{
 "metadata": {
  "name": ""
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Python example\n",
      "\n",
      "This document shows how you can perform a very simple statistical analysis in the Python programming language. To run this, you will need the [IPython notebook](http://ipython.org/notebook.html); however, you can copy and paste the code parts of the document into a plain text file and run it as a python script as follows:\n",
      "\n",
      "```\n",
      "python my_script.py\n",
      "```\n",
      "\n",
      "Assuming you have named the file `my_script.py`."
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Imports and load data\n",
      "\n",
      "Before we start, we need to import the specific libraries that contain the bulk of data and statistical functionality. These are the following:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pandas as pd\n",
      "import statsmodels.api as sm"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Then we can load the file with the data we'll use (you'll need connectivity to pull it down):"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "db = pd.read_csv('https://raw.github.com/darribas/buzz_adam/master/buzz_data.csv')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "db"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<pre>\n",
        "&lt;class 'pandas.core.frame.DataFrame'&gt;\n",
        "Int64Index: 96 entries, 0 to 95\n",
        "Data columns (total 24 columns):\n",
        "id                                     96  non-null values\n",
        "4sq-pct_Arts &amp; Entertainment           96  non-null values\n",
        "4sq-pct_College &amp; University           96  non-null values\n",
        "4sq-pct_Food                           96  non-null values\n",
        "4sq-pct_Other                          96  non-null values\n",
        "4sq-pct_Outdoors &amp; Recreation          96  non-null values\n",
        "4sq-pct_Professional &amp; Other Places    96  non-null values\n",
        "4sq-pct_Travel &amp; Transport             96  non-null values\n",
        "industrie_pct_area                     96  non-null values\n",
        "kantoor_pct_area                       96  non-null values\n",
        "sport_pct_area                         96  non-null values\n",
        "winkel_pct_area                        96  non-null values\n",
        "4sq_total_venues                       96  non-null values\n",
        "total_units                            96  non-null values\n",
        "div_i                                  96  non-null values\n",
        "checkins_all                           96  non-null values\n",
        "('WeekDay', 'Afternoon')               96  non-null values\n",
        "('WeekDay', 'Evening')                 96  non-null values\n",
        "('WeekDay', 'Morning')                 96  non-null values\n",
        "('WeekDay', 'Night')                   96  non-null values\n",
        "('WeekEnd', 'Afternoon')               96  non-null values\n",
        "('WeekEnd', 'Evening')                 96  non-null values\n",
        "('WeekEnd', 'Morning')                 96  non-null values\n",
        "('WeekEnd', 'Night')                   96  non-null values\n",
        "dtypes: float64(20), int64(3), object(1)\n",
        "</pre>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 4,
       "text": [
        "<class 'pandas.core.frame.DataFrame'>\n",
        "Int64Index: 96 entries, 0 to 95\n",
        "Data columns (total 24 columns):\n",
        "id                                     96  non-null values\n",
        "4sq-pct_Arts & Entertainment           96  non-null values\n",
        "4sq-pct_College & University           96  non-null values\n",
        "4sq-pct_Food                           96  non-null values\n",
        "4sq-pct_Other                          96  non-null values\n",
        "4sq-pct_Outdoors & Recreation          96  non-null values\n",
        "4sq-pct_Professional & Other Places    96  non-null values\n",
        "4sq-pct_Travel & Transport             96  non-null values\n",
        "industrie_pct_area                     96  non-null values\n",
        "kantoor_pct_area                       96  non-null values\n",
        "sport_pct_area                         96  non-null values\n",
        "winkel_pct_area                        96  non-null values\n",
        "4sq_total_venues                       96  non-null values\n",
        "total_units                            96  non-null values\n",
        "div_i                                  96  non-null values\n",
        "checkins_all                           96  non-null values\n",
        "('WeekDay', 'Afternoon')               96  non-null values\n",
        "('WeekDay', 'Evening')                 96  non-null values\n",
        "('WeekDay', 'Morning')                 96  non-null values\n",
        "('WeekDay', 'Night')                   96  non-null values\n",
        "('WeekEnd', 'Afternoon')               96  non-null values\n",
        "('WeekEnd', 'Evening')                 96  non-null values\n",
        "('WeekEnd', 'Morning')                 96  non-null values\n",
        "('WeekEnd', 'Night')                   96  non-null values\n",
        "dtypes: float64(20), int64(3), object(1)"
       ]
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Create decriptives\n",
      "\n",
      "To first get a sense of the data, we can inspect the top rows (note the transpose with `.T` in order for the table to fit in):"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "db.head().T"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>0</th>\n",
        "      <th>1</th>\n",
        "      <th>2</th>\n",
        "      <th>3</th>\n",
        "      <th>4</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>id</th>\n",
        "      <td> BU03630000</td>\n",
        "      <td> BU03630001</td>\n",
        "      <td> BU03630002</td>\n",
        "      <td> BU03630003</td>\n",
        "      <td> BU03630004</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Arts &amp; Entertainment</th>\n",
        "      <td>   23.15789</td>\n",
        "      <td>   22.41379</td>\n",
        "      <td>         25</td>\n",
        "      <td>   19.75309</td>\n",
        "      <td>   29.26829</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_College &amp; University</th>\n",
        "      <td>   2.105263</td>\n",
        "      <td>          0</td>\n",
        "      <td>          0</td>\n",
        "      <td>   1.234568</td>\n",
        "      <td>          0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Food</th>\n",
        "      <td>   5.263158</td>\n",
        "      <td>   6.034483</td>\n",
        "      <td>   7.352941</td>\n",
        "      <td>   3.703704</td>\n",
        "      <td>   2.439024</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Other</th>\n",
        "      <td>   57.89474</td>\n",
        "      <td>   52.58621</td>\n",
        "      <td>   58.82353</td>\n",
        "      <td>    65.4321</td>\n",
        "      <td>   56.09756</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Outdoors &amp; Recreation</th>\n",
        "      <td>          0</td>\n",
        "      <td>          0</td>\n",
        "      <td>          0</td>\n",
        "      <td>          0</td>\n",
        "      <td>          0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Professional &amp; Other Places</th>\n",
        "      <td>   4.210526</td>\n",
        "      <td>   2.586207</td>\n",
        "      <td>   5.882353</td>\n",
        "      <td>   4.938272</td>\n",
        "      <td>   2.439024</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Travel &amp; Transport</th>\n",
        "      <td>   4.210526</td>\n",
        "      <td>   12.93103</td>\n",
        "      <td>   2.941176</td>\n",
        "      <td>   3.703704</td>\n",
        "      <td>   4.878049</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>industrie_pct_area</th>\n",
        "      <td>   3.180117</td>\n",
        "      <td>   1.002782</td>\n",
        "      <td>   2.649969</td>\n",
        "      <td>   1.572429</td>\n",
        "      <td>   4.066521</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>kantoor_pct_area</th>\n",
        "      <td>   14.23777</td>\n",
        "      <td>   17.45941</td>\n",
        "      <td>   23.67496</td>\n",
        "      <td>   30.78645</td>\n",
        "      <td>   13.96826</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>sport_pct_area</th>\n",
        "      <td> 0.03911904</td>\n",
        "      <td>  0.9169031</td>\n",
        "      <td> 0.07142607</td>\n",
        "      <td>  0.3230344</td>\n",
        "      <td>  0.3108789</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>winkel_pct_area</th>\n",
        "      <td>    7.09489</td>\n",
        "      <td>   29.07499</td>\n",
        "      <td>   5.959857</td>\n",
        "      <td>   9.063615</td>\n",
        "      <td>   4.053148</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq_total_venues</th>\n",
        "      <td>         95</td>\n",
        "      <td>        116</td>\n",
        "      <td>         68</td>\n",
        "      <td>         81</td>\n",
        "      <td>         41</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>total_units</th>\n",
        "      <td>       4238</td>\n",
        "      <td>       4836</td>\n",
        "      <td>       5923</td>\n",
        "      <td>       3639</td>\n",
        "      <td>       7162</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>div_i</th>\n",
        "      <td>     0.5702</td>\n",
        "      <td>     0.6314</td>\n",
        "      <td>     0.5228</td>\n",
        "      <td>     0.5196</td>\n",
        "      <td>     0.5394</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>checkins_all</th>\n",
        "      <td>       2750</td>\n",
        "      <td>       6620</td>\n",
        "      <td>       2521</td>\n",
        "      <td>       3468</td>\n",
        "      <td>       2076</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekDay', 'Afternoon')</th>\n",
        "      <td>        743</td>\n",
        "      <td>       1834</td>\n",
        "      <td>        685</td>\n",
        "      <td>       1040</td>\n",
        "      <td>        664</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekDay', 'Evening')</th>\n",
        "      <td>        620</td>\n",
        "      <td>       1236</td>\n",
        "      <td>        588</td>\n",
        "      <td>        789</td>\n",
        "      <td>        397</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekDay', 'Morning')</th>\n",
        "      <td>        402</td>\n",
        "      <td>       1407</td>\n",
        "      <td>        427</td>\n",
        "      <td>        463</td>\n",
        "      <td>        422</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekDay', 'Night')</th>\n",
        "      <td>        185</td>\n",
        "      <td>        419</td>\n",
        "      <td>        184</td>\n",
        "      <td>        262</td>\n",
        "      <td>         98</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekEnd', 'Afternoon')</th>\n",
        "      <td>        346</td>\n",
        "      <td>        816</td>\n",
        "      <td>        311</td>\n",
        "      <td>        372</td>\n",
        "      <td>        238</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekEnd', 'Evening')</th>\n",
        "      <td>        203</td>\n",
        "      <td>        333</td>\n",
        "      <td>        145</td>\n",
        "      <td>        241</td>\n",
        "      <td>        124</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekEnd', 'Morning')</th>\n",
        "      <td>        111</td>\n",
        "      <td>        324</td>\n",
        "      <td>         80</td>\n",
        "      <td>         96</td>\n",
        "      <td>         77</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekEnd', 'Night')</th>\n",
        "      <td>        140</td>\n",
        "      <td>        251</td>\n",
        "      <td>        101</td>\n",
        "      <td>        205</td>\n",
        "      <td>         56</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "                                              0           1           2           3           4\n",
        "id                                   BU03630000  BU03630001  BU03630002  BU03630003  BU03630004\n",
        "4sq-pct_Arts & Entertainment           23.15789    22.41379          25    19.75309    29.26829\n",
        "4sq-pct_College & University           2.105263           0           0    1.234568           0\n",
        "4sq-pct_Food                           5.263158    6.034483    7.352941    3.703704    2.439024\n",
        "4sq-pct_Other                          57.89474    52.58621    58.82353     65.4321    56.09756\n",
        "4sq-pct_Outdoors & Recreation                 0           0           0           0           0\n",
        "4sq-pct_Professional & Other Places    4.210526    2.586207    5.882353    4.938272    2.439024\n",
        "4sq-pct_Travel & Transport             4.210526    12.93103    2.941176    3.703704    4.878049\n",
        "industrie_pct_area                     3.180117    1.002782    2.649969    1.572429    4.066521\n",
        "kantoor_pct_area                       14.23777    17.45941    23.67496    30.78645    13.96826\n",
        "sport_pct_area                       0.03911904   0.9169031  0.07142607   0.3230344   0.3108789\n",
        "winkel_pct_area                         7.09489    29.07499    5.959857    9.063615    4.053148\n",
        "4sq_total_venues                             95         116          68          81          41\n",
        "total_units                                4238        4836        5923        3639        7162\n",
        "div_i                                    0.5702      0.6314      0.5228      0.5196      0.5394\n",
        "checkins_all                               2750        6620        2521        3468        2076\n",
        "('WeekDay', 'Afternoon')                    743        1834         685        1040         664\n",
        "('WeekDay', 'Evening')                      620        1236         588         789         397\n",
        "('WeekDay', 'Morning')                      402        1407         427         463         422\n",
        "('WeekDay', 'Night')                        185         419         184         262          98\n",
        "('WeekEnd', 'Afternoon')                    346         816         311         372         238\n",
        "('WeekEnd', 'Evening')                      203         333         145         241         124\n",
        "('WeekEnd', 'Morning')                      111         324          80          96          77\n",
        "('WeekEnd', 'Night')                        140         251         101         205          56"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Or the tail of the table:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "db.tail().T"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>91</th>\n",
        "      <th>92</th>\n",
        "      <th>93</th>\n",
        "      <th>94</th>\n",
        "      <th>95</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>id</th>\n",
        "      <td> BU03631453</td>\n",
        "      <td> BU03631454</td>\n",
        "      <td> BU03631459</td>\n",
        "      <td> BU03631490</td>\n",
        "      <td> BU03631491</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Arts &amp; Entertainment</th>\n",
        "      <td>   33.33333</td>\n",
        "      <td>   22.22222</td>\n",
        "      <td>          0</td>\n",
        "      <td>          0</td>\n",
        "      <td>          0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_College &amp; University</th>\n",
        "      <td>          0</td>\n",
        "      <td>          0</td>\n",
        "      <td>         10</td>\n",
        "      <td>   4.166667</td>\n",
        "      <td>          0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Food</th>\n",
        "      <td>          0</td>\n",
        "      <td>   22.22222</td>\n",
        "      <td>         10</td>\n",
        "      <td>   4.166667</td>\n",
        "      <td>          0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Other</th>\n",
        "      <td>   33.33333</td>\n",
        "      <td>   44.44444</td>\n",
        "      <td>         60</td>\n",
        "      <td>   54.16667</td>\n",
        "      <td>   28.57143</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Outdoors &amp; Recreation</th>\n",
        "      <td>          0</td>\n",
        "      <td>          0</td>\n",
        "      <td>          0</td>\n",
        "      <td>          0</td>\n",
        "      <td>          0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Professional &amp; Other Places</th>\n",
        "      <td>          0</td>\n",
        "      <td>   11.11111</td>\n",
        "      <td>         20</td>\n",
        "      <td>         25</td>\n",
        "      <td>   28.57143</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Travel &amp; Transport</th>\n",
        "      <td>          0</td>\n",
        "      <td>          0</td>\n",
        "      <td>          0</td>\n",
        "      <td>   8.333333</td>\n",
        "      <td>   14.28571</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>industrie_pct_area</th>\n",
        "      <td>  0.5510426</td>\n",
        "      <td>    1.05968</td>\n",
        "      <td>  0.3963571</td>\n",
        "      <td>   1.581789</td>\n",
        "      <td>   1.801225</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>kantoor_pct_area</th>\n",
        "      <td>   1.254399</td>\n",
        "      <td>   5.504788</td>\n",
        "      <td>   50.14588</td>\n",
        "      <td>   36.31685</td>\n",
        "      <td>   18.88625</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>sport_pct_area</th>\n",
        "      <td>  0.5164656</td>\n",
        "      <td>  0.1423928</td>\n",
        "      <td>          0</td>\n",
        "      <td>  0.3649561</td>\n",
        "      <td>   1.867882</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>winkel_pct_area</th>\n",
        "      <td>   3.936081</td>\n",
        "      <td>    3.15024</td>\n",
        "      <td>   1.114295</td>\n",
        "      <td>   3.382682</td>\n",
        "      <td>  0.7877441</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq_total_venues</th>\n",
        "      <td>          3</td>\n",
        "      <td>          9</td>\n",
        "      <td>         10</td>\n",
        "      <td>         24</td>\n",
        "      <td>          7</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>total_units</th>\n",
        "      <td>       3172</td>\n",
        "      <td>       5456</td>\n",
        "      <td>       1444</td>\n",
        "      <td>      10191</td>\n",
        "      <td>       5051</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>div_i</th>\n",
        "      <td>     0.6032</td>\n",
        "      <td>     0.5514</td>\n",
        "      <td>     0.5304</td>\n",
        "      <td>     0.5692</td>\n",
        "      <td>     0.5576</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>checkins_all</th>\n",
        "      <td>        431</td>\n",
        "      <td>        483</td>\n",
        "      <td>        543</td>\n",
        "      <td>       2179</td>\n",
        "      <td>        815</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekDay', 'Afternoon')</th>\n",
        "      <td>         87</td>\n",
        "      <td>         98</td>\n",
        "      <td>        169</td>\n",
        "      <td>        889</td>\n",
        "      <td>        202</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekDay', 'Evening')</th>\n",
        "      <td>         64</td>\n",
        "      <td>        124</td>\n",
        "      <td>         82</td>\n",
        "      <td>        190</td>\n",
        "      <td>        111</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekDay', 'Morning')</th>\n",
        "      <td>         37</td>\n",
        "      <td>        104</td>\n",
        "      <td>        181</td>\n",
        "      <td>        789</td>\n",
        "      <td>        239</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekDay', 'Night')</th>\n",
        "      <td>         88</td>\n",
        "      <td>         30</td>\n",
        "      <td>         18</td>\n",
        "      <td>         54</td>\n",
        "      <td>        115</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekEnd', 'Afternoon')</th>\n",
        "      <td>         55</td>\n",
        "      <td>         55</td>\n",
        "      <td>         46</td>\n",
        "      <td>        102</td>\n",
        "      <td>         59</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekEnd', 'Evening')</th>\n",
        "      <td>         58</td>\n",
        "      <td>         41</td>\n",
        "      <td>         19</td>\n",
        "      <td>         54</td>\n",
        "      <td>         35</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekEnd', 'Morning')</th>\n",
        "      <td>          7</td>\n",
        "      <td>         25</td>\n",
        "      <td>         24</td>\n",
        "      <td>         79</td>\n",
        "      <td>         29</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekEnd', 'Night')</th>\n",
        "      <td>         35</td>\n",
        "      <td>          6</td>\n",
        "      <td>          4</td>\n",
        "      <td>         22</td>\n",
        "      <td>         25</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 9,
       "text": [
        "                                             91          92          93          94          95\n",
        "id                                   BU03631453  BU03631454  BU03631459  BU03631490  BU03631491\n",
        "4sq-pct_Arts & Entertainment           33.33333    22.22222           0           0           0\n",
        "4sq-pct_College & University                  0           0          10    4.166667           0\n",
        "4sq-pct_Food                                  0    22.22222          10    4.166667           0\n",
        "4sq-pct_Other                          33.33333    44.44444          60    54.16667    28.57143\n",
        "4sq-pct_Outdoors & Recreation                 0           0           0           0           0\n",
        "4sq-pct_Professional & Other Places           0    11.11111          20          25    28.57143\n",
        "4sq-pct_Travel & Transport                    0           0           0    8.333333    14.28571\n",
        "industrie_pct_area                    0.5510426     1.05968   0.3963571    1.581789    1.801225\n",
        "kantoor_pct_area                       1.254399    5.504788    50.14588    36.31685    18.88625\n",
        "sport_pct_area                        0.5164656   0.1423928           0   0.3649561    1.867882\n",
        "winkel_pct_area                        3.936081     3.15024    1.114295    3.382682   0.7877441\n",
        "4sq_total_venues                              3           9          10          24           7\n",
        "total_units                                3172        5456        1444       10191        5051\n",
        "div_i                                    0.6032      0.5514      0.5304      0.5692      0.5576\n",
        "checkins_all                                431         483         543        2179         815\n",
        "('WeekDay', 'Afternoon')                     87          98         169         889         202\n",
        "('WeekDay', 'Evening')                       64         124          82         190         111\n",
        "('WeekDay', 'Morning')                       37         104         181         789         239\n",
        "('WeekDay', 'Night')                         88          30          18          54         115\n",
        "('WeekEnd', 'Afternoon')                     55          55          46         102          59\n",
        "('WeekEnd', 'Evening')                       58          41          19          54          35\n",
        "('WeekEnd', 'Morning')                        7          25          24          79          29\n",
        "('WeekEnd', 'Night')                         35           6           4          22          25"
       ]
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Basic descriptives of the data are created with the following simple command (note the transpose again):"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "db.describe().T"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>count</th>\n",
        "      <th>mean</th>\n",
        "      <th>std</th>\n",
        "      <th>min</th>\n",
        "      <th>25%</th>\n",
        "      <th>50%</th>\n",
        "      <th>75%</th>\n",
        "      <th>max</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Arts &amp; Entertainment</th>\n",
        "      <td> 96</td>\n",
        "      <td>    7.993073</td>\n",
        "      <td>   12.321591</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>    0.000000</td>\n",
        "      <td>    0.000000</td>\n",
        "      <td>   15.885417</td>\n",
        "      <td>    46.153846</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_College &amp; University</th>\n",
        "      <td> 96</td>\n",
        "      <td>    1.502825</td>\n",
        "      <td>    7.376999</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>    0.000000</td>\n",
        "      <td>    0.000000</td>\n",
        "      <td>    0.000000</td>\n",
        "      <td>    50.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Food</th>\n",
        "      <td> 96</td>\n",
        "      <td>    6.498157</td>\n",
        "      <td>   16.067714</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>    0.000000</td>\n",
        "      <td>    0.000000</td>\n",
        "      <td>    5.794335</td>\n",
        "      <td>   100.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Other</th>\n",
        "      <td> 96</td>\n",
        "      <td>   46.071709</td>\n",
        "      <td>   30.456685</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>   25.000000</td>\n",
        "      <td>   50.000000</td>\n",
        "      <td>   63.727273</td>\n",
        "      <td>   100.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Outdoors &amp; Recreation</th>\n",
        "      <td> 96</td>\n",
        "      <td>    1.617461</td>\n",
        "      <td>   10.619857</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>    0.000000</td>\n",
        "      <td>    0.000000</td>\n",
        "      <td>    0.000000</td>\n",
        "      <td>   100.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Professional &amp; Other Places</th>\n",
        "      <td> 96</td>\n",
        "      <td>   12.211715</td>\n",
        "      <td>   22.494019</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>    0.000000</td>\n",
        "      <td>    0.000000</td>\n",
        "      <td>   16.666667</td>\n",
        "      <td>   100.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Travel &amp; Transport</th>\n",
        "      <td> 96</td>\n",
        "      <td>    7.041147</td>\n",
        "      <td>   16.066249</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>    0.000000</td>\n",
        "      <td>    0.000000</td>\n",
        "      <td>   11.111111</td>\n",
        "      <td>   100.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>industrie_pct_area</th>\n",
        "      <td> 96</td>\n",
        "      <td>    7.194845</td>\n",
        "      <td>   14.445025</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>    0.788846</td>\n",
        "      <td>    1.970315</td>\n",
        "      <td>    4.891877</td>\n",
        "      <td>    76.819769</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>kantoor_pct_area</th>\n",
        "      <td> 96</td>\n",
        "      <td>    8.522095</td>\n",
        "      <td>   12.678802</td>\n",
        "      <td>  0.013986</td>\n",
        "      <td>    1.398705</td>\n",
        "      <td>    3.651725</td>\n",
        "      <td>   10.338975</td>\n",
        "      <td>    84.004070</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>sport_pct_area</th>\n",
        "      <td> 96</td>\n",
        "      <td>    1.351429</td>\n",
        "      <td>    3.579424</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>    0.090404</td>\n",
        "      <td>    0.362568</td>\n",
        "      <td>    1.204256</td>\n",
        "      <td>    29.412587</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>winkel_pct_area</th>\n",
        "      <td> 96</td>\n",
        "      <td>    3.408922</td>\n",
        "      <td>    3.666317</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>    1.307761</td>\n",
        "      <td>    2.381766</td>\n",
        "      <td>    4.416234</td>\n",
        "      <td>    29.074987</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq_total_venues</th>\n",
        "      <td> 96</td>\n",
        "      <td>   12.864583</td>\n",
        "      <td>   22.031852</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>    1.000000</td>\n",
        "      <td>    6.000000</td>\n",
        "      <td>   11.000000</td>\n",
        "      <td>   116.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>total_units</th>\n",
        "      <td> 96</td>\n",
        "      <td> 4822.031250</td>\n",
        "      <td> 3001.489607</td>\n",
        "      <td> 13.000000</td>\n",
        "      <td> 2390.250000</td>\n",
        "      <td> 4844.500000</td>\n",
        "      <td> 6722.750000</td>\n",
        "      <td> 14763.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>div_i</th>\n",
        "      <td> 96</td>\n",
        "      <td>    0.601440</td>\n",
        "      <td>    0.144747</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>    0.524900</td>\n",
        "      <td>    0.599200</td>\n",
        "      <td>    0.725200</td>\n",
        "      <td>     0.806600</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>checkins_all</th>\n",
        "      <td> 96</td>\n",
        "      <td>  806.531250</td>\n",
        "      <td> 1070.210338</td>\n",
        "      <td>  5.000000</td>\n",
        "      <td>  147.000000</td>\n",
        "      <td>  422.000000</td>\n",
        "      <td> 1028.250000</td>\n",
        "      <td>  6620.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekDay', 'Afternoon')</th>\n",
        "      <td> 96</td>\n",
        "      <td>  204.895833</td>\n",
        "      <td>  299.699480</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>   33.000000</td>\n",
        "      <td>   80.500000</td>\n",
        "      <td>  262.000000</td>\n",
        "      <td>  1834.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekDay', 'Evening')</th>\n",
        "      <td> 96</td>\n",
        "      <td>  155.375000</td>\n",
        "      <td>  220.786644</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>   20.000000</td>\n",
        "      <td>   78.000000</td>\n",
        "      <td>  178.000000</td>\n",
        "      <td>  1236.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekDay', 'Morning')</th>\n",
        "      <td> 96</td>\n",
        "      <td>  184.625000</td>\n",
        "      <td>  250.739212</td>\n",
        "      <td>  1.000000</td>\n",
        "      <td>   33.750000</td>\n",
        "      <td>   87.000000</td>\n",
        "      <td>  274.000000</td>\n",
        "      <td>  1407.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekDay', 'Night')</th>\n",
        "      <td> 96</td>\n",
        "      <td>   59.364583</td>\n",
        "      <td>   78.068003</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>    9.000000</td>\n",
        "      <td>   30.000000</td>\n",
        "      <td>   82.750000</td>\n",
        "      <td>   419.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekEnd', 'Afternoon')</th>\n",
        "      <td> 96</td>\n",
        "      <td>   84.031250</td>\n",
        "      <td>  122.064388</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>   20.000000</td>\n",
        "      <td>   42.000000</td>\n",
        "      <td>   90.750000</td>\n",
        "      <td>   816.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekEnd', 'Evening')</th>\n",
        "      <td> 96</td>\n",
        "      <td>   49.052083</td>\n",
        "      <td>   67.586883</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>    8.750000</td>\n",
        "      <td>   23.500000</td>\n",
        "      <td>   55.000000</td>\n",
        "      <td>   333.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekEnd', 'Morning')</th>\n",
        "      <td> 96</td>\n",
        "      <td>   37.937500</td>\n",
        "      <td>   47.425024</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>    8.750000</td>\n",
        "      <td>   19.500000</td>\n",
        "      <td>   53.250000</td>\n",
        "      <td>   324.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>('WeekEnd', 'Night')</th>\n",
        "      <td> 96</td>\n",
        "      <td>   31.250000</td>\n",
        "      <td>   48.053041</td>\n",
        "      <td>  0.000000</td>\n",
        "      <td>    4.000000</td>\n",
        "      <td>   14.500000</td>\n",
        "      <td>   38.000000</td>\n",
        "      <td>   263.000000</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 12,
       "text": [
        "                                     count         mean          std  \\\n",
        "4sq-pct_Arts & Entertainment            96     7.993073    12.321591   \n",
        "4sq-pct_College & University            96     1.502825     7.376999   \n",
        "4sq-pct_Food                            96     6.498157    16.067714   \n",
        "4sq-pct_Other                           96    46.071709    30.456685   \n",
        "4sq-pct_Outdoors & Recreation           96     1.617461    10.619857   \n",
        "4sq-pct_Professional & Other Places     96    12.211715    22.494019   \n",
        "4sq-pct_Travel & Transport              96     7.041147    16.066249   \n",
        "industrie_pct_area                      96     7.194845    14.445025   \n",
        "kantoor_pct_area                        96     8.522095    12.678802   \n",
        "sport_pct_area                          96     1.351429     3.579424   \n",
        "winkel_pct_area                         96     3.408922     3.666317   \n",
        "4sq_total_venues                        96    12.864583    22.031852   \n",
        "total_units                             96  4822.031250  3001.489607   \n",
        "div_i                                   96     0.601440     0.144747   \n",
        "checkins_all                            96   806.531250  1070.210338   \n",
        "('WeekDay', 'Afternoon')                96   204.895833   299.699480   \n",
        "('WeekDay', 'Evening')                  96   155.375000   220.786644   \n",
        "('WeekDay', 'Morning')                  96   184.625000   250.739212   \n",
        "('WeekDay', 'Night')                    96    59.364583    78.068003   \n",
        "('WeekEnd', 'Afternoon')                96    84.031250   122.064388   \n",
        "('WeekEnd', 'Evening')                  96    49.052083    67.586883   \n",
        "('WeekEnd', 'Morning')                  96    37.937500    47.425024   \n",
        "('WeekEnd', 'Night')                    96    31.250000    48.053041   \n",
        "\n",
        "                                           min          25%          50%  \\\n",
        "4sq-pct_Arts & Entertainment          0.000000     0.000000     0.000000   \n",
        "4sq-pct_College & University          0.000000     0.000000     0.000000   \n",
        "4sq-pct_Food                          0.000000     0.000000     0.000000   \n",
        "4sq-pct_Other                         0.000000    25.000000    50.000000   \n",
        "4sq-pct_Outdoors & Recreation         0.000000     0.000000     0.000000   \n",
        "4sq-pct_Professional & Other Places   0.000000     0.000000     0.000000   \n",
        "4sq-pct_Travel & Transport            0.000000     0.000000     0.000000   \n",
        "industrie_pct_area                    0.000000     0.788846     1.970315   \n",
        "kantoor_pct_area                      0.013986     1.398705     3.651725   \n",
        "sport_pct_area                        0.000000     0.090404     0.362568   \n",
        "winkel_pct_area                       0.000000     1.307761     2.381766   \n",
        "4sq_total_venues                      0.000000     1.000000     6.000000   \n",
        "total_units                          13.000000  2390.250000  4844.500000   \n",
        "div_i                                 0.000000     0.524900     0.599200   \n",
        "checkins_all                          5.000000   147.000000   422.000000   \n",
        "('WeekDay', 'Afternoon')              0.000000    33.000000    80.500000   \n",
        "('WeekDay', 'Evening')                0.000000    20.000000    78.000000   \n",
        "('WeekDay', 'Morning')                1.000000    33.750000    87.000000   \n",
        "('WeekDay', 'Night')                  0.000000     9.000000    30.000000   \n",
        "('WeekEnd', 'Afternoon')              0.000000    20.000000    42.000000   \n",
        "('WeekEnd', 'Evening')                0.000000     8.750000    23.500000   \n",
        "('WeekEnd', 'Morning')                0.000000     8.750000    19.500000   \n",
        "('WeekEnd', 'Night')                  0.000000     4.000000    14.500000   \n",
        "\n",
        "                                             75%           max  \n",
        "4sq-pct_Arts & Entertainment           15.885417     46.153846  \n",
        "4sq-pct_College & University            0.000000     50.000000  \n",
        "4sq-pct_Food                            5.794335    100.000000  \n",
        "4sq-pct_Other                          63.727273    100.000000  \n",
        "4sq-pct_Outdoors & Recreation           0.000000    100.000000  \n",
        "4sq-pct_Professional & Other Places    16.666667    100.000000  \n",
        "4sq-pct_Travel & Transport             11.111111    100.000000  \n",
        "industrie_pct_area                      4.891877     76.819769  \n",
        "kantoor_pct_area                       10.338975     84.004070  \n",
        "sport_pct_area                          1.204256     29.412587  \n",
        "winkel_pct_area                         4.416234     29.074987  \n",
        "4sq_total_venues                       11.000000    116.000000  \n",
        "total_units                          6722.750000  14763.000000  \n",
        "div_i                                   0.725200      0.806600  \n",
        "checkins_all                         1028.250000   6620.000000  \n",
        "('WeekDay', 'Afternoon')              262.000000   1834.000000  \n",
        "('WeekDay', 'Evening')                178.000000   1236.000000  \n",
        "('WeekDay', 'Morning')                274.000000   1407.000000  \n",
        "('WeekDay', 'Night')                   82.750000    419.000000  \n",
        "('WeekEnd', 'Afternoon')               90.750000    816.000000  \n",
        "('WeekEnd', 'Evening')                 55.000000    333.000000  \n",
        "('WeekEnd', 'Morning')                 53.250000    324.000000  \n",
        "('WeekEnd', 'Night')                   38.000000    263.000000  "
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Simple graphics\n",
      "\n",
      "We can visualize the data too. For example, we can see the density distribution of the variable `div_i`:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "db['div_i'].plot(kind='kde')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 14,
       "text": [
        "<matplotlib.axes.AxesSubplot at 0x50fa890>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAD/CAYAAAD8MdEiAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
       "text": [
        "<matplotlib.figure.Figure at 0x43957d0>"
       ]
      }
     ],
     "prompt_number": 14
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Or we can get a scatter plot between `div_i` and `industrie_pct_area`:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "scatter(db['div_i'], db['industrie_pct_area'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 15,
       "text": [
        "<matplotlib.collections.PathCollection at 0x53a0b90>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAWsAAAD6CAYAAABnC2YqAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nIlKA/wf8FrzYg6EgfAAAAABJRU5ErkJggg==\n",
       "text": [
        "<matplotlib.figure.Figure at 0x5112e90>"
       ]
      }
     ],
     "prompt_number": 15
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "we can get a full matrix of plots with the following commands:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from pandas.tools.plotting import scatter_matrix\n",
      "scatter_matrix(db.ix[:, :5], figsize=(12, 12))\n",
      "show()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAs0AAALNCAYAAADUT1yBAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nB8TZ6vXZ9VMuAAAAAElFTkSuQmCC\n",
       "text": [
        "<matplotlib.figure.Figure at 0xd7c5d50>"
       ]
      }
     ],
     "prompt_number": 20
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Estimate a model\n",
      "\n",
      "Let us run an OLS model with the following equation:\n",
      "\n",
      "$$ checkins\\_all = \\alpha + \\beta_1 total\\_units + \\beta_2 div_i $$"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ols = sm.OLS(db['checkins_all'], db[['total_units', 'div_i']]).fit()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 24
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "A plain text summary can be obtained as follows:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "smry = ols.summary()\n",
      "smry"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<table class=\"simpletable\">\n",
        "<caption>OLS Regression Results</caption>\n",
        "<tr>\n",
        "  <th>Dep. Variable:</th>      <td>checkins_all</td>   <th>  R-squared:         </th> <td>   0.392</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.379</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   30.29</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Date:</th>             <td>Tue, 14 Jan 2014</td> <th>  Prob (F-statistic):</th> <td>7.02e-11</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Time:</th>                 <td>20:53:19</td>     <th>  Log-Likelihood:    </th> <td> -803.27</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>No. Observations:</th>      <td>    96</td>      <th>  AIC:               </th> <td>   1611.</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Df Residuals:</th>          <td>    94</td>      <th>  BIC:               </th> <td>   1616.</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Df Model:</th>              <td>     2</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>total_units</th> <td>    0.1100</td> <td>    0.040</td> <td>    2.759</td> <td> 0.007</td> <td>    0.031     0.189</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>div_i</th>       <td>  376.2314</td> <td>  365.721</td> <td>    1.029</td> <td> 0.306</td> <td> -349.916  1102.378</td>\n",
        "</tr>\n",
        "</table>\n",
        "<table class=\"simpletable\">\n",
        "<tr>\n",
        "  <th>Omnibus:</th>       <td>82.475</td> <th>  Durbin-Watson:     </th> <td>   1.138</td> \n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Prob(Omnibus):</th> <td> 0.000</td> <th>  Jarque-Bera (JB):  </th> <td> 580.650</td> \n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Skew:</th>          <td> 2.850</td> <th>  Prob(JB):          </th> <td>8.19e-127</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Kurtosis:</th>      <td>13.615</td> <th>  Cond. No.          </th> <td>1.93e+04</td> \n",
        "</tr>\n",
        "</table>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 28,
       "text": [
        "<class 'statsmodels.iolib.summary.Summary'>\n",
        "\"\"\"\n",
        "                            OLS Regression Results                            \n",
        "==============================================================================\n",
        "Dep. Variable:           checkins_all   R-squared:                       0.392\n",
        "Model:                            OLS   Adj. R-squared:                  0.379\n",
        "Method:                 Least Squares   F-statistic:                     30.29\n",
        "Date:                Tue, 14 Jan 2014   Prob (F-statistic):           7.02e-11\n",
        "Time:                        20:53:19   Log-Likelihood:                -803.27\n",
        "No. Observations:                  96   AIC:                             1611.\n",
        "Df Residuals:                      94   BIC:                             1616.\n",
        "Df Model:                           2                                         \n",
        "===============================================================================\n",
        "                  coef    std err          t      P>|t|      [95.0% Conf. Int.]\n",
        "-------------------------------------------------------------------------------\n",
        "total_units     0.1100      0.040      2.759      0.007         0.031     0.189\n",
        "div_i         376.2314    365.721      1.029      0.306      -349.916  1102.378\n",
        "==============================================================================\n",
        "Omnibus:                       82.475   Durbin-Watson:                   1.138\n",
        "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              580.650\n",
        "Skew:                           2.850   Prob(JB):                    8.19e-127\n",
        "Kurtosis:                      13.615   Cond. No.                     1.93e+04\n",
        "==============================================================================\n",
        "\n",
        "Warnings:\n",
        "[1] The condition number is large, 1.93e+04. This might indicate that there are\n",
        "strong multicollinearity or other numerical problems.\n",
        "\"\"\""
       ]
      }
     ],
     "prompt_number": 28
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "And if we need to export it to latex, it is also easy:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "inlatex = smry.as_latex()\n",
      "print inlatex"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\\begin{center}\n",
        "\\begin{tabular}{lclc}\n",
        "\\toprule\n",
        "\\textbf{Dep. Variable:}    &   checkins_all   & \\textbf{  R-squared:         } &     0.392   \\\\\n",
        "\\textbf{Model:}            &       OLS        & \\textbf{  Adj. R-squared:    } &     0.379   \\\\\n",
        "\\textbf{Method:}           &  Least Squares   & \\textbf{  F-statistic:       } &     30.29   \\\\\n",
        "\\textbf{Date:}             & Tue, 14 Jan 2014 & \\textbf{  Prob (F-statistic):} &  7.02e-11   \\\\\n",
        "\\textbf{Time:}             &     20:53:19     & \\textbf{  Log-Likelihood:    } &   -803.27   \\\\\n",
        "\\textbf{No. Observations:} &          96      & \\textbf{  AIC:               } &     1611.   \\\\\n",
        "\\textbf{Df Residuals:}     &          94      & \\textbf{  BIC:               } &     1616.   \\\\\n",
        "\\bottomrule\n",
        "\\end{tabular}\n",
        "\\begin{tabular}{lccccc}\n",
        "                     & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$>$$|$t$|$} & \\textbf{[95.0\\% Conf. Int.]}  \\\\\n",
        "\\midrule\n",
        "\\textbf{total_units} &       0.1100  &        0.040     &     2.759  &         0.007        &         0.031     0.189       \\\\\n",
        "\\textbf{div_i}       &     376.2314  &      365.721     &     1.029  &         0.306        &      -349.916  1102.378       \\\\\n",
        "\\bottomrule\n",
        "\\end{tabular}\n",
        "\\begin{tabular}{lclc}\n",
        "\\textbf{Omnibus:}       & 82.475 & \\textbf{  Durbin-Watson:     } &     1.138  \\\\\n",
        "\\textbf{Prob(Omnibus):} &  0.000 & \\textbf{  Jarque-Bera (JB):  } &   580.650  \\\\\n",
        "\\textbf{Skew:}          &  2.850 & \\textbf{  Prob(JB):          } & 8.19e-127  \\\\\n",
        "\\textbf{Kurtosis:}      & 13.615 & \\textbf{  Cond. No.          } &  1.93e+04  \\\\\n",
        "\\bottomrule\n",
        "\\end{tabular}\n",
        "%\\caption{OLS Regression Results}\n",
        "\\end{center}\n"
       ]
      }
     ],
     "prompt_number": 29
    }
   ],
   "metadata": {}
  }
 ]
}