{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[![Open in Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/justmarkham/scikit-learn-tips/master?filepath=notebooks%2F31_kfold_shuffle.ipynb)\n",
    "\n",
    "[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/justmarkham/scikit-learn-tips/blob/master/notebooks/31_kfold_shuffle.ipynb)\n",
    "\n",
    "# 🤖⚡ scikit-learn tip #31 ([video](https://www.youtube.com/watch?v=Ld8-_WP0G90&list=PL5-da3qGB5ID7YYAqireYEew2mWVvgmj6&index=31))\n",
    "\n",
    "If you use cross-validation and your samples are NOT in an arbitrary order, shuffling may be required to get meaningful results.\n",
    "\n",
    "Use KFold or StratifiedKFold in order to shuffle!\n",
    "\n",
    "See example 👇"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sklearn.datasets import load_diabetes\n",
    "from sklearn.linear_model import LinearRegression, LogisticRegression\n",
    "from sklearn.model_selection import cross_val_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# set up the regression problem\n",
    "X_reg, y_reg = load_diabetes(return_X_y=True)\n",
    "reg = LinearRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# set up the classification problem\n",
    "df = pd.read_csv('http://bit.ly/kaggletrain')\n",
    "X_clf = df[['Pclass', 'Fare', 'SibSp']]\n",
    "y_clf = df['Survived']\n",
    "clf = LogisticRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import KFold, StratifiedKFold"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Use KFold with regression problems:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.43843604, 0.38982527, 0.52792606, 0.47359858, 0.57449343])"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kf = KFold(5, shuffle=True, random_state=1)\n",
    "cross_val_score(reg, X_reg, y_reg, cv=kf, scoring='r2')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Use StratifiedKFold with classification problems:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.65363128, 0.7247191 , 0.66853933, 0.68539326, 0.65730337])"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "skf = StratifiedKFold(5, shuffle=True, random_state=1)\n",
    "cross_val_score(clf, X_clf, y_clf, cv=skf, scoring='accuracy')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Want more tips? [View all tips on GitHub](https://github.com/justmarkham/scikit-learn-tips) or [Sign up to receive 2 tips by email every week](https://scikit-learn.tips) 💌\n",
    "\n",
    "© 2020 [Data School](https://www.dataschool.io). All rights reserved."
   ]
  }
 ],
 "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": "3.9.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}