Chronic_Kidney_Disease.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "b94027f1",
   "metadata": {},
   "source": [
    "# DATA UNDERSTANDING\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "972c661f",
   "metadata": {},
   "outputs": [],
   "source": [
    "#importing necessary libraries\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "066b35de",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('kidney_disease.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "c29e5010",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(400, 26)"
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "07dbdf10",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>age</th>\n",
       "      <th>bp</th>\n",
       "      <th>sg</th>\n",
       "      <th>al</th>\n",
       "      <th>su</th>\n",
       "      <th>rbc</th>\n",
       "      <th>pc</th>\n",
       "      <th>pcc</th>\n",
       "      <th>ba</th>\n",
       "      <th>...</th>\n",
       "      <th>pcv</th>\n",
       "      <th>wc</th>\n",
       "      <th>rc</th>\n",
       "      <th>htn</th>\n",
       "      <th>dm</th>\n",
       "      <th>cad</th>\n",
       "      <th>appet</th>\n",
       "      <th>pe</th>\n",
       "      <th>ane</th>\n",
       "      <th>classification</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>48.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>1.020</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>normal</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>...</td>\n",
       "      <td>44</td>\n",
       "      <td>7800</td>\n",
       "      <td>5.2</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>good</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>ckd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>7.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>1.020</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>normal</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>...</td>\n",
       "      <td>38</td>\n",
       "      <td>6000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>good</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>ckd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>62.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>1.010</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>normal</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>...</td>\n",
       "      <td>31</td>\n",
       "      <td>7500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>poor</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>ckd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>48.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>1.005</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>abnormal</td>\n",
       "      <td>present</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>...</td>\n",
       "      <td>32</td>\n",
       "      <td>6700</td>\n",
       "      <td>3.9</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>poor</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>ckd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>51.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>1.010</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>normal</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>...</td>\n",
       "      <td>35</td>\n",
       "      <td>7300</td>\n",
       "      <td>4.6</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>good</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>ckd</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 26 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   id   age    bp     sg   al   su     rbc        pc         pcc          ba  \\\n",
       "0   0  48.0  80.0  1.020  1.0  0.0     NaN    normal  notpresent  notpresent   \n",
       "1   1   7.0  50.0  1.020  4.0  0.0     NaN    normal  notpresent  notpresent   \n",
       "2   2  62.0  80.0  1.010  2.0  3.0  normal    normal  notpresent  notpresent   \n",
       "3   3  48.0  70.0  1.005  4.0  0.0  normal  abnormal     present  notpresent   \n",
       "4   4  51.0  80.0  1.010  2.0  0.0  normal    normal  notpresent  notpresent   \n",
       "\n",
       "   ...  pcv    wc   rc  htn   dm  cad appet   pe  ane classification  \n",
       "0  ...   44  7800  5.2  yes  yes   no  good   no   no            ckd  \n",
       "1  ...   38  6000  NaN   no   no   no  good   no   no            ckd  \n",
       "2  ...   31  7500  NaN   no  yes   no  poor   no  yes            ckd  \n",
       "3  ...   32  6700  3.9  yes   no   no  poor  yes  yes            ckd  \n",
       "4  ...   35  7300  4.6   no   no   no  good   no   no            ckd  \n",
       "\n",
       "[5 rows x 26 columns]"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "276c9b78",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>age</th>\n",
       "      <th>bp</th>\n",
       "      <th>sg</th>\n",
       "      <th>al</th>\n",
       "      <th>su</th>\n",
       "      <th>rbc</th>\n",
       "      <th>pc</th>\n",
       "      <th>pcc</th>\n",
       "      <th>ba</th>\n",
       "      <th>...</th>\n",
       "      <th>pcv</th>\n",
       "      <th>wc</th>\n",
       "      <th>rc</th>\n",
       "      <th>htn</th>\n",
       "      <th>dm</th>\n",
       "      <th>cad</th>\n",
       "      <th>appet</th>\n",
       "      <th>pe</th>\n",
       "      <th>ane</th>\n",
       "      <th>classification</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>395</th>\n",
       "      <td>395</td>\n",
       "      <td>55.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>1.020</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>normal</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>...</td>\n",
       "      <td>47</td>\n",
       "      <td>6700</td>\n",
       "      <td>4.9</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>good</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>notckd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>396</th>\n",
       "      <td>396</td>\n",
       "      <td>42.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>1.025</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>normal</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>...</td>\n",
       "      <td>54</td>\n",
       "      <td>7800</td>\n",
       "      <td>6.2</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>good</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>notckd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>397</th>\n",
       "      <td>397</td>\n",
       "      <td>12.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>1.020</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>normal</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>...</td>\n",
       "      <td>49</td>\n",
       "      <td>6600</td>\n",
       "      <td>5.4</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>good</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>notckd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>398</th>\n",
       "      <td>398</td>\n",
       "      <td>17.0</td>\n",
       "      <td>60.0</td>\n",
       "      <td>1.025</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>normal</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>...</td>\n",
       "      <td>51</td>\n",
       "      <td>7200</td>\n",
       "      <td>5.9</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>good</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>notckd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>399</th>\n",
       "      <td>399</td>\n",
       "      <td>58.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>1.025</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>normal</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>...</td>\n",
       "      <td>53</td>\n",
       "      <td>6800</td>\n",
       "      <td>6.1</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>good</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>notckd</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 26 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      id   age    bp     sg   al   su     rbc      pc         pcc          ba  \\\n",
       "395  395  55.0  80.0  1.020  0.0  0.0  normal  normal  notpresent  notpresent   \n",
       "396  396  42.0  70.0  1.025  0.0  0.0  normal  normal  notpresent  notpresent   \n",
       "397  397  12.0  80.0  1.020  0.0  0.0  normal  normal  notpresent  notpresent   \n",
       "398  398  17.0  60.0  1.025  0.0  0.0  normal  normal  notpresent  notpresent   \n",
       "399  399  58.0  80.0  1.025  0.0  0.0  normal  normal  notpresent  notpresent   \n",
       "\n",
       "     ...  pcv    wc   rc  htn  dm  cad appet  pe ane classification  \n",
       "395  ...   47  6700  4.9   no  no   no  good  no  no         notckd  \n",
       "396  ...   54  7800  6.2   no  no   no  good  no  no         notckd  \n",
       "397  ...   49  6600  5.4   no  no   no  good  no  no         notckd  \n",
       "398  ...   51  7200  5.9   no  no   no  good  no  no         notckd  \n",
       "399  ...   53  6800  6.1   no  no   no  good  no  no         notckd  \n",
       "\n",
       "[5 rows x 26 columns]"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "e3fc598c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 400 entries, 0 to 399\n",
      "Data columns (total 26 columns):\n",
      " #   Column          Non-Null Count  Dtype  \n",
      "---  ------          --------------  -----  \n",
      " 0   id              400 non-null    int64  \n",
      " 1   age             391 non-null    float64\n",
      " 2   bp              388 non-null    float64\n",
      " 3   sg              353 non-null    float64\n",
      " 4   al              354 non-null    float64\n",
      " 5   su              351 non-null    float64\n",
      " 6   rbc             248 non-null    object \n",
      " 7   pc              335 non-null    object \n",
      " 8   pcc             396 non-null    object \n",
      " 9   ba              396 non-null    object \n",
      " 10  bgr             356 non-null    float64\n",
      " 11  bu              381 non-null    float64\n",
      " 12  sc              383 non-null    float64\n",
      " 13  sod             313 non-null    float64\n",
      " 14  pot             312 non-null    float64\n",
      " 15  hemo            348 non-null    float64\n",
      " 16  pcv             330 non-null    object \n",
      " 17  wc              295 non-null    object \n",
      " 18  rc              270 non-null    object \n",
      " 19  htn             398 non-null    object \n",
      " 20  dm              398 non-null    object \n",
      " 21  cad             398 non-null    object \n",
      " 22  appet           399 non-null    object \n",
      " 23  pe              399 non-null    object \n",
      " 24  ane             399 non-null    object \n",
      " 25  classification  400 non-null    object \n",
      "dtypes: float64(11), int64(1), object(14)\n",
      "memory usage: 81.4+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "a1a385ed",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id                  0\n",
       "age                 9\n",
       "bp                 12\n",
       "sg                 47\n",
       "al                 46\n",
       "su                 49\n",
       "rbc               152\n",
       "pc                 65\n",
       "pcc                 4\n",
       "ba                  4\n",
       "bgr                44\n",
       "bu                 19\n",
       "sc                 17\n",
       "sod                87\n",
       "pot                88\n",
       "hemo               52\n",
       "pcv                70\n",
       "wc                105\n",
       "rc                130\n",
       "htn                 2\n",
       "dm                  2\n",
       "cad                 2\n",
       "appet               1\n",
       "pe                  1\n",
       "ane                 1\n",
       "classification      0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "afd2629e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "id                400\n",
       "age                76\n",
       "bp                 10\n",
       "sg                  5\n",
       "al                  6\n",
       "su                  6\n",
       "rbc                 2\n",
       "pc                  2\n",
       "pcc                 2\n",
       "ba                  2\n",
       "bgr               146\n",
       "bu                118\n",
       "sc                 84\n",
       "sod                34\n",
       "pot                40\n",
       "hemo              115\n",
       "pcv                44\n",
       "wc                 92\n",
       "rc                 49\n",
       "htn                 2\n",
       "dm                  5\n",
       "cad                 3\n",
       "appet               2\n",
       "pe                  2\n",
       "ane                 2\n",
       "classification      3\n",
       "dtype: int64"
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.nunique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "id": "74d9a534",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "b9590897",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\sibap\\AppData\\Local\\Temp\\ipykernel_19260\\1928163937.py:1: FutureWarning: The default value of numeric_only in DataFrame.corr is deprecated. In a future version, it will default to False. Select only valid columns or specify the value of numeric_only to silence this warning.\n",
      "  df.corr(method='pearson')\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>age</th>\n",
       "      <th>bp</th>\n",
       "      <th>sg</th>\n",
       "      <th>al</th>\n",
       "      <th>su</th>\n",
       "      <th>bgr</th>\n",
       "      <th>bu</th>\n",
       "      <th>sc</th>\n",
       "      <th>sod</th>\n",
       "      <th>pot</th>\n",
       "      <th>hemo</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>id</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.185308</td>\n",
       "      <td>-0.245744</td>\n",
       "      <td>0.642156</td>\n",
       "      <td>-0.541993</td>\n",
       "      <td>-0.283416</td>\n",
       "      <td>-0.338673</td>\n",
       "      <td>-0.307175</td>\n",
       "      <td>-0.268683</td>\n",
       "      <td>0.364251</td>\n",
       "      <td>-0.092347</td>\n",
       "      <td>0.640298</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>age</th>\n",
       "      <td>-0.185308</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.159480</td>\n",
       "      <td>-0.191096</td>\n",
       "      <td>0.122091</td>\n",
       "      <td>0.220866</td>\n",
       "      <td>0.244992</td>\n",
       "      <td>0.196985</td>\n",
       "      <td>0.132531</td>\n",
       "      <td>-0.100046</td>\n",
       "      <td>0.058377</td>\n",
       "      <td>-0.192928</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>bp</th>\n",
       "      <td>-0.245744</td>\n",
       "      <td>0.159480</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.218836</td>\n",
       "      <td>0.160689</td>\n",
       "      <td>0.222576</td>\n",
       "      <td>0.160193</td>\n",
       "      <td>0.188517</td>\n",
       "      <td>0.146222</td>\n",
       "      <td>-0.116422</td>\n",
       "      <td>0.075151</td>\n",
       "      <td>-0.306540</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>sg</th>\n",
       "      <td>0.642156</td>\n",
       "      <td>-0.191096</td>\n",
       "      <td>-0.218836</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.469760</td>\n",
       "      <td>-0.296234</td>\n",
       "      <td>-0.374710</td>\n",
       "      <td>-0.314295</td>\n",
       "      <td>-0.361473</td>\n",
       "      <td>0.412190</td>\n",
       "      <td>-0.072787</td>\n",
       "      <td>0.602582</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>al</th>\n",
       "      <td>-0.541993</td>\n",
       "      <td>0.122091</td>\n",
       "      <td>0.160689</td>\n",
       "      <td>-0.469760</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.269305</td>\n",
       "      <td>0.379464</td>\n",
       "      <td>0.453528</td>\n",
       "      <td>0.399198</td>\n",
       "      <td>-0.459896</td>\n",
       "      <td>0.129038</td>\n",
       "      <td>-0.634632</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>su</th>\n",
       "      <td>-0.283416</td>\n",
       "      <td>0.220866</td>\n",
       "      <td>0.222576</td>\n",
       "      <td>-0.296234</td>\n",
       "      <td>0.269305</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.717827</td>\n",
       "      <td>0.168583</td>\n",
       "      <td>0.223244</td>\n",
       "      <td>-0.131776</td>\n",
       "      <td>0.219450</td>\n",
       "      <td>-0.224775</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>bgr</th>\n",
       "      <td>-0.338673</td>\n",
       "      <td>0.244992</td>\n",
       "      <td>0.160193</td>\n",
       "      <td>-0.374710</td>\n",
       "      <td>0.379464</td>\n",
       "      <td>0.717827</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.143322</td>\n",
       "      <td>0.114875</td>\n",
       "      <td>-0.267848</td>\n",
       "      <td>0.066966</td>\n",
       "      <td>-0.306189</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>bu</th>\n",
       "      <td>-0.307175</td>\n",
       "      <td>0.196985</td>\n",
       "      <td>0.188517</td>\n",
       "      <td>-0.314295</td>\n",
       "      <td>0.453528</td>\n",
       "      <td>0.168583</td>\n",
       "      <td>0.143322</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.586368</td>\n",
       "      <td>-0.323054</td>\n",
       "      <td>0.357049</td>\n",
       "      <td>-0.610360</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>sc</th>\n",
       "      <td>-0.268683</td>\n",
       "      <td>0.132531</td>\n",
       "      <td>0.146222</td>\n",
       "      <td>-0.361473</td>\n",
       "      <td>0.399198</td>\n",
       "      <td>0.223244</td>\n",
       "      <td>0.114875</td>\n",
       "      <td>0.586368</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.690158</td>\n",
       "      <td>0.326107</td>\n",
       "      <td>-0.401670</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>sod</th>\n",
       "      <td>0.364251</td>\n",
       "      <td>-0.100046</td>\n",
       "      <td>-0.116422</td>\n",
       "      <td>0.412190</td>\n",
       "      <td>-0.459896</td>\n",
       "      <td>-0.131776</td>\n",
       "      <td>-0.267848</td>\n",
       "      <td>-0.323054</td>\n",
       "      <td>-0.690158</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.097887</td>\n",
       "      <td>0.365183</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>pot</th>\n",
       "      <td>-0.092347</td>\n",
       "      <td>0.058377</td>\n",
       "      <td>0.075151</td>\n",
       "      <td>-0.072787</td>\n",
       "      <td>0.129038</td>\n",
       "      <td>0.219450</td>\n",
       "      <td>0.066966</td>\n",
       "      <td>0.357049</td>\n",
       "      <td>0.326107</td>\n",
       "      <td>0.097887</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.133746</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>hemo</th>\n",
       "      <td>0.640298</td>\n",
       "      <td>-0.192928</td>\n",
       "      <td>-0.306540</td>\n",
       "      <td>0.602582</td>\n",
       "      <td>-0.634632</td>\n",
       "      <td>-0.224775</td>\n",
       "      <td>-0.306189</td>\n",
       "      <td>-0.610360</td>\n",
       "      <td>-0.401670</td>\n",
       "      <td>0.365183</td>\n",
       "      <td>-0.133746</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            id       age        bp        sg        al        su       bgr  \\\n",
       "id    1.000000 -0.185308 -0.245744  0.642156 -0.541993 -0.283416 -0.338673   \n",
       "age  -0.185308  1.000000  0.159480 -0.191096  0.122091  0.220866  0.244992   \n",
       "bp   -0.245744  0.159480  1.000000 -0.218836  0.160689  0.222576  0.160193   \n",
       "sg    0.642156 -0.191096 -0.218836  1.000000 -0.469760 -0.296234 -0.374710   \n",
       "al   -0.541993  0.122091  0.160689 -0.469760  1.000000  0.269305  0.379464   \n",
       "su   -0.283416  0.220866  0.222576 -0.296234  0.269305  1.000000  0.717827   \n",
       "bgr  -0.338673  0.244992  0.160193 -0.374710  0.379464  0.717827  1.000000   \n",
       "bu   -0.307175  0.196985  0.188517 -0.314295  0.453528  0.168583  0.143322   \n",
       "sc   -0.268683  0.132531  0.146222 -0.361473  0.399198  0.223244  0.114875   \n",
       "sod   0.364251 -0.100046 -0.116422  0.412190 -0.459896 -0.131776 -0.267848   \n",
       "pot  -0.092347  0.058377  0.075151 -0.072787  0.129038  0.219450  0.066966   \n",
       "hemo  0.640298 -0.192928 -0.306540  0.602582 -0.634632 -0.224775 -0.306189   \n",
       "\n",
       "            bu        sc       sod       pot      hemo  \n",
       "id   -0.307175 -0.268683  0.364251 -0.092347  0.640298  \n",
       "age   0.196985  0.132531 -0.100046  0.058377 -0.192928  \n",
       "bp    0.188517  0.146222 -0.116422  0.075151 -0.306540  \n",
       "sg   -0.314295 -0.361473  0.412190 -0.072787  0.602582  \n",
       "al    0.453528  0.399198 -0.459896  0.129038 -0.634632  \n",
       "su    0.168583  0.223244 -0.131776  0.219450 -0.224775  \n",
       "bgr   0.143322  0.114875 -0.267848  0.066966 -0.306189  \n",
       "bu    1.000000  0.586368 -0.323054  0.357049 -0.610360  \n",
       "sc    0.586368  1.000000 -0.690158  0.326107 -0.401670  \n",
       "sod  -0.323054 -0.690158  1.000000  0.097887  0.365183  \n",
       "pot   0.357049  0.326107  0.097887  1.000000 -0.133746  \n",
       "hemo -0.610360 -0.401670  0.365183 -0.133746  1.000000  "
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.corr(method='pearson')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "90f5f172",
   "metadata": {},
   "source": [
    "# NOTE:-\n",
    "1. RBC TO BA : OBJECT --> FIRSTLY CLEANING THEN TO BE CONVERTED INTO INT.\n",
    "2. PCV TO CLASSIFICATION --> CONVERSION TO INT REQUIRED.\n",
    "3. DATAFRAME CONTAINS TOO MANY NULL VALUES....CLEANING HAS TO BE DONE."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2449494e",
   "metadata": {},
   "source": [
    "# DATA PREPARATION"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "1599dcf5",
   "metadata": {},
   "outputs": [],
   "source": [
    "df2 = df.copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "id": "a09249ff",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>age</th>\n",
       "      <th>bp</th>\n",
       "      <th>sg</th>\n",
       "      <th>al</th>\n",
       "      <th>su</th>\n",
       "      <th>rbc</th>\n",
       "      <th>pc</th>\n",
       "      <th>pcc</th>\n",
       "      <th>ba</th>\n",
       "      <th>...</th>\n",
       "      <th>pcv</th>\n",
       "      <th>wc</th>\n",
       "      <th>rc</th>\n",
       "      <th>htn</th>\n",
       "      <th>dm</th>\n",
       "      <th>cad</th>\n",
       "      <th>appet</th>\n",
       "      <th>pe</th>\n",
       "      <th>ane</th>\n",
       "      <th>classification</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>48.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>1.020</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>normal</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>...</td>\n",
       "      <td>44</td>\n",
       "      <td>7800</td>\n",
       "      <td>5.2</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>good</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>ckd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>7.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>1.020</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>normal</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>...</td>\n",
       "      <td>38</td>\n",
       "      <td>6000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>good</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>ckd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>62.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>1.010</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>normal</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>...</td>\n",
       "      <td>31</td>\n",
       "      <td>7500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>poor</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>ckd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>48.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>1.005</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>abnormal</td>\n",
       "      <td>present</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>...</td>\n",
       "      <td>32</td>\n",
       "      <td>6700</td>\n",
       "      <td>3.9</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>poor</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>ckd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>51.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>1.010</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>normal</td>\n",
       "      <td>normal</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>notpresent</td>\n",
       "      <td>...</td>\n",
       "      <td>35</td>\n",
       "      <td>7300</td>\n",
       "      <td>4.6</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>good</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>ckd</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 26 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   id   age    bp     sg   al   su     rbc        pc         pcc          ba  \\\n",
       "0   0  48.0  80.0  1.020  1.0  0.0     NaN    normal  notpresent  notpresent   \n",
       "1   1   7.0  50.0  1.020  4.0  0.0     NaN    normal  notpresent  notpresent   \n",
       "2   2  62.0  80.0  1.010  2.0  3.0  normal    normal  notpresent  notpresent   \n",
       "3   3  48.0  70.0  1.005  4.0  0.0  normal  abnormal     present  notpresent   \n",
       "4   4  51.0  80.0  1.010  2.0  0.0  normal    normal  notpresent  notpresent   \n",
       "\n",
       "   ...  pcv    wc   rc  htn   dm  cad appet   pe  ane classification  \n",
       "0  ...   44  7800  5.2  yes  yes   no  good   no   no            ckd  \n",
       "1  ...   38  6000  NaN   no   no   no  good   no   no            ckd  \n",
       "2  ...   31  7500  NaN   no  yes   no  poor   no  yes            ckd  \n",
       "3  ...   32  6700  3.9  yes   no   no  poor  yes  yes            ckd  \n",
       "4  ...   35  7300  4.6   no   no   no  good   no   no            ckd  \n",
       "\n",
       "[5 rows x 26 columns]"
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "id": "bd1b4ee2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 400 entries, 0 to 399\n",
      "Data columns (total 26 columns):\n",
      " #   Column          Non-Null Count  Dtype  \n",
      "---  ------          --------------  -----  \n",
      " 0   id              400 non-null    int64  \n",
      " 1   age             391 non-null    float64\n",
      " 2   bp              388 non-null    float64\n",
      " 3   sg              353 non-null    float64\n",
      " 4   al              354 non-null    float64\n",
      " 5   su              351 non-null    float64\n",
      " 6   rbc             248 non-null    object \n",
      " 7   pc              335 non-null    object \n",
      " 8   pcc             396 non-null    object \n",
      " 9   ba              396 non-null    object \n",
      " 10  bgr             356 non-null    float64\n",
      " 11  bu              381 non-null    float64\n",
      " 12  sc              383 non-null    float64\n",
      " 13  sod             313 non-null    float64\n",
      " 14  pot             312 non-null    float64\n",
      " 15  hemo            348 non-null    float64\n",
      " 16  pcv             330 non-null    object \n",
      " 17  wc              295 non-null    object \n",
      " 18  rc              270 non-null    object \n",
      " 19  htn             398 non-null    object \n",
      " 20  dm              398 non-null    object \n",
      " 21  cad             398 non-null    object \n",
      " 22  appet           399 non-null    object \n",
      " 23  pe              399 non-null    object \n",
      " 24  ane             399 non-null    object \n",
      " 25  classification  400 non-null    object \n",
      "dtypes: float64(11), int64(1), object(14)\n",
      "memory usage: 81.4+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "id": "158ef1c6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[44 38 31 32 35 39 36 33 29 28 41 16 24 37 30 34 40 45 27 48 52 14 22 18\n",
      " 42 17 46 23 19 25 26 15 21 43 20 47  9 49 50 53 51 54]\n",
      "[ 7800  6000  7500  6700  7300  9800  6900  9600 12100  4500 12200 11000\n",
      "  3800 11400  5300  9200  6200  8300  8400 10300  9100  7900  6400  8600\n",
      " 18900 21600  4300  8500 11300  7200  7700 14600  6300  7100 11800  9400\n",
      "  5500  5800 13200 12500  5600  7000 11900 10400 10700 12700  6800  6500\n",
      " 13600 10200  9000 14900  8200 15200  5000 16300 12400 10500  4200  4700\n",
      " 10900  8100  9500  2200 12800 11200 19100 12300 16700  2600 26400  8800\n",
      "  7400  8000 12000 15700  4100  5700 11500  5400 10800  9900  5200  5900\n",
      "  9300  9700  5100  6600]\n",
      "['5.2' '3.9' '4.6' '4.4' '5' '4.0' '3.7' '3.8' '3.4' '2.6' '2.8' '4.3'\n",
      " '3.2' '3.6' '4' '4.1' '4.9' '2.5' '4.2' '4.5' '3.1' '4.7' '3.5' '6.0'\n",
      " '5.0' '2.1' '5.6' '2.3' '2.9' '2.7' '3.3' '3.0' '3' '2.4' '4.8' '5.4'\n",
      " '6.1' '6.2' '6.3' '5.1' '5.8' '5.5' '5.3' '6.4' '5.7' '5.9' '6.5']\n"
     ]
    }
   ],
   "source": [
    "#STEP 1\n",
    "\n",
    "from sklearn.impute import SimpleImputer\n",
    "\n",
    "\n",
    "df = df[(df['pcv'] !='\\t?') & (df['pcv'] != '\\t43')]\n",
    "print(df['pcv'].unique())\n",
    "df = df[(df['wc'] !='\\t6200') & (df['wc'] != '\\t?') & (df['wc'] != '\\t8400')]\n",
    "print(df['wc'].unique())\n",
    "df = df[(df['rc'] !='\\t?') & (df['rc'] != 'nan')]\n",
    "print(df['rc'].unique())\n",
    "\n",
    "df['pcv'] = SimpleImputer(strategy = 'most_frequent').fit_transform(df[['pcv']])\n",
    "df['pcv'] = df['pcv'].astype(int)\n",
    "\n",
    "df['wc'] = SimpleImputer(strategy = 'most_frequent').fit_transform(df[['wc']])\n",
    "df['wc'] = df['wc'].astype(int)\n",
    "\n",
    "df['rc'] = SimpleImputer(strategy = 'most_frequent').fit_transform(df[['rc']])\n",
    "df['rc'] = df['rc'].astype(float)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 134,
   "id": "1b02892c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# STEP 2 : data cleaning & encoding\n",
    "from sklearn.impute import SimpleImputer\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.compose import ColumnTransformer\n",
    "from sklearn.preprocessing import OneHotEncoder\n",
    "\n",
    "num = ['age','bp','sg','al','su','bgr','bu','sc','sod','pot','hemo']\n",
    "obj = ['rbc','pc','pcc','ba','htn','dm','cad','appet','pe','ane']\n",
    "\n",
    "imputer1 = SimpleImputer(strategy = 'most_frequent')\n",
    "imputer2 = SimpleImputer(strategy = 'mean')\n",
    "encoder = OneHotEncoder()\n",
    "\n",
    "num_pipeline = Pipeline(\n",
    "    steps = [\n",
    "        ('imputer2',imputer2)      \n",
    "    ]\n",
    ")\n",
    "\n",
    "obj_pipeline = Pipeline(\n",
    "    steps = [\n",
    "        ('imputer1',imputer1),\n",
    "        ('encoder',encoder)\n",
    "    ]\n",
    ")\n",
    "\n",
    "transformer = ColumnTransformer(\n",
    "    transformers = [\n",
    "        ('num_pipeline',num_pipeline,num),\n",
    "        ('cat_pipeline',obj_pipeline,obj)\n",
    "    ]\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "id": "4911bd38",
   "metadata": {},
   "outputs": [],
   "source": [
    "x = df.drop(columns = ['id','classification'])\n",
    "y = df.classification"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "id": "dce143d8",
   "metadata": {},
   "outputs": [],
   "source": [
    "x= transformer.fit_transform(x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 137,
   "id": "a48a2753",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dtype('float64')"
      ]
     },
     "execution_count": 137,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.dtype"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 187,
   "id": "85ee74fe",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split \n",
    "\n",
    "X_train,X_test,y_train,y_test = train_test_split(x,y,random_state=39)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0f946715",
   "metadata": {},
   "source": [
    "# DATA MODELLING"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 188,
   "id": "0942daed",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.preprocessing import StandardScaler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 189,
   "id": "d0ab8bd9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy Score Of LogisticRegression(max_iter=6000) is: 0.9696969696969697\n",
      "**************************************************************\n",
      "Accuracy Score Of SVC() is: 0.8383838383838383\n",
      "**************************************************************\n",
      "Accuracy Score Of DecisionTreeClassifier() is: 0.9696969696969697\n",
      "**************************************************************\n",
      "Accuracy Score Of RandomForestClassifier() is: 1.0\n",
      "**************************************************************\n"
     ]
    }
   ],
   "source": [
    "models = [LogisticRegression(max_iter=6000),SVC(),DecisionTreeClassifier(),RandomForestClassifier()]\n",
    "\n",
    "for model in models:\n",
    "    if(model==LogisticRegression(max_iter=6000)):\n",
    "        scaler = StandardScaler()\n",
    "        X_train =  scaler.fit_transform(X_train)\n",
    "        model.fit(X_train,y_train)\n",
    "        print(f\"Accuracy Score Of {model} is: {model.score(X_test,y_test)}\")\n",
    "        print('**************************************************************')\n",
    "    else:\n",
    "        model.fit(X_train,y_train)\n",
    "        print(f\"Accuracy Score Of {model} is: {model.score(X_test,y_test)}\")\n",
    "        print('**************************************************************')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 190,
   "id": "c80cbd4a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestClassifier()"
      ]
     },
     "execution_count": 190,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = RandomForestClassifier()\n",
    "model.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 191,
   "id": "76063da4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "100.0"
      ]
     },
     "execution_count": 191,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.score(X_test,y_test)*100"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6cd5eb95",
   "metadata": {},
   "source": [
    "# SAVING MODEL"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 193,
   "id": "24c7b420",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "\n",
    "with open('Chronic_kidney_disease','wb') as f:\n",
    "    pickle.dump(model,f)\n",
    "    f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b9fa799d",
   "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": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}