Heart Disease Classification.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## I. PROBLEM STATEMENT"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Cardiovascular disease and heart disease all refer to various heart conditions. Examples of diseases under the heart disease umbrella include conditions like coronary artery disease. Every year, about 17.9 million people die from heart disease. Apart from this, there are many factors that raise one's risk of heart disease. Here we create a suitable machine learning technique which classify the heart disease more accurately, it is very helpful to the health organisation as well as patients.\n",
    "\n",
    "List of Machine Learning Algorithm and find out which algorithm predicts accurately.\n",
    "\n",
    "1.Logistic Regression\n",
    "\n",
    "2.Naive Bayes\n",
    "\n",
    "3.Random Forest Classifier\n",
    "\n",
    "4.K-Nearest Neighbour\n",
    "\n",
    "5.Decision Tree\n",
    "\n",
    "6.Support Vector Machine\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## II. DATASET DESCRIPTION"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Public Dataset: https://www.kaggle.com/ronitf/heart-disease-uci\n",
    "\n",
    "This dataset gives the information realated to heart disease. Dataset contain 13 columns, target is the class variable which is affected by other 12 columns. Here the aim is to classify the target variable to (disease\\non disease) using different machine learning algorithms and findout which algorithm suitable for this dataset.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## III. EXPLORATORY DATA ANALYSIS (EDA)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1. Read the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "#loading dataset\n",
    "import pandas as pd\n",
    "import numpy as nps\n",
    "\n",
    "data = pd.read_csv('heart.csv')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2. Overview of the dataset:"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Attribute Information:\n",
    "Age (age in years)\n",
    "\n",
    "Sex (1 = male; 0 = female)\n",
    "\n",
    "CP (chest pain type)\n",
    "\n",
    "TRESTBPS (resting blood pressure (in mm Hg on admission to the hospital))\n",
    "\n",
    "CHOL (serum cholestoral in mg/dl)\n",
    "\n",
    "FPS (fasting blood sugar > 120 mg/dl) (1 = true; 0 = false)\n",
    "\n",
    "RESTECH (resting electrocardiographic results)\n",
    "\n",
    "THALACH (maximum heart rate achieved)\n",
    "\n",
    "EXANG (exercise induced angina (1 = yes; 0 = no))\n",
    "\n",
    "OLDPEAK (ST depression induced by exercise relative to rest)\n",
    "\n",
    "SLOPE (the slope of the peak exercise ST segment)\n",
    "\n",
    "CA (number of major vessels (0-3) colored by flourosopy)\n",
    "\n",
    "THAL (3 = normal; 6 = fixed defect; 7 = reversable defect)\n",
    "\n",
    "TARGET (1 or 0)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3. Print the first five and last five rows of the dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>63</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>145</td>\n",
       "      <td>233</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>150</td>\n",
       "      <td>0</td>\n",
       "      <td>2.3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>37</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>130</td>\n",
       "      <td>250</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>187</td>\n",
       "      <td>0</td>\n",
       "      <td>3.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>41</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>130</td>\n",
       "      <td>204</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>172</td>\n",
       "      <td>0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>56</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>120</td>\n",
       "      <td>236</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>178</td>\n",
       "      <td>0</td>\n",
       "      <td>0.8</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>57</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>120</td>\n",
       "      <td>354</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>163</td>\n",
       "      <td>1</td>\n",
       "      <td>0.6</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  oldpeak  slope  \\\n",
       "0   63    1   3       145   233    1        0      150      0      2.3      0   \n",
       "1   37    1   2       130   250    0        1      187      0      3.5      0   \n",
       "2   41    0   1       130   204    0        0      172      0      1.4      2   \n",
       "3   56    1   1       120   236    0        1      178      0      0.8      2   \n",
       "4   57    0   0       120   354    0        1      163      1      0.6      2   \n",
       "\n",
       "   ca  thal  target  \n",
       "0   0     1       1  \n",
       "1   0     2       1  \n",
       "2   0     2       1  \n",
       "3   0     2       1  \n",
       "4   0     2       1  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#First five rows of the dataset\n",
    "data.head(n=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>298</th>\n",
       "      <td>57</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>140</td>\n",
       "      <td>241</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>123</td>\n",
       "      <td>1</td>\n",
       "      <td>0.2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>299</th>\n",
       "      <td>45</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>110</td>\n",
       "      <td>264</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>132</td>\n",
       "      <td>0</td>\n",
       "      <td>1.2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>300</th>\n",
       "      <td>68</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>144</td>\n",
       "      <td>193</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>141</td>\n",
       "      <td>0</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>301</th>\n",
       "      <td>57</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>130</td>\n",
       "      <td>131</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>115</td>\n",
       "      <td>1</td>\n",
       "      <td>1.2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>302</th>\n",
       "      <td>57</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>130</td>\n",
       "      <td>236</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>174</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  oldpeak  \\\n",
       "298   57    0   0       140   241    0        1      123      1      0.2   \n",
       "299   45    1   3       110   264    0        1      132      0      1.2   \n",
       "300   68    1   0       144   193    1        1      141      0      3.4   \n",
       "301   57    1   0       130   131    0        1      115      1      1.2   \n",
       "302   57    0   1       130   236    0        0      174      0      0.0   \n",
       "\n",
       "     slope  ca  thal  target  \n",
       "298      1   0     3       0  \n",
       "299      1   0     3       0  \n",
       "300      1   2     3       0  \n",
       "301      1   1     3       0  \n",
       "302      1   1     2       0  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Last five rows of the dataset\n",
    "data.tail(n=5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 4. Find the summary statistics of the dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np \n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "%matplotlib inline\n",
    "\n",
    "data = pd.read_csv('heart.csv')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>count</th>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>54.366337</td>\n",
       "      <td>0.683168</td>\n",
       "      <td>0.966997</td>\n",
       "      <td>131.623762</td>\n",
       "      <td>246.264026</td>\n",
       "      <td>0.148515</td>\n",
       "      <td>0.528053</td>\n",
       "      <td>149.646865</td>\n",
       "      <td>0.326733</td>\n",
       "      <td>1.039604</td>\n",
       "      <td>1.399340</td>\n",
       "      <td>0.729373</td>\n",
       "      <td>2.313531</td>\n",
       "      <td>0.544554</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>9.082101</td>\n",
       "      <td>0.466011</td>\n",
       "      <td>1.032052</td>\n",
       "      <td>17.538143</td>\n",
       "      <td>51.830751</td>\n",
       "      <td>0.356198</td>\n",
       "      <td>0.525860</td>\n",
       "      <td>22.905161</td>\n",
       "      <td>0.469794</td>\n",
       "      <td>1.161075</td>\n",
       "      <td>0.616226</td>\n",
       "      <td>1.022606</td>\n",
       "      <td>0.612277</td>\n",
       "      <td>0.498835</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>47.500000</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>133.500000</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>55.000000</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>153.000000</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>274.500000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>166.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.600000</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         fbs  \\\n",
       "count  303.000000  303.000000  303.000000  303.000000  303.000000  303.000000   \n",
       "mean    54.366337    0.683168    0.966997  131.623762  246.264026    0.148515   \n",
       "std      9.082101    0.466011    1.032052   17.538143   51.830751    0.356198   \n",
       "min     29.000000    0.000000    0.000000   94.000000  126.000000    0.000000   \n",
       "25%     47.500000    0.000000    0.000000  120.000000  211.000000    0.000000   \n",
       "50%     55.000000    1.000000    1.000000  130.000000  240.000000    0.000000   \n",
       "75%     61.000000    1.000000    2.000000  140.000000  274.500000    0.000000   \n",
       "max     77.000000    1.000000    3.000000  200.000000  564.000000    1.000000   \n",
       "\n",
       "          restecg     thalach       exang     oldpeak       slope          ca  \\\n",
       "count  303.000000  303.000000  303.000000  303.000000  303.000000  303.000000   \n",
       "mean     0.528053  149.646865    0.326733    1.039604    1.399340    0.729373   \n",
       "std      0.525860   22.905161    0.469794    1.161075    0.616226    1.022606   \n",
       "min      0.000000   71.000000    0.000000    0.000000    0.000000    0.000000   \n",
       "25%      0.000000  133.500000    0.000000    0.000000    1.000000    0.000000   \n",
       "50%      1.000000  153.000000    0.000000    0.800000    1.000000    0.000000   \n",
       "75%      1.000000  166.000000    1.000000    1.600000    2.000000    1.000000   \n",
       "max      2.000000  202.000000    1.000000    6.200000    2.000000    4.000000   \n",
       "\n",
       "             thal      target  \n",
       "count  303.000000  303.000000  \n",
       "mean     2.313531    0.544554  \n",
       "std      0.612277    0.498835  \n",
       "min      0.000000    0.000000  \n",
       "25%      2.000000    0.000000  \n",
       "50%      2.000000    1.000000  \n",
       "75%      3.000000    1.000000  \n",
       "max      3.000000    1.000000  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 5. Find the total count and total percentage of missing values in each column of the DataFrame and display them for columns having at least one null value, in descending order of missing percentages."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age         False\n",
       "sex         False\n",
       "cp          False\n",
       "trestbps    False\n",
       "chol        False\n",
       "fbs         False\n",
       "restecg     False\n",
       "thalach     False\n",
       "exang       False\n",
       "oldpeak     False\n",
       "slope       False\n",
       "ca          False\n",
       "thal        False\n",
       "target      False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#All data has value\n",
    "data.isnull().any()\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 6. Plot the nullity matrix and nullity correlation heatmap."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig,ax=plt.subplots(figsize=(15,5))\n",
    "sns.heatmap(data.isnull(), annot=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 7. Delete the columns having more than 80% of values missing."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age         False\n",
       "sex         False\n",
       "cp          False\n",
       "trestbps    False\n",
       "chol        False\n",
       "fbs         False\n",
       "restecg     False\n",
       "thalach     False\n",
       "exang       False\n",
       "oldpeak     False\n",
       "slope       False\n",
       "ca          False\n",
       "thal        False\n",
       "target      False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#There's nothing to impute since all data has value\n",
    "data.isnull().any()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 8. Impute null values based from the Summary Statistics. Any statistical values can be used for imputation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "# There's nothing to impute since all data has value"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 9. Use OneHotEncoder. Process the dataset to convert all features to numerical values. First, find the number of columns that will stay in their original form (that is, numerical features) and that need to be one-hot encoded (that is, the categorical features). Use OneHotEncoder."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "# All data are already in numerical values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 10. Export the Cleaned Dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "data.to_csv('CleanedData.csv')\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## IV.  AI MODELLING - APPLIED CLASSIFICATION ANALYSIS (ACA) using ENSEMBLE"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1. Import the required dependencies."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "#visualisation\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "import seaborn as sns\n",
    "#EDA\n",
    "from collections import Counter\n",
    "# data preprocessing\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "# data splitting\n",
    "from sklearn.model_selection import train_test_split\n",
    "# data modeling\n",
    "from sklearn.metrics import confusion_matrix,accuracy_score,roc_curve,classification_report\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.svm import SVC\n",
    "#ensembling\n",
    "from mlxtend.classifier import StackingCVClassifier"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2. Read the cleaned data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>Unnamed: 0</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>0</td>\n",
       "      <td>63</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>145</td>\n",
       "      <td>233</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>150</td>\n",
       "      <td>0</td>\n",
       "      <td>2.3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>37</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>130</td>\n",
       "      <td>250</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>187</td>\n",
       "      <td>0</td>\n",
       "      <td>3.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>41</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>130</td>\n",
       "      <td>204</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>172</td>\n",
       "      <td>0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>56</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>120</td>\n",
       "      <td>236</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>178</td>\n",
       "      <td>0</td>\n",
       "      <td>0.8</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>57</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>120</td>\n",
       "      <td>354</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>163</td>\n",
       "      <td>1</td>\n",
       "      <td>0.6</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0  age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  \\\n",
       "0           0   63    1   3       145   233    1        0      150      0   \n",
       "1           1   37    1   2       130   250    0        1      187      0   \n",
       "2           2   41    0   1       130   204    0        0      172      0   \n",
       "3           3   56    1   1       120   236    0        1      178      0   \n",
       "4           4   57    0   0       120   354    0        1      163      1   \n",
       "\n",
       "   oldpeak  slope  ca  thal  target  \n",
       "0      2.3      0   0     1       1  \n",
       "1      3.5      0   0     2       1  \n",
       "2      1.4      2   0     2       1  \n",
       "3      0.8      2   0     2       1  \n",
       "4      0.6      2   0     2       1  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = pd.read_csv('CleanedData.csv')\n",
    "data.head()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3. Divide the dataset into train and validation DataFrames.\n",
    "\n"
   ]
  },
  {
   "cell_type": "raw",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "train, val = train, val = train_test_split(data, test_size=0.20) \n",
    "\n",
    "X_train = train.drop(columns=['target'])\n",
    "y_train = train['target'].values\n",
    "\n",
    "x_val = val.drop(columns=['target'])\n",
    "y_val = val['target'].values\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "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>Unnamed: 0</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",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>260</th>\n",
       "      <td>260</td>\n",
       "      <td>66</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>178</td>\n",
       "      <td>228</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>165</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>267</th>\n",
       "      <td>267</td>\n",
       "      <td>49</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>118</td>\n",
       "      <td>149</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>126</td>\n",
       "      <td>0</td>\n",
       "      <td>0.8</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>7</td>\n",
       "      <td>44</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>120</td>\n",
       "      <td>263</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>173</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>35</td>\n",
       "      <td>46</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>142</td>\n",
       "      <td>177</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>160</td>\n",
       "      <td>1</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>186</th>\n",
       "      <td>186</td>\n",
       "      <td>60</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>130</td>\n",
       "      <td>253</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>144</td>\n",
       "      <td>1</td>\n",
       "      <td>1.4</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Unnamed: 0  age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  \\\n",
       "260         260   66    0   0       178   228    1        1      165      1   \n",
       "267         267   49    1   2       118   149    0        0      126      0   \n",
       "7             7   44    1   1       120   263    0        1      173      0   \n",
       "35           35   46    0   2       142   177    0        0      160      1   \n",
       "186         186   60    1   0       130   253    0        1      144      1   \n",
       "\n",
       "     oldpeak  slope  ca  thal  \n",
       "260      1.0      1   2     3  \n",
       "267      0.8      2   3     2  \n",
       "7        0.0      2   0     3  \n",
       "35       1.4      0   0     2  \n",
       "186      1.4      2   1     3  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_val.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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>Unnamed: 0</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",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>56</th>\n",
       "      <td>56</td>\n",
       "      <td>48</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>122</td>\n",
       "      <td>222</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>186</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>236</th>\n",
       "      <td>236</td>\n",
       "      <td>58</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>125</td>\n",
       "      <td>300</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>171</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>243</th>\n",
       "      <td>243</td>\n",
       "      <td>57</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>152</td>\n",
       "      <td>274</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>88</td>\n",
       "      <td>1</td>\n",
       "      <td>1.2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>157</th>\n",
       "      <td>157</td>\n",
       "      <td>35</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>122</td>\n",
       "      <td>192</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>174</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>266</th>\n",
       "      <td>266</td>\n",
       "      <td>55</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>180</td>\n",
       "      <td>327</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>117</td>\n",
       "      <td>1</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Unnamed: 0  age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  \\\n",
       "56           56   48    1   0       122   222    0        0      186      0   \n",
       "236         236   58    1   0       125   300    0        0      171      0   \n",
       "243         243   57    1   0       152   274    0        1       88      1   \n",
       "157         157   35    1   1       122   192    0        1      174      0   \n",
       "266         266   55    0   0       180   327    0        2      117      1   \n",
       "\n",
       "     oldpeak  slope  ca  thal  \n",
       "56       0.0      2   0     2  \n",
       "236      0.0      2   2     3  \n",
       "243      1.2      1   1     3  \n",
       "157      0.0      2   0     2  \n",
       "266      3.4      1   0     2  "
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 4. Construct an Ensemble model (STACKING Ensemble) using 2 base classifiers and 1 stacked model as classifier. \n",
    "\n",
    "NOTE: \n",
    "1. Hyperparameter Tuning: Choose a base classifier model and define the range of hyperparameter values corresponding to the model to be searched over for hyperparameter tuning. Use RandomizedSearchCV or any Hyperparameter tuning techniques. \n",
    "2. Once the tuning is complete, find the position (iteration number) at which the highest mean test score was obtained. Find the corresponding hyperparameters to be used for your based models and stacked model.\n",
    "3. Split the dataset into training and validation sets and train a new model using the final hyperparameters on the training dataset. Use scikit-learn's train_test_split() method to split X and y into train and test components, with test comprising 15% of the dataset or any which can attain your target accuracy:\n",
    "4. Train both your base models and stacked model using the final hyperparamters used from the hyperparameter tuning done in step 2."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "##Model Preparation \n",
    "y = data[\"target\"]\n",
    "X = data.drop('target',axis=1)\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state = 0)\n",
    "scaler = StandardScaler()\n",
    "X_train = scaler.fit_transform(X_train)\n",
    "X_test = scaler.transform(X_test)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 1]\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Counter({1: 131, 0: 111})"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print(y_test.unique())\n",
    "Counter(y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "confussion matrix\n",
      "[[27  0]\n",
      " [ 0 34]]\n",
      "\n",
      "\n",
      "Accuracy of Logistic Regression: 100.0 \n",
      "\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       1.00      1.00      1.00        27\n",
      "           1       1.00      1.00      1.00        34\n",
      "\n",
      "    accuracy                           1.00        61\n",
      "   macro avg       1.00      1.00      1.00        61\n",
      "weighted avg       1.00      1.00      1.00        61\n",
      "\n",
      "Logistic Regression:\n",
      "> Accuracy on training data = 0.9917\n",
      "> Accuracy on validation data = 0.4590\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\mayew\\anaconda3\\lib\\site-packages\\sklearn\\base.py:443: UserWarning: X has feature names, but LogisticRegression was fitted without feature names\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "#Logistic Regression\n",
    "m1 = 'Logistic Regression'\n",
    "lr = LogisticRegression()\n",
    "model = lr.fit(X_train, y_train)\n",
    "lr_predict = lr.predict(X_test)\n",
    "lr_conf_matrix = confusion_matrix(y_test, lr_predict)\n",
    "lr_acc_score = accuracy_score(y_test, lr_predict)\n",
    "print(\"confussion matrix\")\n",
    "print(lr_conf_matrix)\n",
    "print(\"\\n\")\n",
    "print(\"Accuracy of Logistic Regression:\",lr_acc_score*100,'\\n')\n",
    "print(classification_report(y_test,lr_predict))\n",
    "\n",
    "lr.fit(X_train, y_train)\n",
    "lr_preds_train = lr.predict(X_train)\n",
    "lr_preds_val = lr.predict(x_val)\n",
    "\n",
    "print('Logistic Regression:\\n> Accuracy on training data = {:.4f}\\n> Accuracy on validation data = {:.4f}'.format(\n",
    "    accuracy_score(y_true=y_train, y_pred=lr_preds_train),\n",
    "    accuracy_score(y_true=y_val, y_pred=lr_preds_val)\n",
    "))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "confussion matrix\n",
      "[[27  0]\n",
      " [ 0 34]]\n",
      "\n",
      "\n",
      "Accuracy of Naive Bayes model: 100.0 \n",
      "\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       1.00      1.00      1.00        27\n",
      "           1       1.00      1.00      1.00        34\n",
      "\n",
      "    accuracy                           1.00        61\n",
      "   macro avg       1.00      1.00      1.00        61\n",
      "weighted avg       1.00      1.00      1.00        61\n",
      "\n",
      "Naive Bayes:\n",
      "> Accuracy on training data = 0.9380\n",
      "> Accuracy on validation data = 0.4918\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\mayew\\anaconda3\\lib\\site-packages\\sklearn\\base.py:443: UserWarning: X has feature names, but GaussianNB was fitted without feature names\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "#Naive Bayes\n",
    "m2 = 'Naive Bayes'\n",
    "nb = GaussianNB()\n",
    "nb.fit(X_train,y_train)\n",
    "nbpred = nb.predict(X_test)\n",
    "nb_conf_matrix = confusion_matrix(y_test, nbpred)\n",
    "nb_acc_score = accuracy_score(y_test, nbpred)\n",
    "print(\"confussion matrix\")\n",
    "print(nb_conf_matrix)\n",
    "print(\"\\n\")\n",
    "print(\"Accuracy of Naive Bayes model:\",nb_acc_score*100,'\\n')\n",
    "print(classification_report(y_test,nbpred))\n",
    "\n",
    "nb.fit(X_train, y_train)\n",
    "nb_preds_train = nb.predict(X_train)\n",
    "nb_preds_val = nb.predict(x_val)\n",
    "\n",
    "print('Naive Bayes:\\n> Accuracy on training data = {:.4f}\\n> Accuracy on validation data = {:.4f}'.format(\n",
    "    accuracy_score(y_true=y_train, y_pred=nb_preds_train),\n",
    "    accuracy_score(y_true=y_val, y_pred=nb_preds_val)\n",
    "))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "confussion matrix\n",
      "[[27  0]\n",
      " [ 0 34]]\n",
      "\n",
      "\n",
      "Accuracy of Random Forest: 100.0 \n",
      "\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       1.00      1.00      1.00        27\n",
      "           1       1.00      1.00      1.00        34\n",
      "\n",
      "    accuracy                           1.00        61\n",
      "   macro avg       1.00      1.00      1.00        61\n",
      "weighted avg       1.00      1.00      1.00        61\n",
      "\n",
      "Random Forest:\n",
      "> Accuracy on training data = 1.0000\n",
      "> Accuracy on validation data = 0.4754\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\mayew\\anaconda3\\lib\\site-packages\\sklearn\\base.py:443: UserWarning: X has feature names, but RandomForestClassifier was fitted without feature names\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "#Random Forest Classifier\n",
    "m3 = 'Random Forest Classfier'\n",
    "rf = RandomForestClassifier(n_estimators=20, random_state=2,max_depth=5)\n",
    "rf.fit(X_train,y_train)\n",
    "rf_predicted = rf.predict(X_test)\n",
    "rf_conf_matrix = confusion_matrix(y_test, rf_predicted)\n",
    "rf_acc_score = accuracy_score(y_test, rf_predicted)\n",
    "print(\"confussion matrix\")\n",
    "print(rf_conf_matrix)\n",
    "print(\"\\n\")\n",
    "print(\"Accuracy of Random Forest:\",rf_acc_score*100,'\\n')\n",
    "print(classification_report(y_test,rf_predicted))\n",
    "\n",
    "rf.fit(X_train, y_train)\n",
    "rf_preds_train = rf.predict(X_train)\n",
    "rf_preds_val = rf.predict(x_val)\n",
    "\n",
    "print('Random Forest:\\n> Accuracy on training data = {:.4f}\\n> Accuracy on validation data = {:.4f}'.format(\n",
    "    accuracy_score(y_true=y_train, y_pred=rf_preds_train),\n",
    "    accuracy_score(y_true=y_val, y_pred=rf_preds_val)\n",
    "))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "confussion matrix\n",
      "[[25  2]\n",
      " [ 3 31]]\n",
      "\n",
      "\n",
      "Accuracy of K-NeighborsClassifier: 91.80327868852459 \n",
      "\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.89      0.93      0.91        27\n",
      "           1       0.94      0.91      0.93        34\n",
      "\n",
      "    accuracy                           0.92        61\n",
      "   macro avg       0.92      0.92      0.92        61\n",
      "weighted avg       0.92      0.92      0.92        61\n",
      "\n",
      "K Nearest Neighbor:\n",
      "> Accuracy on training data = 0.9339\n",
      "> Accuracy on validation data = 0.6557\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\mayew\\anaconda3\\lib\\site-packages\\sklearn\\base.py:443: UserWarning: X has feature names, but KNeighborsClassifier was fitted without feature names\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "#KNN Classifier\n",
    "m4 = 'K-NeighborsClassifier'\n",
    "knn = KNeighborsClassifier(n_neighbors=10)\n",
    "knn.fit(X_train, y_train)\n",
    "knn_predicted = knn.predict(X_test)\n",
    "knn_conf_matrix = confusion_matrix(y_test, knn_predicted)\n",
    "knn_acc_score = accuracy_score(y_test, knn_predicted)\n",
    "print(\"confussion matrix\")\n",
    "print(knn_conf_matrix)\n",
    "print(\"\\n\")\n",
    "print(\"Accuracy of K-NeighborsClassifier:\",knn_acc_score*100,'\\n')\n",
    "print(classification_report(y_test,knn_predicted))\n",
    "\n",
    "knn.fit(X_train, y_train)\n",
    "knn_preds_train = knn.predict(X_train)\n",
    "knn_preds_val = knn.predict(x_val)\n",
    "\n",
    "print('K Nearest Neighbor:\\n> Accuracy on training data = {:.4f}\\n> Accuracy on validation data = {:.4f}'.format(\n",
    "    accuracy_score(y_true=y_train, y_pred=knn_preds_train),\n",
    "    accuracy_score(y_true=y_val, y_pred=knn_preds_val)\n",
    "))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "confussion matrix\n",
      "[[27  0]\n",
      " [ 0 34]]\n",
      "\n",
      "\n",
      "Accuracy of DecisionTreeClassifier: 100.0 \n",
      "\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       1.00      1.00      1.00        27\n",
      "           1       1.00      1.00      1.00        34\n",
      "\n",
      "    accuracy                           1.00        61\n",
      "   macro avg       1.00      1.00      1.00        61\n",
      "weighted avg       1.00      1.00      1.00        61\n",
      "\n",
      "Decision Tree:\n",
      "> Accuracy on training data = 1.0000\n",
      "> Accuracy on validation data = 0.4754\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\mayew\\anaconda3\\lib\\site-packages\\sklearn\\base.py:443: UserWarning: X has feature names, but DecisionTreeClassifier was fitted without feature names\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "# Decision Tree\n",
    "\n",
    "m5 = 'DecisionTreeClassifier'\n",
    "dt = DecisionTreeClassifier(criterion = 'entropy',random_state=0,max_depth = 6)\n",
    "dt.fit(X_train, y_train)\n",
    "dt_predicted = dt.predict(X_test)\n",
    "dt_conf_matrix = confusion_matrix(y_test, dt_predicted)\n",
    "dt_acc_score = accuracy_score(y_test, dt_predicted)\n",
    "print(\"confussion matrix\")\n",
    "print(dt_conf_matrix)\n",
    "print(\"\\n\")\n",
    "print(\"Accuracy of DecisionTreeClassifier:\",dt_acc_score*100,'\\n')\n",
    "print(classification_report(y_test,dt_predicted))\n",
    "\n",
    "dt.fit(X_train, y_train)\n",
    "dt_preds_train = dt.predict(X_train)\n",
    "dt_preds_val = dt.predict(x_val)\n",
    "\n",
    "print('Decision Tree:\\n> Accuracy on training data = {:.4f}\\n> Accuracy on validation data = {:.4f}'.format(\n",
    "    accuracy_score(y_true=y_train, y_pred=dt_preds_train),\n",
    "    accuracy_score(y_true=y_val, y_pred=dt_preds_val)\n",
    "))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "confussion matrix\n",
      "[[27  0]\n",
      " [ 0 34]]\n",
      "\n",
      "\n",
      "Accuracy of Support Vector Classifier: 100.0 \n",
      "\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       1.00      1.00      1.00        27\n",
      "           1       1.00      1.00      1.00        34\n",
      "\n",
      "    accuracy                           1.00        61\n",
      "   macro avg       1.00      1.00      1.00        61\n",
      "weighted avg       1.00      1.00      1.00        61\n",
      "\n",
      "Support Vector:\n",
      "> Accuracy on training data = 0.9959\n",
      "> Accuracy on validation data = 0.4590\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\mayew\\anaconda3\\lib\\site-packages\\sklearn\\base.py:443: UserWarning: X has feature names, but SVC was fitted without feature names\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "#Support Vector Classifier\n",
    "m6 = 'Support Vector Classifier'\n",
    "svc =  SVC(kernel='rbf', C=2)\n",
    "svc.fit(X_train, y_train)\n",
    "svc_predicted = svc.predict(X_test)\n",
    "svc_conf_matrix = confusion_matrix(y_test, svc_predicted)\n",
    "svc_acc_score = accuracy_score(y_test, svc_predicted)\n",
    "print(\"confussion matrix\")\n",
    "print(svc_conf_matrix)\n",
    "print(\"\\n\")\n",
    "print(\"Accuracy of Support Vector Classifier:\",svc_acc_score*100,'\\n')\n",
    "print(classification_report(y_test,svc_predicted))\n",
    "\n",
    "svc.fit(X_train, y_train)\n",
    "svc_preds_train = svc.predict(X_train)\n",
    "svc_preds_val = svc.predict(x_val)\n",
    "\n",
    "print('Support Vector:\\n> Accuracy on training data = {:.4f}\\n> Accuracy on validation data = {:.4f}'.format(\n",
    "    accuracy_score(y_true=y_train, y_pred=svc_preds_train),\n",
    "    accuracy_score(y_true=y_val, y_pred=svc_preds_val)\n",
    "))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 5. Calculate the accuracy, precision, and recall for predictions on the validation set, and print the confusion matrix (Target F1-Score >= 80%):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "confussion matrix\n",
      "[[27  0]\n",
      " [ 3 31]]\n",
      "\n",
      "\n",
      "Accuracy of StackingCVClassifier: 95.08196721311475 \n",
      "\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.90      1.00      0.95        27\n",
      "           1       1.00      0.91      0.95        34\n",
      "\n",
      "    accuracy                           0.95        61\n",
      "   macro avg       0.95      0.96      0.95        61\n",
      "weighted avg       0.96      0.95      0.95        61\n",
      "\n"
     ]
    }
   ],
   "source": [
    "scv=StackingCVClassifier(classifiers=[knn,svc],meta_classifier= svc,random_state=42)\n",
    "scv.fit(X_train,y_train)\n",
    "scv_predicted = scv.predict(X_test)\n",
    "scv_conf_matrix = confusion_matrix(y_test, scv_predicted)\n",
    "scv_acc_score = accuracy_score(y_test, scv_predicted)\n",
    "print(\"confussion matrix\")\n",
    "print(scv_conf_matrix)\n",
    "print(\"\\n\")\n",
    "print(\"Accuracy of StackingCVClassifier:\",scv_acc_score*100,'\\n')\n",
    "print(classification_report(y_test,scv_predicted))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 6. Plot the precision-recall curve or the AUC-ROC Curve:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "lr_false_positive_rate,lr_true_positive_rate,lr_threshold = roc_curve(y_test,lr_predict)\n",
    "nb_false_positive_rate,nb_true_positive_rate,nb_threshold = roc_curve(y_test,nbpred)\n",
    "rf_false_positive_rate,rf_true_positive_rate,rf_threshold = roc_curve(y_test,rf_predicted)                                                             \n",
    "knn_false_positive_rate,knn_true_positive_rate,knn_threshold = roc_curve(y_test,knn_predicted)\n",
    "dt_false_positive_rate,dt_true_positive_rate,dt_threshold = roc_curve(y_test,dt_predicted)\n",
    "svc_false_positive_rate,svc_true_positive_rate,svc_threshold = roc_curve(y_test,svc_predicted)\n",
    "\n",
    "\n",
    "sns.set_style('whitegrid')\n",
    "plt.figure(figsize=(10,5))\n",
    "plt.title('Reciver Operating Characterstic Curve')\n",
    "plt.plot(lr_false_positive_rate,lr_true_positive_rate,label='Logistic Regression')\n",
    "plt.plot(nb_false_positive_rate,nb_true_positive_rate,label='Naive Bayes')\n",
    "plt.plot(rf_false_positive_rate,rf_true_positive_rate,label='Random Forest')\n",
    "plt.plot(knn_false_positive_rate,knn_true_positive_rate,label='K-Nearest Neighbor')\n",
    "plt.plot(dt_false_positive_rate,dt_true_positive_rate,label='Desion Tree')\n",
    "plt.plot(svc_false_positive_rate,svc_true_positive_rate,label='Support Vector Classifier')\n",
    "plt.plot([0,1],ls='--')\n",
    "plt.plot([0,0],[1,0],c='.5')\n",
    "plt.plot([1,1],c='.5')\n",
    "plt.ylabel('True positive rate')\n",
    "plt.xlabel('False positive rate')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 7. Predict the final values on the test dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import (accuracy_score, confusion_matrix, precision_score,\n",
    "                             recall_score, f1_score, precision_recall_curve)\n",
    "\n",
    "X_train_with_metapreds = np.zeros((X_train.shape[0], X_train.shape[1]+2))\n",
    "X_train_with_metapreds[:, :-2] = X_train\n",
    "X_train_with_metapreds[:, -2:] = -1\n",
    "#print(X_train_with_metapreds)\n",
    "x_val_with_metapreds = np.zeros((x_val.shape[0], x_val.shape[1]+2))\n",
    "x_val_with_metapreds[:, :-2] = x_val\n",
    "x_val_with_metapreds[:, -2:] = -1\n",
    "#print(x_val_with_metapreds)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\mayew\\anaconda3\\lib\\site-packages\\sklearn\\base.py:443: UserWarning: X has feature names, but SVC was fitted without feature names\n",
      "  warnings.warn(\n",
      "C:\\Users\\mayew\\anaconda3\\lib\\site-packages\\sklearn\\base.py:443: UserWarning: X has feature names, but KNeighborsClassifier was fitted without feature names\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "svc = SVC(random_state=11, max_iter=1000)\n",
    "svc.fit(X_train, y_train)\n",
    "\n",
    "knn = KNeighborsClassifier(n_neighbors=4)\n",
    "knn.fit(X_train, y_train)\n",
    "\n",
    "svc_pred = svc.predict(x_val)\n",
    "knn_pred = knn.predict(x_val)\n",
    "\n",
    "x_val_with_metapreds[:, -2] = svc_pred\n",
    "x_val_with_metapreds[:, -1] = knn_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SVC:\n",
      "> Accuracy on training data = 0.9835\n",
      "> Accuracy on validation data = 0.4590\n",
      "KNN:\n",
      "> Accuracy on training data = 0.9339\n",
      "> Accuracy on validation data = 0.4754\n"
     ]
    }
   ],
   "source": [
    "# Comparing accuracy with that of base predictors\n",
    "\n",
    "print('SVC:\\n> Accuracy on training data = {:.4f}\\n> Accuracy on validation data = {:.4f}'.format(\n",
    "    accuracy_score(y_true=y_train, y_pred=svc.predict(X_train)),\n",
    "    accuracy_score(y_true=y_val, y_pred=svc_pred)\n",
    "))\n",
    "print('KNN:\\n> Accuracy on training data = {:.4f}\\n> Accuracy on validation data = {:.4f}'.format(\n",
    "    accuracy_score(y_true=y_train, y_pred=knn.predict(X_train)),\n",
    "    accuracy_score(y_true=y_val, y_pred=knn_pred)\n",
    "))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 8. Export the Final Model using PICKLE Library."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test score: 100.00 %\n"
     ]
    }
   ],
   "source": [
    "import pickle\n",
    "\n",
    "pkl_filename = \"HeartModel.pkl\"\n",
    "with open(pkl_filename, 'wb') as file:\n",
    "    pickle.dump(model, file)\n",
    "\n",
    "# Load from file\n",
    "with open(pkl_filename, 'rb') as file:\n",
    "    pickle_model = pickle.load(file)\n",
    "    \n",
    "# Calculate the accuracy score and predict target values\n",
    "score = pickle_model.score(X_test, y_test)\n",
    "print(\"Test score: {0:.2f} %\".format(100 * score))\n",
    "Ypredict = pickle_model.predict(X_test)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}