\n",
       "      <td>0.720772</td>\n",
       "      <td>0.76443</td>\n",
       "      <td>0.718604</td>\n",
       "      <td>0.538403</td>\n",
       "      <td>0.493732</td>\n",
       "      <td>0.495043</td>\n",
       "      <td>0.439343</td>\n",
       "      <td>0.43719</td>\n",
       "      <td>0.429173</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>100</th>\n",
       "      <td>gender*smoking_status_Unknown</td>\n",
       "      <td>1.820233</td>\n",
       "      <td>1.945364</td>\n",
       "      <td>1.914713</td>\n",
       "      <td>1.94973</td>\n",
       "      <td>2.135697</td>\n",
       "      <td>2.224161</td>\n",
       "      <td>2.244701</td>\n",
       "      <td>2.374423</td>\n",
       "      <td>2.25699</td>\n",
       "      <td>2.237716</td>\n",
       "      <td>2.245748</td>\n",
       "      <td>2.249313</td>\n",
       "      <td>2.589337</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>101</th>\n",
       "      <td>Residence_type*Residence_type</td>\n",
       "      <td>-0.008313</td>\n",
       "      <td>0.029036</td>\n",
       "      <td>-0.002622</td>\n",
       "      <td>-0.004469</td>\n",
       "      <td>-0.010611</td>\n",
       "      <td>0.0068</td>\n",
       "      <td>-0.023514</td>\n",
       "      <td>-0.006852</td>\n",
       "      <td>0.028871</td>\n",
       "      <td>0.036367</td>\n",
       "      <td>-0.016753</td>\n",
       "      <td>-0.004798</td>\n",
       "      <td>0.016673</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>102</th>\n",
       "      <td>Residence_type*smoking_status_Unknown</td>\n",
       "      <td>1.050397</td>\n",
       "      <td>0.907173</td>\n",
       "      <td>0.996454</td>\n",
       "      <td>0.948782</td>\n",
       "      <td>1.020441</td>\n",
       "      <td>0.964801</td>\n",
       "      <td>1.02766</td>\n",
       "      <td>1.092424</td>\n",
       "      <td>1.196983</td>\n",
       "      <td>1.245719</td>\n",
       "      <td>1.460514</td>\n",
       "      <td>1.446446</td>\n",
       "      <td>1.440634</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>103</th>\n",
       "      <td>smoking_status_Unknown*smoking_status_Unknown</td>\n",
       "      <td>0.000267</td>\n",
       "      <td>0.01757</td>\n",
       "      <td>0.016856</td>\n",
       "      <td>-0.011629</td>\n",
       "      <td>-0.00265</td>\n",
       "      <td>0.027181</td>\n",
       "      <td>-0.01066</td>\n",
       "      <td>0.010928</td>\n",
       "      <td>0.121251</td>\n",
       "      <td>-0.001857</td>\n",
       "      <td>0.004923</td>\n",
       "      <td>-0.030782</td>\n",
       "      <td>0.050835</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>104 rows × 14 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                             Label    Step 1    Step 2  \\\n",
       "0                                     hypertension         -         -   \n",
       "1                                    heart_disease         -         -   \n",
       "2                                avg_glucose_level         -         -   \n",
       "3                                              bmi         -         -   \n",
       "4                                     ever_married         -         -   \n",
       "..                                             ...       ...       ...   \n",
       "99                           gender*Residence_type  0.429994  0.403544   \n",
       "100                  gender*smoking_status_Unknown  1.820233  1.945364   \n",
       "101                  Residence_type*Residence_type -0.008313  0.029036   \n",
       "102          Residence_type*smoking_status_Unknown  1.050397  0.907173   \n",
       "103  smoking_status_Unknown*smoking_status_Unknown  0.000267   0.01757   \n",
       "\n",
       "       Step 3    Step 4    Step 5    Step 6    Step 7    Step 8    Step 9  \\\n",
       "0           -         -         -         -         -         -         -   \n",
       "1           -         -         -         -         -         -         -   \n",
       "2           -         -         -         -         -         -         -   \n",
       "3           -         -         -         -         -         -         -   \n",
       "4           -         -         -         -         -         -         -   \n",
       "..        ...       ...       ...       ...       ...       ...       ...   \n",
       "99   0.558156  0.683972  0.720772   0.76443  0.718604  0.538403  0.493732   \n",
       "100  1.914713   1.94973  2.135697  2.224161  2.244701  2.374423   2.25699   \n",
       "101 -0.002622 -0.004469 -0.010611    0.0068 -0.023514 -0.006852  0.028871   \n",
       "102  0.996454  0.948782  1.020441  0.964801   1.02766  1.092424  1.196983   \n",
       "103  0.016856 -0.011629  -0.00265  0.027181  -0.01066  0.010928  0.121251   \n",
       "\n",
       "      Step 10   Step 11   Step 12   Step 13  \n",
       "0           -         -         -         -  \n",
       "1           -         -         -         -  \n",
       "2           -         -         -         -  \n",
       "3           -         -         -         -  \n",
       "4           -         -         -         -  \n",
       "..        ...       ...       ...       ...  \n",
       "99   0.495043  0.439343   0.43719  0.429173  \n",
       "100  2.237716  2.245748  2.249313  2.589337  \n",
       "101  0.036367 -0.016753 -0.004798  0.016673  \n",
       "102  1.245719  1.460514  1.446446  1.440634  \n",
       "103 -0.001857  0.004923 -0.030782  0.050835  \n",
       "\n",
       "[104 rows x 14 columns]"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_terms_list = []\n",
    "for x in X_copy.columns:\n",
    "    row = [step[x] for step in likelihood_ratio_table]\n",
    "    row.insert(0, x)\n",
    "    final_terms_list.append(row)\n",
    "    \n",
    "final_columns = ['Label']\n",
    "for i in range(0,len(likelihood_ratio_table)):\n",
    "    step = 'Step ' + str(i+1)\n",
    "    final_columns.append(step)\n",
    "    \n",
    "final_terms_df = pd.DataFrame(final_terms_list,columns = final_columns)\n",
    "final_terms_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "23392ac2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['hypertension',\n",
       " 'heart_disease',\n",
       " 'avg_glucose_level',\n",
       " 'bmi',\n",
       " 'ever_married',\n",
       " 'work_type_children',\n",
       " 'work_type_Self-employed',\n",
       " 'smoking_status_formerly smoked',\n",
       " 'work_type_Govt_job',\n",
       " 'work_type_Never_worked',\n",
       " 'gender',\n",
       " 'Residence_type',\n",
       " 'smoking_status_Unknown',\n",
       " 'avg_glucose_level*avg_glucose_level',\n",
       " 'hypertension*bmi',\n",
       " 'hypertension*ever_married',\n",
       " 'bmi*bmi',\n",
       " 'hypertension*smoking_status_formerly smoked',\n",
       " 'ever_married*work_type_Govt_job',\n",
       " 'ever_married*work_type_Self-employed',\n",
       " 'bmi*ever_married',\n",
       " 'work_type_Self-employed*smoking_status_formerly smoked',\n",
       " 'avg_glucose_level*bmi',\n",
       " 'heart_disease*work_type_Govt_job',\n",
       " 'hypertension*gender']"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "f47427bf",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.7765\n",
      "\n",
      "Confusion matrix:\n",
      "[[1466  998]\n",
      " [  99 2345]]\n",
      "\n",
      "F1 score is: 0.8104\n"
     ]
    }
   ],
   "source": [
    "model_final = Pipeline([('scaler', StandardScaler()),('logistic_classifier', lr(class_weight={0:1,1:1.8}))])\n",
    "model_final.fit(X_copy.loc[:,X_2], T)\n",
    "\n",
    "predictions_binary = model_final.predict(X_copy.loc[:,X_2])\n",
    "print('Accuracy: {:.4f}\\n'.format(metrics.accuracy_score(T, predictions_binary)))\n",
    "print('Confusion matrix:\\n{}\\n'.format(metrics.confusion_matrix(T, predictions_binary)))\n",
    "print('F1 score is: {:.4f}'.format(metrics.f1_score(T, predictions_binary)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "c5df67bf",
   "metadata": {},
   "outputs": [],
   "source": [
    "treat_index = []\n",
    "control_index = []\n",
    "for i in range(0,len(T)):\n",
    "    if T[i] == 1:\n",
    "        treat_index.append(i)\n",
    "    elif T[i] == 0:\n",
    "        control_index.append(i)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "5f132490",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-0.005539070631606655"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predictions = model_final.predict_proba(X_copy.loc[:,X_2])\n",
    "\n",
    "ate_ipw = sum([T[i]*Y[i]/predictions[i][1] for i in treat_index]) / sum([T[i]/predictions[i][1] for i in treat_index]) \n",
    "- sum([(1-T[i])*Y[i]/(1-predictions[i][1]) for i in control_index]) / sum([(1-T[i])/(1-predictions[i][1]) for i in control_index])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "1072833e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.079079664663252"
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "A = sum([T[i]*Y[i]/predictions[i][1] for i in treat_index]) / sum([T[i]/predictions[i][1] for i in treat_index])\n",
    "A"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "3a602698",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.005539070631606655"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "B = sum([(1-T[i])*Y[i]/(1-predictions[i][1]) for i in control_index]) / sum([(1-T[i])/(1-predictions[i][1]) for i in control_index])\n",
    "B"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "a1f07fd0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.07354059403164535"
      ]
     },
     "execution_count": 95,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ate_ipw = A - B\n",
    "ate_ipw"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "de8c812d",
   "metadata": {},
   "source": [
    "# Doubly-robust estimator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "46722620",
   "metadata": {},
   "outputs": [],
   "source": [
    "ate_dr = ATE_outcome + ate_ipw - sum([T[i]*mean_1/predictions[i][1] for i in treat_index])/ sum([T[i]/predictions[i][1] for i in treat_index]) + sum([(1-T[i])*mean_0/(1-predictions[i][1]) for i in control_index]) / sum([(1-T[i])/(1-predictions[i][1]) for i in control_index]) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "5c95f033",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.07354059403164537"
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ate_dr"
   ]
  }
 ],
 "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}