Logistic Regression  Heart disease.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "197c1f4d",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "df = pd.read_csv('C:/Users/ACER/heart.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "ab97c6b6",
   "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>sex</th>\n",
       "      <th>cp</th>\n",
       "      <th>trtbps</th>\n",
       "      <th>chol</th>\n",
       "      <th>fbs</th>\n",
       "      <th>restecg</th>\n",
       "      <th>thalachh</th>\n",
       "      <th>exng</th>\n",
       "      <th>oldpeak</th>\n",
       "      <th>slp</th>\n",
       "      <th>caa</th>\n",
       "      <th>thall</th>\n",
       "      <th>output</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>63</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>145</td>\n",
       "      <td>233</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>150</td>\n",
       "      <td>0</td>\n",
       "      <td>2.3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>37</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>130</td>\n",
       "      <td>250</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>187</td>\n",
       "      <td>0</td>\n",
       "      <td>3.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>41</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>130</td>\n",
       "      <td>204</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>172</td>\n",
       "      <td>0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>56</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>120</td>\n",
       "      <td>236</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>178</td>\n",
       "      <td>0</td>\n",
       "      <td>0.8</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>57</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>120</td>\n",
       "      <td>354</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>163</td>\n",
       "      <td>1</td>\n",
       "      <td>0.6</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  sex  cp  trtbps  chol  fbs  restecg  thalachh  exng  oldpeak  slp  \\\n",
       "0   63    1   3     145   233    1        0       150     0      2.3    0   \n",
       "1   37    1   2     130   250    0        1       187     0      3.5    0   \n",
       "2   41    0   1     130   204    0        0       172     0      1.4    2   \n",
       "3   56    1   1     120   236    0        1       178     0      0.8    2   \n",
       "4   57    0   0     120   354    0        1       163     1      0.6    2   \n",
       "\n",
       "   caa  thall  output  \n",
       "0    0      1       1  \n",
       "1    0      2       1  \n",
       "2    0      2       1  \n",
       "3    0      2       1  \n",
       "4    0      2       1  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "4b902a98",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = df.drop(['output'], axis=1)\n",
    "y = df['output']\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "6bf0e35d",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\ACER\\anaconda3\\lib\\site-packages\\sklearn\\linear_model\\_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lg = LogisticRegression()\n",
    "lg.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "60cbc474",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8421052631578947"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lg.score(X_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "3d7b76ee",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 1, 1, 0, 1, 1, 0, 1, 1, 0], dtype=int64)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lg.predict(X_test.head(10).values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "163dd343",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "162    1\n",
       "70     1\n",
       "159    1\n",
       "214    0\n",
       "46     1\n",
       "69     1\n",
       "193    0\n",
       "65     1\n",
       "278    0\n",
       "51     1\n",
       "Name: output, dtype: int64"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_test.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "70707f29",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle \n",
    "\n",
    "with open('summ','wb') as file:\n",
    "    pickle.dump(lg,file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "dff366cc",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('summ','rb') as file:\n",
    "    p = pickle.load(file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "82b9b1dc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 1, 1, 0, 1, 1, 0, 1, 1, 0], dtype=int64)"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "p.predict(X_test.head(10).values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4546c1ea",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1196d889",
   "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}