Deskriptif dan Linear Regresi.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Belajar Bersama www.jendelastatistik.com"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Deskriptif dan Linear Regresi "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Deskriptif adalah teknik untuk menggambarkan secara umum data yang meliputi nilai dari pemusatan dan sebaran data.\n",
    "\n",
    "Linear Regresi adalah teknik yang digunakan untuk mengukur hubungan antara dua variabel.\n",
    "\n",
    "Ide dasar linear regresi adalah bagaimana menemukan persamaan garis yang tepat untuk menggambarkan hubungan antara variabel prediktor (independent) = $X$ dengan variabel respon (dependent) = $Y$.\n",
    "\n",
    "### Formula Dasar Linear Regresi\n",
    "\n",
    "$$ y = \\alpha + \\beta x + \\epsilon $$\n",
    "\n",
    "$\\beta$ adalah slope, $\\alpha$ adalah intersep dari Y dan $\\epsilon$ adalah sebaran selisih nilai diantara garis linear.\n",
    "\n",
    "Nilai $\\alpha$ adalah representasi dari nilai y ketika nilai $\\beta$ = 0\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# import Packages\n",
    "import pandas as pd   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>TV</th>\n",
       "      <th>Radio</th>\n",
       "      <th>Newspaper</th>\n",
       "      <th>Sales</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>230.1</td>\n",
       "      <td>37.8</td>\n",
       "      <td>69.2</td>\n",
       "      <td>22.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>44.5</td>\n",
       "      <td>39.3</td>\n",
       "      <td>45.1</td>\n",
       "      <td>10.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>17.2</td>\n",
       "      <td>45.9</td>\n",
       "      <td>69.3</td>\n",
       "      <td>9.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>151.5</td>\n",
       "      <td>41.3</td>\n",
       "      <td>58.5</td>\n",
       "      <td>18.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>180.8</td>\n",
       "      <td>10.8</td>\n",
       "      <td>58.4</td>\n",
       "      <td>12.9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      TV  Radio  Newspaper  Sales\n",
       "1  230.1   37.8       69.2   22.1\n",
       "2   44.5   39.3       45.1   10.4\n",
       "3   17.2   45.9       69.3    9.3\n",
       "4  151.5   41.3       58.5   18.5\n",
       "5  180.8   10.8       58.4   12.9"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# import Data set\n",
    "data = pd.read_csv('http://www-bcf.usc.edu/~gareth/ISL/Advertising.csv', index_col=0)\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Data contoh diatas adalah data mengenai periklanan yang variabelnya didefinisikan sebagai berikut: \n",
    "\n",
    "- TV    : Biaya yang di keluarkan untuk periklanan di Tv (Ribuan Dolar)\n",
    "- Radio : Biaya yang di keluarkan untuk periklanan di Radio (Ribuan Dolar)\n",
    "- Newspaper : Biaya yang di keluarkan untuk periklanan di Newspaper (Ribuan Dolar)\n",
    "- Sales : Penjualan satu produk di pasar (dalam ribuan widget)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(200, 4)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Pengecekan total data\n",
    "data.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Total jumlah data untuk masing-masing adalah 200 dari 4 variabel."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Analisis deskriptif dari dataset diatas adalah sebagai berikut:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>TV</th>\n",
       "      <th>Radio</th>\n",
       "      <th>Newspaper</th>\n",
       "      <th>Sales</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>200.000000</td>\n",
       "      <td>200.000000</td>\n",
       "      <td>200.000000</td>\n",
       "      <td>200.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>147.042500</td>\n",
       "      <td>23.264000</td>\n",
       "      <td>30.554000</td>\n",
       "      <td>14.022500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>85.854236</td>\n",
       "      <td>14.846809</td>\n",
       "      <td>21.778621</td>\n",
       "      <td>5.217457</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.700000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.300000</td>\n",
       "      <td>1.600000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>74.375000</td>\n",
       "      <td>9.975000</td>\n",
       "      <td>12.750000</td>\n",
       "      <td>10.375000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>149.750000</td>\n",
       "      <td>22.900000</td>\n",
       "      <td>25.750000</td>\n",
       "      <td>12.900000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>218.825000</td>\n",
       "      <td>36.525000</td>\n",
       "      <td>45.100000</td>\n",
       "      <td>17.400000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>296.400000</td>\n",
       "      <td>49.600000</td>\n",
       "      <td>114.000000</td>\n",
       "      <td>27.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               TV       Radio   Newspaper       Sales\n",
       "count  200.000000  200.000000  200.000000  200.000000\n",
       "mean   147.042500   23.264000   30.554000   14.022500\n",
       "std     85.854236   14.846809   21.778621    5.217457\n",
       "min      0.700000    0.000000    0.300000    1.600000\n",
       "25%     74.375000    9.975000   12.750000   10.375000\n",
       "50%    149.750000   22.900000   25.750000   12.900000\n",
       "75%    218.825000   36.525000   45.100000   17.400000\n",
       "max    296.400000   49.600000  114.000000   27.000000"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.describe ()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "TV           7370.949893\n",
       "Radio         220.427743\n",
       "Newspaper     474.308326\n",
       "Sales          27.221853\n",
       "dtype: float64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Variansi data\n",
    "data.var()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>TV</th>\n",
       "      <th>Radio</th>\n",
       "      <th>Newspaper</th>\n",
       "      <th>Sales</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>TV</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.054809</td>\n",
       "      <td>0.056648</td>\n",
       "      <td>0.782224</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Radio</th>\n",
       "      <td>0.054809</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.354104</td>\n",
       "      <td>0.576223</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Newspaper</th>\n",
       "      <td>0.056648</td>\n",
       "      <td>0.354104</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.228299</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Sales</th>\n",
       "      <td>0.782224</td>\n",
       "      <td>0.576223</td>\n",
       "      <td>0.228299</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 TV     Radio  Newspaper     Sales\n",
       "TV         1.000000  0.054809   0.056648  0.782224\n",
       "Radio      0.054809  1.000000   0.354104  0.576223\n",
       "Newspaper  0.056648  0.354104   1.000000  0.228299\n",
       "Sales      0.782224  0.576223   0.228299  1.000000"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Corelation data\n",
    "data.corr ()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Packages untuk Membuat dan menampilkan plot\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x72c7250>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA7AAAAHjCAYAAAAaOPOyAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nSUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x71f5490>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axs = plt.subplots(1, 3, sharey=True)\n",
    "data.plot(kind='scatter', x='TV', y='Sales', ax=axs[0], figsize=(16, 8))\n",
    "data.plot(kind='scatter', x='Radio', y='Sales', ax=axs[1])\n",
    "data.plot(kind='scatter', x='Newspaper', y='Sales', ax=axs[2])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Kemudian mari kita coba untuk menggunakan model linear regresi sederhana untuk melakukan prediksi. \n",
    "\n",
    "\n",
    "\n",
    "$$y = \\beta_0 + \\beta_1x + \\epsilon $$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import statsmodels.formula.api as smf\n",
    "\n",
    "# fitting model\n",
    "lm = smf.ols(formula='Sales ~ TV', data=data).fit()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>          <td>Sales</td>      <th>  R-squared:         </th> <td>   0.612</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.610</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   312.1</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Date:</th>             <td>Sat, 10 Jun 2017</td> <th>  Prob (F-statistic):</th> <td>1.47e-42</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Time:</th>                 <td>22:16:17</td>     <th>  Log-Likelihood:    </th> <td> -519.05</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>      <td>   200</td>      <th>  AIC:               </th> <td>   1042.</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Residuals:</th>          <td>   198</td>      <th>  BIC:               </th> <td>   1049.</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Model:</th>              <td>     1</td>      <th>                     </th>     <td> </td>   \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>   \n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th> <th>[95.0% Conf. Int.]</th> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Intercept</th> <td>    7.0326</td> <td>    0.458</td> <td>   15.360</td> <td> 0.000</td> <td>    6.130     7.935</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>TV</th>        <td>    0.0475</td> <td>    0.003</td> <td>   17.668</td> <td> 0.000</td> <td>    0.042     0.053</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "  <th>Omnibus:</th>       <td> 0.531</td> <th>  Durbin-Watson:     </th> <td>   1.935</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prob(Omnibus):</th> <td> 0.767</td> <th>  Jarque-Bera (JB):  </th> <td>   0.669</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Skew:</th>          <td>-0.089</td> <th>  Prob(JB):          </th> <td>   0.716</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Kurtosis:</th>      <td> 2.779</td> <th>  Cond. No.          </th> <td>    338.</td>\n",
       "</tr>\n",
       "</table>"
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                            OLS Regression Results                            \n",
       "==============================================================================\n",
       "Dep. Variable:                  Sales   R-squared:                       0.612\n",
       "Model:                            OLS   Adj. R-squared:                  0.610\n",
       "Method:                 Least Squares   F-statistic:                     312.1\n",
       "Date:                Sat, 10 Jun 2017   Prob (F-statistic):           1.47e-42\n",
       "Time:                        22:16:17   Log-Likelihood:                -519.05\n",
       "No. Observations:                 200   AIC:                             1042.\n",
       "Df Residuals:                     198   BIC:                             1049.\n",
       "Df Model:                           1                                         \n",
       "Covariance Type:            nonrobust                                         \n",
       "==============================================================================\n",
       "                 coef    std err          t      P>|t|      [95.0% Conf. Int.]\n",
       "------------------------------------------------------------------------------\n",
       "Intercept      7.0326      0.458     15.360      0.000         6.130     7.935\n",
       "TV             0.0475      0.003     17.668      0.000         0.042     0.053\n",
       "==============================================================================\n",
       "Omnibus:                        0.531   Durbin-Watson:                   1.935\n",
       "Prob(Omnibus):                  0.767   Jarque-Bera (JB):                0.669\n",
       "Skew:                          -0.089   Prob(JB):                        0.716\n",
       "Kurtosis:                       2.779   Cond. No.                         338.\n",
       "==============================================================================\n",
       "\n",
       "Warnings:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "\"\"\""
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lm.summary ()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Interprestasi Koefisien Model\n",
    "\n",
    "Ketika nilai Periklanan TV konstan ($ 0) atau tidak melakukan periklanan maka nilai penjualan Sales sebesar 7.0326 widgets. \n",
    "\n",
    "Namun, Jika melakukan penambahan $1.000 dihabiskan untuk Periklanan di TV maka akan menghasilkan kenaikan nilai penjualan Sales sebesar 47.537 widgets."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##  Model Prediksi\n",
    "\n",
    "$$y = \\beta_0 + \\beta_1x + \\epsilon $$\n",
    "\n",
    "$$y = 7.0326 + 0.0475.TV + \\epsilon $$"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Misalkan kita ingin memprediksikan ketika nilai TV = 50 maka berapa nilai y (Sales) dengan menggunakan persama model yang dihasilkan diatas."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>TV</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>45</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   TV\n",
       "0  50\n",
       "1  45\n",
       "2  24\n",
       "3  35\n",
       "4   1"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# data contoh untuk aplikasi test model\n",
    "\n",
    "X_new = pd.DataFrame({'TV': [50, 45, 24, 35, 1]})\n",
    "X_new.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[ 9.40942557  9.17174237  8.17347292  8.69637596  7.08013019]\n"
     ]
    }
   ],
   "source": [
    "# Hasil Prediksi dengan menggunakan model yang terbentuk.\n",
    "\n",
    "Predict= lm.predict(X_new)\n",
    "\n",
    "print Predict"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}