{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "이 노트북의 코드에 대한 설명은 [Pipeline에서 캐싱을 사용하기](https://tensorflow.blog/2017/12/08/pipeline%ec%97%90%ec%84%9c-%ec%ba%90%ec%8b%b1%ec%9d%84-%ec%82%ac%ec%9a%a9%ed%95%98%ea%b8%b0/) 글을 참고하세요."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 보스턴 주택 데이터셋이 1.0 버전에 deprecated 되었고 1.2 버전에서 삭제됩니다.\n",
    "# 경고 메시지를 피하기 위해 다음 코드를 추가합니다.\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\", category=FutureWarning)\n",
    "\n",
    "from sklearn.datasets import load_boston\n",
    "from sklearn.preprocessing import StandardScaler, PolynomialFeatures\n",
    "from sklearn.linear_model import Ridge\n",
    "from sklearn.model_selection import train_test_split, GridSearchCV\n",
    "from sklearn.pipeline import make_pipeline\n",
    "\n",
    "boston = load_boston()\n",
    "X_train, X_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=0)\n",
    "param_grid = {'polynomialfeatures__degree': [1, 2, 3, 4, 5],\n",
    "                      'ridge__alpha': [0.001, 0.01, 0.1, 1, 10, 100]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "pipe = make_pipeline(StandardScaler(), PolynomialFeatures(), Ridge())\n",
    "grid = GridSearchCV(pipe, param_grid=param_grid, cv=5, n_jobs=-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "696 ms ± 19.9 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%timeit grid.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from tempfile import mkdtemp\n",
    "from shutil import rmtree"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "cache_dir = mkdtemp()\n",
    "pipe2 = make_pipeline(StandardScaler(), PolynomialFeatures(), Ridge(), memory=cache_dir)\n",
    "grid2 = GridSearchCV(pipe2, param_grid=param_grid, cv=5, n_jobs=-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "714 ms ± 9.09 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%timeit grid2.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "rmtree(cache_dir)"
   ]
  }
 ],
 "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": 2
}