{
 "metadata": {
  "name": ""
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from IPython.display import HTML\n",
      "lic = \"\"\"\n",
      "<a rel=\"license\" href=\"http://creativecommons.org/licenses/by/4.0/\"><img alt=\"Creative Commons License\" style=\"border-width:0\" src=\"http://i.creativecommons.org/l/by/4.0/88x31.png\" /></a><br /><span xmlns:dct=\"http://purl.org/dc/terms/\" href=\"http://purl.org/dc/dcmitype/Text\" property=\"dct:title\" rel=\"dct:type\">\"Replication of results for The socio-cultural sources of urban buzz\"</span> by <a xmlns:cc=\"http://creativecommons.org/ns#\" href=\"http://darribas.org\" property=\"cc:attributionName\" rel=\"cc:attributionURL\">Daniel Arribas-Bel</a> is licensed under a <a rel=\"license\" href=\"http://creativecommons.org/licenses/by/4.0/\">Creative Commons Attribution 4.0 International License</a>.\"\"\"\n",
      "HTML(lic)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "\n",
        "<a rel=\"license\" href=\"http://creativecommons.org/licenses/by/4.0/\"><img alt=\"Creative Commons License\" style=\"border-width:0\" src=\"http://i.creativecommons.org/l/by/4.0/88x31.png\" /></a><br /><span xmlns:dct=\"http://purl.org/dc/terms/\" href=\"http://purl.org/dc/dcmitype/Text\" property=\"dct:title\" rel=\"dct:type\">\"Replication of results for The socio-cultural sources of urban buzz\"</span> by <a xmlns:cc=\"http://creativecommons.org/ns#\" href=\"http://darribas.org\" property=\"cc:attributionName\" rel=\"cc:attributionURL\">Daniel Arribas-Bel</a> is licensed under a <a rel=\"license\" href=\"http://creativecommons.org/licenses/by/4.0/\">Creative Commons Attribution 4.0 International License</a>."
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 1,
       "text": [
        "<IPython.core.display.HTML at 0x2bde550>"
       ]
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Replication of results for *The socio-cultural sources of urban buzz*\n",
      "\n",
      "- Author: [Dani Arribas-Bel](http://darribas.org)\n",
      "\n",
      "This notebook is stored in an open repository on the following link:\n",
      "\n",
      "* https://github.com/darribas/buzz_adam"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import copy\n",
      "import pysal as ps\n",
      "import numpy as np\n",
      "import pandas as pd\n",
      "import statsmodels.api as sm\n",
      "from pyGDsandbox.dataIO import dbf2df, df2dbf"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Data\n",
      "\n",
      "The data are provided in the same repository as this notebook and incorporate a `csv` file with the attributes plus a shapefile with the geometry of the neighborhoods in Amsterdam. If you have downloaded the repository, you can load the data with:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "db = pd.read_csv('buzz_data.csv', index_col=0)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "If you don't have the csv around but you are connected to the internet, you can load it remotely like this:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "url = 'https://raw.github.com/darribas/buzz_adam/master/buzz_data.csv'\n",
      "db = pd.read_csv(url, index_col=0)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 4
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "If the data has loaded correctly, the info of the table should look like this, 23 columns with data on 96 neighborhoods:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "db"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<pre>\n",
        "&lt;class 'pandas.core.frame.DataFrame'&gt;\n",
        "Index: 96 entries, BU03630000 to BU03631491\n",
        "Data columns (total 23 columns):\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)\n",
        "</pre>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 5,
       "text": [
        "<class 'pandas.core.frame.DataFrame'>\n",
        "Index: 96 entries, BU03630000 to BU03631491\n",
        "Data columns (total 23 columns):\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)"
       ]
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Descriptive figures\n",
      "\n",
      "The paper contains two descriptives: a choropleth of the distribution and a table that shows basic statistics of each variable. The latter is very simple to replicate (note I only show the variables displayed in the table of the paper, although the dataset contains a few more:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "vars = ['4sq-pct_Arts & Entertainment', \\\n",
      "        '4sq-pct_College & University', \\\n",
      "        '4sq-pct_Food', \\\n",
      "        '4sq-pct_Other', \\\n",
      "        '4sq-pct_Outdoors & Recreation', \\\n",
      "        '4sq-pct_Professional & Other Places', \\\n",
      "        '4sq-pct_Travel & Transport', \\\n",
      "        'industrie_pct_area', \\\n",
      "        'kantoor_pct_area', \\\n",
      "        'sport_pct_area', \\\n",
      "        'winkel_pct_area', \\\n",
      "        '4sq_total_venues', \\\n",
      "        'total_units', \\\n",
      "        'div_i', \\\n",
      "        'checkins_all']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "np.round(db[vars].describe().T[['mean', 'std', 'min', '25%', '50%', '75%', 'max']], 3)"
     ],
     "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>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>    7.993</td>\n",
        "      <td>   12.322</td>\n",
        "      <td>  0.000</td>\n",
        "      <td>    0.000</td>\n",
        "      <td>    0.000</td>\n",
        "      <td>   15.885</td>\n",
        "      <td>    46.154</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_College &amp; University</th>\n",
        "      <td>    1.503</td>\n",
        "      <td>    7.377</td>\n",
        "      <td>  0.000</td>\n",
        "      <td>    0.000</td>\n",
        "      <td>    0.000</td>\n",
        "      <td>    0.000</td>\n",
        "      <td>    50.000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Food</th>\n",
        "      <td>    6.498</td>\n",
        "      <td>   16.068</td>\n",
        "      <td>  0.000</td>\n",
        "      <td>    0.000</td>\n",
        "      <td>    0.000</td>\n",
        "      <td>    5.794</td>\n",
        "      <td>   100.000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Other</th>\n",
        "      <td>   46.072</td>\n",
        "      <td>   30.457</td>\n",
        "      <td>  0.000</td>\n",
        "      <td>   25.000</td>\n",
        "      <td>   50.000</td>\n",
        "      <td>   63.727</td>\n",
        "      <td>   100.000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Outdoors &amp; Recreation</th>\n",
        "      <td>    1.617</td>\n",
        "      <td>   10.620</td>\n",
        "      <td>  0.000</td>\n",
        "      <td>    0.000</td>\n",
        "      <td>    0.000</td>\n",
        "      <td>    0.000</td>\n",
        "      <td>   100.000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Professional &amp; Other Places</th>\n",
        "      <td>   12.212</td>\n",
        "      <td>   22.494</td>\n",
        "      <td>  0.000</td>\n",
        "      <td>    0.000</td>\n",
        "      <td>    0.000</td>\n",
        "      <td>   16.667</td>\n",
        "      <td>   100.000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq-pct_Travel &amp; Transport</th>\n",
        "      <td>    7.041</td>\n",
        "      <td>   16.066</td>\n",
        "      <td>  0.000</td>\n",
        "      <td>    0.000</td>\n",
        "      <td>    0.000</td>\n",
        "      <td>   11.111</td>\n",
        "      <td>   100.000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>industrie_pct_area</th>\n",
        "      <td>    7.195</td>\n",
        "      <td>   14.445</td>\n",
        "      <td>  0.000</td>\n",
        "      <td>    0.789</td>\n",
        "      <td>    1.970</td>\n",
        "      <td>    4.892</td>\n",
        "      <td>    76.820</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>kantoor_pct_area</th>\n",
        "      <td>    8.522</td>\n",
        "      <td>   12.679</td>\n",
        "      <td>  0.014</td>\n",
        "      <td>    1.399</td>\n",
        "      <td>    3.652</td>\n",
        "      <td>   10.339</td>\n",
        "      <td>    84.004</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>sport_pct_area</th>\n",
        "      <td>    1.351</td>\n",
        "      <td>    3.579</td>\n",
        "      <td>  0.000</td>\n",
        "      <td>    0.090</td>\n",
        "      <td>    0.363</td>\n",
        "      <td>    1.204</td>\n",
        "      <td>    29.413</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>winkel_pct_area</th>\n",
        "      <td>    3.409</td>\n",
        "      <td>    3.666</td>\n",
        "      <td>  0.000</td>\n",
        "      <td>    1.308</td>\n",
        "      <td>    2.382</td>\n",
        "      <td>    4.416</td>\n",
        "      <td>    29.075</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4sq_total_venues</th>\n",
        "      <td>   12.865</td>\n",
        "      <td>   22.032</td>\n",
        "      <td>  0.000</td>\n",
        "      <td>    1.000</td>\n",
        "      <td>    6.000</td>\n",
        "      <td>   11.000</td>\n",
        "      <td>   116.000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>total_units</th>\n",
        "      <td> 4822.031</td>\n",
        "      <td> 3001.490</td>\n",
        "      <td> 13.000</td>\n",
        "      <td> 2390.250</td>\n",
        "      <td> 4844.500</td>\n",
        "      <td> 6722.750</td>\n",
        "      <td> 14763.000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>div_i</th>\n",
        "      <td>    0.601</td>\n",
        "      <td>    0.145</td>\n",
        "      <td>  0.000</td>\n",
        "      <td>    0.525</td>\n",
        "      <td>    0.599</td>\n",
        "      <td>    0.725</td>\n",
        "      <td>     0.807</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>checkins_all</th>\n",
        "      <td>  806.531</td>\n",
        "      <td> 1070.210</td>\n",
        "      <td>  5.000</td>\n",
        "      <td>  147.000</td>\n",
        "      <td>  422.000</td>\n",
        "      <td> 1028.250</td>\n",
        "      <td>  6620.000</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 7,
       "text": [
        "                                         mean       std     min       25%       50%       75%        max\n",
        "4sq-pct_Arts & Entertainment            7.993    12.322   0.000     0.000     0.000    15.885     46.154\n",
        "4sq-pct_College & University            1.503     7.377   0.000     0.000     0.000     0.000     50.000\n",
        "4sq-pct_Food                            6.498    16.068   0.000     0.000     0.000     5.794    100.000\n",
        "4sq-pct_Other                          46.072    30.457   0.000    25.000    50.000    63.727    100.000\n",
        "4sq-pct_Outdoors & Recreation           1.617    10.620   0.000     0.000     0.000     0.000    100.000\n",
        "4sq-pct_Professional & Other Places    12.212    22.494   0.000     0.000     0.000    16.667    100.000\n",
        "4sq-pct_Travel & Transport              7.041    16.066   0.000     0.000     0.000    11.111    100.000\n",
        "industrie_pct_area                      7.195    14.445   0.000     0.789     1.970     4.892     76.820\n",
        "kantoor_pct_area                        8.522    12.679   0.014     1.399     3.652    10.339     84.004\n",
        "sport_pct_area                          1.351     3.579   0.000     0.090     0.363     1.204     29.413\n",
        "winkel_pct_area                         3.409     3.666   0.000     1.308     2.382     4.416     29.075\n",
        "4sq_total_venues                       12.865    22.032   0.000     1.000     6.000    11.000    116.000\n",
        "total_units                          4822.031  3001.490  13.000  2390.250  4844.500  6722.750  14763.000\n",
        "div_i                                   0.601     0.145   0.000     0.525     0.599     0.725      0.807\n",
        "checkins_all                          806.531  1070.210   5.000   147.000   422.000  1028.250   6620.000"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "The map in the paper was created using [QGIS](http://qgis.org), and it overlays the neighborhood polygons with the actual checkin points. I cannot re-share the individual data (although you can contact the authors), but we can re-create the choropleth (you will need PySAL 1.7 to reproduce the following cell):"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from pysal.contrib.viz import mapping as maps\n",
      "shp_link = 'adam_buzz_buurts.shp'\n",
      "\n",
      "_ = maps.plot_choropleth(shp_link, db['checkins_all'].values, 'quantiles', \\\n",
      "                         k=9, cmap='YlGn', figsize=(12, 12), \\\n",
      "                         title='Checkin volume')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAArkAAAKDCAYAAAAevxJ/AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nYII=\n",
       "text": [
        "<matplotlib.figure.Figure at 0x45650d0>"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Aggregated volume regressions\n",
      "\n",
      "The main part of the paper is devoted to regressions on the total volume of checkins of a neighborhood. In particular, we estimate a baseline OLS model as specified in Equation (1):\n",
      "\n",
      "$$\n",
      "B_i = \\alpha + \\beta_1 F_i + \\beta_2 E_i + \\gamma Div_i + \\epsilon_i\n",
      "$$\n",
      "\n",
      "Such regression, displayed in the first column of Table 2 is estimated next:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "name_y = 'checkins_all'\n",
      "x = db[vars[:-1]]\n",
      "x['constant'] = 1\n",
      "model = sm.OLS(np.log(db[name_y]), x).fit()\n",
      "print model.summary()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "                            OLS Regression Results                            \n",
        "==============================================================================\n",
        "Dep. Variable:           checkins_all   R-squared:                       0.735\n",
        "Model:                            OLS   Adj. R-squared:                  0.689\n",
        "Method:                 Least Squares   F-statistic:                     16.04\n",
        "Date:                Wed, 18 Dec 2013   Prob (F-statistic):           7.37e-18\n",
        "Time:                        11:40:45   Log-Likelihood:                -108.82\n",
        "No. Observations:                  96   AIC:                             247.6\n",
        "Df Residuals:                      81   BIC:                             286.1\n",
        "Df Model:                          14                                         \n",
        "=======================================================================================================\n",
        "                                          coef    std err          t      P>|t|      [95.0% Conf. Int.]\n",
        "-------------------------------------------------------------------------------------------------------\n",
        "4sq-pct_Arts & Entertainment            0.0285      0.008      3.456      0.001         0.012     0.045\n",
        "4sq-pct_College & University           -0.0104      0.012     -0.880      0.381        -0.034     0.013\n",
        "4sq-pct_Food                            0.0208      0.006      3.633      0.000         0.009     0.032\n",
        "4sq-pct_Other                           0.0121      0.003      3.590      0.001         0.005     0.019\n",
        "4sq-pct_Outdoors & Recreation           0.0171      0.008      2.059      0.043         0.001     0.034\n",
        "4sq-pct_Professional & Other Places     0.0129      0.005      2.513      0.014         0.003     0.023\n",
        "4sq-pct_Travel & Transport              0.0138      0.006      2.423      0.018         0.002     0.025\n",
        "industrie_pct_area                      0.0184      0.008      2.339      0.022         0.003     0.034\n",
        "kantoor_pct_area                        0.0339      0.008      4.467      0.000         0.019     0.049\n",
        "sport_pct_area                         -0.0271      0.030     -0.915      0.363        -0.086     0.032\n",
        "winkel_pct_area                         0.0187      0.032      0.593      0.555        -0.044     0.081\n",
        "4sq_total_venues                        0.0209      0.006      3.390      0.001         0.009     0.033\n",
        "total_units                             0.0002   3.63e-05      5.097      0.000         0.000     0.000\n",
        "div_i                                   1.5176      0.803      1.890      0.062        -0.080     3.116\n",
        "constant                                2.1549      0.524      4.112      0.000         1.112     3.198\n",
        "==============================================================================\n",
        "Omnibus:                        2.335   Durbin-Watson:                   1.596\n",
        "Prob(Omnibus):                  0.311   Jarque-Bera (JB):                1.711\n",
        "Skew:                          -0.273   Prob(JB):                        0.425\n",
        "Kurtosis:                       3.360   Cond. No.                     6.24e+04\n",
        "==============================================================================\n",
        "\n",
        "Warnings:\n",
        "[1] The condition number is large, 6.24e+04. This might indicate that there are\n",
        "strong multicollinearity or other numerical problems.\n"
       ]
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "As mentioned in the paper, values for nearby neighborhoods are likely to be correlated. To statistically test, the presence of spatial autocorrelation and, if so, of what type, we run the LM-Lag and LM-Error diagnostics. For that we previously require a spatial weights matrix, which we build following the queen contiguity and row-standardize (we also write it out for later use):"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "wo = ps.queen_from_shapefile('adam_buzz_buurts.shp')\n",
      "neigh = copy.copy(wo.neighbors)\n",
      "weigh = copy.copy(wo.weights)\n",
      "neigh[27].extend([26, 28])\n",
      "weigh[27].extend([1., 1.])\n",
      "w = ps.W(neigh, weigh)\n",
      "ps.open('adam_buzz_buurts_queenPS.gal', 'w').write(w)\n",
      "w.transform = 'r'"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "WARNING: there is one disconnected observation (no neighbors)\n",
        "Island id:  [27]\n"
       ]
      }
     ],
     "prompt_number": 10
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "The island mentioned in the warning is actually a coding error in the shapefile, so in this case we fix it manually. The diagnostics are easily run as follows (note that we require an OLS from PySAL, which we create as `mmodel`):"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "mmodel = ps.spreg.OLS(np.log(db[[name_y]].values),\n",
      "        db[vars[:-1]].values, w=w, spat_diag=True, nonspat_diag=False)\n",
      "\n",
      "from pysal.spreg.summary_output import summary_spat_diag_ols\n",
      "print '\\n\\t\\tSPATIAL DIAGNOSTICS'\n",
      "print '\\t\\t-------------------\\n'\n",
      "print summary_spat_diag_ols(mmodel, False)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "\t\tSPATIAL DIAGNOSTICS\n",
        "\t\t-------------------\n",
        "\n",
        "Lagrange Multiplier (lag)         1       20.874762        0.0000049\n",
        "Robust LM (lag)                   1       12.079756        0.0005097\n",
        "Lagrange Multiplier (error)       1        8.942169        0.0027866\n",
        "Robust LM (error)                 1        0.147163        0.7012617\n",
        "Lagrange Multiplier (SARMA)       2       21.021925        0.0000272\n",
        "\n",
        "\n"
       ]
      }
     ],
     "prompt_number": 11
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "The clear indication towards a spatial lag prompts us to run such specficiation. In formal notation, this boils down to:\n",
      "\n",
      "$$\n",
      "B_i = \\alpha + \\rho \\displaystyle\\sum^N_j w_{ij} B_j + \\beta_1 F_i + \\beta_2 E_i + \\gamma Div_i + \\epsilon_i\n",
      "$$\n",
      "\n",
      "Since the model is estimated using ML, we use `spdep` in R for the regression:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%load_ext rmagic\n",
      "%R library(spdep)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "text": [
        "Loading required package: sp\n",
        "Loading required package: Matrix\n",
        "Loading required package: lattice\n"
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "\n",
      "%%R\n",
      "db.link = 'adam_vars_richdiv.csv'\n",
      "db = read.csv(db.link, sep=';')\n",
      "landuses = names(db)[grep('_pct_area', names(db))]\n",
      "landuses = c('industrie_pct_area', 'kantoor_pct_area', 'sport_pct_area',\n",
      "             'winkel_pct_area')\n",
      "sq4 = names(db)[grep('X4sq.pct', names(db))][1:7]\n",
      "other = c()\n",
      "name.X = c(sq4, landuses, \n",
      "           c(\n",
      "            'X4sq_total_venues',\n",
      "            'total_units',\n",
      "            'div_i'\n",
      "            )\n",
      "        )\n",
      "x = db[name.X]\n",
      "########### Rescaling ##############\n",
      "x['total_units'] <- x['total_units'] / 1000\n",
      "x['div_i'] <- x['div_i'] * 10\n",
      "####################################\n",
      "y = 'checkins_all'\n",
      "y = log(db[, y])\n",
      "\n",
      "wnb <- read.gal('adam_buzz_buurts_queenPS.gal',\n",
      "                override.id=T)\n",
      "w <- nb2listw(wnb, style=\"W\")\n",
      "model <- lagsarlm(y ~ ., data=x, w)\n",
      "print(summary(model))\n"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "text": [
        "\n",
        "Call:lagsarlm(formula = y ~ ., data = x, listw = w)\n",
        "\n",
        "Residuals:\n",
        "       Min         1Q     Median         3Q        Max \n",
        "-1.5708760 -0.3645739 -0.0035605  0.4496111  2.1311628 \n",
        "\n",
        "Type: lag \n",
        "Coefficients: (asymptotic standard errors) \n",
        "                                       Estimate Std. Error z value  Pr(>|z|)\n",
        "(Intercept)                          -0.0510550  0.6701247 -0.0762 0.9392701\n",
        "X4sq.pct_Arts...Entertainment         0.0157820  0.0068313  2.3102 0.0208746\n",
        "X4sq.pct_College...University        -0.0063080  0.0096102 -0.6564 0.5115730\n",
        "X4sq.pct_Food                         0.0132307  0.0048092  2.7511 0.0059391\n",
        "X4sq.pct_Other                        0.0127954  0.0027478  4.6566 3.214e-06\n",
        "X4sq.pct_Outdoors...Recreation        0.0093330  0.0067592  1.3808 0.1673445\n",
        "X4sq.pct_Professional...Other.Places  0.0099200  0.0042057  2.3587 0.0183402\n",
        "X4sq.pct_Travel...Transport           0.0134285  0.0046176  2.9081 0.0036366\n",
        "industrie_pct_area                    0.0216871  0.0063970  3.3902 0.0006985\n",
        "kantoor_pct_area                      0.0223510  0.0063125  3.5407 0.0003990\n",
        "sport_pct_area                       -0.0213363  0.0242902 -0.8784 0.3797309\n",
        "winkel_pct_area                       0.0407958  0.0256985  1.5875 0.1124046\n",
        "X4sq_total_venues                     0.0137894  0.0053181  2.5929 0.0095162\n",
        "total_units                           0.1736649  0.0295318  5.8806 4.088e-09\n",
        "div_i                                 0.1266651  0.0652172  1.9422 0.0521123\n",
        "\n",
        "Rho: 0.43991, LR test value: 19.808, p-value: 8.5624e-06\n",
        "Asymptotic standard error: 0.09327\n",
        "    z-value: 4.7165, p-value: 2.3991e-06\n",
        "Wald statistic: 22.246, p-value: 2.3991e-06\n",
        "\n",
        "Log likelihood: -98.91989 for lag model\n",
        "ML residual variance (sigma squared): 0.44128, (sigma: 0.66429)\n",
        "Number of observations: 96 \n",
        "Number of parameters estimated: 17 \n",
        "AIC: 231.84, (AIC for lm: 249.65)\n",
        "LM test for residual autocorrelation\n",
        "test value: 3.6243, p-value: 0.056941\n",
        "\n"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "These results match those in the second column of Table 2."
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Regressions by time of the week\n",
      "\n",
      "The last part of the paper explores the variability of the effect of diversity over different times of the week. To do that, we run a separate regression for the volume of checkins that occur within a given time window of the week. This is equivalent to:\n",
      "\n",
      "$$\n",
      "B_{it} = \\alpha + \\rho \\displaystyle\\sum^N_j w_{ij} B_{jt} + \\beta_1 F_i + \\beta_2 E_i + \\gamma Div_i + \\epsilon_i\n",
      "$$\n",
      "\n",
      "Since we are just exploring this variability, we do not report the entire model but only keep the coefficient for $Div_i$ to plot it over the week, together with its confidence intervals. The regressions though output the entire summary of the model to a file named `'lag_models_summaries.txt'` in the same folder."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "\n",
      "%%R\n",
      "cross.walk <- list(\"X..WeekDay....Morning..\" = \"Morning-WeekDay\",\n",
      "                   \"X..WeekDay....Afternoon..\" = \"Afternoon-WeekDay\",\n",
      "                   \"X..WeekDay....Evening..\" = \"Evening-WeekDay\",\n",
      "                   \"X..WeekDay....Night..\" = \"Night-WeekDay\",\n",
      "                   \"X..WeekEnd....Morning..\" = \"Morning-WeekEnd\",\n",
      "                   \"X..WeekEnd....Afternoon..\" = \"Afternoon-WeekEnd\",\n",
      "                   \"X..WeekEnd....Evening..\" = \"Evening-WeekEnd\",\n",
      "                   \"X..WeekEnd....Night..\" = \"Night-WeekEnd\"\n",
      "                   )\n",
      "db.link = 'buzz_data.csv'\n",
      "db = read.csv(db.link)\n",
      "landuses = names(db)[grep('_pct_area', names(db))]\n",
      "landuses = c('industrie_pct_area', 'kantoor_pct_area', 'sport_pct_area',\n",
      "             'winkel_pct_area')\n",
      "sq4 = names(db)[grep('X4sq.pct', names(db))][1:7]\n",
      "other = c()\n",
      "name.X = c(sq4, landuses, \n",
      "           c(\n",
      "            'X4sq_total_venues',\n",
      "            'total_units',\n",
      "            'div_i'\n",
      "            )\n",
      "        )\n",
      "########### Rescaling ##############\n",
      "db['total_units'] <- db['total_units'] / 1000\n",
      "db['div_i'] <- db['div_i'] * 10\n",
      "####################################\n",
      "\n",
      "wnb <- read.gal('adam_buzz_buurts_queenPS.gal',\n",
      "                override.id=T)\n",
      "w <- nb2listw(wnb, style=\"W\")\n",
      "\n",
      "week.times <- names(db)[grep('Week', names(db))]\n",
      "res <- data.frame()\n",
      "divs <- data.frame()\n",
      "vari <- 15 # Position for Div_i\n",
      "print('Running regressions')\n",
      "sink('lag_models_summaries.txt')\n",
      "for(wtime in week.times){\n",
      "    print(paste('Model for week time:', wtime))\n",
      "    y = db[, wtime]\n",
      "    y[y == 0] = 0.000001\n",
      "    y = log(y)\n",
      "    x = db[name.X]\n",
      "    model <- lagsarlm(y ~ ., data=x, w)\n",
      "    coefs <- as.data.frame(model$coefficients)\n",
      "    colnames(coefs) <- cross.walk[wtime]\n",
      "    res <- c(res, coefs)\n",
      "    print(summary(model))\n",
      "\n",
      "    div <- data.frame(beta=model$coefficients[vari], se=model$rest.se[vari],\n",
      "                      lower=model$coefficients[vari] - model$rest.se[vari]*1.96, \n",
      "                      upper=model$coefficients[vari] + model$rest.se[vari]*1.96\n",
      "                      )\n",
      "    rownames(div) <- cross.walk[wtime]\n",
      "    divs <- rbind(div, divs)\n",
      "}\n",
      "sink()\n",
      "res <- as.data.frame(res)\n",
      "time.line <- c(\"Morning-WeekDay\", \"Afternoon-WeekDay\", \"Evening-WeekDay\", \"Night-WeekDay\", \n",
      "               \"Morning-WeekEnd\", \"Afternoon-WeekEnd\", \"Evening-WeekEnd\", \"Night-WeekEnd\")\n",
      "divs <- divs[time.line, ]\n",
      "print(divs)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "text": [
        "[1] \"Running regressions\"\n",
        "                       beta        se       lower     upper\n",
        "Morning-WeekDay   0.1047662 0.0789775 -0.05002975 0.2595621\n",
        "Afternoon-WeekDay 0.3147000 0.1538102  0.01323208 0.6161680\n",
        "Evening-WeekDay   0.4999191 0.2386536  0.03215808 0.9676800\n",
        "Night-WeekDay     1.1662525 0.3208840  0.53731992 1.7951850\n",
        "Morning-WeekEnd   0.7755847 0.2077812  0.36833347 1.1828359\n",
        "Afternoon-WeekEnd 0.6429518 0.1903473  0.26987110 1.0160325\n",
        "Evening-WeekEnd   0.8430234 0.2695521  0.31470129 1.3713454\n",
        "Night-WeekEnd     0.8461017 0.2893739  0.27892897 1.4132745\n"
       ]
      }
     ],
     "prompt_number": 14
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "These results can be then plotted, reproducing the structure in Figure 2 of the paper."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "\n",
      "%%R\n",
      "par(mar = c(7, 4, 4, 2) + 0.1, bty='n')\n",
      "ylab <- 'Div. coefficients'\n",
      "plot(seq(8), xaxt = \"n\", divs$beta, type='l', xlab='', ylab=ylab,\n",
      "     ylim=c(min(divs$lower), max(divs$upper)))\n",
      "#lines(seq(8), xaxt = \"n\", divs$lower, col='green', lw=0.5, type='l', xlab='', ylab='Div_i Coef.')\n",
      "#lines(seq(8), xaxt = \"n\", divs$upper, col='green', lw=0.5, type='l', xlab='', ylab='Div_i Coef.')\n",
      "xx <- c(seq(8), rev(seq(8)))\n",
      "yy <- c(divs$upper, rev(divs$lower))\n",
      "polygon(xx, yy, col = 'darkgray', border = NA)\n",
      "lines(seq(8), xaxt = \"n\", divs$beta, type='l', xlab='', ylab='Div. Coef.',\n",
      "     ylim=c(min(divs$lower), max(divs$upper)))\n",
      "abline(h=0, col='red', lw=2)\n",
      "\n",
      "abline(v=4.5, col='black', lw=0.5)\n",
      "axis(1, labels = FALSE)\n",
      "text(1:8, par(\"usr\")[3] - 0.075, srt = 45, adj = 1,\n",
      "               labels = time.line, xpd = TRUE)\n",
      "text(2.25, 1.5, labels='Week days')\n",
      "text(6.75, 1.5, labels='Weekend')\n",
      "title(main=paste('Effect of diversity on buzz\\n(spatial lag models)'))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAeAAAAHgCAIAAADytinCAAAgAElEQVR4nOzdd1wT5x8H8IchGwEB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\nACAUgQYAoQg0AAhFoAFAKAINAEL9AU94EPwCDmLFAAAAAElFTkSuQmCC\n"
      }
     ],
     "prompt_number": 15
    }
   ],
   "metadata": {}
  }
 ]
}