PredictingHeartDisease.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "#KNN Classifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "# The Main Steps to build (train) and use (test/predict) a predictive model in sklearn:\n",
    "\n",
    "## Step1: Importing the sklearn class (machine learning algorithm) that you would like to use for modeling:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "## The following line will import LinearRegression \"Class\"\n",
    "# The following line will import KNeighborsClassifier \"Class\"\n",
    "# KNeighborsClassifier is name of a \"sklearn class\" to perform \"KNN Classification\" \n",
    "from sklearn.linear_model import LinearRegression\n",
    "\n",
    "\n",
    "from sklearn.neighbors import KNeighborsClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Importing the required packages and libraries\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "#a Read the dataset file “Hearts_s.csv” (you should download it from CSNS), and assign it to a Pandas DataFrame."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'/Users/pranaytheja/Desktop/CS4661/HW3'"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pwd\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Credit.csv   HW3.pdf      Heart_s.csv\r\n"
     ]
    }
   ],
   "source": [
    "ls"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/Users/pranaytheja/Desktop\n"
     ]
    }
   ],
   "source": [
    "cd ~/Desktop"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[34mCS3112\u001b[m\u001b[m/                                \u001b[34mInternship Resume\u001b[m\u001b[m/\r\n",
      "CS3112_Course_syllabus_JungsooLim.pdf  \u001b[34mMatsoft Training Material\u001b[m\u001b[m/\r\n",
      "\u001b[34mCS3220\u001b[m\u001b[m/                                Project 3_ Reinforcement Learning.pdf\r\n",
      "\u001b[34mCS4660\u001b[m\u001b[m/                                \u001b[34mPsycic Protection\u001b[m\u001b[m/\r\n",
      "\u001b[34mCS4661\u001b[m\u001b[m/                                \u001b[34mResumes\u001b[m\u001b[m/\r\n",
      "\u001b[34mCSULA Campus Jobs\u001b[m\u001b[m/                     cert.pdf\r\n",
      "\u001b[34mCSWeb\u001b[m\u001b[m/                                 counting with rules.png\r\n",
      "\u001b[34mDocuments\u001b[m\u001b[m/                             qlearningagent.pdf\r\n",
      "\u001b[34mEclipse.app\u001b[m\u001b[m/                           thinkful-job-guarantee.pdf\r\n"
     ]
    }
   ],
   "source": [
    "ls"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/Users/pranaytheja/Desktop/CS4661\n"
     ]
    }
   ],
   "source": [
    "cd CS4661"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "An-introduction-to-neural-networks-for-beginners.pdf\r\n",
      "CS4661-Lec01.pdf\r\n",
      "CS4661-Lec02.pdf\r\n",
      "CS4661-Lec03.pdf\r\n",
      "CS4661-Lec04.pdf\r\n",
      "CS4661-Lec05.pdf\r\n",
      "CS4661-Lec06.pdf\r\n",
      "CS4661-Lec07.pdf\r\n",
      "CS4661-Lec08.pdf\r\n",
      "CS4661-Lec09.pdf\r\n",
      "CS4661-Lec10.pdf\r\n",
      "CS4661-Lec11.pdf\r\n",
      "CS4661-Lec12.pdf\r\n",
      "CS4661-Lec13.pdf\r\n",
      "CS4661-Lec14.pdf\r\n",
      "CS4661-Lec15-PythonDataScienceTutorial-Lab4.ipynb\r\n",
      "CS4661-Lec16.pdf\r\n",
      "CS4661-Lec17.pdf\r\n",
      "\u001b[34mHW3\u001b[m\u001b[m/\r\n",
      "ISLR Seventh Printing.pdf\r\n",
      "\u001b[34mProject 3 - Pacman, etc\u001b[m\u001b[m/\r\n",
      "Project.pdf\r\n",
      "\u001b[34mPython Classes\u001b[m\u001b[m/\r\n",
      "\u001b[34mPython Homework\u001b[m\u001b[m/\r\n",
      "\u001b[34mPython Lab Assignments\u001b[m\u001b[m/\r\n",
      "\u001b[34mPython Resources\u001b[m\u001b[m/\r\n",
      "\u001b[34mall\u001b[m\u001b[m/\r\n",
      "\u001b[34mkaggle-api-master\u001b[m\u001b[m/\r\n",
      "login.html\r\n",
      "new doc 2018-10-05 11.57.17.pdf\r\n",
      "\u001b[34mputty-0 2.70\u001b[m\u001b[m/\r\n"
     ]
    }
   ],
   "source": [
    "ls\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/Users/pranaytheja/Desktop/CS4661/HW3\n"
     ]
    }
   ],
   "source": [
    "cd HW3\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Credit.csv   HW3.pdf      Heart_s.csv\r\n"
     ]
    }
   ],
   "source": [
    "ls"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "Heart_df = pd.read_csv(\"Heart_s.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "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>Gender</th>\n",
       "      <th>ChestPain</th>\n",
       "      <th>RestBP</th>\n",
       "      <th>Chol</th>\n",
       "      <th>RestECG</th>\n",
       "      <th>MaxHR</th>\n",
       "      <th>Oldpeak</th>\n",
       "      <th>Thal</th>\n",
       "      <th>AHD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>63</td>\n",
       "      <td>f</td>\n",
       "      <td>typical</td>\n",
       "      <td>145</td>\n",
       "      <td>233</td>\n",
       "      <td>2</td>\n",
       "      <td>150</td>\n",
       "      <td>2.3</td>\n",
       "      <td>fixed</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>67</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>160</td>\n",
       "      <td>286</td>\n",
       "      <td>2</td>\n",
       "      <td>108</td>\n",
       "      <td>1.5</td>\n",
       "      <td>normal</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>67</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>120</td>\n",
       "      <td>229</td>\n",
       "      <td>2</td>\n",
       "      <td>129</td>\n",
       "      <td>2.6</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>37</td>\n",
       "      <td>f</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>130</td>\n",
       "      <td>250</td>\n",
       "      <td>0</td>\n",
       "      <td>187</td>\n",
       "      <td>3.5</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>41</td>\n",
       "      <td>m</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>130</td>\n",
       "      <td>204</td>\n",
       "      <td>2</td>\n",
       "      <td>172</td>\n",
       "      <td>1.4</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>56</td>\n",
       "      <td>f</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>120</td>\n",
       "      <td>236</td>\n",
       "      <td>0</td>\n",
       "      <td>178</td>\n",
       "      <td>0.8</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>62</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>140</td>\n",
       "      <td>268</td>\n",
       "      <td>2</td>\n",
       "      <td>160</td>\n",
       "      <td>3.6</td>\n",
       "      <td>normal</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>57</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>120</td>\n",
       "      <td>354</td>\n",
       "      <td>0</td>\n",
       "      <td>163</td>\n",
       "      <td>0.6</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>63</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>130</td>\n",
       "      <td>254</td>\n",
       "      <td>2</td>\n",
       "      <td>147</td>\n",
       "      <td>1.4</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>53</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>140</td>\n",
       "      <td>203</td>\n",
       "      <td>2</td>\n",
       "      <td>155</td>\n",
       "      <td>3.1</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>57</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>140</td>\n",
       "      <td>192</td>\n",
       "      <td>0</td>\n",
       "      <td>148</td>\n",
       "      <td>0.4</td>\n",
       "      <td>fixed</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>56</td>\n",
       "      <td>m</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>140</td>\n",
       "      <td>294</td>\n",
       "      <td>2</td>\n",
       "      <td>153</td>\n",
       "      <td>1.3</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>56</td>\n",
       "      <td>f</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>130</td>\n",
       "      <td>256</td>\n",
       "      <td>2</td>\n",
       "      <td>142</td>\n",
       "      <td>0.6</td>\n",
       "      <td>fixed</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>44</td>\n",
       "      <td>f</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>120</td>\n",
       "      <td>263</td>\n",
       "      <td>0</td>\n",
       "      <td>173</td>\n",
       "      <td>0.0</td>\n",
       "      <td>reversable</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>52</td>\n",
       "      <td>f</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>172</td>\n",
       "      <td>199</td>\n",
       "      <td>0</td>\n",
       "      <td>162</td>\n",
       "      <td>0.5</td>\n",
       "      <td>reversable</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>57</td>\n",
       "      <td>f</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>150</td>\n",
       "      <td>168</td>\n",
       "      <td>0</td>\n",
       "      <td>174</td>\n",
       "      <td>1.6</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>48</td>\n",
       "      <td>f</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>110</td>\n",
       "      <td>229</td>\n",
       "      <td>0</td>\n",
       "      <td>168</td>\n",
       "      <td>1.0</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>54</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>140</td>\n",
       "      <td>239</td>\n",
       "      <td>0</td>\n",
       "      <td>160</td>\n",
       "      <td>1.2</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>48</td>\n",
       "      <td>m</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>130</td>\n",
       "      <td>275</td>\n",
       "      <td>0</td>\n",
       "      <td>139</td>\n",
       "      <td>0.2</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>49</td>\n",
       "      <td>f</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>130</td>\n",
       "      <td>266</td>\n",
       "      <td>0</td>\n",
       "      <td>171</td>\n",
       "      <td>0.6</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>64</td>\n",
       "      <td>f</td>\n",
       "      <td>typical</td>\n",
       "      <td>110</td>\n",
       "      <td>211</td>\n",
       "      <td>2</td>\n",
       "      <td>144</td>\n",
       "      <td>1.8</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>58</td>\n",
       "      <td>m</td>\n",
       "      <td>typical</td>\n",
       "      <td>150</td>\n",
       "      <td>283</td>\n",
       "      <td>2</td>\n",
       "      <td>162</td>\n",
       "      <td>1.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>58</td>\n",
       "      <td>f</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>120</td>\n",
       "      <td>284</td>\n",
       "      <td>2</td>\n",
       "      <td>160</td>\n",
       "      <td>1.8</td>\n",
       "      <td>normal</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>58</td>\n",
       "      <td>f</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>132</td>\n",
       "      <td>224</td>\n",
       "      <td>2</td>\n",
       "      <td>173</td>\n",
       "      <td>3.2</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>60</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>130</td>\n",
       "      <td>206</td>\n",
       "      <td>2</td>\n",
       "      <td>132</td>\n",
       "      <td>2.4</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>50</td>\n",
       "      <td>m</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>120</td>\n",
       "      <td>219</td>\n",
       "      <td>0</td>\n",
       "      <td>158</td>\n",
       "      <td>1.6</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>58</td>\n",
       "      <td>m</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>120</td>\n",
       "      <td>340</td>\n",
       "      <td>0</td>\n",
       "      <td>172</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>66</td>\n",
       "      <td>m</td>\n",
       "      <td>typical</td>\n",
       "      <td>150</td>\n",
       "      <td>226</td>\n",
       "      <td>0</td>\n",
       "      <td>114</td>\n",
       "      <td>2.6</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>43</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>150</td>\n",
       "      <td>247</td>\n",
       "      <td>0</td>\n",
       "      <td>171</td>\n",
       "      <td>1.5</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>40</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>110</td>\n",
       "      <td>167</td>\n",
       "      <td>2</td>\n",
       "      <td>114</td>\n",
       "      <td>2.0</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>271</th>\n",
       "      <td>71</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>112</td>\n",
       "      <td>149</td>\n",
       "      <td>0</td>\n",
       "      <td>125</td>\n",
       "      <td>1.6</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>272</th>\n",
       "      <td>59</td>\n",
       "      <td>f</td>\n",
       "      <td>typical</td>\n",
       "      <td>134</td>\n",
       "      <td>204</td>\n",
       "      <td>0</td>\n",
       "      <td>162</td>\n",
       "      <td>0.8</td>\n",
       "      <td>normal</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>273</th>\n",
       "      <td>64</td>\n",
       "      <td>f</td>\n",
       "      <td>typical</td>\n",
       "      <td>170</td>\n",
       "      <td>227</td>\n",
       "      <td>2</td>\n",
       "      <td>155</td>\n",
       "      <td>0.6</td>\n",
       "      <td>reversable</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>274</th>\n",
       "      <td>66</td>\n",
       "      <td>m</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>146</td>\n",
       "      <td>278</td>\n",
       "      <td>2</td>\n",
       "      <td>152</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>275</th>\n",
       "      <td>39</td>\n",
       "      <td>m</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>138</td>\n",
       "      <td>220</td>\n",
       "      <td>0</td>\n",
       "      <td>152</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>276</th>\n",
       "      <td>57</td>\n",
       "      <td>f</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>154</td>\n",
       "      <td>232</td>\n",
       "      <td>2</td>\n",
       "      <td>164</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>277</th>\n",
       "      <td>58</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>130</td>\n",
       "      <td>197</td>\n",
       "      <td>0</td>\n",
       "      <td>131</td>\n",
       "      <td>0.6</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>278</th>\n",
       "      <td>57</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>110</td>\n",
       "      <td>335</td>\n",
       "      <td>0</td>\n",
       "      <td>143</td>\n",
       "      <td>3.0</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>279</th>\n",
       "      <td>47</td>\n",
       "      <td>f</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>130</td>\n",
       "      <td>253</td>\n",
       "      <td>0</td>\n",
       "      <td>179</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>280</th>\n",
       "      <td>55</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>128</td>\n",
       "      <td>205</td>\n",
       "      <td>1</td>\n",
       "      <td>130</td>\n",
       "      <td>2.0</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>281</th>\n",
       "      <td>35</td>\n",
       "      <td>f</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>122</td>\n",
       "      <td>192</td>\n",
       "      <td>0</td>\n",
       "      <td>174</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>282</th>\n",
       "      <td>61</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>148</td>\n",
       "      <td>203</td>\n",
       "      <td>0</td>\n",
       "      <td>161</td>\n",
       "      <td>0.0</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>283</th>\n",
       "      <td>58</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>114</td>\n",
       "      <td>318</td>\n",
       "      <td>1</td>\n",
       "      <td>140</td>\n",
       "      <td>4.4</td>\n",
       "      <td>fixed</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>284</th>\n",
       "      <td>58</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>170</td>\n",
       "      <td>225</td>\n",
       "      <td>2</td>\n",
       "      <td>146</td>\n",
       "      <td>2.8</td>\n",
       "      <td>fixed</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>285</th>\n",
       "      <td>58</td>\n",
       "      <td>f</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>125</td>\n",
       "      <td>220</td>\n",
       "      <td>0</td>\n",
       "      <td>144</td>\n",
       "      <td>0.4</td>\n",
       "      <td>reversable</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>286</th>\n",
       "      <td>56</td>\n",
       "      <td>f</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>130</td>\n",
       "      <td>221</td>\n",
       "      <td>2</td>\n",
       "      <td>163</td>\n",
       "      <td>0.0</td>\n",
       "      <td>reversable</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>287</th>\n",
       "      <td>56</td>\n",
       "      <td>f</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>120</td>\n",
       "      <td>240</td>\n",
       "      <td>0</td>\n",
       "      <td>169</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>288</th>\n",
       "      <td>67</td>\n",
       "      <td>f</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>152</td>\n",
       "      <td>212</td>\n",
       "      <td>2</td>\n",
       "      <td>150</td>\n",
       "      <td>0.8</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>289</th>\n",
       "      <td>55</td>\n",
       "      <td>m</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>132</td>\n",
       "      <td>342</td>\n",
       "      <td>0</td>\n",
       "      <td>166</td>\n",
       "      <td>1.2</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>290</th>\n",
       "      <td>44</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>120</td>\n",
       "      <td>169</td>\n",
       "      <td>0</td>\n",
       "      <td>144</td>\n",
       "      <td>2.8</td>\n",
       "      <td>fixed</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>291</th>\n",
       "      <td>63</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>140</td>\n",
       "      <td>187</td>\n",
       "      <td>2</td>\n",
       "      <td>144</td>\n",
       "      <td>4.0</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>292</th>\n",
       "      <td>63</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>124</td>\n",
       "      <td>197</td>\n",
       "      <td>0</td>\n",
       "      <td>136</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>293</th>\n",
       "      <td>41</td>\n",
       "      <td>f</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>120</td>\n",
       "      <td>157</td>\n",
       "      <td>0</td>\n",
       "      <td>182</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>294</th>\n",
       "      <td>59</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>164</td>\n",
       "      <td>176</td>\n",
       "      <td>2</td>\n",
       "      <td>90</td>\n",
       "      <td>1.0</td>\n",
       "      <td>fixed</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>295</th>\n",
       "      <td>57</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>140</td>\n",
       "      <td>241</td>\n",
       "      <td>0</td>\n",
       "      <td>123</td>\n",
       "      <td>0.2</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>296</th>\n",
       "      <td>45</td>\n",
       "      <td>f</td>\n",
       "      <td>typical</td>\n",
       "      <td>110</td>\n",
       "      <td>264</td>\n",
       "      <td>0</td>\n",
       "      <td>132</td>\n",
       "      <td>1.2</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>297</th>\n",
       "      <td>68</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>144</td>\n",
       "      <td>193</td>\n",
       "      <td>0</td>\n",
       "      <td>141</td>\n",
       "      <td>3.4</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>298</th>\n",
       "      <td>57</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>130</td>\n",
       "      <td>131</td>\n",
       "      <td>0</td>\n",
       "      <td>115</td>\n",
       "      <td>1.2</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>299</th>\n",
       "      <td>57</td>\n",
       "      <td>m</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>130</td>\n",
       "      <td>236</td>\n",
       "      <td>2</td>\n",
       "      <td>174</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>300</th>\n",
       "      <td>38</td>\n",
       "      <td>f</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>138</td>\n",
       "      <td>175</td>\n",
       "      <td>0</td>\n",
       "      <td>173</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>301 rows × 10 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Age Gender     ChestPain  RestBP  Chol  RestECG  MaxHR  Oldpeak  \\\n",
       "0     63      f       typical     145   233        2    150      2.3   \n",
       "1     67      f  asymptomatic     160   286        2    108      1.5   \n",
       "2     67      f  asymptomatic     120   229        2    129      2.6   \n",
       "3     37      f    nonanginal     130   250        0    187      3.5   \n",
       "4     41      m    nontypical     130   204        2    172      1.4   \n",
       "5     56      f    nontypical     120   236        0    178      0.8   \n",
       "6     62      m  asymptomatic     140   268        2    160      3.6   \n",
       "7     57      m  asymptomatic     120   354        0    163      0.6   \n",
       "8     63      f  asymptomatic     130   254        2    147      1.4   \n",
       "9     53      f  asymptomatic     140   203        2    155      3.1   \n",
       "10    57      f  asymptomatic     140   192        0    148      0.4   \n",
       "11    56      m    nontypical     140   294        2    153      1.3   \n",
       "12    56      f    nonanginal     130   256        2    142      0.6   \n",
       "13    44      f    nontypical     120   263        0    173      0.0   \n",
       "14    52      f    nonanginal     172   199        0    162      0.5   \n",
       "15    57      f    nonanginal     150   168        0    174      1.6   \n",
       "16    48      f    nontypical     110   229        0    168      1.0   \n",
       "17    54      f  asymptomatic     140   239        0    160      1.2   \n",
       "18    48      m    nonanginal     130   275        0    139      0.2   \n",
       "19    49      f    nontypical     130   266        0    171      0.6   \n",
       "20    64      f       typical     110   211        2    144      1.8   \n",
       "21    58      m       typical     150   283        2    162      1.0   \n",
       "22    58      f    nontypical     120   284        2    160      1.8   \n",
       "23    58      f    nonanginal     132   224        2    173      3.2   \n",
       "24    60      f  asymptomatic     130   206        2    132      2.4   \n",
       "25    50      m    nonanginal     120   219        0    158      1.6   \n",
       "26    58      m    nonanginal     120   340        0    172      0.0   \n",
       "27    66      m       typical     150   226        0    114      2.6   \n",
       "28    43      f  asymptomatic     150   247        0    171      1.5   \n",
       "29    40      f  asymptomatic     110   167        2    114      2.0   \n",
       "..   ...    ...           ...     ...   ...      ...    ...      ...   \n",
       "271   71      m  asymptomatic     112   149        0    125      1.6   \n",
       "272   59      f       typical     134   204        0    162      0.8   \n",
       "273   64      f       typical     170   227        2    155      0.6   \n",
       "274   66      m    nonanginal     146   278        2    152      0.0   \n",
       "275   39      m    nonanginal     138   220        0    152      0.0   \n",
       "276   57      f    nontypical     154   232        2    164      0.0   \n",
       "277   58      m  asymptomatic     130   197        0    131      0.6   \n",
       "278   57      f  asymptomatic     110   335        0    143      3.0   \n",
       "279   47      f    nonanginal     130   253        0    179      0.0   \n",
       "280   55      m  asymptomatic     128   205        1    130      2.0   \n",
       "281   35      f    nontypical     122   192        0    174      0.0   \n",
       "282   61      f  asymptomatic     148   203        0    161      0.0   \n",
       "283   58      f  asymptomatic     114   318        1    140      4.4   \n",
       "284   58      m  asymptomatic     170   225        2    146      2.8   \n",
       "285   58      f    nontypical     125   220        0    144      0.4   \n",
       "286   56      f    nontypical     130   221        2    163      0.0   \n",
       "287   56      f    nontypical     120   240        0    169      0.0   \n",
       "288   67      f    nonanginal     152   212        2    150      0.8   \n",
       "289   55      m    nontypical     132   342        0    166      1.2   \n",
       "290   44      f  asymptomatic     120   169        0    144      2.8   \n",
       "291   63      f  asymptomatic     140   187        2    144      4.0   \n",
       "292   63      m  asymptomatic     124   197        0    136      0.0   \n",
       "293   41      f    nontypical     120   157        0    182      0.0   \n",
       "294   59      f  asymptomatic     164   176        2     90      1.0   \n",
       "295   57      m  asymptomatic     140   241        0    123      0.2   \n",
       "296   45      f       typical     110   264        0    132      1.2   \n",
       "297   68      f  asymptomatic     144   193        0    141      3.4   \n",
       "298   57      f  asymptomatic     130   131        0    115      1.2   \n",
       "299   57      m    nontypical     130   236        2    174      0.0   \n",
       "300   38      f    nonanginal     138   175        0    173      0.0   \n",
       "\n",
       "           Thal  AHD  \n",
       "0         fixed   No  \n",
       "1        normal  Yes  \n",
       "2    reversable  Yes  \n",
       "3        normal   No  \n",
       "4        normal   No  \n",
       "5        normal   No  \n",
       "6        normal  Yes  \n",
       "7        normal   No  \n",
       "8    reversable  Yes  \n",
       "9    reversable  Yes  \n",
       "10        fixed   No  \n",
       "11       normal   No  \n",
       "12        fixed  Yes  \n",
       "13   reversable   No  \n",
       "14   reversable   No  \n",
       "15       normal   No  \n",
       "16   reversable  Yes  \n",
       "17       normal   No  \n",
       "18       normal   No  \n",
       "19       normal   No  \n",
       "20       normal   No  \n",
       "21       normal   No  \n",
       "22       normal  Yes  \n",
       "23   reversable  Yes  \n",
       "24   reversable  Yes  \n",
       "25       normal   No  \n",
       "26       normal   No  \n",
       "27       normal   No  \n",
       "28       normal   No  \n",
       "29   reversable  Yes  \n",
       "..          ...  ...  \n",
       "271      normal   No  \n",
       "272      normal  Yes  \n",
       "273  reversable   No  \n",
       "274      normal   No  \n",
       "275      normal   No  \n",
       "276      normal  Yes  \n",
       "277      normal   No  \n",
       "278  reversable  Yes  \n",
       "279      normal   No  \n",
       "280  reversable  Yes  \n",
       "281      normal   No  \n",
       "282  reversable  Yes  \n",
       "283       fixed  Yes  \n",
       "284       fixed  Yes  \n",
       "285  reversable   No  \n",
       "286  reversable   No  \n",
       "287      normal   No  \n",
       "288  reversable  Yes  \n",
       "289      normal   No  \n",
       "290       fixed  Yes  \n",
       "291  reversable  Yes  \n",
       "292      normal  Yes  \n",
       "293      normal   No  \n",
       "294       fixed  Yes  \n",
       "295  reversable  Yes  \n",
       "296  reversable  Yes  \n",
       "297  reversable  Yes  \n",
       "298  reversable  Yes  \n",
       "299      normal  Yes  \n",
       "300      normal   No  \n",
       "\n",
       "[301 rows x 10 columns]"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.read_csv(\"Heart_s.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "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>Gender</th>\n",
       "      <th>ChestPain</th>\n",
       "      <th>RestBP</th>\n",
       "      <th>Chol</th>\n",
       "      <th>RestECG</th>\n",
       "      <th>MaxHR</th>\n",
       "      <th>Oldpeak</th>\n",
       "      <th>Thal</th>\n",
       "      <th>AHD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>63</td>\n",
       "      <td>f</td>\n",
       "      <td>typical</td>\n",
       "      <td>145</td>\n",
       "      <td>233</td>\n",
       "      <td>2</td>\n",
       "      <td>150</td>\n",
       "      <td>2.3</td>\n",
       "      <td>fixed</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>57</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>140</td>\n",
       "      <td>192</td>\n",
       "      <td>0</td>\n",
       "      <td>148</td>\n",
       "      <td>0.4</td>\n",
       "      <td>fixed</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>64</td>\n",
       "      <td>f</td>\n",
       "      <td>typical</td>\n",
       "      <td>110</td>\n",
       "      <td>211</td>\n",
       "      <td>2</td>\n",
       "      <td>144</td>\n",
       "      <td>1.8</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>69</td>\n",
       "      <td>m</td>\n",
       "      <td>typical</td>\n",
       "      <td>140</td>\n",
       "      <td>239</td>\n",
       "      <td>0</td>\n",
       "      <td>151</td>\n",
       "      <td>1.8</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40</th>\n",
       "      <td>65</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>150</td>\n",
       "      <td>225</td>\n",
       "      <td>2</td>\n",
       "      <td>114</td>\n",
       "      <td>1.0</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50</th>\n",
       "      <td>41</td>\n",
       "      <td>m</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>105</td>\n",
       "      <td>198</td>\n",
       "      <td>0</td>\n",
       "      <td>168</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60</th>\n",
       "      <td>51</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>130</td>\n",
       "      <td>305</td>\n",
       "      <td>0</td>\n",
       "      <td>142</td>\n",
       "      <td>1.2</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>70</th>\n",
       "      <td>65</td>\n",
       "      <td>m</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>155</td>\n",
       "      <td>269</td>\n",
       "      <td>0</td>\n",
       "      <td>148</td>\n",
       "      <td>0.8</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>80</th>\n",
       "      <td>45</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>104</td>\n",
       "      <td>208</td>\n",
       "      <td>2</td>\n",
       "      <td>148</td>\n",
       "      <td>3.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>90</th>\n",
       "      <td>62</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>160</td>\n",
       "      <td>164</td>\n",
       "      <td>2</td>\n",
       "      <td>145</td>\n",
       "      <td>6.2</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>100</th>\n",
       "      <td>34</td>\n",
       "      <td>f</td>\n",
       "      <td>typical</td>\n",
       "      <td>118</td>\n",
       "      <td>182</td>\n",
       "      <td>2</td>\n",
       "      <td>174</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>110</th>\n",
       "      <td>56</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>125</td>\n",
       "      <td>249</td>\n",
       "      <td>2</td>\n",
       "      <td>144</td>\n",
       "      <td>1.2</td>\n",
       "      <td>normal</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>120</th>\n",
       "      <td>63</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>150</td>\n",
       "      <td>407</td>\n",
       "      <td>2</td>\n",
       "      <td>154</td>\n",
       "      <td>4.0</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>130</th>\n",
       "      <td>51</td>\n",
       "      <td>f</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>94</td>\n",
       "      <td>227</td>\n",
       "      <td>0</td>\n",
       "      <td>154</td>\n",
       "      <td>0.0</td>\n",
       "      <td>reversable</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>140</th>\n",
       "      <td>59</td>\n",
       "      <td>f</td>\n",
       "      <td>typical</td>\n",
       "      <td>170</td>\n",
       "      <td>288</td>\n",
       "      <td>2</td>\n",
       "      <td>159</td>\n",
       "      <td>0.2</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>150</th>\n",
       "      <td>42</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>102</td>\n",
       "      <td>265</td>\n",
       "      <td>2</td>\n",
       "      <td>122</td>\n",
       "      <td>0.6</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>160</th>\n",
       "      <td>77</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>125</td>\n",
       "      <td>304</td>\n",
       "      <td>2</td>\n",
       "      <td>162</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>170</th>\n",
       "      <td>53</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>142</td>\n",
       "      <td>226</td>\n",
       "      <td>2</td>\n",
       "      <td>111</td>\n",
       "      <td>0.0</td>\n",
       "      <td>reversable</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>180</th>\n",
       "      <td>56</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>134</td>\n",
       "      <td>409</td>\n",
       "      <td>2</td>\n",
       "      <td>150</td>\n",
       "      <td>1.9</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>190</th>\n",
       "      <td>51</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>140</td>\n",
       "      <td>298</td>\n",
       "      <td>0</td>\n",
       "      <td>122</td>\n",
       "      <td>4.2</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>200</th>\n",
       "      <td>64</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>180</td>\n",
       "      <td>325</td>\n",
       "      <td>0</td>\n",
       "      <td>154</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>210</th>\n",
       "      <td>38</td>\n",
       "      <td>f</td>\n",
       "      <td>typical</td>\n",
       "      <td>120</td>\n",
       "      <td>231</td>\n",
       "      <td>0</td>\n",
       "      <td>182</td>\n",
       "      <td>3.8</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>220</th>\n",
       "      <td>54</td>\n",
       "      <td>m</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>108</td>\n",
       "      <td>267</td>\n",
       "      <td>2</td>\n",
       "      <td>167</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>230</th>\n",
       "      <td>55</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>180</td>\n",
       "      <td>327</td>\n",
       "      <td>1</td>\n",
       "      <td>117</td>\n",
       "      <td>3.4</td>\n",
       "      <td>normal</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>240</th>\n",
       "      <td>41</td>\n",
       "      <td>m</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>126</td>\n",
       "      <td>306</td>\n",
       "      <td>0</td>\n",
       "      <td>163</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>250</th>\n",
       "      <td>58</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>146</td>\n",
       "      <td>218</td>\n",
       "      <td>0</td>\n",
       "      <td>105</td>\n",
       "      <td>2.0</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>260</th>\n",
       "      <td>58</td>\n",
       "      <td>m</td>\n",
       "      <td>nontypical</td>\n",
       "      <td>136</td>\n",
       "      <td>319</td>\n",
       "      <td>2</td>\n",
       "      <td>152</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>270</th>\n",
       "      <td>46</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>140</td>\n",
       "      <td>311</td>\n",
       "      <td>0</td>\n",
       "      <td>120</td>\n",
       "      <td>1.8</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>280</th>\n",
       "      <td>55</td>\n",
       "      <td>m</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>128</td>\n",
       "      <td>205</td>\n",
       "      <td>1</td>\n",
       "      <td>130</td>\n",
       "      <td>2.0</td>\n",
       "      <td>reversable</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>290</th>\n",
       "      <td>44</td>\n",
       "      <td>f</td>\n",
       "      <td>asymptomatic</td>\n",
       "      <td>120</td>\n",
       "      <td>169</td>\n",
       "      <td>0</td>\n",
       "      <td>144</td>\n",
       "      <td>2.8</td>\n",
       "      <td>fixed</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>300</th>\n",
       "      <td>38</td>\n",
       "      <td>f</td>\n",
       "      <td>nonanginal</td>\n",
       "      <td>138</td>\n",
       "      <td>175</td>\n",
       "      <td>0</td>\n",
       "      <td>173</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Age Gender     ChestPain  RestBP  Chol  RestECG  MaxHR  Oldpeak  \\\n",
       "0     63      f       typical     145   233        2    150      2.3   \n",
       "10    57      f  asymptomatic     140   192        0    148      0.4   \n",
       "20    64      f       typical     110   211        2    144      1.8   \n",
       "30    69      m       typical     140   239        0    151      1.8   \n",
       "40    65      m  asymptomatic     150   225        2    114      1.0   \n",
       "50    41      m    nontypical     105   198        0    168      0.0   \n",
       "60    51      m  asymptomatic     130   305        0    142      1.2   \n",
       "70    65      m    nonanginal     155   269        0    148      0.8   \n",
       "80    45      f  asymptomatic     104   208        2    148      3.0   \n",
       "90    62      m  asymptomatic     160   164        2    145      6.2   \n",
       "100   34      f       typical     118   182        2    174      0.0   \n",
       "110   56      f  asymptomatic     125   249        2    144      1.2   \n",
       "120   63      m  asymptomatic     150   407        2    154      4.0   \n",
       "130   51      f    nonanginal      94   227        0    154      0.0   \n",
       "140   59      f       typical     170   288        2    159      0.2   \n",
       "150   42      m  asymptomatic     102   265        2    122      0.6   \n",
       "160   77      f  asymptomatic     125   304        2    162      0.0   \n",
       "170   53      f  asymptomatic     142   226        2    111      0.0   \n",
       "180   56      m  asymptomatic     134   409        2    150      1.9   \n",
       "190   51      f  asymptomatic     140   298        0    122      4.2   \n",
       "200   64      m  asymptomatic     180   325        0    154      0.0   \n",
       "210   38      f       typical     120   231        0    182      3.8   \n",
       "220   54      m    nonanginal     108   267        2    167      0.0   \n",
       "230   55      m  asymptomatic     180   327        1    117      3.4   \n",
       "240   41      m    nontypical     126   306        0    163      0.0   \n",
       "250   58      f  asymptomatic     146   218        0    105      2.0   \n",
       "260   58      m    nontypical     136   319        2    152      0.0   \n",
       "270   46      f  asymptomatic     140   311        0    120      1.8   \n",
       "280   55      m  asymptomatic     128   205        1    130      2.0   \n",
       "290   44      f  asymptomatic     120   169        0    144      2.8   \n",
       "300   38      f    nonanginal     138   175        0    173      0.0   \n",
       "\n",
       "           Thal  AHD  \n",
       "0         fixed   No  \n",
       "10        fixed   No  \n",
       "20       normal   No  \n",
       "30       normal   No  \n",
       "40   reversable  Yes  \n",
       "50       normal   No  \n",
       "60   reversable  Yes  \n",
       "70       normal   No  \n",
       "80       normal   No  \n",
       "90   reversable  Yes  \n",
       "100      normal   No  \n",
       "110      normal  Yes  \n",
       "120  reversable  Yes  \n",
       "130  reversable   No  \n",
       "140  reversable  Yes  \n",
       "150      normal   No  \n",
       "160      normal  Yes  \n",
       "170  reversable   No  \n",
       "180  reversable  Yes  \n",
       "190  reversable  Yes  \n",
       "200      normal   No  \n",
       "210  reversable  Yes  \n",
       "220      normal   No  \n",
       "230      normal  Yes  \n",
       "240      normal   No  \n",
       "250  reversable  Yes  \n",
       "260      normal  Yes  \n",
       "270  reversable  Yes  \n",
       "280  reversable  Yes  \n",
       "290       fixed  Yes  \n",
       "300      normal   No  "
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Heart_df[0::10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "#b.Check out the dataset. As you see, the dataset contains \n",
    "#a number of features including both contextual and biological factors (e.g. age, gender, vital signs, ...). \n",
    "#The last column “AHD” is the label with “Yes” meaning that a human subject has Heart Disease, and “No” meaning that \n",
    "#the subject does not have Heart Disease."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "#As you see, there are at least 3 categorical features in the dataset \n",
    "#(Gender, ChestPain, Thal). \n",
    "#Let’s ignore these categorical features for now, only keep the numerical features and \n",
    "#build your feature matrix and label vector."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "#### Step2: Set up the Feature Matrix and Label Vector:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "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>RestBP</th>\n",
       "      <th>Chol</th>\n",
       "      <th>MaxHR</th>\n",
       "      <th>Oldpeak</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>63</td>\n",
       "      <td>145</td>\n",
       "      <td>233</td>\n",
       "      <td>150</td>\n",
       "      <td>2.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>67</td>\n",
       "      <td>160</td>\n",
       "      <td>286</td>\n",
       "      <td>108</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>67</td>\n",
       "      <td>120</td>\n",
       "      <td>229</td>\n",
       "      <td>129</td>\n",
       "      <td>2.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>37</td>\n",
       "      <td>130</td>\n",
       "      <td>250</td>\n",
       "      <td>187</td>\n",
       "      <td>3.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>41</td>\n",
       "      <td>130</td>\n",
       "      <td>204</td>\n",
       "      <td>172</td>\n",
       "      <td>1.4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Age  RestBP  Chol  MaxHR  Oldpeak\n",
       "0   63     145   233    150      2.3\n",
       "1   67     160   286    108      1.5\n",
       "2   67     120   229    129      2.6\n",
       "3   37     130   250    187      3.5\n",
       "4   41     130   204    172      1.4"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Creating the Feature Matrix for heart dataset:\n",
    "\n",
    "# create a python list of feature names that would like to pick from the dataset:\n",
    "feature_cols = ['Age','RestBP','Chol','MaxHR','Oldpeak']\n",
    "\n",
    "# use the above list to select the features from the original DataFrame\n",
    "X = Heart_df[feature_cols] \n",
    "\n",
    "# print the first 5 rows\n",
    "X.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(301, 5)\n"
     ]
    }
   ],
   "source": [
    "# checking the size of Feature Matix X:\n",
    "\n",
    "print(X.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0           typical\n",
       "10     asymptomatic\n",
       "20          typical\n",
       "30          typical\n",
       "40     asymptomatic\n",
       "50       nontypical\n",
       "60     asymptomatic\n",
       "70       nonanginal\n",
       "80     asymptomatic\n",
       "90     asymptomatic\n",
       "100         typical\n",
       "110    asymptomatic\n",
       "120    asymptomatic\n",
       "130      nonanginal\n",
       "140         typical\n",
       "150    asymptomatic\n",
       "160    asymptomatic\n",
       "170    asymptomatic\n",
       "180    asymptomatic\n",
       "190    asymptomatic\n",
       "200    asymptomatic\n",
       "210         typical\n",
       "220      nonanginal\n",
       "230    asymptomatic\n",
       "240      nontypical\n",
       "250    asymptomatic\n",
       "260      nontypical\n",
       "270    asymptomatic\n",
       "280    asymptomatic\n",
       "290    asymptomatic\n",
       "300      nonanginal\n",
       "Name: ChestPain, dtype: object"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# select a Series of labels (the last column) from the DataFrame\n",
    "y = Heart_df['ChestPain']\n",
    "\n",
    "# checking the label vector by printing every 10 values\n",
    "y[::10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Step3: Defining (instantiating) an \"object\" from the sklearn class:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "# In the following line, \"knn\" is instantiated as an \"object\" of KNeighborsClassifier \"class\". \n",
    "\n",
    "k = 3\n",
    "knn = KNeighborsClassifier(n_neighbors=k) \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',\n",
       "           metric_params=None, n_jobs=1, n_neighbors=3, p=2,\n",
       "           weights='uniform')"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# We can use the method \"fit\" of the \"object knn\" along with training dataset and labels to train the model.\n",
    "\n",
    "knn.fit(X, y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['typical']\n"
     ]
    }
   ],
   "source": [
    "# We can use the method \"predict\" of the *trained* object knn on one or more testing data sample to perform prediction:\n",
    "\n",
    "X_Testing = [[63, 145, 233, 150, 2.3]]\n",
    "\n",
    "y_predict = knn.predict(X_Testing)\n",
    "\n",
    "print(y_predict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['typical' 'nonanginal']\n"
     ]
    }
   ],
   "source": [
    "# We can use the method \"predict\" of the *trained* object knn on one or more testing data sample to perform prediction:\n",
    "# Two new data samples:\n",
    "\n",
    "X_Testing = [63, 145, 233, 150, 2.3],[41, 130, 204, 172, 1.4]\n",
    "\n",
    "y_predict = knn.predict(X_Testing)\n",
    "\n",
    "print(y_predict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Evaluating the accuracy of our classifier:\n",
    "\n",
    "#### 1- Let's split the Heart Dataset RANDOMLY into two new datasets: \n",
    "#Training Set (e.g. 70% of the dataset) and Testing Set (30% of the dataset).\n",
    "#### 2- Let's pretend that we do NOT know the label of the Testing Set!\n",
    "#### 3- Let's Train the model on only Training Set, and then Predict on the Testing Set!\n",
    "#### 4- After prediction, we can compare the \"predicted labels\" for the Testing Set with its \"actual labels\" to evaluate the accuracy of our KNN Classifier!\n",
    "\n",
    "#### We will learn more about model and accuracy evaluation in future tutorials!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Randomly splitting the original dataset into training set and testing set\n",
    "# The function\"train_test_split\" from \"sklearn.cross_validation\" library performs random splitting.\n",
    "# \"test_size=0.3\" means that pick 30% of data samples for testing set, and the rest (70%) for training set.\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(225, 5)\n",
      "(225,)\n"
     ]
    }
   ],
   "source": [
    "# print the size of the traning set:\n",
    "print(X_train.shape)\n",
    "print(y_train.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(76, 5)\n",
      "(76,)\n"
     ]
    }
   ],
   "source": [
    "# print the size of the testing set:\n",
    "print(X_test.shape)\n",
    "print(y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "     Age  RestBP  Chol  MaxHR  Oldpeak\n",
      "294   59     164   176     90      1.0\n",
      "208   62     150   244    154      1.4\n",
      "18    48     130   275    139      0.2\n",
      "43    59     150   212    157      1.6\n",
      "241   49     130   269    163      0.0\n",
      "193   68     120   211    115      1.5\n",
      "169   70     160   269    112      2.9\n",
      "182   59     178   270    145      4.2\n",
      "13    44     120   263    173      0.0\n",
      "248   62     128   208    140      0.0\n",
      "124   45     130   234    175      0.6\n",
      "204   45     142   309    147      0.0\n",
      "6     62     140   268    160      3.6\n",
      "33    59     135   234    161      0.5\n",
      "61    46     142   177    160      1.4\n",
      "192   62     138   294    106      1.9\n",
      "250   58     146   218    105      2.0\n",
      "24    60     130   206    132      2.4\n",
      "297   68     144   193    141      3.4\n",
      "223   63     108   269    169      1.8\n",
      "63    54     135   304    170      0.0\n",
      "112   43     132   341    136      3.0\n",
      "177   43     130   315    162      1.9\n",
      "123   65     138   282    174      1.4\n",
      "235   56     130   283    103      1.6\n",
      "253   43     115   303    181      1.2\n",
      "14    52     172   199    162      0.5\n",
      "142   64     125   309    131      1.8\n",
      "296   45     110   264    132      1.2\n",
      "70    65     155   269    148      0.8\n",
      "..   ...     ...   ...    ...      ...\n",
      "179   48     124   274    166      0.5\n",
      "71    67     125   254    163      0.2\n",
      "221   39      94   199    179      0.0\n",
      "1     67     160   286    108      1.5\n",
      "80    45     104   208    148      3.0\n",
      "298   57     130   131    115      1.2\n",
      "12    56     130   256    142      0.6\n",
      "206   50     144   200    126      0.9\n",
      "113   62     130   263     97      1.2\n",
      "225   47     112   204    143      0.1\n",
      "246   47     110   275    118      1.0\n",
      "156   58     125   300    171      0.0\n",
      "11    56     140   294    153      1.3\n",
      "64    54     120   188    113      1.4\n",
      "39    61     150   243    137      1.0\n",
      "293   41     120   157    182      0.0\n",
      "93    63     135   252    172      0.0\n",
      "47    50     150   243    128      2.6\n",
      "175   52     108   233    147      0.1\n",
      "84    52     120   325    172      0.2\n",
      "16    48     110   229    168      1.0\n",
      "83    68     180   274    150      1.6\n",
      "292   63     124   197    136      0.0\n",
      "42    71     160   302    162      0.4\n",
      "106   57     128   229    150      0.4\n",
      "160   77     125   304    162      0.0\n",
      "69    46     150   231    147      3.6\n",
      "300   38     138   175    173      0.0\n",
      "116   35     138   183    182      1.4\n",
      "88    51     130   256    149      0.5\n",
      "\n",
      "[76 rows x 5 columns]\n",
      "\n",
      "\n",
      "294    asymptomatic\n",
      "208    asymptomatic\n",
      "18       nonanginal\n",
      "43       nonanginal\n",
      "241    asymptomatic\n",
      "193      nonanginal\n",
      "169      nonanginal\n",
      "182         typical\n",
      "13       nontypical\n",
      "248      nontypical\n",
      "124      nontypical\n",
      "204    asymptomatic\n",
      "6      asymptomatic\n",
      "33     asymptomatic\n",
      "61       nonanginal\n",
      "192    asymptomatic\n",
      "250    asymptomatic\n",
      "24     asymptomatic\n",
      "297    asymptomatic\n",
      "223    asymptomatic\n",
      "63       nonanginal\n",
      "112    asymptomatic\n",
      "177      nonanginal\n",
      "123         typical\n",
      "235    asymptomatic\n",
      "253    asymptomatic\n",
      "14       nonanginal\n",
      "142      nonanginal\n",
      "296         typical\n",
      "70       nonanginal\n",
      "           ...     \n",
      "179    asymptomatic\n",
      "71     asymptomatic\n",
      "221      nonanginal\n",
      "1      asymptomatic\n",
      "80     asymptomatic\n",
      "298    asymptomatic\n",
      "12       nonanginal\n",
      "206    asymptomatic\n",
      "113      nonanginal\n",
      "225    asymptomatic\n",
      "246    asymptomatic\n",
      "156    asymptomatic\n",
      "11       nontypical\n",
      "64     asymptomatic\n",
      "39       nonanginal\n",
      "293      nontypical\n",
      "93       nonanginal\n",
      "47     asymptomatic\n",
      "175    asymptomatic\n",
      "84       nontypical\n",
      "16       nontypical\n",
      "83       nonanginal\n",
      "292    asymptomatic\n",
      "42       nontypical\n",
      "106      nonanginal\n",
      "160    asymptomatic\n",
      "69       nonanginal\n",
      "300      nonanginal\n",
      "116    asymptomatic\n",
      "88       nonanginal\n",
      "Name: ChestPain, Length: 76, dtype: object\n"
     ]
    }
   ],
   "source": [
    "print(X_test)\n",
    "print('\\n')\n",
    "print(y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Training ONLY on the training set:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',\n",
       "           metric_params=None, n_jobs=1, n_neighbors=3, p=2,\n",
       "           weights='uniform')"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "knn.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Testing on the testing set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['asymptomatic' 'typical' 'asymptomatic' 'nonanginal' 'nontypical'\n",
      " 'asymptomatic' 'asymptomatic' 'asymptomatic' 'nonanginal' 'asymptomatic'\n",
      " 'nonanginal' 'asymptomatic' 'asymptomatic' 'asymptomatic' 'nonanginal'\n",
      " 'asymptomatic' 'asymptomatic' 'asymptomatic' 'asymptomatic'\n",
      " 'asymptomatic' 'asymptomatic' 'asymptomatic' 'nontypical' 'asymptomatic'\n",
      " 'asymptomatic' 'nontypical' 'nonanginal' 'asymptomatic' 'asymptomatic'\n",
      " 'asymptomatic' 'asymptomatic' 'asymptomatic' 'nonanginal' 'asymptomatic'\n",
      " 'asymptomatic' 'asymptomatic' 'nonanginal' 'asymptomatic' 'asymptomatic'\n",
      " 'nonanginal' 'asymptomatic' 'nonanginal' 'asymptomatic' 'asymptomatic'\n",
      " 'asymptomatic' 'nonanginal' 'nontypical' 'asymptomatic' 'nontypical'\n",
      " 'asymptomatic' 'asymptomatic' 'asymptomatic' 'asymptomatic'\n",
      " 'asymptomatic' 'asymptomatic' 'asymptomatic' 'asymptomatic'\n",
      " 'asymptomatic' 'asymptomatic' 'asymptomatic' 'typical' 'typical'\n",
      " 'asymptomatic' 'asymptomatic' 'nonanginal' 'asymptomatic' 'asymptomatic'\n",
      " 'asymptomatic' 'asymptomatic' 'asymptomatic' 'nonanginal' 'asymptomatic'\n",
      " 'asymptomatic' 'nonanginal' 'typical' 'asymptomatic']\n"
     ]
    }
   ],
   "source": [
    "# Testing on the testing set:\n",
    "\n",
    "y_predict = knn.predict(X_test)\n",
    "\n",
    "print(y_predict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Accuracy Evaluation:\n",
    "#After prediction, we can now compare the \"predicted labels\" for the Testing Set with its \"actual labels\" \n",
    "#to evaluate the accuracy of our KNN Classifier!\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5\n"
     ]
    }
   ],
   "source": [
    "# We can now compare the \"predicted labels\" for the Testing Set with its \"actual labels\" to evaluate the accuracy \n",
    "# Function \"accuracy_score\" from \"sklearn.metrics\" will perform the element-to-element comparision and returns the \n",
    "# portion of correct predictions:\n",
    "\n",
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "accuracy = accuracy_score(y_test, y_predict)\n",
    "\n",
    "print(accuracy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "           actual    prediction\n",
      "294  asymptomatic  asymptomatic\n",
      "208  asymptomatic       typical\n",
      "18     nonanginal  asymptomatic\n",
      "43     nonanginal    nonanginal\n",
      "241  asymptomatic    nontypical\n",
      "193    nonanginal  asymptomatic\n",
      "169    nonanginal  asymptomatic\n",
      "182       typical  asymptomatic\n",
      "13     nontypical    nonanginal\n",
      "248    nontypical  asymptomatic\n",
      "124    nontypical    nonanginal\n",
      "204  asymptomatic  asymptomatic\n",
      "6    asymptomatic  asymptomatic\n",
      "33   asymptomatic  asymptomatic\n",
      "61     nonanginal    nonanginal\n",
      "192  asymptomatic  asymptomatic\n",
      "250  asymptomatic  asymptomatic\n",
      "24   asymptomatic  asymptomatic\n",
      "297  asymptomatic  asymptomatic\n",
      "223  asymptomatic  asymptomatic\n",
      "63     nonanginal  asymptomatic\n",
      "112  asymptomatic  asymptomatic\n",
      "177    nonanginal    nontypical\n",
      "123       typical  asymptomatic\n",
      "235  asymptomatic  asymptomatic\n",
      "253  asymptomatic    nontypical\n",
      "14     nonanginal    nonanginal\n",
      "142    nonanginal  asymptomatic\n",
      "296       typical  asymptomatic\n",
      "70     nonanginal  asymptomatic\n",
      "..            ...           ...\n",
      "179  asymptomatic    nontypical\n",
      "71   asymptomatic  asymptomatic\n",
      "221    nonanginal    nontypical\n",
      "1    asymptomatic  asymptomatic\n",
      "80   asymptomatic  asymptomatic\n",
      "298  asymptomatic  asymptomatic\n",
      "12     nonanginal  asymptomatic\n",
      "206  asymptomatic  asymptomatic\n",
      "113    nonanginal  asymptomatic\n",
      "225  asymptomatic  asymptomatic\n",
      "246  asymptomatic  asymptomatic\n",
      "156  asymptomatic  asymptomatic\n",
      "11     nontypical  asymptomatic\n",
      "64   asymptomatic  asymptomatic\n",
      "39     nonanginal       typical\n",
      "293    nontypical       typical\n",
      "93     nonanginal  asymptomatic\n",
      "47   asymptomatic  asymptomatic\n",
      "175  asymptomatic    nonanginal\n",
      "84     nontypical  asymptomatic\n",
      "16     nontypical  asymptomatic\n",
      "83     nonanginal  asymptomatic\n",
      "292  asymptomatic  asymptomatic\n",
      "42     nontypical  asymptomatic\n",
      "106    nonanginal    nonanginal\n",
      "160  asymptomatic  asymptomatic\n",
      "69     nonanginal  asymptomatic\n",
      "300    nonanginal    nonanginal\n",
      "116  asymptomatic       typical\n",
      "88     nonanginal  asymptomatic\n",
      "\n",
      "[76 rows x 2 columns]\n"
     ]
    }
   ],
   "source": [
    "results = pd.DataFrame()\n",
    "\n",
    "results['actual'] = y_test \n",
    "results['prediction'] = y_predict \n",
    "\n",
    "print(results)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Decision Tree Calssifier:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [],
   "source": [
    "# The following line will import DecisionTreeClassifier \"Class\"\n",
    "# DecisionTreeClassifier is name of a \"sklearn class\" to perform \"Decision Tree Classification\" \n",
    "\n",
    "from sklearn.tree import DecisionTreeClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [],
   "source": [
    "# \"my_decisiontree\" is instantiated as an \"object\" of DecisionTreeClassifier \"class\". \n",
    "\n",
    "my_decisiontree = DecisionTreeClassifier()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,\n",
       "            max_features=None, max_leaf_nodes=None,\n",
       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "            min_weight_fraction_leaf=0.0, presort=False, random_state=None,\n",
       "            splitter='best')"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# We can use the method \"fit\" of the objects \"my_decisiontree\" along with training dataset and labels to train the model.\n",
    "\n",
    "my_decisiontree.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['asymptomatic' 'typical' 'typical' 'asymptomatic' 'nonanginal'\n",
      " 'asymptomatic' 'typical' 'asymptomatic' 'nonanginal' 'asymptomatic'\n",
      " 'nontypical' 'nonanginal' 'nonanginal' 'typical' 'asymptomatic'\n",
      " 'nontypical' 'asymptomatic' 'asymptomatic' 'asymptomatic' 'nontypical'\n",
      " 'nontypical' 'asymptomatic' 'nontypical' 'nonanginal' 'asymptomatic'\n",
      " 'asymptomatic' 'asymptomatic' 'asymptomatic' 'asymptomatic' 'nonanginal'\n",
      " 'nontypical' 'typical' 'asymptomatic' 'asymptomatic' 'nonanginal'\n",
      " 'asymptomatic' 'nonanginal' 'typical' 'asymptomatic' 'asymptomatic'\n",
      " 'nonanginal' 'asymptomatic' 'asymptomatic' 'typical' 'asymptomatic'\n",
      " 'nonanginal' 'nontypical' 'asymptomatic' 'nontypical' 'nontypical'\n",
      " 'nonanginal' 'asymptomatic' 'asymptomatic' 'typical' 'asymptomatic'\n",
      " 'asymptomatic' 'asymptomatic' 'nonanginal' 'nonanginal' 'asymptomatic'\n",
      " 'asymptomatic' 'typical' 'typical' 'typical' 'nonanginal' 'nontypical'\n",
      " 'nontypical' 'asymptomatic' 'asymptomatic' 'typical' 'asymptomatic'\n",
      " 'asymptomatic' 'asymptomatic' 'asymptomatic' 'typical' 'asymptomatic']\n"
     ]
    }
   ],
   "source": [
    "# Testing on the testing set:\n",
    "\n",
    "y_predict = my_decisiontree.predict(X_test)\n",
    "\n",
    "print(y_predict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.35526315789473684\n"
     ]
    }
   ],
   "source": [
    "# We can now compare the \"predicted labels\" for the Testing Set with its \"actual labels\" to evaluate the accuracy \n",
    "# Function \"accuracy_score\" from \"sklearn.metrics\" will perform the element-to-element comparision and returns the \n",
    "# portion of correct predictions:\n",
    "\n",
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "accuracy = accuracy_score(y_test, y_predict)\n",
    "\n",
    "print(accuracy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}