Medication_Compliance_Forecasting.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Importing packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#Importing packages\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import average_precision_score, f1_score,confusion_matrix\n",
    "from xgboost.sklearn import XGBClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.metrics import accuracy_score,confusion_matrix,classification_report"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### LOading Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(180212, 11)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>patient_id</th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Prescription_period</th>\n",
       "      <th>Diabetes</th>\n",
       "      <th>Alcoholism</th>\n",
       "      <th>HyperTension</th>\n",
       "      <th>Smokes</th>\n",
       "      <th>Tuberculosis</th>\n",
       "      <th>Sms_Reminder</th>\n",
       "      <th>Adherence</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>19</td>\n",
       "      <td>M</td>\n",
       "      <td>7</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>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>24</td>\n",
       "      <td>F</td>\n",
       "      <td>59</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>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>F</td>\n",
       "      <td>43</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>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>38</td>\n",
       "      <td>M</td>\n",
       "      <td>66</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>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>46</td>\n",
       "      <td>F</td>\n",
       "      <td>98</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>No</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   patient_id  Age Gender  Prescription_period  Diabetes  Alcoholism  \\\n",
       "0           1   19      M                    7         0           0   \n",
       "1           2   24      F                   59         0           0   \n",
       "2           3    4      F                   43         0           0   \n",
       "3           4   38      M                   66         0           0   \n",
       "4           5   46      F                   98         0           0   \n",
       "\n",
       "   HyperTension  Smokes  Tuberculosis  Sms_Reminder Adherence  \n",
       "0             0       0             0             0        No  \n",
       "1             0       0             0             0        No  \n",
       "2             0       0             0             0        No  \n",
       "3             0       0             0             1        No  \n",
       "4             0       0             0             1        No  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# load train data\n",
    "df = pd.read_csv(r\"C:\\Users\\Triloki-Gupta\\Downloads\\Training Data.csv\")\n",
    "print(df.shape)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(119788, 10)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>patient_id</th>\n",
       "      <th>Age</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Prescription_period</th>\n",
       "      <th>Diabetes</th>\n",
       "      <th>Alcoholism</th>\n",
       "      <th>HyperTension</th>\n",
       "      <th>Smokes</th>\n",
       "      <th>Tuberculosis</th>\n",
       "      <th>Sms_Reminder</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>M</td>\n",
       "      <td>28</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>1</th>\n",
       "      <td>2</td>\n",
       "      <td>62</td>\n",
       "      <td>F</td>\n",
       "      <td>9</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>F</td>\n",
       "      <td>73</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>4</td>\n",
       "      <td>33</td>\n",
       "      <td>M</td>\n",
       "      <td>117</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>38</td>\n",
       "      <td>M</td>\n",
       "      <td>8</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",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   patient_id  Age Gender  Prescription_period  Diabetes  Alcoholism  \\\n",
       "0           1    5      M                   28         0           0   \n",
       "1           2   62      F                    9         1           0   \n",
       "2           3    4      F                   73         0           0   \n",
       "3           4   33      M                  117         0           0   \n",
       "4           5   38      M                    8         0           0   \n",
       "\n",
       "   HyperTension  Smokes  Tuberculosis  Sms_Reminder  \n",
       "0             0       0             0             1  \n",
       "1             1       0             0             0  \n",
       "2             0       0             0             1  \n",
       "3             0       0             0             0  \n",
       "4             0       0             0             1  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#loading test data\n",
    "test_df = pd.read_csv(r\"C:\\Users\\Triloki-Gupta\\Downloads\\Test Data.csv\")\n",
    "print(test_df.shape)\n",
    "test_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### EDA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 180212 entries, 0 to 180211\n",
      "Data columns (total 11 columns):\n",
      "patient_id             180212 non-null int64\n",
      "Age                    180212 non-null int64\n",
      "Gender                 180212 non-null object\n",
      "Prescription_period    180212 non-null int64\n",
      "Diabetes               180212 non-null int64\n",
      "Alcoholism             180212 non-null int64\n",
      "HyperTension           180212 non-null int64\n",
      "Smokes                 180212 non-null int64\n",
      "Tuberculosis           180212 non-null int64\n",
      "Sms_Reminder           180212 non-null int64\n",
      "Adherence              180212 non-null object\n",
      "dtypes: int64(9), object(2)\n",
      "memory usage: 15.1+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "patient_id             0\n",
       "Age                    0\n",
       "Gender                 0\n",
       "Prescription_period    0\n",
       "Diabetes               0\n",
       "Alcoholism             0\n",
       "HyperTension           0\n",
       "Smokes                 0\n",
       "Tuberculosis           0\n",
       "Sms_Reminder           0\n",
       "Adherence              0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>patient_id</th>\n",
       "      <th>Age</th>\n",
       "      <th>Prescription_period</th>\n",
       "      <th>Diabetes</th>\n",
       "      <th>Alcoholism</th>\n",
       "      <th>HyperTension</th>\n",
       "      <th>Smokes</th>\n",
       "      <th>Tuberculosis</th>\n",
       "      <th>Sms_Reminder</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>180212.000000</td>\n",
       "      <td>180212.000000</td>\n",
       "      <td>180212.000000</td>\n",
       "      <td>180212.000000</td>\n",
       "      <td>180212.000000</td>\n",
       "      <td>180212.000000</td>\n",
       "      <td>180212.000000</td>\n",
       "      <td>180212.000000</td>\n",
       "      <td>180212.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>90106.500000</td>\n",
       "      <td>37.795363</td>\n",
       "      <td>54.668485</td>\n",
       "      <td>0.078524</td>\n",
       "      <td>0.025043</td>\n",
       "      <td>0.216512</td>\n",
       "      <td>0.052566</td>\n",
       "      <td>0.000338</td>\n",
       "      <td>0.573968</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>52022.867693</td>\n",
       "      <td>22.852072</td>\n",
       "      <td>35.752491</td>\n",
       "      <td>0.268995</td>\n",
       "      <td>0.156255</td>\n",
       "      <td>0.411868</td>\n",
       "      <td>0.223166</td>\n",
       "      <td>0.018395</td>\n",
       "      <td>0.499824</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>45053.750000</td>\n",
       "      <td>19.000000</td>\n",
       "      <td>22.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>90106.500000</td>\n",
       "      <td>38.000000</td>\n",
       "      <td>51.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>135159.250000</td>\n",
       "      <td>56.000000</td>\n",
       "      <td>86.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>180212.000000</td>\n",
       "      <td>113.000000</td>\n",
       "      <td>120.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          patient_id            Age  Prescription_period       Diabetes  \\\n",
       "count  180212.000000  180212.000000        180212.000000  180212.000000   \n",
       "mean    90106.500000      37.795363            54.668485       0.078524   \n",
       "std     52022.867693      22.852072            35.752491       0.268995   \n",
       "min         1.000000       0.000000             1.000000       0.000000   \n",
       "25%     45053.750000      19.000000            22.000000       0.000000   \n",
       "50%     90106.500000      38.000000            51.000000       0.000000   \n",
       "75%    135159.250000      56.000000            86.000000       0.000000   \n",
       "max    180212.000000     113.000000           120.000000       1.000000   \n",
       "\n",
       "          Alcoholism   HyperTension         Smokes   Tuberculosis  \\\n",
       "count  180212.000000  180212.000000  180212.000000  180212.000000   \n",
       "mean        0.025043       0.216512       0.052566       0.000338   \n",
       "std         0.156255       0.411868       0.223166       0.018395   \n",
       "min         0.000000       0.000000       0.000000       0.000000   \n",
       "25%         0.000000       0.000000       0.000000       0.000000   \n",
       "50%         0.000000       0.000000       0.000000       0.000000   \n",
       "75%         0.000000       0.000000       0.000000       0.000000   \n",
       "max         1.000000       1.000000       1.000000       1.000000   \n",
       "\n",
       "        Sms_Reminder  \n",
       "count  180212.000000  \n",
       "mean        0.573968  \n",
       "std         0.499824  \n",
       "min         0.000000  \n",
       "25%         0.000000  \n",
       "50%         1.000000  \n",
       "75%         1.000000  \n",
       "max         2.000000  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>Adherence</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>M</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>F</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>F</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Gender Adherence\n",
       "0      M        No\n",
       "1      F        No\n",
       "2      F        No"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.select_dtypes(include = ['object']).head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>patient_id</th>\n",
       "      <th>Age</th>\n",
       "      <th>Prescription_period</th>\n",
       "      <th>Diabetes</th>\n",
       "      <th>Alcoholism</th>\n",
       "      <th>HyperTension</th>\n",
       "      <th>Smokes</th>\n",
       "      <th>Tuberculosis</th>\n",
       "      <th>Sms_Reminder</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>19</td>\n",
       "      <td>7</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>24</td>\n",
       "      <td>59</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>43</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",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   patient_id  Age  Prescription_period  Diabetes  Alcoholism  HyperTension  \\\n",
       "0           1   19                    7         0           0             0   \n",
       "1           2   24                   59         0           0             0   \n",
       "2           3    4                   43         0           0             0   \n",
       "\n",
       "   Smokes  Tuberculosis  Sms_Reminder  \n",
       "0       0             0             0  \n",
       "1       0             0             0  \n",
       "2       0             0             0  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.select_dtypes(include = ['int64','float64']).head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "No     125822\n",
       "Yes     54390\n",
       "Name: Adherence, dtype: int64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.Adherence.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "F    120438\n",
       "M     59774\n",
       "Name: Gender, dtype: int64"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.Gender.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>Gender</th>\n",
       "      <th>Prescription_period</th>\n",
       "      <th>Diabetes</th>\n",
       "      <th>Alcoholism</th>\n",
       "      <th>HyperTension</th>\n",
       "      <th>Smokes</th>\n",
       "      <th>Tuberculosis</th>\n",
       "      <th>Sms_Reminder</th>\n",
       "      <th>Adherence</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Age</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.102932</td>\n",
       "      <td>0.061055</td>\n",
       "      <td>0.295050</td>\n",
       "      <td>0.071761</td>\n",
       "      <td>0.509416</td>\n",
       "      <td>0.090797</td>\n",
       "      <td>0.001300</td>\n",
       "      <td>-0.051713</td>\n",
       "      <td>-0.100818</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Gender</th>\n",
       "      <td>-0.102932</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.004764</td>\n",
       "      <td>-0.019222</td>\n",
       "      <td>0.094593</td>\n",
       "      <td>-0.047295</td>\n",
       "      <td>0.040503</td>\n",
       "      <td>0.008821</td>\n",
       "      <td>-0.030121</td>\n",
       "      <td>0.010232</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Prescription_period</th>\n",
       "      <td>0.061055</td>\n",
       "      <td>-0.004764</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.017072</td>\n",
       "      <td>-0.015018</td>\n",
       "      <td>0.035913</td>\n",
       "      <td>-0.016020</td>\n",
       "      <td>-0.001677</td>\n",
       "      <td>0.001959</td>\n",
       "      <td>-0.612656</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Diabetes</th>\n",
       "      <td>0.295050</td>\n",
       "      <td>-0.019222</td>\n",
       "      <td>0.017072</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.021997</td>\n",
       "      <td>0.423884</td>\n",
       "      <td>0.041240</td>\n",
       "      <td>0.004721</td>\n",
       "      <td>-0.031252</td>\n",
       "      <td>-0.031004</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Alcoholism</th>\n",
       "      <td>0.071761</td>\n",
       "      <td>0.094593</td>\n",
       "      <td>-0.015018</td>\n",
       "      <td>0.021997</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.068796</td>\n",
       "      <td>0.390472</td>\n",
       "      <td>0.045315</td>\n",
       "      <td>-0.017998</td>\n",
       "      <td>0.024982</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>HyperTension</th>\n",
       "      <td>0.509416</td>\n",
       "      <td>-0.047295</td>\n",
       "      <td>0.035913</td>\n",
       "      <td>0.423884</td>\n",
       "      <td>0.068796</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.077154</td>\n",
       "      <td>-0.001617</td>\n",
       "      <td>-0.043751</td>\n",
       "      <td>-0.061314</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Smokes</th>\n",
       "      <td>0.090797</td>\n",
       "      <td>0.040503</td>\n",
       "      <td>-0.016020</td>\n",
       "      <td>0.041240</td>\n",
       "      <td>0.390472</td>\n",
       "      <td>0.077154</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.021349</td>\n",
       "      <td>-0.011701</td>\n",
       "      <td>0.023993</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tuberculosis</th>\n",
       "      <td>0.001300</td>\n",
       "      <td>0.008821</td>\n",
       "      <td>-0.001677</td>\n",
       "      <td>0.004721</td>\n",
       "      <td>0.045315</td>\n",
       "      <td>-0.001617</td>\n",
       "      <td>0.021349</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.006043</td>\n",
       "      <td>0.002359</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Sms_Reminder</th>\n",
       "      <td>-0.051713</td>\n",
       "      <td>-0.030121</td>\n",
       "      <td>0.001959</td>\n",
       "      <td>-0.031252</td>\n",
       "      <td>-0.017998</td>\n",
       "      <td>-0.043751</td>\n",
       "      <td>-0.011701</td>\n",
       "      <td>-0.006043</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.002519</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Adherence</th>\n",
       "      <td>-0.100818</td>\n",
       "      <td>0.010232</td>\n",
       "      <td>-0.612656</td>\n",
       "      <td>-0.031004</td>\n",
       "      <td>0.024982</td>\n",
       "      <td>-0.061314</td>\n",
       "      <td>0.023993</td>\n",
       "      <td>0.002359</td>\n",
       "      <td>-0.002519</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                          Age    Gender  Prescription_period  Diabetes  \\\n",
       "Age                  1.000000 -0.102932             0.061055  0.295050   \n",
       "Gender              -0.102932  1.000000            -0.004764 -0.019222   \n",
       "Prescription_period  0.061055 -0.004764             1.000000  0.017072   \n",
       "Diabetes             0.295050 -0.019222             0.017072  1.000000   \n",
       "Alcoholism           0.071761  0.094593            -0.015018  0.021997   \n",
       "HyperTension         0.509416 -0.047295             0.035913  0.423884   \n",
       "Smokes               0.090797  0.040503            -0.016020  0.041240   \n",
       "Tuberculosis         0.001300  0.008821            -0.001677  0.004721   \n",
       "Sms_Reminder        -0.051713 -0.030121             0.001959 -0.031252   \n",
       "Adherence           -0.100818  0.010232            -0.612656 -0.031004   \n",
       "\n",
       "                     Alcoholism  HyperTension    Smokes  Tuberculosis  \\\n",
       "Age                    0.071761      0.509416  0.090797      0.001300   \n",
       "Gender                 0.094593     -0.047295  0.040503      0.008821   \n",
       "Prescription_period   -0.015018      0.035913 -0.016020     -0.001677   \n",
       "Diabetes               0.021997      0.423884  0.041240      0.004721   \n",
       "Alcoholism             1.000000      0.068796  0.390472      0.045315   \n",
       "HyperTension           0.068796      1.000000  0.077154     -0.001617   \n",
       "Smokes                 0.390472      0.077154  1.000000      0.021349   \n",
       "Tuberculosis           0.045315     -0.001617  0.021349      1.000000   \n",
       "Sms_Reminder          -0.017998     -0.043751 -0.011701     -0.006043   \n",
       "Adherence              0.024982     -0.061314  0.023993      0.002359   \n",
       "\n",
       "                     Sms_Reminder  Adherence  \n",
       "Age                     -0.051713  -0.100818  \n",
       "Gender                  -0.030121   0.010232  \n",
       "Prescription_period      0.001959  -0.612656  \n",
       "Diabetes                -0.031252  -0.031004  \n",
       "Alcoholism              -0.017998   0.024982  \n",
       "HyperTension            -0.043751  -0.061314  \n",
       "Smokes                  -0.011701   0.023993  \n",
       "Tuberculosis            -0.006043   0.002359  \n",
       "Sms_Reminder             1.000000  -0.002519  \n",
       "Adherence               -0.002519   1.000000  "
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.corr()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "test = test_df.copy()\n",
    "test['Gender']=test['Gender'].apply(lambda x: 1 if x=='M' else 0)\n",
    "test = test.drop(['patient_id'], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df['Adherence']=df['Adherence'].apply(lambda x: 1 if x=='Yes' else 0)\n",
    "df['Gender']=df['Gender'].apply(lambda x: 1 if x=='M' else 0)\n",
    "data = df.drop(['patient_id'], axis=1)\n",
    "X=data.drop('Adherence',axis=1)\n",
    "y=data.Adherence"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# splinting data into X_train, X_test, y_train, y_test\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3,random_state=42, shuffle=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### ML Model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### XGBClassifier\n",
    "\n",
    "***Parameter tuning***"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=3, error_score='raise-deprecating',\n",
       "       estimator=XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n",
       "       colsample_bynode=1, colsample_bytree=1, gamma=0, learning_rate=0.1,\n",
       "       max_delta_step=0, max_depth=3, min_child_weight=1, missing=None,\n",
       "       n_estimators=100, n_jobs=1, nthread=None,\n",
       "       objective='binary:logistic', random_state=0, reg_alpha=0,\n",
       "       reg_lambda=1, scale_pos_weight=1, seed=None, silent=None,\n",
       "       subsample=1, verbosity=1),\n",
       "       fit_params=None, iid='warn', n_jobs=None,\n",
       "       param_grid={'min_child_weight': [1, 5, 10], 'gamma': [0.5, 1, 1.5, 2, 5], 'subsample': [0.6, 0.8, 1.0], 'colsample_bytree': [0.6, 0.8, 1.0], 'max_depth': [3, 4, 5], 'learning_rate': [0.01, 0.1, 1, 10]},\n",
       "       pre_dispatch='2*n_jobs', refit=True, return_train_score='warn',\n",
       "       scoring=None, verbose=0)"
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import RandomizedSearchCV, GridSearchCV\n",
    "xgb=XGBClassifier()\n",
    "params = {\n",
    "        'min_child_weight': [1, 5, 10],\n",
    "        'gamma': [0.5, 1, 1.5, 2, 5],\n",
    "        'subsample': [0.6, 0.8, 1.0],\n",
    "        'colsample_bytree': [0.6, 0.8, 1.0],\n",
    "        'max_depth': [3, 4, 5],\n",
    "        'learning_rate':[0.01,0.1,1,10]\n",
    "        }\n",
    "CV_xgb = GridSearchCV(estimator=xgb, param_grid=params, cv= 3)\n",
    "CV_xgb.fit(X, y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'colsample_bytree': 0.6,\n",
       " 'gamma': 0.5,\n",
       " 'learning_rate': 0.01,\n",
       " 'max_depth': 3,\n",
       " 'min_child_weight': 1,\n",
       " 'subsample': 0.6}"
      ]
     },
     "execution_count": 104,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "CV_xgb.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Wall time: 17.3 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "xgb = XGBClassifier(colsample_bytree=0.6,gamma=0.5,learning_rate=0.01,max_depth=3,min_child_weight=1,subsample=0.6)\n",
    "xgb.fit(X, y)\n",
    "y_pred=xgb.predict(test)\n",
    "# print(\"classification_report\")\n",
    "# print(classification_report(y_test,y_pred))\n",
    "# print('Confusion_matrix : ')\n",
    "# print(confusion_matrix(y_test,y_pred))\n",
    "# print(\"accuracy_score\")\n",
    "# print(accuracy_score(y_test,y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(119788, 3)\n",
      "   patient_id Adherence  Probability_Score\n",
      "0           1       Yes           0.583873\n",
      "1           2       Yes           0.528068\n",
      "2           3        No           0.280868\n",
      "3           4        No           0.283300\n",
      "4           5       Yes           0.580708\n",
      "Wall time: 2.37 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "prob = pd.DataFrame(xgb.predict_proba(test), columns=[\"prob0\",\"Probability_Score\"])\n",
    "adhe = pd.DataFrame(xgb.predict(test), columns=[\"Adherence\"])\n",
    "adhe['Adherence'] = adhe['Adherence'].apply(lambda x: 'Yes' if x==1 else 'No')\n",
    "patient_id = test_df.patient_id\n",
    "output = pd.concat([patient_id,adhe, prob.Probability_Score], axis=1)\n",
    "print(output.shape)\n",
    "print(output.head())\n",
    "output.to_csv(r'C:\\Users\\Triloki-Gupta\\Downloads\\Results.csv',index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### RandomForestClassifier\n",
    "\n",
    "***Parameter tuning***"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=2, error_score='raise-deprecating',\n",
       "       estimator=RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
       "            max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "            min_weight_fraction_leaf=0.0, n_estimators='warn', n_jobs=None,\n",
       "            oob_score=False, random_state=42, verbose=0, warm_start=False),\n",
       "       fit_params=None, iid='warn', n_jobs=None,\n",
       "       param_grid={'n_estimators': [200, 500], 'max_features': ['auto', 'sqrt', 'log2'], 'max_depth': [4, 5, 6, 7, 8], 'criterion': ['gini', 'entropy']},\n",
       "       pre_dispatch='2*n_jobs', refit=True, return_train_score='warn',\n",
       "       scoring=None, verbose=0)"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import RandomizedSearchCV, GridSearchCV\n",
    "rfc=RandomForestClassifier(random_state=42)\n",
    "param_grid = { \n",
    "    'n_estimators': [200, 500],\n",
    "    'max_features': ['auto', 'sqrt', 'log2'],\n",
    "    'max_depth' : [4,5,6,7,8],\n",
    "    'criterion' :['gini', 'entropy']\n",
    "}\n",
    "CV_rfc = GridSearchCV(estimator=rfc, param_grid=param_grid, cv= 2)\n",
    "CV_rfc.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'criterion': 'entropy',\n",
       " 'max_depth': 8,\n",
       " 'max_features': 'auto',\n",
       " 'n_estimators': 500}"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "CV_rfc.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=3, error_score='raise-deprecating',\n",
       "       estimator=RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
       "            max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "            min_weight_fraction_leaf=0.0, n_estimators='warn', n_jobs=None,\n",
       "            oob_score=False, random_state=42, verbose=0, warm_start=False),\n",
       "       fit_params=None, iid='warn', n_jobs=None,\n",
       "       param_grid={'n_estimators': [100, 200, 500], 'max_features': ['auto', 'sqrt', 'log2'], 'max_depth': [4, 5, 6, 7, 8], 'criterion': ['gini', 'entropy']},\n",
       "       pre_dispatch='2*n_jobs', refit=True, return_train_score='warn',\n",
       "       scoring=None, verbose=0)"
      ]
     },
     "execution_count": 107,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import RandomizedSearchCV, GridSearchCV\n",
    "rfc=RandomForestClassifier(random_state=42)\n",
    "param_grid = { \n",
    "    'n_estimators': [100, 200, 500],\n",
    "    'max_features': ['auto', 'sqrt', 'log2'],\n",
    "    'max_depth' : [4,5,6,7,8],\n",
    "    'criterion' :['gini', 'entropy']\n",
    "}\n",
    "CV_rfc = GridSearchCV(estimator=rfc, param_grid=param_grid, cv= 3)\n",
    "CV_rfc.fit(X, y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'criterion': 'gini',\n",
       " 'max_depth': 4,\n",
       " 'max_features': 'auto',\n",
       " 'n_estimators': 100}"
      ]
     },
     "execution_count": 108,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "CV_rfc.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Wall time: 4.21 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "rf = RandomForestClassifier(criterion='gini',\n",
    " max_depth=4,\n",
    " max_features='auto',\n",
    " n_estimators=100)\n",
    "rf.fit(X, y)\n",
    "# y_pred=clf2.predict(X_test)\n",
    "# print(\"classification_report\")\n",
    "# print(classification_report(y_test,y_pred))\n",
    "# print('Confusion_matrix : ')\n",
    "# print(confusion_matrix(y_test,y_pred))\n",
    "# print(\"accuracy_score\")\n",
    "# print(accuracy_score(y_test,y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}