{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# univariate select example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "! pip install numpy\n",
    "! pip install pandas\n",
    "! pip install sklearn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import warnings\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "import os\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import hourse_price_preprocessor as hpp\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.feature_selection import SelectKBest # specify number\n",
    "from sklearn.feature_selection import SelectPercentile # specify remaining ratio\n",
    "from sklearn.model_selection import cross_val_score\n",
    "from sklearn.linear_model import LinearRegression"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Load data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "DATA_DIR = \"data/house_price/\"\n",
    "TEST_FILENAME = \"test.csv\"\n",
    "TRAIN_FILENAME = \"train.csv\"\n",
    "\n",
    "test_file = os.path.join(DATA_DIR, TEST_FILENAME)\n",
    "train_file = os.path.join(DATA_DIR, TRAIN_FILENAME)\n",
    "\n",
    "X_train, X_test, y_train, test_id_idx = hpp.get_train_test_split_dataset(train_file, test_file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1460, 67) (1460,) (1459, 67) (1459,)\n"
     ]
    }
   ],
   "source": [
    "print(X_train.shape, y_train.shape, X_test.shape, test_id_idx.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Feature selection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1460, 37)\n"
     ]
    }
   ],
   "source": [
    "select = SelectPercentile(percentile=55)\n",
    "select.fit(X_train, y_train)\n",
    "\n",
    "# transform training set\n",
    "X_train_selected = select.transform(X_train)\n",
    "print(X_train_selected.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Get cross validation score of selected feature model and original"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "+ selected feature model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8000781632789679"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.mean(cross_val_score(LinearRegression(), X_train_selected, y_train, scoring=\"r2\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "+ original model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-2.009795549320303e+20"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.mean(cross_val_score(LinearRegression(), X_train, y_train, scoring=\"r2\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "+ get selected features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([False,  True, False, False, False,  True, False,  True, False,\n",
       "       False, False,  True, False, False, False,  True,  True,  True,\n",
       "        True,  True, False,  True,  True,  True,  True,  True,  True,\n",
       "        True, False, False, False, False, False, False, False,  True,\n",
       "        True,  True,  True,  True, False,  True,  True,  True,  True,\n",
       "       False,  True, False, False,  True,  True,  True, False,  True,\n",
       "        True,  True,  True,  True,  True,  True, False, False, False,\n",
       "       False,  True, False, False])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "select.get_support()"
   ]
  }
 ],
 "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": "3.6.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}