{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 128,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.read_csv('pima_diabetes_dataset.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "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": "code",
   "execution_count": 131,
   "metadata": {},
   "outputs": [],
   "source": [
    "# feature = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width']\n",
    "# predection_class = ['species']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = data.drop(columns=['Outcome'])\n",
    "y = data['Outcome']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape of X_test is (231, 8)\n",
      "Shape of X_train is (537, 8)\n",
      "Shape of Y_test is (231,)\n",
      "Shape of Y_train is (537,)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, Y_train, Y_test = train_test_split(X,y,test_size=0.30)\n",
    "print(f\"Shape of X_test is {X_test.shape}\")\n",
    "print(f\"Shape of X_train is {X_train.shape}\")\n",
    "print(f\"Shape of Y_test is {Y_test.shape}\")\n",
    "print(f\"Shape of Y_train is {Y_train.shape}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 134,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.naive_bayes import MultinomialNB\n",
    "clf = MultinomialNB()\n",
    "clf.fit(X_train, Y_train)\n",
    "Y_pred = clf.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy 56.27705627705628\n"
     ]
    }
   ],
   "source": [
    "from sklearn import metrics\n",
    "print(\"Accuracy\", metrics.accuracy_score(Y_test, Y_pred)*100)"
   ]
  }
 ],
 "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": "3.10.7"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}