Liver_Disease_Prediction_Supervised_ML (2).ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**IMPORTING NECESSARY LIBRARIES** "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 310,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**READING THE DATA**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 311,
   "metadata": {},
   "outputs": [],
   "source": [
    "liver=pd.read_csv('liver_disease_dataset')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 312,
   "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>Total_Bilirubin</th>\n",
       "      <th>Direct_Bilirubin</th>\n",
       "      <th>Alkaline_Phosphotase</th>\n",
       "      <th>Alamine_Aminotransferase</th>\n",
       "      <th>Aspartate_Aminotransferase</th>\n",
       "      <th>Total_Protiens</th>\n",
       "      <th>Albumin</th>\n",
       "      <th>Albumin_and_Globulin_Ratio</th>\n",
       "      <th>Dataset</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>65</td>\n",
       "      <td>Female</td>\n",
       "      <td>0.7</td>\n",
       "      <td>0.1</td>\n",
       "      <td>187</td>\n",
       "      <td>16</td>\n",
       "      <td>18</td>\n",
       "      <td>6.8</td>\n",
       "      <td>3.3</td>\n",
       "      <td>0.90</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>62</td>\n",
       "      <td>Male</td>\n",
       "      <td>10.9</td>\n",
       "      <td>5.5</td>\n",
       "      <td>699</td>\n",
       "      <td>64</td>\n",
       "      <td>100</td>\n",
       "      <td>7.5</td>\n",
       "      <td>3.2</td>\n",
       "      <td>0.74</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>62</td>\n",
       "      <td>Male</td>\n",
       "      <td>7.3</td>\n",
       "      <td>4.1</td>\n",
       "      <td>490</td>\n",
       "      <td>60</td>\n",
       "      <td>68</td>\n",
       "      <td>7.0</td>\n",
       "      <td>3.3</td>\n",
       "      <td>0.89</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>58</td>\n",
       "      <td>Male</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.4</td>\n",
       "      <td>182</td>\n",
       "      <td>14</td>\n",
       "      <td>20</td>\n",
       "      <td>6.8</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>72</td>\n",
       "      <td>Male</td>\n",
       "      <td>3.9</td>\n",
       "      <td>2.0</td>\n",
       "      <td>195</td>\n",
       "      <td>27</td>\n",
       "      <td>59</td>\n",
       "      <td>7.3</td>\n",
       "      <td>2.4</td>\n",
       "      <td>0.40</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>578</th>\n",
       "      <td>60</td>\n",
       "      <td>Male</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.1</td>\n",
       "      <td>500</td>\n",
       "      <td>20</td>\n",
       "      <td>34</td>\n",
       "      <td>5.9</td>\n",
       "      <td>1.6</td>\n",
       "      <td>0.37</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>579</th>\n",
       "      <td>40</td>\n",
       "      <td>Male</td>\n",
       "      <td>0.6</td>\n",
       "      <td>0.1</td>\n",
       "      <td>98</td>\n",
       "      <td>35</td>\n",
       "      <td>31</td>\n",
       "      <td>6.0</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.10</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>580</th>\n",
       "      <td>52</td>\n",
       "      <td>Male</td>\n",
       "      <td>0.8</td>\n",
       "      <td>0.2</td>\n",
       "      <td>245</td>\n",
       "      <td>48</td>\n",
       "      <td>49</td>\n",
       "      <td>6.4</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>581</th>\n",
       "      <td>31</td>\n",
       "      <td>Male</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.5</td>\n",
       "      <td>184</td>\n",
       "      <td>29</td>\n",
       "      <td>32</td>\n",
       "      <td>6.8</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>582</th>\n",
       "      <td>38</td>\n",
       "      <td>Male</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.3</td>\n",
       "      <td>216</td>\n",
       "      <td>21</td>\n",
       "      <td>24</td>\n",
       "      <td>7.3</td>\n",
       "      <td>4.4</td>\n",
       "      <td>1.50</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>583 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Age  Gender  Total_Bilirubin  Direct_Bilirubin  Alkaline_Phosphotase  \\\n",
       "0     65  Female              0.7               0.1                   187   \n",
       "1     62    Male             10.9               5.5                   699   \n",
       "2     62    Male              7.3               4.1                   490   \n",
       "3     58    Male              1.0               0.4                   182   \n",
       "4     72    Male              3.9               2.0                   195   \n",
       "..   ...     ...              ...               ...                   ...   \n",
       "578   60    Male              0.5               0.1                   500   \n",
       "579   40    Male              0.6               0.1                    98   \n",
       "580   52    Male              0.8               0.2                   245   \n",
       "581   31    Male              1.3               0.5                   184   \n",
       "582   38    Male              1.0               0.3                   216   \n",
       "\n",
       "     Alamine_Aminotransferase  Aspartate_Aminotransferase  Total_Protiens  \\\n",
       "0                          16                          18             6.8   \n",
       "1                          64                         100             7.5   \n",
       "2                          60                          68             7.0   \n",
       "3                          14                          20             6.8   \n",
       "4                          27                          59             7.3   \n",
       "..                        ...                         ...             ...   \n",
       "578                        20                          34             5.9   \n",
       "579                        35                          31             6.0   \n",
       "580                        48                          49             6.4   \n",
       "581                        29                          32             6.8   \n",
       "582                        21                          24             7.3   \n",
       "\n",
       "     Albumin  Albumin_and_Globulin_Ratio  Dataset  \n",
       "0        3.3                        0.90        1  \n",
       "1        3.2                        0.74        1  \n",
       "2        3.3                        0.89        1  \n",
       "3        3.4                        1.00        1  \n",
       "4        2.4                        0.40        1  \n",
       "..       ...                         ...      ...  \n",
       "578      1.6                        0.37        2  \n",
       "579      3.2                        1.10        1  \n",
       "580      3.2                        1.00        1  \n",
       "581      3.4                        1.00        1  \n",
       "582      4.4                        1.50        2  \n",
       "\n",
       "[583 rows x 11 columns]"
      ]
     },
     "execution_count": 312,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "liver"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**EXPLORATORY DATA ANALYSIS :-**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 313,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1a2b9d8510>"
      ]
     },
     "execution_count": 313,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x432 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig=plt.figure(figsize=(10,6))\n",
    "sns.heatmap(liver.corr(),cmap='coolwarm')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Quantitites like Direct_Bilirubin,Total_Bilirubin and Aspartate_Aminotransferase,Alamine_Aminotransferase look correlated.**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**ANALYSING THE DATA OF DISEASED PATIENTS**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 314,
   "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>Total_Bilirubin</th>\n",
       "      <th>Direct_Bilirubin</th>\n",
       "      <th>Alkaline_Phosphotase</th>\n",
       "      <th>Alamine_Aminotransferase</th>\n",
       "      <th>Aspartate_Aminotransferase</th>\n",
       "      <th>Total_Protiens</th>\n",
       "      <th>Albumin</th>\n",
       "      <th>Albumin_and_Globulin_Ratio</th>\n",
       "      <th>Dataset</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>65</td>\n",
       "      <td>Female</td>\n",
       "      <td>0.7</td>\n",
       "      <td>0.1</td>\n",
       "      <td>187</td>\n",
       "      <td>16</td>\n",
       "      <td>18</td>\n",
       "      <td>6.8</td>\n",
       "      <td>3.3</td>\n",
       "      <td>0.90</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>62</td>\n",
       "      <td>Male</td>\n",
       "      <td>10.9</td>\n",
       "      <td>5.5</td>\n",
       "      <td>699</td>\n",
       "      <td>64</td>\n",
       "      <td>100</td>\n",
       "      <td>7.5</td>\n",
       "      <td>3.2</td>\n",
       "      <td>0.74</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>62</td>\n",
       "      <td>Male</td>\n",
       "      <td>7.3</td>\n",
       "      <td>4.1</td>\n",
       "      <td>490</td>\n",
       "      <td>60</td>\n",
       "      <td>68</td>\n",
       "      <td>7.0</td>\n",
       "      <td>3.3</td>\n",
       "      <td>0.89</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>58</td>\n",
       "      <td>Male</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.4</td>\n",
       "      <td>182</td>\n",
       "      <td>14</td>\n",
       "      <td>20</td>\n",
       "      <td>6.8</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>72</td>\n",
       "      <td>Male</td>\n",
       "      <td>3.9</td>\n",
       "      <td>2.0</td>\n",
       "      <td>195</td>\n",
       "      <td>27</td>\n",
       "      <td>59</td>\n",
       "      <td>7.3</td>\n",
       "      <td>2.4</td>\n",
       "      <td>0.40</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>576</th>\n",
       "      <td>32</td>\n",
       "      <td>Male</td>\n",
       "      <td>15.0</td>\n",
       "      <td>8.2</td>\n",
       "      <td>289</td>\n",
       "      <td>58</td>\n",
       "      <td>80</td>\n",
       "      <td>5.3</td>\n",
       "      <td>2.2</td>\n",
       "      <td>0.70</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>577</th>\n",
       "      <td>32</td>\n",
       "      <td>Male</td>\n",
       "      <td>12.7</td>\n",
       "      <td>8.4</td>\n",
       "      <td>190</td>\n",
       "      <td>28</td>\n",
       "      <td>47</td>\n",
       "      <td>5.4</td>\n",
       "      <td>2.6</td>\n",
       "      <td>0.90</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>579</th>\n",
       "      <td>40</td>\n",
       "      <td>Male</td>\n",
       "      <td>0.6</td>\n",
       "      <td>0.1</td>\n",
       "      <td>98</td>\n",
       "      <td>35</td>\n",
       "      <td>31</td>\n",
       "      <td>6.0</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.10</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>580</th>\n",
       "      <td>52</td>\n",
       "      <td>Male</td>\n",
       "      <td>0.8</td>\n",
       "      <td>0.2</td>\n",
       "      <td>245</td>\n",
       "      <td>48</td>\n",
       "      <td>49</td>\n",
       "      <td>6.4</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>581</th>\n",
       "      <td>31</td>\n",
       "      <td>Male</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.5</td>\n",
       "      <td>184</td>\n",
       "      <td>29</td>\n",
       "      <td>32</td>\n",
       "      <td>6.8</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>416 rows × 11 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Age  Gender  Total_Bilirubin  Direct_Bilirubin  Alkaline_Phosphotase  \\\n",
       "0     65  Female              0.7               0.1                   187   \n",
       "1     62    Male             10.9               5.5                   699   \n",
       "2     62    Male              7.3               4.1                   490   \n",
       "3     58    Male              1.0               0.4                   182   \n",
       "4     72    Male              3.9               2.0                   195   \n",
       "..   ...     ...              ...               ...                   ...   \n",
       "576   32    Male             15.0               8.2                   289   \n",
       "577   32    Male             12.7               8.4                   190   \n",
       "579   40    Male              0.6               0.1                    98   \n",
       "580   52    Male              0.8               0.2                   245   \n",
       "581   31    Male              1.3               0.5                   184   \n",
       "\n",
       "     Alamine_Aminotransferase  Aspartate_Aminotransferase  Total_Protiens  \\\n",
       "0                          16                          18             6.8   \n",
       "1                          64                         100             7.5   \n",
       "2                          60                          68             7.0   \n",
       "3                          14                          20             6.8   \n",
       "4                          27                          59             7.3   \n",
       "..                        ...                         ...             ...   \n",
       "576                        58                          80             5.3   \n",
       "577                        28                          47             5.4   \n",
       "579                        35                          31             6.0   \n",
       "580                        48                          49             6.4   \n",
       "581                        29                          32             6.8   \n",
       "\n",
       "     Albumin  Albumin_and_Globulin_Ratio  Dataset  \n",
       "0        3.3                        0.90        1  \n",
       "1        3.2                        0.74        1  \n",
       "2        3.3                        0.89        1  \n",
       "3        3.4                        1.00        1  \n",
       "4        2.4                        0.40        1  \n",
       "..       ...                         ...      ...  \n",
       "576      2.2                        0.70        1  \n",
       "577      2.6                        0.90        1  \n",
       "579      3.2                        1.10        1  \n",
       "580      3.2                        1.00        1  \n",
       "581      3.4                        1.00        1  \n",
       "\n",
       "[416 rows x 11 columns]"
      ]
     },
     "execution_count": 314,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "liver_diseased=liver[liver['Dataset']==1]\n",
    "liver_diseased"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 315,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1a2baddb10>"
      ]
     },
     "execution_count": 315,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.set_style('darkgrid')\n",
    "fig=plt.figure(figsize=(10,6))\n",
    "sns.distplot(liver_diseased['Age'],bins=10,kde=False,axlabel='AGE',color='green')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**PEOPLE MOSTLY IN THE AGE GROUP OF 30-40 YEARS ARE DISEASED**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 316,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1a2bd27b10>"
      ]
     },
     "execution_count": 316,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.countplot(x='Gender',data=liver_diseased,palette='coolwarm')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**MORE MEN THAN WOMEN ARE DISEASED**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**DATA CLEANING :-**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**MAPPING THE VALUE 2 OF THE DATASET TO 0 - MEANING - NOT DISEASED**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 317,
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in range(583):\n",
    "    if liver.iloc[i,10]==2:\n",
    "        liver.iloc[i,10]=0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 318,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 0])"
      ]
     },
     "execution_count": 318,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "liver['Dataset'].unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**CONVERTING TEXTUAL DATA OF GENDER TO NUMERICAL DATA (MALE=0, FEMALE=1) FOR SUITABLY FITTING IN ALGORITHM**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 319,
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in range(583):\n",
    "    if liver.iloc[i,1]=='Male':\n",
    "        liver.iloc[i,1]=0\n",
    "    else:\n",
    "        liver.iloc[i,1]=1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 320,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 0], dtype=object)"
      ]
     },
     "execution_count": 320,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "liver['Gender'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 321,
   "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>Total_Bilirubin</th>\n",
       "      <th>Direct_Bilirubin</th>\n",
       "      <th>Alkaline_Phosphotase</th>\n",
       "      <th>Alamine_Aminotransferase</th>\n",
       "      <th>Aspartate_Aminotransferase</th>\n",
       "      <th>Total_Protiens</th>\n",
       "      <th>Albumin</th>\n",
       "      <th>Albumin_and_Globulin_Ratio</th>\n",
       "      <th>Dataset</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>65</td>\n",
       "      <td>1</td>\n",
       "      <td>0.7</td>\n",
       "      <td>0.1</td>\n",
       "      <td>187</td>\n",
       "      <td>16</td>\n",
       "      <td>18</td>\n",
       "      <td>6.8</td>\n",
       "      <td>3.3</td>\n",
       "      <td>0.90</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>62</td>\n",
       "      <td>0</td>\n",
       "      <td>10.9</td>\n",
       "      <td>5.5</td>\n",
       "      <td>699</td>\n",
       "      <td>64</td>\n",
       "      <td>100</td>\n",
       "      <td>7.5</td>\n",
       "      <td>3.2</td>\n",
       "      <td>0.74</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>62</td>\n",
       "      <td>0</td>\n",
       "      <td>7.3</td>\n",
       "      <td>4.1</td>\n",
       "      <td>490</td>\n",
       "      <td>60</td>\n",
       "      <td>68</td>\n",
       "      <td>7.0</td>\n",
       "      <td>3.3</td>\n",
       "      <td>0.89</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>58</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.4</td>\n",
       "      <td>182</td>\n",
       "      <td>14</td>\n",
       "      <td>20</td>\n",
       "      <td>6.8</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>72</td>\n",
       "      <td>0</td>\n",
       "      <td>3.9</td>\n",
       "      <td>2.0</td>\n",
       "      <td>195</td>\n",
       "      <td>27</td>\n",
       "      <td>59</td>\n",
       "      <td>7.3</td>\n",
       "      <td>2.4</td>\n",
       "      <td>0.40</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Age Gender  Total_Bilirubin  Direct_Bilirubin  Alkaline_Phosphotase  \\\n",
       "0   65      1              0.7               0.1                   187   \n",
       "1   62      0             10.9               5.5                   699   \n",
       "2   62      0              7.3               4.1                   490   \n",
       "3   58      0              1.0               0.4                   182   \n",
       "4   72      0              3.9               2.0                   195   \n",
       "\n",
       "   Alamine_Aminotransferase  Aspartate_Aminotransferase  Total_Protiens  \\\n",
       "0                        16                          18             6.8   \n",
       "1                        64                         100             7.5   \n",
       "2                        60                          68             7.0   \n",
       "3                        14                          20             6.8   \n",
       "4                        27                          59             7.3   \n",
       "\n",
       "   Albumin  Albumin_and_Globulin_Ratio  Dataset  \n",
       "0      3.3                        0.90        1  \n",
       "1      3.2                        0.74        1  \n",
       "2      3.3                        0.89        1  \n",
       "3      3.4                        1.00        1  \n",
       "4      2.4                        0.40        1  "
      ]
     },
     "execution_count": 321,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "liver.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**CHECKING FOR NULL VALUES IN EACH COLUMNS**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 322,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0\n",
      "0\n",
      "0\n",
      "0\n",
      "0\n",
      "0\n",
      "0\n",
      "0\n",
      "0\n",
      "4\n",
      "0\n"
     ]
    }
   ],
   "source": [
    "for i in range(11):\n",
    "    print(sum(liver.iloc[:,i].isnull()))    \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "   "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**FILLING THE NULL VALUES IN THE SECOND LAST COLUMN WITH THE MEAN OF THE VALUES OF THAT COLUMN**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 323,
   "metadata": {},
   "outputs": [],
   "source": [
    "liver['Albumin_and_Globulin_Ratio'].fillna(liver['Albumin_and_Globulin_Ratio'].mean(),inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 324,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 324,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(liver['Albumin_and_Globulin_Ratio'].isnull())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**SCALING THE DATA FOR USE BY ALGORITHMS**  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 325,
   "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>Total_Bilirubin</th>\n",
       "      <th>Direct_Bilirubin</th>\n",
       "      <th>Alkaline_Phosphotase</th>\n",
       "      <th>Alamine_Aminotransferase</th>\n",
       "      <th>Aspartate_Aminotransferase</th>\n",
       "      <th>Total_Protiens</th>\n",
       "      <th>Albumin</th>\n",
       "      <th>Albumin_and_Globulin_Ratio</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.252098</td>\n",
       "      <td>1.762281</td>\n",
       "      <td>-0.418878</td>\n",
       "      <td>-0.493964</td>\n",
       "      <td>-0.426715</td>\n",
       "      <td>-0.354665</td>\n",
       "      <td>-0.318393</td>\n",
       "      <td>0.292120</td>\n",
       "      <td>0.198969</td>\n",
       "      <td>-0.147898</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.066637</td>\n",
       "      <td>-0.567446</td>\n",
       "      <td>1.225171</td>\n",
       "      <td>1.430423</td>\n",
       "      <td>1.682629</td>\n",
       "      <td>-0.091599</td>\n",
       "      <td>-0.034333</td>\n",
       "      <td>0.937566</td>\n",
       "      <td>0.073157</td>\n",
       "      <td>-0.650697</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.066637</td>\n",
       "      <td>-0.567446</td>\n",
       "      <td>0.644919</td>\n",
       "      <td>0.931508</td>\n",
       "      <td>0.821588</td>\n",
       "      <td>-0.113522</td>\n",
       "      <td>-0.145186</td>\n",
       "      <td>0.476533</td>\n",
       "      <td>0.198969</td>\n",
       "      <td>-0.179323</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.819356</td>\n",
       "      <td>-0.567446</td>\n",
       "      <td>-0.370523</td>\n",
       "      <td>-0.387054</td>\n",
       "      <td>-0.447314</td>\n",
       "      <td>-0.365626</td>\n",
       "      <td>-0.311465</td>\n",
       "      <td>0.292120</td>\n",
       "      <td>0.324781</td>\n",
       "      <td>0.166351</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.684839</td>\n",
       "      <td>-0.567446</td>\n",
       "      <td>0.096902</td>\n",
       "      <td>0.183135</td>\n",
       "      <td>-0.393756</td>\n",
       "      <td>-0.294379</td>\n",
       "      <td>-0.176363</td>\n",
       "      <td>0.753153</td>\n",
       "      <td>-0.933340</td>\n",
       "      <td>-1.719144</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Age    Gender  Total_Bilirubin  Direct_Bilirubin  \\\n",
       "0  1.252098  1.762281        -0.418878         -0.493964   \n",
       "1  1.066637 -0.567446         1.225171          1.430423   \n",
       "2  1.066637 -0.567446         0.644919          0.931508   \n",
       "3  0.819356 -0.567446        -0.370523         -0.387054   \n",
       "4  1.684839 -0.567446         0.096902          0.183135   \n",
       "\n",
       "   Alkaline_Phosphotase  Alamine_Aminotransferase  Aspartate_Aminotransferase  \\\n",
       "0             -0.426715                 -0.354665                   -0.318393   \n",
       "1              1.682629                 -0.091599                   -0.034333   \n",
       "2              0.821588                 -0.113522                   -0.145186   \n",
       "3             -0.447314                 -0.365626                   -0.311465   \n",
       "4             -0.393756                 -0.294379                   -0.176363   \n",
       "\n",
       "   Total_Protiens   Albumin  Albumin_and_Globulin_Ratio  \n",
       "0        0.292120  0.198969                   -0.147898  \n",
       "1        0.937566  0.073157                   -0.650697  \n",
       "2        0.476533  0.198969                   -0.179323  \n",
       "3        0.292120  0.324781                    0.166351  \n",
       "4        0.753153 -0.933340                   -1.719144  "
      ]
     },
     "execution_count": 325,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "scaler = StandardScaler()\n",
    "scaler.fit(liver.drop('Dataset',axis=1))\n",
    "scaled_features = scaler.transform(liver.drop('Dataset',axis=1))\n",
    "liver_scaled = pd.DataFrame(scaled_features,columns=liver.columns[:-1])\n",
    "liver_scaled.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 326,
   "metadata": {},
   "outputs": [],
   "source": [
    "X=liver_scaled\n",
    "y=liver['Dataset']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**SPLITTING THE DATA INTO TRAINING AND TESTING SET**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 327,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 328,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import precision_score,accuracy_score,recall_score,f1_score,mean_absolute_error,mean_squared_error"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 329,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 330,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    124\n",
       "0     51\n",
       "Name: Dataset, dtype: int64"
      ]
     },
     "execution_count": 330,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_test.value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**SUPPORT VECTOR MACHINES ALGORITHM**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![](svm_image.png)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 331,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.svm import SVC"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 332,
   "metadata": {},
   "outputs": [],
   "source": [
    "model=SVC()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "USING GRID SEARCH CV TO FIND THE BEST PARAMETERS"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 448,
   "metadata": {},
   "outputs": [],
   "source": [
    "param_grid = {'C': [0.1,1, 10,50,100,200,1000], 'gamma': [1,0.1,0.01,0.001,0.0001], 'kernel': ['rbf']} \n",
    "from sklearn.model_selection import GridSearchCV\n",
    "grid = GridSearchCV(SVC(),param_grid,refit=True,verbose=3)\n",
    "grid.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 334,
   "metadata": {},
   "outputs": [],
   "source": [
    "svm_predictions=grid.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 335,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import classification_report,confusion_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 336,
   "metadata": {},
   "outputs": [],
   "source": [
    "svm_acc=accuracy_score(y_test,svm_predictions)\n",
    "svm_prec=precision_score(y_test,svm_predictions)\n",
    "svm_rec=recall_score(y_test,svm_predictions)\n",
    "svm_f1=f1_score(y_test,svm_predictions)\n",
    "svm_mas=mean_absolute_error(y_test,svm_predictions)\n",
    "svm_rms=np.sqrt(mean_squared_error(y_test,svm_predictions))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 370,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.64      0.14      0.23        51\n",
      "           1       0.73      0.97      0.83       124\n",
      "\n",
      "    accuracy                           0.73       175\n",
      "   macro avg       0.68      0.55      0.53       175\n",
      "weighted avg       0.70      0.73      0.66       175\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(y_test,svm_predictions))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**LOGISTIC REGRESSION ALGORITHM**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![](logistic_regression.png)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 338,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 339,
   "metadata": {},
   "outputs": [],
   "source": [
    "lg=LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 340,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
       "                   intercept_scaling=1, l1_ratio=None, max_iter=100,\n",
       "                   multi_class='auto', n_jobs=None, penalty='l2',\n",
       "                   random_state=None, solver='lbfgs', tol=0.0001, verbose=0,\n",
       "                   warm_start=False)"
      ]
     },
     "execution_count": 340,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lg.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 341,
   "metadata": {},
   "outputs": [],
   "source": [
    "lg_predictions=lg.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 342,
   "metadata": {},
   "outputs": [],
   "source": [
    "lg_acc=accuracy_score(y_test,lg_predictions)\n",
    "lg_prec=precision_score(y_test,lg_predictions)\n",
    "lg_rec=recall_score(y_test,lg_predictions)\n",
    "lg_f1=f1_score(y_test,lg_predictions)\n",
    "lg_mas=mean_absolute_error(y_test,lg_predictions)\n",
    "lg_rms=np.sqrt(mean_squared_error(y_test,lg_predictions))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 343,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.63      0.24      0.34        51\n",
      "           1       0.75      0.94      0.84       124\n",
      "\n",
      "    accuracy                           0.74       175\n",
      "   macro avg       0.69      0.59      0.59       175\n",
      "weighted avg       0.72      0.74      0.69       175\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(y_test,lg_predictions))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**RANDOM FOREST CLASSIFIER ALGORITHM**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![](ggff5544hh.png)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 344,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 345,
   "metadata": {},
   "outputs": [],
   "source": [
    "rfc= RandomForestClassifier(n_estimators=600)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 346,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None,\n",
       "                       criterion='gini', max_depth=None, max_features='auto',\n",
       "                       max_leaf_nodes=None, max_samples=None,\n",
       "                       min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "                       min_samples_leaf=1, min_samples_split=2,\n",
       "                       min_weight_fraction_leaf=0.0, n_estimators=600,\n",
       "                       n_jobs=None, oob_score=False, random_state=None,\n",
       "                       verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 346,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rfc.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 347,
   "metadata": {},
   "outputs": [],
   "source": [
    "rfc_predictions=rfc.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 348,
   "metadata": {},
   "outputs": [],
   "source": [
    "rfc_acc=accuracy_score(y_test,rfc_predictions)\n",
    "rfc_prec=precision_score(y_test,rfc_predictions)\n",
    "rfc_rec=recall_score(y_test,rfc_predictions)\n",
    "rfc_f1=f1_score(y_test,rfc_predictions)\n",
    "rfc_mas=mean_absolute_error(y_test,rfc_predictions)\n",
    "rfc_rms=np.sqrt(mean_squared_error(y_test,rfc_predictions))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 349,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.62      0.25      0.36        51\n",
      "           1       0.75      0.94      0.83       124\n",
      "\n",
      "    accuracy                           0.74       175\n",
      "   macro avg       0.69      0.60      0.60       175\n",
      "weighted avg       0.71      0.74      0.70       175\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(y_test,rfc_predictions))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**DECISION TREE CLASSIFIER ALGORITHM**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![](1_r5ikdb.jpeg)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 350,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 351,
   "metadata": {},
   "outputs": [],
   "source": [
    "dtree=DecisionTreeClassifier()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 352,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini',\n",
       "                       max_depth=None, 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='deprecated',\n",
       "                       random_state=None, splitter='best')"
      ]
     },
     "execution_count": 352,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dtree.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 353,
   "metadata": {},
   "outputs": [],
   "source": [
    "dtree_predictions=dtree.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 354,
   "metadata": {},
   "outputs": [],
   "source": [
    "dtree_acc=accuracy_score(y_test,dtree_predictions)\n",
    "dtree_prec=precision_score(y_test,dtree_predictions)\n",
    "dtree_rec=recall_score(y_test,dtree_predictions)\n",
    "dtree_f1=f1_score(y_test,dtree_predictions)\n",
    "dtree_mas=mean_absolute_error(y_test,dtree_predictions)\n",
    "dtree_rms=np.sqrt(mean_squared_error(y_test,dtree_predictions))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 355,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.40      0.37      0.38        51\n",
      "           1       0.75      0.77      0.76       124\n",
      "\n",
      "    accuracy                           0.65       175\n",
      "   macro avg       0.57      0.57      0.57       175\n",
      "weighted avg       0.65      0.65      0.65       175\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(y_test,dtree_predictions))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**K NEAREST NEIGHBOURS ALGORITHM**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![](knn2.jpg)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 356,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.neighbors import KNeighborsClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 357,
   "metadata": {},
   "outputs": [],
   "source": [
    "error_rate = []\n",
    "\n",
    "for i in range(1,40):\n",
    "    \n",
    "    knn = KNeighborsClassifier(n_neighbors=i)\n",
    "    knn.fit(X_train,y_train)\n",
    "    pred_i = knn.predict(X_test)\n",
    "    error_rate.append(np.mean(pred_i != y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "FINDING OUT THE K VALUE FOR LEAST ERROR RATE"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 358,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Error Rate')"
      ]
     },
     "execution_count": 358,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10,6))\n",
    "plt.plot(range(1,40),error_rate,color='blue', linestyle='dashed', marker='o',\n",
    "         markerfacecolor='red', markersize=10)\n",
    "plt.title('Error Rate vs. K Value')\n",
    "plt.xlabel('K')\n",
    "plt.ylabel('Error Rate')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 362,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.2857142857142857"
      ]
     },
     "execution_count": 362,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "error_rate[36]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 364,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WITH K=36\n",
      "\n",
      "\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.67      0.16      0.25        51\n",
      "           1       0.74      0.97      0.84       124\n",
      "\n",
      "    accuracy                           0.73       175\n",
      "   macro avg       0.70      0.56      0.55       175\n",
      "weighted avg       0.72      0.73      0.67       175\n",
      "\n"
     ]
    }
   ],
   "source": [
    "knn = KNeighborsClassifier(n_neighbors=36)\n",
    "\n",
    "knn.fit(X_train,y_train)\n",
    "knn_predictions = knn.predict(X_test)\n",
    "\n",
    "print('WITH K=36')\n",
    "print('\\n')\n",
    "print(classification_report(y_test,knn_predictions))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 365,
   "metadata": {},
   "outputs": [],
   "source": [
    "knn_acc=accuracy_score(y_test,knn_predictions)\n",
    "knn_prec=precision_score(y_test,knn_predictions)\n",
    "knn_rec=recall_score(y_test,knn_predictions)\n",
    "knn_f1=f1_score(y_test,knn_predictions)\n",
    "knn_mas=mean_absolute_error(y_test,knn_predictions)\n",
    "knn_rms=np.sqrt(mean_squared_error(y_test,knn_predictions))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "     "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**ANALYSING PERFORMANCE OF EACH OF THE ABOVE MACHINE LEARNING MODELS**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![](1_pOtBHai4jFd-ujaNXPilRg.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![](1_lqDsPkfXPGen32Uem1PTNg.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![](MAE.png)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 389,
   "metadata": {},
   "outputs": [],
   "source": [
    "d={'Machine Learning Algorithm':['Support Vector Machine','Logistic Regression','Random Forest Classifier','Decision Tree Classifier','K Nearest Neighbours'],'Accuracy_Score':[svm_acc*100,lg_acc*100,rfc_acc*100,dtree_acc*100,knn_acc*100],'Precision_Score':[svm_prec*100,lg_prec*100,rfc_prec*100,dtree_prec*100,knn_prec*100],'Recall_Score':[svm_rec*100,lg_rec*100,rfc_rec*100,dtree_rec*100,knn_rec*100],'F1_Score':[svm_f1*100,lg_f1*100,rfc_f1*100,dtree_f1*100,knn_f1*100],'Mean_Absolute_Error':[svm_mas*100,lg_mas*100,rfc_mas*100,dtree_mas*100,knn_mas*100],'Root_Mean_Square_Error':[svm_rms*100,lg_rms*100,rfc_rms*100,dtree_rms*100,knn_rms*100]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 390,
   "metadata": {},
   "outputs": [],
   "source": [
    "results=pd.DataFrame(d)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 391,
   "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>Machine Learning Algorithm</th>\n",
       "      <th>Accuracy_Score</th>\n",
       "      <th>Precision_Score</th>\n",
       "      <th>Recall_Score</th>\n",
       "      <th>F1_Score</th>\n",
       "      <th>Mean_Absolute_Error</th>\n",
       "      <th>Root_Mean_Square_Error</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Support Vector Machine</td>\n",
       "      <td>72.571429</td>\n",
       "      <td>73.170732</td>\n",
       "      <td>96.774194</td>\n",
       "      <td>83.333333</td>\n",
       "      <td>27.428571</td>\n",
       "      <td>52.372294</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Logistic Regression</td>\n",
       "      <td>73.714286</td>\n",
       "      <td>75.000000</td>\n",
       "      <td>94.354839</td>\n",
       "      <td>83.571429</td>\n",
       "      <td>26.285714</td>\n",
       "      <td>51.269596</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Random Forest Classifier</td>\n",
       "      <td>73.714286</td>\n",
       "      <td>75.324675</td>\n",
       "      <td>93.548387</td>\n",
       "      <td>83.453237</td>\n",
       "      <td>26.285714</td>\n",
       "      <td>51.269596</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Decision Tree Classifier</td>\n",
       "      <td>65.142857</td>\n",
       "      <td>74.803150</td>\n",
       "      <td>76.612903</td>\n",
       "      <td>75.697211</td>\n",
       "      <td>34.857143</td>\n",
       "      <td>59.039938</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>K Nearest Neighbours</td>\n",
       "      <td>73.142857</td>\n",
       "      <td>73.619632</td>\n",
       "      <td>96.774194</td>\n",
       "      <td>83.623693</td>\n",
       "      <td>26.857143</td>\n",
       "      <td>51.823878</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Machine Learning Algorithm  Accuracy_Score  Precision_Score  Recall_Score  \\\n",
       "0     Support Vector Machine       72.571429        73.170732     96.774194   \n",
       "1        Logistic Regression       73.714286        75.000000     94.354839   \n",
       "2   Random Forest Classifier       73.714286        75.324675     93.548387   \n",
       "3   Decision Tree Classifier       65.142857        74.803150     76.612903   \n",
       "4       K Nearest Neighbours       73.142857        73.619632     96.774194   \n",
       "\n",
       "    F1_Score  Mean_Absolute_Error  Root_Mean_Square_Error  \n",
       "0  83.333333            27.428571               52.372294  \n",
       "1  83.571429            26.285714               51.269596  \n",
       "2  83.453237            26.285714               51.269596  \n",
       "3  75.697211            34.857143               59.039938  \n",
       "4  83.623693            26.857143               51.823878  "
      ]
     },
     "execution_count": 391,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "results"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 442,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x1a3f58cad0>"
      ]
     },
     "execution_count": 442,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1008x504 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "results.plot.bar(x='Machine Learning Algorithm',figsize=(14,7))\n",
    "plt.legend(loc='center left', bbox_to_anchor=(1,0.5))"
   ]
  }
 ],
 "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}