{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "source": [
    "# <center> Automatic Feature Selection </center>\n",
    "\n",
    "- <b><span style='color:green'>to reduce dimensionality<span></b>\n",
    "- common methods: univariate statistics, model-based selection, iterative selection"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1. Univariate Statistics\n",
    "\n",
    "- determines the relationship between each feature and output (target)\n",
    "- only the features with highest confidence are selected\n",
    "- <b><span style='color:blue'>SelectKBest</span></b> - selecting K number of features\n",
    "- <b><span style='color:blue'>SelectPercentile</span></b> - selection is made based on a percentage of the original features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "X_train.shape is: (284, 80)\n",
      "X_train_selected.shape is: (284, 40)\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "from sklearn.datasets import load_breast_cancer\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.feature_selection import SelectPercentile\n",
    "\n",
    "cancer = load_breast_cancer()\n",
    "\n",
    "rng = np.random.RandomState(42)\n",
    "noise = rng.normal(size=(len(cancer.data), 50))\n",
    "\n",
    "X_w_noise = np.hstack([cancer.data, noise])\n",
    "X_train, X_test, y_train, y_test = train_test_split(X_w_noise, cancer.target, random_state=0, test_size=.5)\n",
    "\n",
    "select = SelectPercentile(percentile=50)\n",
    "select.fit(X_train, y_train)\n",
    "X_train_selected = select.transform(X_train)\n",
    "\n",
    "print('X_train.shape is: {}'.format(X_train.shape))\n",
    "print('X_train_selected.shape is: {}'.format(X_train_selected.shape))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.5.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}