Heart_Disease_Prediction_Model.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Innovative Assignment Name : Heart Disease Prediction Model\n",
    "\n",
    "Course Code & Name :- 2CS404, Programming for Scientific Computing\n",
    "\n",
    "Group Members Roll no. :- 21BCE248, 21BCE259, 21BCE296\n",
    "\n",
    "Faculty Name :- Malaram Kumhar"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "aTb-9TFFqprC"
   },
   "source": [
    "Importing the Dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "id": "3q9U3S_whh3-"
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "# libraries to handle the null values\n",
    "from sklearn.experimental import enable_iterative_imputer\n",
    "from sklearn.impute import IterativeImputer\n",
    "from sklearn.ensemble import RandomForestRegressor"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Important links to explore above libraries\n",
    "\n",
    "Pandas :\n",
    "https://pandas.pydata.org/docs/user_guide/index.html\n",
    "\n",
    "Numpy :\n",
    "https://numpy.org/doc/stable/user/index.html\n",
    "\n",
    "Logistic Regression :\n",
    "https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
    "\n",
    "RandomForestRegressor :\n",
    "https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestRegressor.html#sklearn-ensemble-randomforestregressor\n",
    "\n",
    "Random Forest :\n",
    "https://scikit-learn.org/stable/modules/ensemble.html#random-forests\n",
    "\n",
    "Preprocessing Data :\n",
    "https://scikit-learn.org/stable/modules/preprocessing.html#preprocessing-data\n",
    "\n",
    "Handling null values :\n",
    "https://towardsdatascience.com/6-tips-for-dealing-with-null-values-e16d1d1a1b33"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "egMd5zeurTMR"
   },
   "source": [
    "Data Collection and Processing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "id": "0q-3-LkQrREV"
   },
   "outputs": [],
   "source": [
    "# loading the csv data to a Pandas DataFrame\n",
    "heart_data = pd.read_csv('heart_disease_data.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 198
    },
    "id": "M8dQxSTqriWD",
    "outputId": "ea695a74-7589-47fe-e400-2dd925f7b5bb"
   },
   "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>sex</th>\n",
       "      <th>cp</th>\n",
       "      <th>trestbps</th>\n",
       "      <th>chol</th>\n",
       "      <th>fbs</th>\n",
       "      <th>restecg</th>\n",
       "      <th>thalach</th>\n",
       "      <th>exang</th>\n",
       "      <th>oldpeak</th>\n",
       "      <th>slope</th>\n",
       "      <th>ca</th>\n",
       "      <th>thal</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>52.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>125</td>\n",
       "      <td>212.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>168.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>53.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>140</td>\n",
       "      <td>203.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>155.0</td>\n",
       "      <td>1</td>\n",
       "      <td>3.1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>70.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>145</td>\n",
       "      <td>174.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>125.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2.6</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>61.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>148</td>\n",
       "      <td>203.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>161.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>62.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>138</td>\n",
       "      <td>294.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>106.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1.9</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    age  sex  cp  trestbps   chol  fbs  restecg  thalach  exang  oldpeak  \\\n",
       "0  52.0  1.0   0       125  212.0    0        1    168.0      0      1.0   \n",
       "1  53.0  1.0   0       140  203.0    1        0    155.0      1      3.1   \n",
       "2  70.0  1.0   0       145  174.0    0        1    125.0      1      2.6   \n",
       "3  61.0  1.0   0       148  203.0    0        1    161.0      0      0.0   \n",
       "4  62.0  0.0   0       138  294.0    1        1    106.0      0      1.9   \n",
       "\n",
       "   slope  ca  thal  target  \n",
       "0      2   2     3     0.0  \n",
       "1      0   0     3     0.0  \n",
       "2      0   0     3     0.0  \n",
       "3      2   1     3     0.0  \n",
       "4      1   3     2     0.0  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# print first 5 rows of the dataset\n",
    "heart_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 198
    },
    "id": "Fx_aCZDgrqdR",
    "outputId": "770eb646-bdff-45da-ac1c-06aae06f7446"
   },
   "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>sex</th>\n",
       "      <th>cp</th>\n",
       "      <th>trestbps</th>\n",
       "      <th>chol</th>\n",
       "      <th>fbs</th>\n",
       "      <th>restecg</th>\n",
       "      <th>thalach</th>\n",
       "      <th>exang</th>\n",
       "      <th>oldpeak</th>\n",
       "      <th>slope</th>\n",
       "      <th>ca</th>\n",
       "      <th>thal</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1023</th>\n",
       "      <td>50.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>110</td>\n",
       "      <td>254.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>159.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1024</th>\n",
       "      <td>54.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>120</td>\n",
       "      <td>188.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>113.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1025</th>\n",
       "      <td>61.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>148</td>\n",
       "      <td>203.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>161.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1026</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>112</td>\n",
       "      <td>204.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>143.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1027</th>\n",
       "      <td>47.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2</td>\n",
       "      <td>108</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       age  sex  cp  trestbps   chol  fbs  restecg  thalach  exang  oldpeak  \\\n",
       "1023  50.0  0.0   0       110  254.0    0        0    159.0      0      0.0   \n",
       "1024  54.0  1.0   0       120  188.0    0        1    113.0      0      1.4   \n",
       "1025  61.0  NaN   0       148  203.0    0        1    161.0      0      0.0   \n",
       "1026   NaN  1.0   0       112  204.0    0        1    143.0      0      0.1   \n",
       "1027  47.0  1.0   2       108    NaN    0        1      NaN      0      0.0   \n",
       "\n",
       "      slope  ca  thal  target  \n",
       "1023      2   0     2     1.0  \n",
       "1024      1   1     3     0.0  \n",
       "1025      2   1     3     NaN  \n",
       "1026      2   0     2     NaN  \n",
       "1027      2   0     2     0.0  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# print last 5 rows of the dataset\n",
    "heart_data.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "8nX1tIzbrz0u",
    "outputId": "6f650e4c-22b6-4750-ca57-ba6758d1c3a2"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1028, 14)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# number of rows and columns in the dataset\n",
    "heart_data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "7_xTcw1Sr6aJ",
    "outputId": "1948e00e-0656-43ef-c4c4-740ee51a6381"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 1028 entries, 0 to 1027\n",
      "Data columns (total 14 columns):\n",
      " #   Column    Non-Null Count  Dtype  \n",
      "---  ------    --------------  -----  \n",
      " 0   age       1027 non-null   float64\n",
      " 1   sex       1027 non-null   float64\n",
      " 2   cp        1028 non-null   int64  \n",
      " 3   trestbps  1028 non-null   int64  \n",
      " 4   chol      1027 non-null   float64\n",
      " 5   fbs       1028 non-null   int64  \n",
      " 6   restecg   1028 non-null   int64  \n",
      " 7   thalach   1027 non-null   float64\n",
      " 8   exang     1028 non-null   int64  \n",
      " 9   oldpeak   1028 non-null   float64\n",
      " 10  slope     1028 non-null   int64  \n",
      " 11  ca        1028 non-null   int64  \n",
      " 12  thal      1028 non-null   int64  \n",
      " 13  target    1026 non-null   float64\n",
      "dtypes: float64(6), int64(8)\n",
      "memory usage: 112.6 KB\n"
     ]
    }
   ],
   "source": [
    "# getting some info about the data\n",
    "heart_data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "GjHtW31rsGlb",
    "outputId": "8c1c23ce-b5b4-4872-a579-9b4185d12522"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age         1\n",
       "sex         1\n",
       "cp          0\n",
       "trestbps    0\n",
       "chol        1\n",
       "fbs         0\n",
       "restecg     0\n",
       "thalach     1\n",
       "exang       0\n",
       "oldpeak     0\n",
       "slope       0\n",
       "ca          0\n",
       "thal        0\n",
       "target      2\n",
       "dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# checking for missing values\n",
    "heart_data.isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Handling the null values."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>sex</th>\n",
       "      <th>cp</th>\n",
       "      <th>trestbps</th>\n",
       "      <th>chol</th>\n",
       "      <th>fbs</th>\n",
       "      <th>restecg</th>\n",
       "      <th>thalach</th>\n",
       "      <th>exang</th>\n",
       "      <th>oldpeak</th>\n",
       "      <th>slope</th>\n",
       "      <th>ca</th>\n",
       "      <th>thal</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>52.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>125.0</td>\n",
       "      <td>212.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>168.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>53.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>203.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>155.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>70.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>145.0</td>\n",
       "      <td>174.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>125.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.6</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>61.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>148.0</td>\n",
       "      <td>203.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>161.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>62.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>138.0</td>\n",
       "      <td>294.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>106.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.9</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1023</th>\n",
       "      <td>50.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>110.0</td>\n",
       "      <td>254.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>159.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1024</th>\n",
       "      <td>54.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>120.0</td>\n",
       "      <td>188.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>113.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1025</th>\n",
       "      <td>61.00</td>\n",
       "      <td>0.99</td>\n",
       "      <td>0.0</td>\n",
       "      <td>148.0</td>\n",
       "      <td>203.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>161.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1026</th>\n",
       "      <td>47.02</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>112.0</td>\n",
       "      <td>204.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>143.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1027</th>\n",
       "      <td>47.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>2.0</td>\n",
       "      <td>108.0</td>\n",
       "      <td>242.61</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>152.24</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1028 rows × 14 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        age   sex   cp  trestbps    chol  fbs  restecg  thalach  exang  \\\n",
       "0     52.00  1.00  0.0     125.0  212.00  0.0      1.0   168.00    0.0   \n",
       "1     53.00  1.00  0.0     140.0  203.00  1.0      0.0   155.00    1.0   \n",
       "2     70.00  1.00  0.0     145.0  174.00  0.0      1.0   125.00    1.0   \n",
       "3     61.00  1.00  0.0     148.0  203.00  0.0      1.0   161.00    0.0   \n",
       "4     62.00  0.00  0.0     138.0  294.00  1.0      1.0   106.00    0.0   \n",
       "...     ...   ...  ...       ...     ...  ...      ...      ...    ...   \n",
       "1023  50.00  0.00  0.0     110.0  254.00  0.0      0.0   159.00    0.0   \n",
       "1024  54.00  1.00  0.0     120.0  188.00  0.0      1.0   113.00    0.0   \n",
       "1025  61.00  0.99  0.0     148.0  203.00  0.0      1.0   161.00    0.0   \n",
       "1026  47.02  1.00  0.0     112.0  204.00  0.0      1.0   143.00    0.0   \n",
       "1027  47.00  1.00  2.0     108.0  242.61  0.0      1.0   152.24    0.0   \n",
       "\n",
       "      oldpeak  slope   ca  thal  target  \n",
       "0         1.0    2.0  2.0   3.0     0.0  \n",
       "1         3.1    0.0  0.0   3.0     0.0  \n",
       "2         2.6    0.0  0.0   3.0     0.0  \n",
       "3         0.0    2.0  1.0   3.0     0.0  \n",
       "4         1.9    1.0  3.0   2.0     0.0  \n",
       "...       ...    ...  ...   ...     ...  \n",
       "1023      0.0    2.0  0.0   2.0     1.0  \n",
       "1024      1.4    1.0  1.0   3.0     0.0  \n",
       "1025      0.0    2.0  1.0   3.0     0.0  \n",
       "1026      0.1    2.0  0.0   2.0     1.0  \n",
       "1027      0.0    2.0  0.0   2.0     0.0  \n",
       "\n",
       "[1028 rows x 14 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Here we are using RandomForestRegressor. We can use any other regression model also.\n",
    "# we will do imputation and will save imputed dataset as heart_data2\n",
    "\n",
    "heart_data1 = heart_data[['age', 'sex', 'cp', 'trestbps', 'chol', 'fbs', 'restecg', 'thalach', 'exang', 'oldpeak', 'slope', 'ca', 'thal', 'target']]\n",
    "imptr = IterativeImputer(RandomForestRegressor(), max_iter=10, random_state=0)\n",
    "heart_data2 = pd.DataFrame(imptr.fit_transform(heart_data1), columns = heart_data1.columns)\n",
    "heart_data2 # unimputed data, the data that handled the null values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age         0\n",
       "sex         0\n",
       "cp          0\n",
       "trestbps    0\n",
       "chol        0\n",
       "fbs         0\n",
       "restecg     0\n",
       "thalach     0\n",
       "exang       0\n",
       "oldpeak     0\n",
       "slope       0\n",
       "ca          0\n",
       "thal        0\n",
       "target      0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# checking for missing values\n",
    "heart_data2.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>sex</th>\n",
       "      <th>cp</th>\n",
       "      <th>trestbps</th>\n",
       "      <th>chol</th>\n",
       "      <th>fbs</th>\n",
       "      <th>restecg</th>\n",
       "      <th>thalach</th>\n",
       "      <th>exang</th>\n",
       "      <th>oldpeak</th>\n",
       "      <th>slope</th>\n",
       "      <th>ca</th>\n",
       "      <th>thal</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>52.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>125.0</td>\n",
       "      <td>212.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>168.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>53.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>140.0</td>\n",
       "      <td>203.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>155.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>70.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>145.0</td>\n",
       "      <td>174.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>125.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.6</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>61.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>148.0</td>\n",
       "      <td>203.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>161.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>62.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>138.0</td>\n",
       "      <td>294.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>106.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.9</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1023</th>\n",
       "      <td>50.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>110.0</td>\n",
       "      <td>254.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>159.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1024</th>\n",
       "      <td>54.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>120.0</td>\n",
       "      <td>188.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>113.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1025</th>\n",
       "      <td>61.00</td>\n",
       "      <td>0.99</td>\n",
       "      <td>0.0</td>\n",
       "      <td>148.0</td>\n",
       "      <td>203.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>161.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1026</th>\n",
       "      <td>47.02</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>112.0</td>\n",
       "      <td>204.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>143.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1027</th>\n",
       "      <td>47.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>2.0</td>\n",
       "      <td>108.0</td>\n",
       "      <td>242.61</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>152.24</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1028 rows × 14 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        age   sex   cp  trestbps    chol  fbs  restecg  thalach  exang  \\\n",
       "0     52.00  1.00  0.0     125.0  212.00  0.0      1.0   168.00    0.0   \n",
       "1     53.00  1.00  0.0     140.0  203.00  1.0      0.0   155.00    1.0   \n",
       "2     70.00  1.00  0.0     145.0  174.00  0.0      1.0   125.00    1.0   \n",
       "3     61.00  1.00  0.0     148.0  203.00  0.0      1.0   161.00    0.0   \n",
       "4     62.00  0.00  0.0     138.0  294.00  1.0      1.0   106.00    0.0   \n",
       "...     ...   ...  ...       ...     ...  ...      ...      ...    ...   \n",
       "1023  50.00  0.00  0.0     110.0  254.00  0.0      0.0   159.00    0.0   \n",
       "1024  54.00  1.00  0.0     120.0  188.00  0.0      1.0   113.00    0.0   \n",
       "1025  61.00  0.99  0.0     148.0  203.00  0.0      1.0   161.00    0.0   \n",
       "1026  47.02  1.00  0.0     112.0  204.00  0.0      1.0   143.00    0.0   \n",
       "1027  47.00  1.00  2.0     108.0  242.61  0.0      1.0   152.24    0.0   \n",
       "\n",
       "      oldpeak  slope   ca  thal  target  \n",
       "0         1.0    2.0  2.0   3.0     0.0  \n",
       "1         3.1    0.0  0.0   3.0     0.0  \n",
       "2         2.6    0.0  0.0   3.0     0.0  \n",
       "3         0.0    2.0  1.0   3.0     0.0  \n",
       "4         1.9    1.0  3.0   2.0     0.0  \n",
       "...       ...    ...  ...   ...     ...  \n",
       "1023      0.0    2.0  0.0   2.0     1.0  \n",
       "1024      1.4    1.0  1.0   3.0     0.0  \n",
       "1025      0.0    2.0  1.0   3.0     0.0  \n",
       "1026      0.1    2.0  0.0   2.0     1.0  \n",
       "1027      0.0    2.0  0.0   2.0     0.0  \n",
       "\n",
       "[1028 rows x 14 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Replacing imputed data with new data. / Imputation\n",
    "heart_data = heart_data2\n",
    "heart_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 308
    },
    "id": "OHmcP7DJsSEP",
    "outputId": "400a121e-dbd2-4e77-8c72-021c12af5927"
   },
   "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>sex</th>\n",
       "      <th>cp</th>\n",
       "      <th>trestbps</th>\n",
       "      <th>chol</th>\n",
       "      <th>fbs</th>\n",
       "      <th>restecg</th>\n",
       "      <th>thalach</th>\n",
       "      <th>exang</th>\n",
       "      <th>oldpeak</th>\n",
       "      <th>slope</th>\n",
       "      <th>ca</th>\n",
       "      <th>thal</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1028.000000</td>\n",
       "      <td>1028.000000</td>\n",
       "      <td>1028.000000</td>\n",
       "      <td>1028.000000</td>\n",
       "      <td>1028.000000</td>\n",
       "      <td>1028.000000</td>\n",
       "      <td>1028.000000</td>\n",
       "      <td>1028.000000</td>\n",
       "      <td>1028.000000</td>\n",
       "      <td>1028.000000</td>\n",
       "      <td>1028.000000</td>\n",
       "      <td>1028.000000</td>\n",
       "      <td>1028.000000</td>\n",
       "      <td>1028.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>54.426089</td>\n",
       "      <td>0.696488</td>\n",
       "      <td>0.941634</td>\n",
       "      <td>131.585603</td>\n",
       "      <td>245.914018</td>\n",
       "      <td>0.148833</td>\n",
       "      <td>0.531128</td>\n",
       "      <td>149.122802</td>\n",
       "      <td>0.335603</td>\n",
       "      <td>1.068482</td>\n",
       "      <td>1.387160</td>\n",
       "      <td>0.752918</td>\n",
       "      <td>2.323930</td>\n",
       "      <td>0.512646</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>9.067264</td>\n",
       "      <td>0.459988</td>\n",
       "      <td>1.029505</td>\n",
       "      <td>17.524762</td>\n",
       "      <td>51.551270</td>\n",
       "      <td>0.356097</td>\n",
       "      <td>0.527717</td>\n",
       "      <td>22.976089</td>\n",
       "      <td>0.472431</td>\n",
       "      <td>1.174676</td>\n",
       "      <td>0.617744</td>\n",
       "      <td>1.029857</td>\n",
       "      <td>0.620277</td>\n",
       "      <td>0.500083</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>29.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>94.000000</td>\n",
       "      <td>126.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>71.000000</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>48.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>120.000000</td>\n",
       "      <td>211.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>132.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>56.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>130.000000</td>\n",
       "      <td>240.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>152.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.800000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>61.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>140.000000</td>\n",
       "      <td>275.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>166.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.800000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>77.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>200.000000</td>\n",
       "      <td>564.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>202.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>6.200000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               age          sex           cp     trestbps         chol  \\\n",
       "count  1028.000000  1028.000000  1028.000000  1028.000000  1028.000000   \n",
       "mean     54.426089     0.696488     0.941634   131.585603   245.914018   \n",
       "std       9.067264     0.459988     1.029505    17.524762    51.551270   \n",
       "min      29.000000     0.000000     0.000000    94.000000   126.000000   \n",
       "25%      48.000000     0.000000     0.000000   120.000000   211.000000   \n",
       "50%      56.000000     1.000000     1.000000   130.000000   240.000000   \n",
       "75%      61.000000     1.000000     2.000000   140.000000   275.000000   \n",
       "max      77.000000     1.000000     3.000000   200.000000   564.000000   \n",
       "\n",
       "               fbs      restecg      thalach        exang      oldpeak  \\\n",
       "count  1028.000000  1028.000000  1028.000000  1028.000000  1028.000000   \n",
       "mean      0.148833     0.531128   149.122802     0.335603     1.068482   \n",
       "std       0.356097     0.527717    22.976089     0.472431     1.174676   \n",
       "min       0.000000     0.000000    71.000000     0.000000     0.000000   \n",
       "25%       0.000000     0.000000   132.000000     0.000000     0.000000   \n",
       "50%       0.000000     1.000000   152.000000     0.000000     0.800000   \n",
       "75%       0.000000     1.000000   166.000000     1.000000     1.800000   \n",
       "max       1.000000     2.000000   202.000000     1.000000     6.200000   \n",
       "\n",
       "             slope           ca         thal       target  \n",
       "count  1028.000000  1028.000000  1028.000000  1028.000000  \n",
       "mean      1.387160     0.752918     2.323930     0.512646  \n",
       "std       0.617744     1.029857     0.620277     0.500083  \n",
       "min       0.000000     0.000000     0.000000     0.000000  \n",
       "25%       1.000000     0.000000     2.000000     0.000000  \n",
       "50%       1.000000     0.000000     2.000000     1.000000  \n",
       "75%       2.000000     1.000000     3.000000     1.000000  \n",
       "max       2.000000     4.000000     3.000000     1.000000  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# statistical measures about the data\n",
    "heart_data.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "4InaOSIUsfWP",
    "outputId": "6c38694f-7445-47b3-e235-cdd0157a4ec6"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0    527\n",
       "0.0    501\n",
       "Name: target, dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# checking the distribution of Target Variable\n",
    "heart_data['target'].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "aSOBu4qDtJy5"
   },
   "source": [
    "1 --> Defective Heart\n",
    "\n",
    "0 --> Healthy Heart"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "tW8i4igjtPRC"
   },
   "source": [
    "Splitting the Features and Target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "id": "Q6yfbswrs7m3"
   },
   "outputs": [],
   "source": [
    "X = heart_data.drop(columns='target', axis=1)\n",
    "Y = heart_data['target']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "XJoCp4ZKtpZy",
    "outputId": "549bc077-393d-4763-f64f-3d2e5faa0c7f"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "        age   sex   cp  trestbps    chol  fbs  restecg  thalach  exang  \\\n",
      "0     52.00  1.00  0.0     125.0  212.00  0.0      1.0   168.00    0.0   \n",
      "1     53.00  1.00  0.0     140.0  203.00  1.0      0.0   155.00    1.0   \n",
      "2     70.00  1.00  0.0     145.0  174.00  0.0      1.0   125.00    1.0   \n",
      "3     61.00  1.00  0.0     148.0  203.00  0.0      1.0   161.00    0.0   \n",
      "4     62.00  0.00  0.0     138.0  294.00  1.0      1.0   106.00    0.0   \n",
      "...     ...   ...  ...       ...     ...  ...      ...      ...    ...   \n",
      "1023  50.00  0.00  0.0     110.0  254.00  0.0      0.0   159.00    0.0   \n",
      "1024  54.00  1.00  0.0     120.0  188.00  0.0      1.0   113.00    0.0   \n",
      "1025  61.00  0.99  0.0     148.0  203.00  0.0      1.0   161.00    0.0   \n",
      "1026  47.02  1.00  0.0     112.0  204.00  0.0      1.0   143.00    0.0   \n",
      "1027  47.00  1.00  2.0     108.0  242.61  0.0      1.0   152.24    0.0   \n",
      "\n",
      "      oldpeak  slope   ca  thal  \n",
      "0         1.0    2.0  2.0   3.0  \n",
      "1         3.1    0.0  0.0   3.0  \n",
      "2         2.6    0.0  0.0   3.0  \n",
      "3         0.0    2.0  1.0   3.0  \n",
      "4         1.9    1.0  3.0   2.0  \n",
      "...       ...    ...  ...   ...  \n",
      "1023      0.0    2.0  0.0   2.0  \n",
      "1024      1.4    1.0  1.0   3.0  \n",
      "1025      0.0    2.0  1.0   3.0  \n",
      "1026      0.1    2.0  0.0   2.0  \n",
      "1027      0.0    2.0  0.0   2.0  \n",
      "\n",
      "[1028 rows x 13 columns]\n"
     ]
    }
   ],
   "source": [
    "print(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "nukuj-YItq1w",
    "outputId": "7c604a47-1690-4db4-fec7-bed3e9497428"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0       0.0\n",
      "1       0.0\n",
      "2       0.0\n",
      "3       0.0\n",
      "4       0.0\n",
      "       ... \n",
      "1023    1.0\n",
      "1024    0.0\n",
      "1025    0.0\n",
      "1026    1.0\n",
      "1027    0.0\n",
      "Name: target, Length: 1028, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "print(Y)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_EcjSE3Et18n"
   },
   "source": [
    "Splitting the Data into Training data & Test Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "id": "a-UUfRUxtuga"
   },
   "outputs": [],
   "source": [
    "X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, stratify=Y, random_state=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "x7PrjC6zuf6X",
    "outputId": "f2d66421-d671-4475-a51c-b37de3a2edac"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1028, 13) (822, 13) (206, 13)\n"
     ]
    }
   ],
   "source": [
    "print(X.shape, X_train.shape, X_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "beSkZmpVuvn9"
   },
   "source": [
    "Model Training"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "gi2NOWZjuxzw"
   },
   "source": [
    "Logistic Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "id": "4-Md74FYuqNL"
   },
   "outputs": [],
   "source": [
    "model = LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "kCdHYxGUu7XD",
    "outputId": "ff7185b7-1dd2-418d-c22f-778005b4655b"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:814: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# training the LogisticRegression model with Training data\n",
    "model.fit(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ZYIw8Gi9vXfU"
   },
   "source": [
    "Model Evaluation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "wmxAekfZvZa9"
   },
   "source": [
    "Accuracy Score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "id": "g19JaUTMvPKy"
   },
   "outputs": [],
   "source": [
    "# accuracy on training data\n",
    "X_train_prediction = model.predict(X_train)\n",
    "training_data_accuracy = accuracy_score(X_train_prediction, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "uQBZvBh8v7R_",
    "outputId": "e798e765-9f84-43e2-d3a0-f0fea3192ac2"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy on Training data :  0.8479318734793188\n"
     ]
    }
   ],
   "source": [
    "print('Accuracy on Training data : ', training_data_accuracy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "id": "mDONDJdlwBIO"
   },
   "outputs": [],
   "source": [
    "# accuracy on test data\n",
    "X_test_prediction = model.predict(X_test)\n",
    "test_data_accuracy = accuracy_score(X_test_prediction, Y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "_MBS-OqdwYpf",
    "outputId": "a2f5bd57-7135-47c2-c8f2-01f1823ad66a"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy on Test data :  0.8009708737864077\n"
     ]
    }
   ],
   "source": [
    "print('Accuracy on Test data : ', test_data_accuracy)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "jIruVh3Qwq0e"
   },
   "source": [
    "Building a Predictive System"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "9ercruC9wb4C",
    "outputId": "6a7f8964-d7c5-4a54-bb76-ef18f2add04a"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Enter the number of persons : 2\n",
      "\n",
      "How you want to enter the data (1)Manually or (2)In string format? \n",
      " Enter the number of your choice : 2\n",
      "Input the data in string format (values separated by ',' comma.)\n",
      "\n",
      "Enter the data of person no.(1) : 42,1,0,140,226,0,1,178,0,0,2,0,2\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\base.py:450: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Enter the data of person no.(2) : 39,1,0,118,219,0,1,140,0,1.2,1,0,3\n",
      "\n",
      "The pateint no.(1) has a Heart Disease.\n",
      "\n",
      "The pateint no.(2) does not have a Heart Disease.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\base.py:450: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "print(\"Enter the number of persons : \",end='')\n",
    "n = int(input())\n",
    "result = []\n",
    "\n",
    "print(\"\\nHow you want to enter the data (1)Manually or (2)In string format? \\n Enter the number of your choice : \", end='')\n",
    "choice = int(input())\n",
    "\n",
    "if(choice==2):\n",
    "    print(\"Input the data in string format (values separated by ',' comma.)\")\n",
    "\n",
    "for i in range(n):\n",
    "    \n",
    "    if(choice==1):\n",
    "        print(\"\\nEnter the details of person no.({})\".format(i+1))\n",
    "        age = int(input(\"\\nAge (between 0 to 100 years): \"))\n",
    "        sex = int(input(\"Sex (1 = male, 0 = female) : \"))\n",
    "        cp = int(input(\"Chest Pain type (0 to 4) : \"))\n",
    "        trestbps = int(input(\"Resting blood pressure (in mm Hg) : \"))\n",
    "        chol = int(input(\"Serum cholestoral (in mg/dl) : \"))\n",
    "        fbs = int(input(\"Fasting blood sugar & gt (in mg/dl) (1 = true, 0 = false) : \"))\n",
    "        restecg = int(input(\"Resting electrocardiographic : \"))\n",
    "        thalach = int(input(\"Maximum heart rate achieved : \"))\n",
    "        exang = int(input(\"Exercise induced angina (1 = yes, 0 = no) : \"))\n",
    "        oldpeak = float(input(\"ST depression induced by exercise relative to rest : \"))\n",
    "        slope = int(input(\"The slope of exercise ST segment (0 to 2) : \"))\n",
    "        ca = int(input(\"Number of major vessels (0-3 colored by flourosopy (0 to 3) : )\"))\n",
    "        thal = int(input(\"Thalassemia (1 = normal, 2 = fixed defect, 3 = reversable defect) : \"))\n",
    "        \n",
    "        input_data = (age,sex,cp,trestbps,chol,fbs,restecg,thalach,exang,oldpeak,slope,ca,thal)\n",
    "        \n",
    "    elif(choice==2):\n",
    "        print(\"\\nEnter the data of person no.({}) : \".format(i+1), end='')\n",
    "        input_str = input()\n",
    "        input_split = input_str.split(\",\")\n",
    "        \n",
    "        age = int(input_split[0])\n",
    "        sex = int(input_split[1])\n",
    "        cp = int(input_split[2])\n",
    "        trestbps = int(input_split[3])\n",
    "        chol = int(input_split[4])\n",
    "        fbs = int(input_split[5])\n",
    "        restecg = int(input_split[6])\n",
    "        thalach = int(input_split[7])\n",
    "        exang = int(input_split[8])\n",
    "        oldpeak = float(input_split[9])\n",
    "        slope = int(input_split[10])\n",
    "        ca = int(input_split[11])\n",
    "        thal = int(input_split[12])\n",
    "        \n",
    "        input_data = (age,sex,cp,trestbps,chol,fbs,restecg,thalach,exang,oldpeak,slope,ca,thal)\n",
    "    \n",
    "#     input_data = (62,0,0,140,268,0,0,160,0,3.6,0,2,2)\n",
    "#     input_data = (64,1,3,110,211,0,0,144,1,1.8,1,0,2)\n",
    "\n",
    "    # change the input data to a numpy array\n",
    "    input_data_as_numpy_array = np.asarray(input_data)\n",
    "\n",
    "    # reshape the numpy array as we are predicting for only on instance\n",
    "    input_data_reshaped = input_data_as_numpy_array.reshape(1,-1)\n",
    "\n",
    "    prediction = model.predict(input_data_reshaped)\n",
    "#     print(prediction)\n",
    "\n",
    "    if (prediction[0]== 0):\n",
    "#       print('The Person does not have a Heart Disease')\n",
    "        result.append(0)\n",
    "    else:\n",
    "#       print('The Person has Heart Disease')\n",
    "        result.append(1)\n",
    "    \n",
    "for i in range(n):\n",
    "    if(result[i]==0):\n",
    "        print(\"\\nThe pateint no.({}) does not have a Heart Disease.\".format(i+1))\n",
    "    else:\n",
    "        print(\"\\nThe pateint no.({}) has a Heart Disease.\".format(i+1))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Thank You."
   ]
  }
 ],
 "metadata": {
  "colab": {
   "provenance": []
  },
  "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}