F01. 06. Multiple Linear.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[ 103015.20159796  132582.27760816  132447.73845175   71976.09851259\n",
      "  178537.48221054  116161.24230163   67851.69209676   98791.73374688\n",
      "  113969.43533012  167921.0656955 ]\n"
     ]
    }
   ],
   "source": [
    "# Multiple Linear Regression\n",
    "\n",
    "# Importing the libraries\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline \n",
    "import pandas as pd\n",
    "\n",
    "# Importing the dataset\n",
    "dataset = pd.read_csv('data/LinearRegression/50_Startups.csv')\n",
    "X = dataset.iloc[:, :-1].values\n",
    "y = dataset.iloc[:, 4].values\n",
    "\n",
    "# Encoding categorical data\n",
    "from sklearn.preprocessing import LabelEncoder, OneHotEncoder\n",
    "labelencoder = LabelEncoder()\n",
    "X[:, 3] = labelencoder.fit_transform(X[:, 3])\n",
    "onehotencoder = OneHotEncoder(categorical_features = [3])\n",
    "X = onehotencoder.fit_transform(X).toarray()\n",
    "\n",
    "# Avoiding the Dummy Variable Trap\n",
    "X = X[:, 1:]\n",
    "\n",
    "# Splitting the dataset into the Training set and Test set\n",
    "from sklearn.cross_validation import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)\n",
    "\n",
    "# Feature Scaling\n",
    "\"\"\"from sklearn.preprocessing import StandardScaler\n",
    "sc_X = StandardScaler()\n",
    "X_train = sc_X.fit_transform(X_train)\n",
    "X_test = sc_X.transform(X_test)\n",
    "sc_y = StandardScaler()\n",
    "y_train = sc_y.fit_transform(y_train)\"\"\"\n",
    "\n",
    "# Fitting Multiple Linear Regression to the Training set\n",
    "from sklearn.linear_model import LinearRegression\n",
    "regressor = LinearRegression()\n",
    "regressor.fit(X_train, y_train)\n",
    "\n",
    "# Predicting the Test set results\n",
    "y_pred = regressor.predict(X_test)\n",
    "print(y_pred)"
   ]
  },
  {
   "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": "3.4.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}