bmi_dr.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "8f952a9f",
   "metadata": {},
   "source": [
    "# Outcome regression for bmi"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "c76eee83",
   "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": "32575a33",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_raw = pd.read_csv('./stroke_data_dummies.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b8e42aca",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_r = df_raw[df_raw.Gender_Other == 0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "8de2c2b2",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df_r.drop(columns = ['Unnamed: 0','id','bmi','Gender_Other'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "3c995eba",
   "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>age</th>\n",
       "      <th>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>avg_glucose_level</th>\n",
       "      <th>stroke</th>\n",
       "      <th>marriage</th>\n",
       "      <th>Obesity</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>67.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>228.69</td>\n",
       "      <td>1</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>80.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>105.92</td>\n",
       "      <td>1</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>49.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>171.23</td>\n",
       "      <td>1</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>79.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>174.12</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>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>186.21</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>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",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    age  hypertension  heart_disease  avg_glucose_level  stroke  marriage  \\\n",
       "0  67.0             0              1             228.69       1         1   \n",
       "1  80.0             0              1             105.92       1         1   \n",
       "2  49.0             0              0             171.23       1         1   \n",
       "3  79.0             1              0             174.12       1         1   \n",
       "4  81.0             0              0             186.21       1         1   \n",
       "\n",
       "   Obesity  Gender_Female  Gender_Male  Work_Govt_job  Work_Never_worked  \\\n",
       "0        1              0            1              0                  0   \n",
       "1        1              0            1              0                  0   \n",
       "2        1              1            0              0                  0   \n",
       "3        0              1            0              0                  0   \n",
       "4        0              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",
       "   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  \n",
       "0                0                1  \n",
       "1                1                0  \n",
       "2                0                1  \n",
       "3                1                0  \n",
       "4                0                1  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "7f1c4182",
   "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>age</th>\n",
       "      <th>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>avg_glucose_level</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>67.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>228.69</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>80.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>105.92</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>49.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>171.23</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>79.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>174.12</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>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>186.21</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>13.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>103.08</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>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>125.20</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>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>82.99</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>51.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>166.29</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>44.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>85.28</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": [
       "       age  hypertension  heart_disease  avg_glucose_level  marriage  \\\n",
       "0     67.0             0              1             228.69         1   \n",
       "1     80.0             0              1             105.92         1   \n",
       "2     49.0             0              0             171.23         1   \n",
       "3     79.0             1              0             174.12         1   \n",
       "4     81.0             0              0             186.21         1   \n",
       "...    ...           ...            ...                ...       ...   \n",
       "4904  13.0             0              0             103.08         0   \n",
       "4905  81.0             0              0             125.20         1   \n",
       "4906  35.0             0              0              82.99         1   \n",
       "4907  51.0             0              0             166.29         1   \n",
       "4908  44.0             0              0              85.28         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": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = df.drop(columns = ['stroke', 'Obesity'])\n",
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "1c711652",
   "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>age</th>\n",
       "      <th>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>avg_glucose_level</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>3</th>\n",
       "      <td>79.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>174.12</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>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>186.21</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>5</th>\n",
       "      <td>74.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>70.09</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>6</th>\n",
       "      <td>69.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>94.39</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>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>78.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>58.57</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>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>...</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>4901</th>\n",
       "      <td>45.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>97.95</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>57.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>77.93</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>4904</th>\n",
       "      <td>13.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>103.08</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>4907</th>\n",
       "      <td>51.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>166.29</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",
       "    <tr>\n",
       "      <th>4908</th>\n",
       "      <td>44.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>85.28</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>2988 rows × 19 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       age  hypertension  heart_disease  avg_glucose_level  stroke  marriage  \\\n",
       "3     79.0             1              0             174.12       1         1   \n",
       "4     81.0             0              0             186.21       1         1   \n",
       "5     74.0             1              1              70.09       1         1   \n",
       "6     69.0             0              0              94.39       1         0   \n",
       "7     78.0             0              0              58.57       1         1   \n",
       "...    ...           ...            ...                ...     ...       ...   \n",
       "4901  45.0             0              0              97.95       0         1   \n",
       "4902  57.0             0              0              77.93       0         1   \n",
       "4904  13.0             0              0             103.08       0         0   \n",
       "4907  51.0             0              0             166.29       0         1   \n",
       "4908  44.0             0              0              85.28       0         1   \n",
       "\n",
       "      Gender_Female  Gender_Male  Work_Govt_job  Work_Never_worked  \\\n",
       "3                 1            0              0                  0   \n",
       "4                 0            1              0                  0   \n",
       "5                 0            1              0                  0   \n",
       "6                 1            0              0                  0   \n",
       "7                 1            0              0                  0   \n",
       "...             ...          ...            ...                ...   \n",
       "4901              1            0              0                  0   \n",
       "4902              1            0              0                  0   \n",
       "4904              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",
       "3                0                   1              0                0   \n",
       "4                1                   0              0                0   \n",
       "5                1                   0              0                0   \n",
       "6                1                   0              0                0   \n",
       "7                1                   0              0                1   \n",
       "...            ...                 ...            ...              ...   \n",
       "4901             1                   0              0                1   \n",
       "4902             1                   0              0                0   \n",
       "4904             0                   0              1                1   \n",
       "4907             1                   0              0                0   \n",
       "4908             0                   0              0                1   \n",
       "\n",
       "      smoking_formerly smoked  smoking_never smoked  smoking_smokes  \\\n",
       "3                           0                     1               0   \n",
       "4                           1                     0               0   \n",
       "5                           0                     1               0   \n",
       "6                           0                     1               0   \n",
       "7                           0                     0               0   \n",
       "...                       ...                   ...             ...   \n",
       "4901                        0                     0               0   \n",
       "4902                        0                     1               0   \n",
       "4904                        0                     0               0   \n",
       "4907                        1                     0               0   \n",
       "4908                        0                     0               0   \n",
       "\n",
       "      Residence_Rural  Residence_Urban  \n",
       "3                   1                0  \n",
       "4                   0                1  \n",
       "5                   1                0  \n",
       "6                   0                1  \n",
       "7                   0                1  \n",
       "...               ...              ...  \n",
       "4901                0                1  \n",
       "4902                1                0  \n",
       "4904                1                0  \n",
       "4907                1                0  \n",
       "4908                0                1  \n",
       "\n",
       "[2988 rows x 19 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_0 = df[df['Obesity'] == 0]\n",
    "df_0 = df_0.drop(columns = ['Obesity'])\n",
    "df_0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d43d958b",
   "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>age</th>\n",
       "      <th>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>avg_glucose_level</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>67.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>228.69</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>80.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>105.92</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>49.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>171.23</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>9</th>\n",
       "      <td>61.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>120.46</td>\n",
       "      <td>1</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>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>12</th>\n",
       "      <td>50.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>167.41</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>...</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>4894</th>\n",
       "      <td>76.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>82.35</td>\n",
       "      <td>0</td>\n",
       "      <td>1</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>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>4898</th>\n",
       "      <td>68.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>91.68</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>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>18.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>82.85</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>4905</th>\n",
       "      <td>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>125.20</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>4906</th>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>82.99</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",
       "  </tbody>\n",
       "</table>\n",
       "<p>1920 rows × 19 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       age  hypertension  heart_disease  avg_glucose_level  stroke  marriage  \\\n",
       "0     67.0             0              1             228.69       1         1   \n",
       "1     80.0             0              1             105.92       1         1   \n",
       "2     49.0             0              0             171.23       1         1   \n",
       "9     61.0             0              1             120.46       1         1   \n",
       "12    50.0             1              0             167.41       1         1   \n",
       "...    ...           ...            ...                ...     ...       ...   \n",
       "4894  76.0             0              0              82.35       0         1   \n",
       "4898  68.0             0              0              91.68       0         1   \n",
       "4903  18.0             0              0              82.85       0         0   \n",
       "4905  81.0             0              0             125.20       0         1   \n",
       "4906  35.0             0              0              82.99       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",
       "9                 1            0              1                  0   \n",
       "12                1            0              0                  0   \n",
       "...             ...          ...            ...                ...   \n",
       "4894              0            1              1                  0   \n",
       "4898              0            1              0                  0   \n",
       "4903              1            0              0                  0   \n",
       "4905              1            0              0                  0   \n",
       "4906              1            0              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",
       "9                0                   0              0                0   \n",
       "12               0                   1              0                0   \n",
       "...            ...                 ...            ...              ...   \n",
       "4894             0                   0              0                0   \n",
       "4898             0                   1              0                1   \n",
       "4903             1                   0              0                1   \n",
       "4905             0                   1              0                0   \n",
       "4906             0                   1              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",
       "9                           0                     0               1   \n",
       "12                          0                     1               0   \n",
       "...                       ...                   ...             ...   \n",
       "4894                        0                     1               0   \n",
       "4898                        0                     0               0   \n",
       "4903                        0                     0               0   \n",
       "4905                        0                     1               0   \n",
       "4906                        0                     1               0   \n",
       "\n",
       "      Residence_Rural  Residence_Urban  \n",
       "0                   0                1  \n",
       "1                   1                0  \n",
       "2                   0                1  \n",
       "9                   1                0  \n",
       "12                  1                0  \n",
       "...               ...              ...  \n",
       "4894                0                1  \n",
       "4898                0                1  \n",
       "4903                0                1  \n",
       "4905                0                1  \n",
       "4906                1                0  \n",
       "\n",
       "[1920 rows x 19 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_1 = df[df['Obesity'] == 1]\n",
    "df_1 = df_1.drop(columns = ['Obesity'])\n",
    "df_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "5cb16027",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_0 = df_0['stroke']\n",
    "x_0 = df_0.drop(columns = ['stroke'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "407a9ce8",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_1 = df_1['stroke']\n",
    "x_1 = df_1.drop(columns = ['stroke'])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c4855a15",
   "metadata": {},
   "source": [
    "# Model for controlled group"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "11b3ff39",
   "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": 12,
   "id": "4539e000",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9618454591799578"
      ]
     },
     "execution_count": 12,
     "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": 13,
   "id": "3b04f32b",
   "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": 14,
   "id": "aafa2232",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "nan 30\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(30,50):\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(30,50)][scorel.index(max(scorel))]))\n",
    "plt.figure(figsize=[60,20])\n",
    "plt.plot(range(30,50),scorel)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "990475ad",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=43, random_state=60),\n",
       "             param_grid={'max_depth': array([ 1,  3,  5,  7,  9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31, 33,\n",
       "       35, 37, 39, 41, 43, 45, 47, 49, 51, 53, 55, 57, 59, 61, 63, 65, 67,\n",
       "       69, 71, 73, 75, 77, 79, 81, 83, 85, 87, 89, 91, 93, 95, 97, 99])})"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid = {'max_depth':np.arange(1, 100, 2)}\n",
    "rfc = RandomForestClassifier(n_estimators=43\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": 16,
   "id": "55a5160a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'max_depth': 7}"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "e19cab65",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9631866131101438"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "1a933691",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=43, 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": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid = {'max_features':np.arange(1,20,1)}\n",
    "rfc = RandomForestClassifier(n_estimators=43\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": 19,
   "id": "9b8d8bd3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'max_features': 4}"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "c0a014d9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9621804675551671"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "2526cfa9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=43, 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": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid={'min_samples_leaf':np.arange(1, 20, 1)}\n",
    "rfc = RandomForestClassifier(n_estimators=43\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": 22,
   "id": "f97696aa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'min_samples_leaf': 3}"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "7ff34c0c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9628516047349344"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "92328f94",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=43, 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": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid={'min_samples_split':np.arange(2, 2+20, 1)}\n",
    "rfc = RandomForestClassifier(n_estimators=43\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": 25,
   "id": "4a754867",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'min_samples_split': 9}"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "31877552",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9631866131101438"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "35870344",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9628516047349344"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rfc_0 = RandomForestClassifier(n_estimators=43,max_depth = 7,max_features = 4, min_samples_split = 9, 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": 28,
   "id": "42465c36",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0010061455549765785"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "score_0 - score_pre_0"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1f88e5c9",
   "metadata": {},
   "source": [
    "# Model for treatment gruop"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "915b600c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9427083333333334"
      ]
     },
     "execution_count": 29,
     "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": 30,
   "id": "2f8a589c",
   "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(1,201,10),scorel)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "f8d05b09",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "nan 20\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(20,80):\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(20,60)][scorel.index(max(scorel))]))\n",
    "plt.figure(figsize=[20,5])\n",
    "plt.plot(range(20,80),scorel)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "78013922",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=45, random_state=80),\n",
       "             param_grid={'max_depth': array([ 1,  3,  5,  7,  9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31, 33,\n",
       "       35, 37, 39, 41, 43, 45, 47, 49, 51, 53, 55, 57, 59, 61, 63, 65, 67,\n",
       "       69, 71, 73, 75, 77, 79, 81, 83, 85, 87, 89, 91, 93, 95, 97, 99])})"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid = {'max_depth':np.arange(1, 100, 2)}\n",
    "rfc = RandomForestClassifier(n_estimators=45\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": 33,
   "id": "f9a8936a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'max_depth': 1}"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "0f5ec627",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9489583333333333"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "183da178",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=45, 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": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid = {'max_features':np.arange(1,20,1)}\n",
    "rfc = RandomForestClassifier(n_estimators=45\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": 36,
   "id": "e1d70de9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'max_features': 3}"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "2ba027dc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9447916666666666"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "0b78bace",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=45, 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": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid={'min_samples_leaf':np.arange(1, 20, 1)}\n",
    "rfc = RandomForestClassifier(n_estimators=45\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": 39,
   "id": "40dfd9b7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'min_samples_leaf': 5}"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "0600a6ba",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9489583333333333"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "c37985a9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=RandomForestClassifier(n_estimators=45, 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": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid={'min_samples_split':np.arange(2, 2+20, 1)}\n",
    "rfc = RandomForestClassifier(n_estimators=45\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": 42,
   "id": "62dab771",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'min_samples_split': 9}"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "55b1586f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9484375"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "GS.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "f970e691",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9489583333333333"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rfc_1 = RandomForestClassifier(n_estimators=45,max_depth = 1, 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": 45,
   "id": "a42c774b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.006249999999999978"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "score_1 - score_pre_1"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f0f71ce0",
   "metadata": {},
   "source": [
    "# Outcome modeling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "00654010",
   "metadata": {},
   "outputs": [],
   "source": [
    "from scipy import stats\n",
    "import scipy.stats"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "92c7fcb8",
   "metadata": {},
   "outputs": [],
   "source": [
    "rfc0 = rfc_0.fit(x_0, y_0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "9f37c6c2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.00020374898125509371"
      ]
     },
     "execution_count": 48,
     "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": 49,
   "id": "07455f63",
   "metadata": {},
   "outputs": [],
   "source": [
    "rfc1 = rfc_1.fit(x_1, y_1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "c0dbfe89",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0"
      ]
     },
     "execution_count": 50,
     "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": 51,
   "id": "57605a4e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-0.00020374898125509371"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ATE_outcome = mean_1 - mean_0\n",
    "ATE_outcome"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "be894336",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9999999999999998 0.8413200916568588\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": "3cacf2e1",
   "metadata": {},
   "source": [
    "# IPW for bmi"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "556179a6",
   "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": 54,
   "id": "467ab8b0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Enabled to remove warnings for demo purposes.\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "6e792126",
   "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": 56,
   "id": "9f8f81c7",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('./healthcare-dataset-stroke-data.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "bad8c2e6",
   "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": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "cbfa8dcd",
   "metadata": {},
   "outputs": [],
   "source": [
    "# delete row with NA value\n",
    "df_na = df.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "e585f6ef",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_na.reset_index(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "4df97d68",
   "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": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.isnull(df_na).any()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "060820bf",
   "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": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_na"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "f888ec40",
   "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": 63,
   "id": "35688b91",
   "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": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.isnull(df_na).any()\n",
    "# there is one sample with 'Other' gender'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "df39f2da",
   "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": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# delete the row with 'gender' value of 'Other'\n",
    "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": 65,
   "id": "ee947865",
   "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": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_na"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "92143edf",
   "metadata": {},
   "outputs": [],
   "source": [
    "def BMI_check(x):\n",
    "    if x >= 30:\n",
    "        return 1\n",
    "    else:\n",
    "        return 0\n",
    "    \n",
    "# Use bmi as treatment. The bound is 30. 1 means higher or equal. 0 means lower.\n",
    "df_na['treatment_bmi'] = df_na.bmi.apply(BMI_check)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "123f502b",
   "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>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>smoking_status</th>\n",
       "      <th>stroke</th>\n",
       "      <th>treatment_bmi</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\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>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>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>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>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>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>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>never smoked</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\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>formerly smoked</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4903</th>\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>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>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>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>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>never smoked</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4906</th>\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>formerly smoked</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4907</th>\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>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   age  hypertension  heart_disease  ever_married      work_type  \\\n",
       "0        1.0  67.0             0              1             1        Private   \n",
       "1        1.0  80.0             0              1             1        Private   \n",
       "2        0.0  49.0             0              0             1        Private   \n",
       "3        0.0  79.0             1              0             1  Self-employed   \n",
       "4        1.0  81.0             0              0             1        Private   \n",
       "...      ...   ...           ...            ...           ...            ...   \n",
       "4903     0.0  13.0             0              0             0       children   \n",
       "4904     0.0  81.0             0              0             1  Self-employed   \n",
       "4905     0.0  35.0             0              0             1  Self-employed   \n",
       "4906     1.0  51.0             0              0             1        Private   \n",
       "4907     0.0  44.0             0              0             1       Govt_job   \n",
       "\n",
       "      Residence_type  avg_glucose_level   smoking_status  stroke  \\\n",
       "0                  1             228.69  formerly smoked       1   \n",
       "1                  0             105.92     never smoked       1   \n",
       "2                  1             171.23           smokes       1   \n",
       "3                  0             174.12     never smoked       1   \n",
       "4                  1             186.21  formerly smoked       1   \n",
       "...              ...                ...              ...     ...   \n",
       "4903               0             103.08          Unknown       0   \n",
       "4904               1             125.20     never smoked       0   \n",
       "4905               0              82.99     never smoked       0   \n",
       "4906               0             166.29  formerly smoked       0   \n",
       "4907               1              85.28          Unknown       0   \n",
       "\n",
       "      treatment_bmi  \n",
       "0                 1  \n",
       "1                 1  \n",
       "2                 1  \n",
       "3                 0  \n",
       "4                 0  \n",
       "...             ...  \n",
       "4903              0  \n",
       "4904              1  \n",
       "4905              1  \n",
       "4906              0  \n",
       "4907              0  \n",
       "\n",
       "[4908 rows x 11 columns]"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_data = df_na.drop(columns=['index','id','bmi'])\n",
    "df_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "d4cbd3db",
   "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>age</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>stroke</th>\n",
       "      <th>treatment_bmi</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>67.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>228.69</td>\n",
       "      <td>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>80.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>105.92</td>\n",
       "      <td>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>49.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>171.23</td>\n",
       "      <td>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>79.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>174.12</td>\n",
       "      <td>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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>186.21</td>\n",
       "      <td>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>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>13.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>103.08</td>\n",
       "      <td>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>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>125.20</td>\n",
       "      <td>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>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>82.99</td>\n",
       "      <td>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>4906</th>\n",
       "      <td>1.0</td>\n",
       "      <td>51.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>166.29</td>\n",
       "      <td>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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4907</th>\n",
       "      <td>0.0</td>\n",
       "      <td>44.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>85.28</td>\n",
       "      <td>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   age  hypertension  heart_disease  ever_married  Residence_type  \\\n",
       "0        1.0  67.0             0              1             1               1   \n",
       "1        1.0  80.0             0              1             1               0   \n",
       "2        0.0  49.0             0              0             1               1   \n",
       "3        0.0  79.0             1              0             1               0   \n",
       "4        1.0  81.0             0              0             1               1   \n",
       "...      ...   ...           ...            ...           ...             ...   \n",
       "4903     0.0  13.0             0              0             0               0   \n",
       "4904     0.0  81.0             0              0             1               1   \n",
       "4905     0.0  35.0             0              0             1               0   \n",
       "4906     1.0  51.0             0              0             1               0   \n",
       "4907     0.0  44.0             0              0             1               1   \n",
       "\n",
       "      avg_glucose_level  stroke  treatment_bmi  work_type_Govt_job  \\\n",
       "0                228.69       1              1                   0   \n",
       "1                105.92       1              1                   0   \n",
       "2                171.23       1              1                   0   \n",
       "3                174.12       1              0                   0   \n",
       "4                186.21       1              0                   0   \n",
       "...                 ...     ...            ...                 ...   \n",
       "4903             103.08       0              0                   0   \n",
       "4904             125.20       0              1                   0   \n",
       "4905              82.99       0              1                   0   \n",
       "4906             166.29       0              0                   0   \n",
       "4907              85.28       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": 68,
     "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": 69,
   "id": "7143a633",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_treatment = df_encoded[df_encoded['treatment_bmi']==1]\n",
    "df_control = df_encoded[df_encoded['treatment_bmi']==0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "00c8b8bf",
   "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": 71,
   "id": "81e24ec7",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_list = ['gender','age','hypertension','heart_disease','ever_married','Residence_type','avg_glucose_level','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','age of the sample','observation of hypertension','observation of heart_disease',\n",
    "             'Marriage states','0 to Rural and 1 to Urban','average glucose level','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": 72,
   "id": "7befb0d8",
   "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>0.403614</td>\n",
       "      <td>0.490704</td>\n",
       "      <td>0.419271</td>\n",
       "      <td>0.493568</td>\n",
       "      <td>-1.086971</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>age</td>\n",
       "      <td>age of the sample</td>\n",
       "      <td>38.435181</td>\n",
       "      <td>24.417835</td>\n",
       "      <td>49.768646</td>\n",
       "      <td>17.166306</td>\n",
       "      <td>-19.074881</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>hypertension</td>\n",
       "      <td>observation of hypertension</td>\n",
       "      <td>0.058568</td>\n",
       "      <td>0.234853</td>\n",
       "      <td>0.143750</td>\n",
       "      <td>0.350927</td>\n",
       "      <td>-9.372606</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>heart_disease</td>\n",
       "      <td>observation of heart_disease</td>\n",
       "      <td>0.041165</td>\n",
       "      <td>0.198704</td>\n",
       "      <td>0.062500</td>\n",
       "      <td>0.242125</td>\n",
       "      <td>-3.225694</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ever_married</td>\n",
       "      <td>Marriage states</td>\n",
       "      <td>0.557229</td>\n",
       "      <td>0.496797</td>\n",
       "      <td>0.801562</td>\n",
       "      <td>0.398927</td>\n",
       "      <td>-18.993364</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Residence_type</td>\n",
       "      <td>0 to Rural and 1 to Urban</td>\n",
       "      <td>0.508367</td>\n",
       "      <td>0.500014</td>\n",
       "      <td>0.505729</td>\n",
       "      <td>0.500097</td>\n",
       "      <td>0.180334</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>avg_glucose_level</td>\n",
       "      <td>average glucose level</td>\n",
       "      <td>99.631493</td>\n",
       "      <td>37.844651</td>\n",
       "      <td>114.114974</td>\n",
       "      <td>51.861464</td>\n",
       "      <td>-10.562708</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>0.111446</td>\n",
       "      <td>0.314736</td>\n",
       "      <td>0.154688</td>\n",
       "      <td>0.361701</td>\n",
       "      <td>-4.296516</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>0.005689</td>\n",
       "      <td>0.075226</td>\n",
       "      <td>0.002604</td>\n",
       "      <td>0.050978</td>\n",
       "      <td>1.712078</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>work_type_Private</td>\n",
       "      <td>Whether job is private</td>\n",
       "      <td>0.524766</td>\n",
       "      <td>0.499470</td>\n",
       "      <td>0.646875</td>\n",
       "      <td>0.478066</td>\n",
       "      <td>-8.580426</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>0.143574</td>\n",
       "      <td>0.350716</td>\n",
       "      <td>0.180208</td>\n",
       "      <td>0.384461</td>\n",
       "      <td>-3.370298</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>work_type_children</td>\n",
       "      <td>Whether job is children</td>\n",
       "      <td>0.214525</td>\n",
       "      <td>0.410561</td>\n",
       "      <td>0.015625</td>\n",
       "      <td>0.124052</td>\n",
       "      <td>24.779856</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>0.368139</td>\n",
       "      <td>0.482380</td>\n",
       "      <td>0.199479</td>\n",
       "      <td>0.399713</td>\n",
       "      <td>13.288610</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>0.141232</td>\n",
       "      <td>0.348319</td>\n",
       "      <td>0.215625</td>\n",
       "      <td>0.411362</td>\n",
       "      <td>-6.556604</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>0.355422</td>\n",
       "      <td>0.478721</td>\n",
       "      <td>0.411458</td>\n",
       "      <td>0.492226</td>\n",
       "      <td>-3.934077</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>smoking_status_smokes</td>\n",
       "      <td>Whether is smokes</td>\n",
       "      <td>0.135207</td>\n",
       "      <td>0.342002</td>\n",
       "      <td>0.173437</td>\n",
       "      <td>0.378724</td>\n",
       "      <td>-3.582940</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                              age                  age of the sample   \n",
       "2                     hypertension        observation of hypertension   \n",
       "3                    heart_disease       observation of heart_disease   \n",
       "4                     ever_married                    Marriage states   \n",
       "5                   Residence_type          0 to Rural and 1 to Urban   \n",
       "6                avg_glucose_level              average glucose level   \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        0.403614      0.490704      0.419271     0.493568     -1.086971  \n",
       "1       38.435181     24.417835     49.768646    17.166306    -19.074881  \n",
       "2        0.058568      0.234853      0.143750     0.350927     -9.372606  \n",
       "3        0.041165      0.198704      0.062500     0.242125     -3.225694  \n",
       "4        0.557229      0.496797      0.801562     0.398927    -18.993364  \n",
       "5        0.508367      0.500014      0.505729     0.500097      0.180334  \n",
       "6       99.631493     37.844651    114.114974    51.861464    -10.562708  \n",
       "7        0.111446      0.314736      0.154688     0.361701     -4.296516  \n",
       "8        0.005689      0.075226      0.002604     0.050978      1.712078  \n",
       "9        0.524766      0.499470      0.646875     0.478066     -8.580426  \n",
       "10       0.143574      0.350716      0.180208     0.384461     -3.370298  \n",
       "11       0.214525      0.410561      0.015625     0.124052     24.779856  \n",
       "12       0.368139      0.482380      0.199479     0.399713     13.288610  \n",
       "13       0.141232      0.348319      0.215625     0.411362     -6.556604  \n",
       "14       0.355422      0.478721      0.411458     0.492226     -3.934077  \n",
       "15       0.135207      0.342002      0.173437     0.378724     -3.582940  "
      ]
     },
     "execution_count": 72,
     "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": 73,
   "id": "418d2e98",
   "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>age</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>stroke</th>\n",
       "      <th>treatment_bmi</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>67.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>228.69</td>\n",
       "      <td>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>80.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>105.92</td>\n",
       "      <td>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>49.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>171.23</td>\n",
       "      <td>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>79.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>174.12</td>\n",
       "      <td>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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>186.21</td>\n",
       "      <td>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>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>13.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>103.08</td>\n",
       "      <td>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>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>125.20</td>\n",
       "      <td>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>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>82.99</td>\n",
       "      <td>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>4906</th>\n",
       "      <td>1.0</td>\n",
       "      <td>51.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>166.29</td>\n",
       "      <td>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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4907</th>\n",
       "      <td>0.0</td>\n",
       "      <td>44.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>85.28</td>\n",
       "      <td>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   age  hypertension  heart_disease  ever_married  Residence_type  \\\n",
       "0        1.0  67.0             0              1             1               1   \n",
       "1        1.0  80.0             0              1             1               0   \n",
       "2        0.0  49.0             0              0             1               1   \n",
       "3        0.0  79.0             1              0             1               0   \n",
       "4        1.0  81.0             0              0             1               1   \n",
       "...      ...   ...           ...            ...           ...             ...   \n",
       "4903     0.0  13.0             0              0             0               0   \n",
       "4904     0.0  81.0             0              0             1               1   \n",
       "4905     0.0  35.0             0              0             1               0   \n",
       "4906     1.0  51.0             0              0             1               0   \n",
       "4907     0.0  44.0             0              0             1               1   \n",
       "\n",
       "      avg_glucose_level  stroke  treatment_bmi  work_type_Govt_job  \\\n",
       "0                228.69       1              1                   0   \n",
       "1                105.92       1              1                   0   \n",
       "2                171.23       1              1                   0   \n",
       "3                174.12       1              0                   0   \n",
       "4                186.21       1              0                   0   \n",
       "...                 ...     ...            ...                 ...   \n",
       "4903             103.08       0              0                   0   \n",
       "4904             125.20       0              1                   0   \n",
       "4905              82.99       0              1                   0   \n",
       "4906             166.29       0              0                   0   \n",
       "4907              85.28       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": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = df_encoded\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "3c53f7f7",
   "metadata": {},
   "outputs": [],
   "source": [
    "Y = df.stroke\n",
    "\n",
    "df_data = df.loc[:,df.columns !='stroke']\n",
    "T = df_data.treatment_bmi\n",
    "X = df_data.loc[:,df_data.columns !='treatment_bmi']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "dd9a10c7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Choose age,hypertension,heart_disease,avg_glucose_level as X_b\n",
    "X_b = ['age','hypertension','heart_disease','avg_glucose_level']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "fd445e2f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.39119804400978"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "T.mean()\n",
    "# Since the sample size is unbalanced, we will weighted them in the regression model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "42b0ed9b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.6055\n",
      "\n",
      "Confusion matrix:\n",
      "[[1895 1093]\n",
      " [ 843 1077]]\n",
      "\n",
      "F1 score is: 0.5267\n"
     ]
    }
   ],
   "source": [
    "# weighted based on size ratio of treatment group and control group\n",
    "model_initial = Pipeline([('scaler', StandardScaler()),('logistic_classifier', lr(class_weight={0:1,1:1.5}))])\n",
    "model_initial.fit(X.loc[:,X_b], T)\n",
    "\n",
    "predictions_binary = model_initial.predict(X.loc[:,X_b])\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": 78,
   "id": "f1e2df86",
   "metadata": {},
   "outputs": [],
   "source": [
    "likelihood_ratio_table = []\n",
    "X_l = X_b.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={0:1,1:1.5}))])\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={0:1,1:1.5}))])\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": 79,
   "id": "22b1e566",
   "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",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>gender</td>\n",
       "      <td>1.569423</td>\n",
       "      <td>5.786234</td>\n",
       "      <td>5.734279</td>\n",
       "      <td>5.162963</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>age</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>hypertension</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>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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ever_married</td>\n",
       "      <td>78.561411</td>\n",
       "      <td>35.931638</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Residence_type</td>\n",
       "      <td>0.100047</td>\n",
       "      <td>0.064964</td>\n",
       "      <td>0.052424</td>\n",
       "      <td>0.054262</td>\n",
       "      <td>0.046287</td>\n",
       "      <td>0.039798</td>\n",
       "      <td>0.029011</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>work_type_Govt_job</td>\n",
       "      <td>5.97007</td>\n",
       "      <td>1.604171</td>\n",
       "      <td>0.986685</td>\n",
       "      <td>0.974741</td>\n",
       "      <td>1.011634</td>\n",
       "      <td>0.443847</td>\n",
       "      <td>0.412827</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>work_type_Never_worked</td>\n",
       "      <td>0.076288</td>\n",
       "      <td>2.512238</td>\n",
       "      <td>1.338486</td>\n",
       "      <td>1.273616</td>\n",
       "      <td>1.379935</td>\n",
       "      <td>1.378694</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>work_type_Private</td>\n",
       "      <td>55.49972</td>\n",
       "      <td>0.527418</td>\n",
       "      <td>0.484006</td>\n",
       "      <td>0.508618</td>\n",
       "      <td>0.479834</td>\n",
       "      <td>0.179588</td>\n",
       "      <td>0.404223</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>work_type_Self-employed</td>\n",
       "      <td>6.334057</td>\n",
       "      <td>3.312974</td>\n",
       "      <td>2.591416</td>\n",
       "      <td>2.740302</td>\n",
       "      <td>2.61367</td>\n",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>work_type_children</td>\n",
       "      <td>256.016912</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>45.929546</td>\n",
       "      <td>2.610227</td>\n",
       "      <td>1.832277</td>\n",
       "      <td>0.594814</td>\n",
       "      <td>0.739174</td>\n",
       "      <td>0.72227</td>\n",
       "      <td>0.69802</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>smoking_status_formerly smoked</td>\n",
       "      <td>7.159841</td>\n",
       "      <td>6.245291</td>\n",
       "      <td>5.862391</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>3.138342</td>\n",
       "      <td>1.162451</td>\n",
       "      <td>0.997757</td>\n",
       "      <td>-0.01816</td>\n",
       "      <td>-0.006603</td>\n",
       "      <td>0.00784</td>\n",
       "      <td>0.013669</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>smoking_status_smokes</td>\n",
       "      <td>7.077157</td>\n",
       "      <td>0.325009</td>\n",
       "      <td>0.080508</td>\n",
       "      <td>0.73304</td>\n",
       "      <td>0.57945</td>\n",
       "      <td>0.535198</td>\n",
       "      <td>0.473018</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                             Label      Step 1     Step 2    Step 3    Step 4  \\\n",
       "0                           gender    1.569423   5.786234  5.734279  5.162963   \n",
       "1                              age           -          -         -         -   \n",
       "2                     hypertension           -          -         -         -   \n",
       "3                    heart_disease           -          -         -         -   \n",
       "4                     ever_married   78.561411  35.931638         -         -   \n",
       "5                   Residence_type    0.100047   0.064964  0.052424  0.054262   \n",
       "6                avg_glucose_level           -          -         -         -   \n",
       "7               work_type_Govt_job     5.97007   1.604171  0.986685  0.974741   \n",
       "8           work_type_Never_worked    0.076288   2.512238  1.338486  1.273616   \n",
       "9                work_type_Private    55.49972   0.527418  0.484006  0.508618   \n",
       "10         work_type_Self-employed    6.334057   3.312974  2.591416  2.740302   \n",
       "11              work_type_children  256.016912          -         -         -   \n",
       "12          smoking_status_Unknown   45.929546   2.610227  1.832277  0.594814   \n",
       "13  smoking_status_formerly smoked    7.159841   6.245291  5.862391         -   \n",
       "14     smoking_status_never smoked    3.138342   1.162451  0.997757  -0.01816   \n",
       "15           smoking_status_smokes    7.077157   0.325009  0.080508   0.73304   \n",
       "\n",
       "      Step 5    Step 6    Step 7  \n",
       "0          -         -         -  \n",
       "1          -         -         -  \n",
       "2          -         -         -  \n",
       "3          -         -         -  \n",
       "4          -         -         -  \n",
       "5   0.046287  0.039798  0.029011  \n",
       "6          -         -         -  \n",
       "7   1.011634  0.443847  0.412827  \n",
       "8   1.379935  1.378694         -  \n",
       "9   0.479834  0.179588  0.404223  \n",
       "10   2.61367         -         -  \n",
       "11         -         -         -  \n",
       "12  0.739174   0.72227   0.69802  \n",
       "13         -         -         -  \n",
       "14 -0.006603   0.00784  0.013669  \n",
       "15   0.57945  0.535198  0.473018  "
      ]
     },
     "execution_count": 79,
     "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": 80,
   "id": "fd069596",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['age',\n",
       " 'hypertension',\n",
       " 'heart_disease',\n",
       " 'avg_glucose_level',\n",
       " 'work_type_children',\n",
       " 'ever_married',\n",
       " 'smoking_status_formerly smoked',\n",
       " 'gender',\n",
       " 'work_type_Self-employed',\n",
       " 'work_type_Never_worked']"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# The linear terms we need to include\n",
    "X_l"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "ceb3d653",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.6037\n",
      "\n",
      "Confusion matrix:\n",
      "[[1506 1482]\n",
      " [ 463 1457]]\n",
      "\n",
      "F1 score is: 0.5997\n"
     ]
    }
   ],
   "source": [
    "model_linear = Pipeline([('scaler', StandardScaler()),('logistic_classifier', lr(class_weight={0:1,1:1.5}))])\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": 82,
   "id": "08cc5e7a",
   "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>age</th>\n",
       "      <th>hypertension</th>\n",
       "      <th>heart_disease</th>\n",
       "      <th>avg_glucose_level</th>\n",
       "      <th>work_type_children</th>\n",
       "      <th>ever_married</th>\n",
       "      <th>smoking_status_formerly smoked</th>\n",
       "      <th>gender</th>\n",
       "      <th>work_type_Self-employed</th>\n",
       "      <th>work_type_Never_worked</th>\n",
       "      <th>...</th>\n",
       "      <th>smoking_status_formerly smoked*smoking_status_formerly smoked</th>\n",
       "      <th>smoking_status_formerly smoked*gender</th>\n",
       "      <th>smoking_status_formerly smoked*work_type_Self-employed</th>\n",
       "      <th>smoking_status_formerly smoked*work_type_Never_worked</th>\n",
       "      <th>gender*gender</th>\n",
       "      <th>gender*work_type_Self-employed</th>\n",
       "      <th>gender*work_type_Never_worked</th>\n",
       "      <th>work_type_Self-employed*work_type_Self-employed</th>\n",
       "      <th>work_type_Self-employed*work_type_Never_worked</th>\n",
       "      <th>work_type_Never_worked*work_type_Never_worked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>67.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>228.69</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</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>1</th>\n",
       "      <td>80.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>105.92</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</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>49.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>171.23</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</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>3</th>\n",
       "      <td>79.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>174.12</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>186.21</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</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>...</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>13.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>103.08</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</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>4904</th>\n",
       "      <td>81.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>125.20</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4905</th>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>82.99</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4906</th>\n",
       "      <td>51.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>166.29</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</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>44.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>85.28</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</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",
       "  </tbody>\n",
       "</table>\n",
       "<p>4908 rows × 65 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       age  hypertension  heart_disease  avg_glucose_level  \\\n",
       "0     67.0             0              1             228.69   \n",
       "1     80.0             0              1             105.92   \n",
       "2     49.0             0              0             171.23   \n",
       "3     79.0             1              0             174.12   \n",
       "4     81.0             0              0             186.21   \n",
       "...    ...           ...            ...                ...   \n",
       "4903  13.0             0              0             103.08   \n",
       "4904  81.0             0              0             125.20   \n",
       "4905  35.0             0              0              82.99   \n",
       "4906  51.0             0              0             166.29   \n",
       "4907  44.0             0              0              85.28   \n",
       "\n",
       "      work_type_children  ever_married  smoking_status_formerly smoked  \\\n",
       "0                      0             1                               1   \n",
       "1                      0             1                               0   \n",
       "2                      0             1                               0   \n",
       "3                      0             1                               0   \n",
       "4                      0             1                               1   \n",
       "...                  ...           ...                             ...   \n",
       "4903                   1             0                               0   \n",
       "4904                   0             1                               0   \n",
       "4905                   0             1                               0   \n",
       "4906                   0             1                               1   \n",
       "4907                   0             1                               0   \n",
       "\n",
       "      gender  work_type_Self-employed  work_type_Never_worked  ...  \\\n",
       "0        1.0                        0                       0  ...   \n",
       "1        1.0                        0                       0  ...   \n",
       "2        0.0                        0                       0  ...   \n",
       "3        0.0                        1                       0  ...   \n",
       "4        1.0                        0                       0  ...   \n",
       "...      ...                      ...                     ...  ...   \n",
       "4903     0.0                        0                       0  ...   \n",
       "4904     0.0                        1                       0  ...   \n",
       "4905     0.0                        1                       0  ...   \n",
       "4906     1.0                        0                       0  ...   \n",
       "4907     0.0                        0                       0  ...   \n",
       "\n",
       "      smoking_status_formerly smoked*smoking_status_formerly smoked  \\\n",
       "0                                                     1               \n",
       "1                                                     0               \n",
       "2                                                     0               \n",
       "3                                                     0               \n",
       "4                                                     1               \n",
       "...                                                 ...               \n",
       "4903                                                  0               \n",
       "4904                                                  0               \n",
       "4905                                                  0               \n",
       "4906                                                  1               \n",
       "4907                                                  0               \n",
       "\n",
       "      smoking_status_formerly smoked*gender  \\\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                                    0.0   \n",
       "\n",
       "      smoking_status_formerly smoked*work_type_Self-employed  \\\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",
       "      smoking_status_formerly smoked*work_type_Never_worked  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*work_type_Self-employed  gender*work_type_Never_worked  \\\n",
       "0                                0.0                            0.0   \n",
       "1                                0.0                            0.0   \n",
       "2                                0.0                            0.0   \n",
       "3                                0.0                            0.0   \n",
       "4                                0.0                            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",
       "      work_type_Self-employed*work_type_Self-employed  \\\n",
       "0                                                   0   \n",
       "1                                                   0   \n",
       "2                                                   0   \n",
       "3                                                   1   \n",
       "4                                                   0   \n",
       "...                                               ...   \n",
       "4903                                                0   \n",
       "4904                                                1   \n",
       "4905                                                1   \n",
       "4906                                                0   \n",
       "4907                                                0   \n",
       "\n",
       "      work_type_Self-employed*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",
       "[4908 rows x 65 columns]"
      ]
     },
     "execution_count": 82,
     "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": 83,
   "id": "13452500",
   "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={0:1,1:1.5}))])\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={0:1,1:1.5}))])\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": 84,
   "id": "5bdd6523",
   "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",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>age</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>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",
       "    </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",
       "      <td>-</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>work_type_children</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60</th>\n",
       "      <td>gender*work_type_Self-employed</td>\n",
       "      <td>0.047222</td>\n",
       "      <td>0.030021</td>\n",
       "      <td>0.051126</td>\n",
       "      <td>0.068857</td>\n",
       "      <td>0.087996</td>\n",
       "      <td>0.089939</td>\n",
       "      <td>0.059366</td>\n",
       "      <td>0.003143</td>\n",
       "      <td>-0.016522</td>\n",
       "      <td>-0.006677</td>\n",
       "      <td>0.010198</td>\n",
       "      <td>0.005247</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>61</th>\n",
       "      <td>gender*work_type_Never_worked</td>\n",
       "      <td>0.095687</td>\n",
       "      <td>0.145792</td>\n",
       "      <td>0.129843</td>\n",
       "      <td>0.155005</td>\n",
       "      <td>0.19042</td>\n",
       "      <td>0.172197</td>\n",
       "      <td>0.049688</td>\n",
       "      <td>0.063308</td>\n",
       "      <td>0.039769</td>\n",
       "      <td>0.066014</td>\n",
       "      <td>0.091861</td>\n",
       "      <td>0.091554</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>62</th>\n",
       "      <td>work_type_Self-employed*work_type_Self-employed</td>\n",
       "      <td>0.003233</td>\n",
       "      <td>0.006437</td>\n",
       "      <td>0.000343</td>\n",
       "      <td>0.000102</td>\n",
       "      <td>-0.016273</td>\n",
       "      <td>0.001892</td>\n",
       "      <td>-0.001782</td>\n",
       "      <td>0.01273</td>\n",
       "      <td>-0.019186</td>\n",
       "      <td>-0.038871</td>\n",
       "      <td>0.000656</td>\n",
       "      <td>0.009972</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>63</th>\n",
       "      <td>work_type_Self-employed*work_type_Never_worked</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>-0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64</th>\n",
       "      <td>work_type_Never_worked*work_type_Never_worked</td>\n",
       "      <td>-0.001001</td>\n",
       "      <td>0.002358</td>\n",
       "      <td>-0.001768</td>\n",
       "      <td>-0.011141</td>\n",
       "      <td>0.019711</td>\n",
       "      <td>-0.019584</td>\n",
       "      <td>0.016569</td>\n",
       "      <td>0.009184</td>\n",
       "      <td>-0.008235</td>\n",
       "      <td>0.007469</td>\n",
       "      <td>0.030418</td>\n",
       "      <td>-0.004646</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>65 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              Label    Step 1    Step 2  \\\n",
       "0                                               age         -         -   \n",
       "1                                      hypertension         -         -   \n",
       "2                                     heart_disease         -         -   \n",
       "3                                 avg_glucose_level         -         -   \n",
       "4                                work_type_children         -         -   \n",
       "..                                              ...       ...       ...   \n",
       "60                   gender*work_type_Self-employed  0.047222  0.030021   \n",
       "61                    gender*work_type_Never_worked  0.095687  0.145792   \n",
       "62  work_type_Self-employed*work_type_Self-employed  0.003233  0.006437   \n",
       "63   work_type_Self-employed*work_type_Never_worked      -0.0       0.0   \n",
       "64    work_type_Never_worked*work_type_Never_worked -0.001001  0.002358   \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",
       "60  0.051126  0.068857  0.087996  0.089939  0.059366  0.003143 -0.016522   \n",
       "61  0.129843  0.155005   0.19042  0.172197  0.049688  0.063308  0.039769   \n",
       "62  0.000343  0.000102 -0.016273  0.001892 -0.001782   0.01273 -0.019186   \n",
       "63      -0.0      -0.0      -0.0      -0.0      -0.0      -0.0       0.0   \n",
       "64 -0.001768 -0.011141  0.019711 -0.019584  0.016569  0.009184 -0.008235   \n",
       "\n",
       "     Step 10   Step 11   Step 12  \n",
       "0          -         -         -  \n",
       "1          -         -         -  \n",
       "2          -         -         -  \n",
       "3          -         -         -  \n",
       "4          -         -         -  \n",
       "..       ...       ...       ...  \n",
       "60 -0.006677  0.010198  0.005247  \n",
       "61  0.066014  0.091861  0.091554  \n",
       "62 -0.038871  0.000656  0.009972  \n",
       "63      -0.0      -0.0       0.0  \n",
       "64  0.007469  0.030418 -0.004646  \n",
       "\n",
       "[65 rows x 13 columns]"
      ]
     },
     "execution_count": 84,
     "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": 85,
   "id": "47534ed9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['age',\n",
       " 'hypertension',\n",
       " 'heart_disease',\n",
       " 'avg_glucose_level',\n",
       " 'work_type_children',\n",
       " 'ever_married',\n",
       " 'smoking_status_formerly smoked',\n",
       " 'gender',\n",
       " 'work_type_Self-employed',\n",
       " 'work_type_Never_worked',\n",
       " 'age*age',\n",
       " 'age*hypertension',\n",
       " 'age*work_type_children',\n",
       " 'age*avg_glucose_level',\n",
       " 'age*ever_married',\n",
       " 'age*gender',\n",
       " 'avg_glucose_level*work_type_Self-employed',\n",
       " 'ever_married*work_type_Self-employed',\n",
       " 'avg_glucose_level*ever_married',\n",
       " 'work_type_children*smoking_status_formerly smoked',\n",
       " 'age*smoking_status_formerly smoked']"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This is the final labela that we need to consider\n",
    "X_2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "270befb5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.6318\n",
      "\n",
      "Confusion matrix:\n",
      "[[1633 1355]\n",
      " [ 452 1468]]\n",
      "\n",
      "F1 score is: 0.6190\n"
     ]
    }
   ],
   "source": [
    "model_final = Pipeline([('scaler', StandardScaler()),('logistic_classifier', lr(class_weight={0:1,1:1.5}))])\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": 87,
   "id": "395cdfb3",
   "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": 88,
   "id": "f7c423a7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-0.044172488914728664"
      ]
     },
     "execution_count": 88,
     "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": 89,
   "id": "4c09e865",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.042554580466869205"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ate_ipw"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "98e02f93",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.042554580466869205"
      ]
     },
     "execution_count": 95,
     "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": 96,
   "id": "f65baa33",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.044172488914728664"
      ]
     },
     "execution_count": 96,
     "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": 97,
   "id": "3b2f8a2f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-0.001617908447859459"
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ate_ipw = A - B\n",
    "ate_ipw"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "id": "5ff608cc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mean_1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "7ae4a9ee",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.00020374898125509371"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mean_0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "2c72602f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-0.00020374898125509371"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ATE_outcome"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2b2d7c6d",
   "metadata": {},
   "source": [
    "# Doubly-robust esimator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "id": "ef2f9c40",
   "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": 102,
   "id": "68d31839",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-0.0016179084478594589"
      ]
     },
     "execution_count": 102,
     "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
}