{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e17fb0a7",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.datasets import load_breast_cancer\n",
    "import pandas as pd\n",
    "from sklearn.model_selection import KFold\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "53ce0c7f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "KFold(n_splits=5, random_state=None, shuffle=False)\n"
     ]
    }
   ],
   "source": [
    "print(KFold())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b8720fb1",
   "metadata": {},
   "outputs": [],
   "source": [
    "data = load_breast_cancer(as_frame = True)\n",
    "df = data.frame\n",
    "X = df.iloc[:,:-1]\n",
    "Y = df.iloc[:,-1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "3359880e",
   "metadata": {},
   "outputs": [],
   "source": [
    "k = 5\n",
    "kf = KFold(n_splits = k)\n",
    "model = LogisticRegression(solver = 'liblinear')\n",
    "\n",
    "acc_score = []\n",
    "\n",
    "for train_index, test_index in kf.split(X):\n",
    "    X_train, X_test = X.iloc[train_index,:],X.iloc[test_index,:]\n",
    "    Y_train, Y_test = Y[train_index], Y[test_index]\n",
    "    \n",
    "    model.fit(X_train, Y_train)\n",
    "    pred_values = model.predict(X_test)\n",
    "    \n",
    "    acc = accuracy_score(pred_values, Y_test)\n",
    "    acc_score.append(acc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "f2716eaa",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of each fold is: [0.9122807017543859, 0.9473684210526315, 0.9736842105263158, 0.9736842105263158, 0.9557522123893806]\n",
      "Average accuracy is: 0.952553951249806\n"
     ]
    }
   ],
   "source": [
    "avg_acc_score = sum(acc_score)/k\n",
    "\n",
    "print('Accuracy of each fold is: {}'.format(acc_score))\n",
    "print('Average accuracy is: {}'.format(avg_acc_score))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "58d128e3",
   "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}