{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "5600f60e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import time\n",
    "import gc\n",
    "import random\n",
    "from sklearn.model_selection import cross_val_score, GridSearchCV, cross_validate, train_test_split\n",
    "from sklearn.metrics import accuracy_score, classification_report\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.preprocessing import StandardScaler, normalize\n",
    "from sklearn.decomposition import PCA\n",
    "from sklearn.impute import SimpleImputer\n",
    "\n",
    "df = pd.read_csv(\"data/pima-indians-diabetes.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "ba9ed7e8",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_data = df.filter(regex='x\\d')\n",
    "y_data = df.filter(regex='y')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "4e150ff2",
   "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>y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>763</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>764</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>765</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>766</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>767</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>768 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     y\n",
       "0    1\n",
       "1    0\n",
       "2    1\n",
       "3    0\n",
       "4    1\n",
       "..  ..\n",
       "763  0\n",
       "764  0\n",
       "765  0\n",
       "766  1\n",
       "767  0\n",
       "\n",
       "[768 rows x 1 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "e2870990",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train, x_test, y_train, y_test = train_test_split(x_data, y_data, train_size=0.7,test_size=0.3, random_state= 614, shuffle = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "9b3459f7",
   "metadata": {},
   "outputs": [],
   "source": [
    "linear_regression_classifier = LinearRegression().fit(x_train, y_train)\n",
    "y_predict_train = linear_regression_classifier.predict(x_train)\n",
    "y_predict_test = linear_regression_classifier.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "d57b40fb",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_predict_train = [i.round() for i in y_predict_train]\n",
    "train_accuracy = accuracy_score(y_train,y_predict_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "af7edfc2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7821229050279329"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_accuracy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "4209f55e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7821229050279329"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_accuracy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "682449cc",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}