Diabetes Prediction.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "50300a49",
   "metadata": {},
   "source": [
    "## Exploring the dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "eca608cd",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d899a3ef",
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.read_csv(r\"data/diabetes.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b12b7394",
   "metadata": {},
   "source": [
    "Check first 5 and last 5 rows of dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "be51f0cf",
   "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>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148</td>\n",
       "      <td>72</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>33.6</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>66</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>26.6</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23.3</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>168</td>\n",
       "      <td>43.1</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin   BMI  \\\n",
       "0            6      148             72             35        0  33.6   \n",
       "1            1       85             66             29        0  26.6   \n",
       "2            8      183             64              0        0  23.3   \n",
       "3            1       89             66             23       94  28.1   \n",
       "4            0      137             40             35      168  43.1   \n",
       "\n",
       "   DiabetesPedigreeFunction  Age  Outcome  \n",
       "0                     0.627   50        1  \n",
       "1                     0.351   31        0  \n",
       "2                     0.672   32        1  \n",
       "3                     0.167   21        0  \n",
       "4                     2.288   33        1  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "f90af03f",
   "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>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>763</th>\n",
       "      <td>10</td>\n",
       "      <td>101</td>\n",
       "      <td>76</td>\n",
       "      <td>48</td>\n",
       "      <td>180</td>\n",
       "      <td>32.9</td>\n",
       "      <td>0.171</td>\n",
       "      <td>63</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>764</th>\n",
       "      <td>2</td>\n",
       "      <td>122</td>\n",
       "      <td>70</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>36.8</td>\n",
       "      <td>0.340</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>765</th>\n",
       "      <td>5</td>\n",
       "      <td>121</td>\n",
       "      <td>72</td>\n",
       "      <td>23</td>\n",
       "      <td>112</td>\n",
       "      <td>26.2</td>\n",
       "      <td>0.245</td>\n",
       "      <td>30</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>766</th>\n",
       "      <td>1</td>\n",
       "      <td>126</td>\n",
       "      <td>60</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.1</td>\n",
       "      <td>0.349</td>\n",
       "      <td>47</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>767</th>\n",
       "      <td>1</td>\n",
       "      <td>93</td>\n",
       "      <td>70</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>30.4</td>\n",
       "      <td>0.315</td>\n",
       "      <td>23</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Pregnancies  Glucose  BloodPressure  SkinThickness  Insulin   BMI  \\\n",
       "763           10      101             76             48      180  32.9   \n",
       "764            2      122             70             27        0  36.8   \n",
       "765            5      121             72             23      112  26.2   \n",
       "766            1      126             60              0        0  30.1   \n",
       "767            1       93             70             31        0  30.4   \n",
       "\n",
       "     DiabetesPedigreeFunction  Age  Outcome  \n",
       "763                     0.171   63        0  \n",
       "764                     0.340   27        0  \n",
       "765                     0.245   30        0  \n",
       "766                     0.349   47        1  \n",
       "767                     0.315   23        0  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.tail()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "acb6c861",
   "metadata": {},
   "source": [
    "Size of dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "dd7d4992",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of Rows 768\n",
      "Number of Columns 9\n"
     ]
    }
   ],
   "source": [
    "rows, columns = data.shape\n",
    "print(\"Number of Rows\", rows)\n",
    "print(\"Number of Columns\", columns)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6704aa3a",
   "metadata": {},
   "source": [
    "Get Information About Our Dataset Like Total Number Rows, Total Number of Columns, Datatypes of Each Column And Memory Requirement"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "5a557a04",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 768 entries, 0 to 767\n",
      "Data columns (total 9 columns):\n",
      " #   Column                    Non-Null Count  Dtype  \n",
      "---  ------                    --------------  -----  \n",
      " 0   Pregnancies               768 non-null    int64  \n",
      " 1   Glucose                   768 non-null    int64  \n",
      " 2   BloodPressure             768 non-null    int64  \n",
      " 3   SkinThickness             768 non-null    int64  \n",
      " 4   Insulin                   768 non-null    int64  \n",
      " 5   BMI                       768 non-null    float64\n",
      " 6   DiabetesPedigreeFunction  768 non-null    float64\n",
      " 7   Age                       768 non-null    int64  \n",
      " 8   Outcome                   768 non-null    int64  \n",
      "dtypes: float64(2), int64(7)\n",
      "memory usage: 54.1 KB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "040534a1",
   "metadata": {},
   "source": [
    "Overall statistics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "fda29c63",
   "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>Pregnancies</th>\n",
       "      <th>Glucose</th>\n",
       "      <th>BloodPressure</th>\n",
       "      <th>SkinThickness</th>\n",
       "      <th>Insulin</th>\n",
       "      <th>BMI</th>\n",
       "      <th>DiabetesPedigreeFunction</th>\n",
       "      <th>Age</th>\n",
       "      <th>Outcome</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "      <td>768.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>3.845052</td>\n",
       "      <td>120.894531</td>\n",
       "      <td>69.105469</td>\n",
       "      <td>20.536458</td>\n",
       "      <td>79.799479</td>\n",
       "      <td>31.992578</td>\n",
       "      <td>0.471876</td>\n",
       "      <td>33.240885</td>\n",
       "      <td>0.348958</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.369578</td>\n",
       "      <td>31.972618</td>\n",
       "      <td>19.355807</td>\n",
       "      <td>15.952218</td>\n",
       "      <td>115.244002</td>\n",
       "      <td>7.884160</td>\n",
       "      <td>0.331329</td>\n",
       "      <td>11.760232</td>\n",
       "      <td>0.476951</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.078000</td>\n",
       "      <td>21.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>99.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>27.300000</td>\n",
       "      <td>0.243750</td>\n",
       "      <td>24.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>3.000000</td>\n",
       "      <td>117.000000</td>\n",
       "      <td>72.000000</td>\n",
       "      <td>23.000000</td>\n",
       "      <td>30.500000</td>\n",
       "      <td>32.000000</td>\n",
       "      <td>0.372500</td>\n",
       "      <td>29.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>6.000000</td>\n",
       "      <td>140.250000</td>\n",
       "      <td>80.000000</td>\n",
       "      <td>32.000000</td>\n",
       "      <td>127.250000</td>\n",
       "      <td>36.600000</td>\n",
       "      <td>0.626250</td>\n",
       "      <td>41.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>17.000000</td>\n",
       "      <td>199.000000</td>\n",
       "      <td>122.000000</td>\n",
       "      <td>99.000000</td>\n",
       "      <td>846.000000</td>\n",
       "      <td>67.100000</td>\n",
       "      <td>2.420000</td>\n",
       "      <td>81.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Pregnancies     Glucose  BloodPressure  SkinThickness     Insulin  \\\n",
       "count   768.000000  768.000000     768.000000     768.000000  768.000000   \n",
       "mean      3.845052  120.894531      69.105469      20.536458   79.799479   \n",
       "std       3.369578   31.972618      19.355807      15.952218  115.244002   \n",
       "min       0.000000    0.000000       0.000000       0.000000    0.000000   \n",
       "25%       1.000000   99.000000      62.000000       0.000000    0.000000   \n",
       "50%       3.000000  117.000000      72.000000      23.000000   30.500000   \n",
       "75%       6.000000  140.250000      80.000000      32.000000  127.250000   \n",
       "max      17.000000  199.000000     122.000000      99.000000  846.000000   \n",
       "\n",
       "              BMI  DiabetesPedigreeFunction         Age     Outcome  \n",
       "count  768.000000                768.000000  768.000000  768.000000  \n",
       "mean    31.992578                  0.471876   33.240885    0.348958  \n",
       "std      7.884160                  0.331329   11.760232    0.476951  \n",
       "min      0.000000                  0.078000   21.000000    0.000000  \n",
       "25%     27.300000                  0.243750   24.000000    0.000000  \n",
       "50%     32.000000                  0.372500   29.000000    0.000000  \n",
       "75%     36.600000                  0.626250   41.000000    1.000000  \n",
       "max     67.100000                  2.420000   81.000000    1.000000  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9b186261",
   "metadata": {},
   "source": [
    "Check Null Values In The Dataset\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "4eb7b2cc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Pregnancies                 0\n",
       "Glucose                     0\n",
       "BloodPressure               0\n",
       "SkinThickness               0\n",
       "Insulin                     0\n",
       "BMI                         0\n",
       "DiabetesPedigreeFunction    0\n",
       "Age                         0\n",
       "Outcome                     0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "23467786",
   "metadata": {},
   "source": [
    "There are no null values but there may be zero values so lets check"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "d8cd25e0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Pregnancies                 111\n",
       "Glucose                       5\n",
       "BloodPressure                35\n",
       "SkinThickness               227\n",
       "Insulin                     374\n",
       "BMI                          11\n",
       "DiabetesPedigreeFunction      0\n",
       "Age                           0\n",
       "Outcome                     500\n",
       "dtype: int64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.replace(0, np.nan).isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "782a292b",
   "metadata": {},
   "source": [
    "## Data Imputation"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5c91a2d9",
   "metadata": {},
   "source": [
    "Replacing zero values with mean of that column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "4515ed10",
   "metadata": {},
   "outputs": [],
   "source": [
    "columns_to_impute = [\"Glucose\", \"BloodPressure\", \"SkinThickness\", \"Insulin\", \"BMI\"]\n",
    "for column in columns_to_impute:\n",
    "    data[column] = data[column].replace(0, data[column].mean())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c8b9a86e",
   "metadata": {},
   "source": [
    "Store Feature Matrix In X and Response(Target) In Vector y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "a0c7979f",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = data.drop(\"Outcome\", axis=1)\n",
    "y = data[\"Outcome\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4e8e10aa",
   "metadata": {},
   "source": [
    "## Choosing appropriate model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cb277c9d",
   "metadata": {},
   "source": [
    "Splitting The Dataset Into The Training Set And Test Set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "9ba2ef82",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.20, random_state=42\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "27f80fe0",
   "metadata": {},
   "source": [
    "Building Scikit-Learn Pipelines to choose appropriate model\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "11931602",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.svm import SVC\n",
    "\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.ensemble import GradientBoostingClassifier\n",
    "\n",
    "from sklearn.pipeline import Pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "a63b3708",
   "metadata": {},
   "outputs": [],
   "source": [
    "pipeline_logistic_regression = Pipeline(\n",
    "    [(\"scaler\", StandardScaler()), (\"logistic_regression\", LogisticRegression())]\n",
    ")\n",
    "\n",
    "pipeline_knn = Pipeline(\n",
    "    [(\"scaler\", StandardScaler()), (\"k_nearest_neighbors\", KNeighborsClassifier())]\n",
    ")\n",
    "\n",
    "pipeline_svc = Pipeline(\n",
    "    [(\"scaler\", StandardScaler()), (\"support_vector_classifier\", SVC())]\n",
    ")\n",
    "\n",
    "pipeline_decision_tree = Pipeline(\n",
    "    [(\"decision_tree_classifier\", DecisionTreeClassifier())]\n",
    ")\n",
    "\n",
    "pipeline_random_forest = Pipeline(\n",
    "    [(\"random_forest_classifier\", RandomForestClassifier())]\n",
    ")\n",
    "\n",
    "pipeline_gradient_boosting = Pipeline(\n",
    "    [(\"gradient_boosting_classifier\", GradientBoostingClassifier())]\n",
    ")\n",
    "\n",
    "pipelines = [\n",
    "    pipeline_logistic_regression,\n",
    "    pipeline_knn,\n",
    "    pipeline_svc,\n",
    "    pipeline_decision_tree,\n",
    "    pipeline_random_forest,\n",
    "    pipeline_gradient_boosting,\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "ebdd52d1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Pipeline(steps=[('scaler', StandardScaler()),\n",
       "                 ('logistic_regression', LogisticRegression())]),\n",
       " Pipeline(steps=[('scaler', StandardScaler()),\n",
       "                 ('k_nearest_neighbors', KNeighborsClassifier())]),\n",
       " Pipeline(steps=[('scaler', StandardScaler()),\n",
       "                 ('support_vector_classifier', SVC())]),\n",
       " Pipeline(steps=[('decision_tree_classifier', DecisionTreeClassifier())]),\n",
       " Pipeline(steps=[('random_forest_classifier', RandomForestClassifier())]),\n",
       " Pipeline(steps=[('gradient_boosting_classifier', GradientBoostingClassifier())])]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipelines"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d5b2e01d",
   "metadata": {},
   "source": [
    "Fitting data to all the scalers and models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "c110603e",
   "metadata": {},
   "outputs": [],
   "source": [
    "for pipe in pipelines:\n",
    "    pipe.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "ef4a5cd2",
   "metadata": {},
   "outputs": [],
   "source": [
    "pipe_dict = {\n",
    "    0: \"Logistic Regression\",\n",
    "    1: \"K-Nearest Neighbors\",\n",
    "    2: \"Support Vector Classifier\",\n",
    "    3: \"Decision Tree\",\n",
    "    4: \"Random Forest\",\n",
    "    5: \"Gradient Boosting Classifier\",\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "069e0bb2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Logistic Regression Test Accuracy:76.62337662337663\n",
      "K-Nearest Neighbors Test Accuracy:76.62337662337663\n",
      "Support Vector Classifier Test Accuracy:73.37662337662337\n",
      "Decision Tree Test Accuracy:73.37662337662337\n",
      "Random Forest Test Accuracy:75.97402597402598\n",
      "Gradient Boosting Classifier Test Accuracy:76.62337662337663\n"
     ]
    }
   ],
   "source": [
    "for i, model in enumerate(pipelines):\n",
    "    print(\"{} Test Accuracy:{}\".format(pipe_dict[i], model.score(X_test, y_test) * 100))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ff784ba0",
   "metadata": {},
   "source": [
    "The best results are given by Logistic Regression, K-Nearest Neighbors, and Gradient Boosting Classifier."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "99520a89",
   "metadata": {},
   "source": [
    "But lets do hyper parameter tuning on Random forest classifier and Gradient Boosting classifier."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "6b14161f",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import GridSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "32bc0b93",
   "metadata": {},
   "outputs": [],
   "source": [
    "random_forest = RandomForestClassifier()\n",
    "gradient_boosting = GradientBoostingClassifier()\n",
    "\n",
    "param_grid_rf = {\n",
    "    \"n_estimators\": [50, 75, 100],\n",
    "    \"max_depth\": [3, 5, 10],\n",
    "    \"min_samples_split\": [2, 10, 20],\n",
    "}\n",
    "\n",
    "param_grid_gbc = {\n",
    "    \"n_estimators\": [50, 75, 100],\n",
    "    \"learning_rate\": [0.01, 0.1, 0.2],\n",
    "    \"max_depth\": [3, 5, 10],\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "e8bce9ca",
   "metadata": {},
   "outputs": [],
   "source": [
    "models = {\n",
    "    \"Random Forest\": (random_forest, param_grid_rf),\n",
    "    \"Gradient Boosting Classifier\": (gradient_boosting, param_grid_gbc),\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "edfbd81f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best parameters for Random Forest: {'max_depth': 10, 'min_samples_split': 2, 'n_estimators': 50}\n",
      "Best score for Random Forest: 0.7850326536052246\n",
      "Best parameters for Gradient Boosting Classifier: {'learning_rate': 0.1, 'max_depth': 3, 'n_estimators': 100}\n",
      "Best score for Gradient Boosting Classifier: 0.7654938024790083\n",
      "\n",
      "Accuracy for Random Forest on test data: 0.7467532467532467\n",
      "Classification Report for Random Forest:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.81      0.80      0.80        99\n",
      "           1       0.64      0.65      0.65        55\n",
      "\n",
      "    accuracy                           0.75       154\n",
      "   macro avg       0.72      0.73      0.73       154\n",
      "weighted avg       0.75      0.75      0.75       154\n",
      "\n",
      "\n",
      "Accuracy for Gradient Boosting Classifier on test data: 0.7662337662337663\n",
      "Classification Report for Gradient Boosting Classifier:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.84      0.79      0.81        99\n",
      "           1       0.66      0.73      0.69        55\n",
      "\n",
      "    accuracy                           0.77       154\n",
      "   macro avg       0.75      0.76      0.75       154\n",
      "weighted avg       0.77      0.77      0.77       154\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.metrics import classification_report\n",
    "\n",
    "\n",
    "best_models = {}\n",
    "for name, (model, param_grid) in models.items():\n",
    "    grid_search = GridSearchCV(model, param_grid, cv=5, scoring=\"accuracy\", n_jobs=-1)\n",
    "    grid_search.fit(X_train, y_train)\n",
    "    best_models[name] = grid_search.best_estimator_\n",
    "    print(f\"Best parameters for {name}: {grid_search.best_params_}\")\n",
    "    print(f\"Best score for {name}: {grid_search.best_score_}\")\n",
    "\n",
    "for name, model in best_models.items():\n",
    "    y_pred = model.predict(X_test)\n",
    "    accuracy = accuracy_score(y_test, y_pred)\n",
    "    print(f\"\\nAccuracy for {name} on test data: {accuracy}\")\n",
    "    print(f\"Classification Report for {name}:\\n{classification_report(y_test, y_pred)}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "041950ee",
   "metadata": {},
   "source": [
    "As gradient boosting classifier performs better lets use that model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "b9391c8f",
   "metadata": {},
   "outputs": [],
   "source": [
    "gbc = best_models[\"Gradient Boosting Classifier\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "deb44764",
   "metadata": {},
   "source": [
    "Prediction on New Data\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "6e316f51",
   "metadata": {},
   "outputs": [],
   "source": [
    "new_data = pd.DataFrame(\n",
    "    {\n",
    "        \"Pregnancies\": 6,\n",
    "        \"Glucose\": 148.0,\n",
    "        \"BloodPressure\": 72.0,\n",
    "        \"SkinThickness\": 35.0,\n",
    "        \"Insulin\": 79.799479,\n",
    "        \"BMI\": 33.6,\n",
    "        \"DiabetesPedigreeFunction\": 0.627,\n",
    "        \"Age\": 50,\n",
    "    },\n",
    "    index=[0],\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "a2d4f5b5",
   "metadata": {},
   "outputs": [],
   "source": [
    "p = gbc.predict(new_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "0c26df74",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "diabetic\n"
     ]
    }
   ],
   "source": [
    "if p[0] == 0:\n",
    "    print(\"non-diabetic\")\n",
    "else:\n",
    "    print(\"diabetic\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "442cdba1",
   "metadata": {},
   "source": [
    "## Save Model Using Joblib\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "634914cf",
   "metadata": {},
   "outputs": [],
   "source": [
    "import joblib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "1b8180ed",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['model/model_joblib_diabetes']"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "joblib.dump(gbc, r\"model/model_joblib_diabetes\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "61582da8",
   "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": "3.12.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}