Downloading and Plotting U.S. Census Bureau Data Using Python

cenpy_intro.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Downloading and Plotting U.S. Census Bureau Data Using Python\n",
    "David C. Folch | Florida State University | github: @dfolch\n",
    "\n",
    "Rebecca Davies | University of Colorado Boulder | github: @beckymasond"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Motivation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Sources of US Census Bureau data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "There are a number of point-and-click sources:\n",
    "* [NHGIS](https://www.nhgis.org/) (National Historical Geographic Information System)\n",
    "* [Social Explorer](http://www.socialexplorer.com/)\n",
    "* [American Factfinder](http://factfinder.census.gov) from the US Census Bureau"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Accessing the API (using python)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Why this approach when there are all these nice websites?\n",
    "* Reproducible (data) science\n",
    "* Efficiency\n",
    "* One platform\n",
    "\n",
    "Tools\n",
    "* [US Census Bureau API](http://www.census.gov/developers/)\n",
    "* [Python](https://www.python.org/) \n",
    "* [Cenpy](https://github.com/ljwolf/cenpy) package to interface with the Census API\n",
    "* [GeoPandas](http://geopandas.org/) package to hold and plot data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Installation\n",
    "\n",
    "I recommend installing [Canopy Python](https://www.enthought.com/products/canopy/) or [Anaconda Python](https://www.continuum.io/downloads). These come with the python programming language and many common libraries preinstalled. \n",
    "\n",
    "#### Cenpy\n",
    "* Dependencies\n",
    "    * [Pandas](https://pandas.pydata.org/)\n",
    "    * [Requests](https://docs.python-requests.org)\n",
    "* `pip install cenpy`\n",
    "\n",
    "#### GeoPandas\n",
    "* Dependencies\n",
    "    * [Pandas](https://pandas.pydata.org/)\n",
    "    * [Matplotlib](http://matplotlib.org/)\n",
    "    * [Shapely](http://toblerity.org/shapely/)\n",
    "    * [Fiona](http://toblerity.org/fiona/)\n",
    "    * [Pyproj](https://github.com/jswhit/pyproj)\n",
    "    * [Descartes](https://pypi.python.org/pypi/descartes)\n",
    "    * [PySAL](http://pysal.org) (optional - needed for choropleth maps)\n",
    "* `pip install geopandas`\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "from matplotlib import rcParams\n",
    "rcParams['figure.figsize'] = 12,12  # change this line if you want to change the default map size\n",
    "import pandas as pd\n",
    "import geopandas as gpd\n",
    "import cenpy as cen"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Work Flow"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1. Select database  (ex. 2008-2012 ACS)\n",
    "2. Select geography(s)  (ex. Leon County census tracts)\n",
    "3. Select attributes  (ex. income and poverty)\n",
    "4. Pull down the data\n",
    "5. Pull down the geography\n",
    "6. Link the data to the geography"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1. Database\n",
    "\n",
    "The Census Bureau provides [many databases](http://www.census.gov/data/developers/data-sets.html) through their API, including the decennial census, economic census, etc."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Explore database options"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "total number of databases: 85\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[(u'NONEMP2012_old', u'2012 Nonemployer Statistics: Nonemployer Statistics'),\n",
       " (u'ASMState',\n",
       "  u'Time Series Annual Survey of Manufactures: Statistics for All Manufacturing by State'),\n",
       " (u'IDBSINGLEYEAR',\n",
       "  u'Time Series International Database: International Populations by Single Year of Age and Sex'),\n",
       " (u'2012popproj/deaths',\n",
       "  u'Vintage 2012 Population Projections - : Projected Deaths'),\n",
       " (u'NONEMP2009', u'2009 Nonemployer Statistics: Non Employer Statistics')]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "databases = [(k,v) for k,v in cen.explorer.available(verbose=True).items()]\n",
    "print 'total number of databases:', len(databases)\n",
    "databases[0:5]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For this example we will use the 2008-2012 [American Community Survey](https://www.census.gov/programs-surveys/acs/)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#api_database = '2010acs5'     # ACS 2006-2010\n",
    "api_database = 'ACSSF5Y2012'  # ACS 2008-2012\n",
    "#api_database = 'ACSSF5Y2013'  # ACS 2009-2013"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{u'2008-2012 American Community Survey - Summarized Data: 5-Year Summary File': u\"The American Community Survey (ACS) is a nationwide survey designed to provide communities a fresh look at how they are changing. The ACS replaced the decennial census long form in 2010 and thereafter by collecting long form type information throughout the decade rather than only once every 10 years. Questionnaires are mailed to a sample of addresses to obtain information about households -- that is, about each person and the housing unit itself. The American Community Survey produces demographic, social, housing and economic estimates in the form of 1-year, 3-year and 5-year estimates based on population thresholds. The strength of the ACS is in estimating population and housing characteristics. It produces estimates for small areas, including census tracts and population subgroups. Although the ACS produces population, demographic and housing unit estimates,it is the Census Bureau's Population Estimates Program that produces and disseminates the official estimates of the population for the nation, states, counties, cities and towns, and estimates of housing units for states and counties.  For 2010 and other decennial census years, the Decennial Census provides the official counts of population and housing units.\"}"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cen.explorer.explain(api_database)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n",
    "#### Connect to database"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "api_conn = cen.base.Connection(api_database)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Connection to 2008-2012 American Community Survey - Summarized Data: 5-Year Summary File (ID: http://api.census.gov/data/id/ACSSF5Y2012)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "api_conn"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2. Geography"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Data is provided at a variety of geographic scales, which depend on the database selected. For this example we're working with the ACS. Data for large geographies, like states, can be queried directly. But smaller geographies, like counties or census tracts, can only be selected by first choosing a bounding geography; this is sometimes referred to as *geo-in-geo*.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[u'fips']"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "api_conn.geographies.keys()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>geoLevelId</th>\n",
       "      <th>name</th>\n",
       "      <th>optionalWithWCFor</th>\n",
       "      <th>requires</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>310</td>\n",
       "      <td>metropolitan statistical area/micropolitan sta...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>010</td>\n",
       "      <td>us</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>020</td>\n",
       "      <td>region</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>030</td>\n",
       "      <td>division</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>400</td>\n",
       "      <td>urban area</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>250</td>\n",
       "      <td>american indian area/alaska native area/hawaii...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>330</td>\n",
       "      <td>combined statistical area</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>350</td>\n",
       "      <td>new england city and town area</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>040</td>\n",
       "      <td>state</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>860</td>\n",
       "      <td>zip code tabulation area</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>795</td>\n",
       "      <td>public use microdata area</td>\n",
       "      <td>state</td>\n",
       "      <td>[state]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>950</td>\n",
       "      <td>school district (elementary)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[state]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>960</td>\n",
       "      <td>school district (secondary)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[state]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>970</td>\n",
       "      <td>school district (unified)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[state]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>320</td>\n",
       "      <td>metropolitan statistical area/micropolitan sta...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[state]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>340</td>\n",
       "      <td>combined statistical area</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[state]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>500</td>\n",
       "      <td>congressional district</td>\n",
       "      <td>state</td>\n",
       "      <td>[state]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>610</td>\n",
       "      <td>state legislative district (upper chamber)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[state]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>620</td>\n",
       "      <td>state legislative district (lower chamber)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[state]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>050</td>\n",
       "      <td>county</td>\n",
       "      <td>state</td>\n",
       "      <td>[state]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>160</td>\n",
       "      <td>place</td>\n",
       "      <td>state</td>\n",
       "      <td>[state]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>140</td>\n",
       "      <td>tract</td>\n",
       "      <td>county</td>\n",
       "      <td>[state, county]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>060</td>\n",
       "      <td>county subdivision</td>\n",
       "      <td>county</td>\n",
       "      <td>[state, county]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>150</td>\n",
       "      <td>block group</td>\n",
       "      <td>tract</td>\n",
       "      <td>[state, county, tract]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   geoLevelId                                               name  \\\n",
       "0         310  metropolitan statistical area/micropolitan sta...   \n",
       "1         010                                                 us   \n",
       "2         020                                             region   \n",
       "3         030                                           division   \n",
       "4         400                                         urban area   \n",
       "5         250  american indian area/alaska native area/hawaii...   \n",
       "6         330                          combined statistical area   \n",
       "7         350                     new england city and town area   \n",
       "8         040                                              state   \n",
       "9         860                           zip code tabulation area   \n",
       "10        795                          public use microdata area   \n",
       "11        950                       school district (elementary)   \n",
       "12        960                        school district (secondary)   \n",
       "13        970                          school district (unified)   \n",
       "14        320  metropolitan statistical area/micropolitan sta...   \n",
       "15        340                          combined statistical area   \n",
       "16        500                             congressional district   \n",
       "17        610         state legislative district (upper chamber)   \n",
       "18        620         state legislative district (lower chamber)   \n",
       "19        050                                             county   \n",
       "20        160                                              place   \n",
       "21        140                                              tract   \n",
       "22        060                                 county subdivision   \n",
       "23        150                                        block group   \n",
       "\n",
       "   optionalWithWCFor                requires  \n",
       "0                NaN                     NaN  \n",
       "1                NaN                     NaN  \n",
       "2                NaN                     NaN  \n",
       "3                NaN                     NaN  \n",
       "4                NaN                     NaN  \n",
       "5                NaN                     NaN  \n",
       "6                NaN                     NaN  \n",
       "7                NaN                     NaN  \n",
       "8                NaN                     NaN  \n",
       "9                NaN                     NaN  \n",
       "10             state                 [state]  \n",
       "11               NaN                 [state]  \n",
       "12               NaN                 [state]  \n",
       "13               NaN                 [state]  \n",
       "14               NaN                 [state]  \n",
       "15               NaN                 [state]  \n",
       "16             state                 [state]  \n",
       "17               NaN                 [state]  \n",
       "18               NaN                 [state]  \n",
       "19             state                 [state]  \n",
       "20             state                 [state]  \n",
       "21            county         [state, county]  \n",
       "22            county         [state, county]  \n",
       "23             tract  [state, county, tract]  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "api_conn.geographies['fips']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The geographic query requires selecting a spatial scale from the `name` column in the table above, and in some cases an encompassing geography, based on the rules in the `requires` column. In either case, [FIPS codes](http://mcdc.missouri.edu/webrepts/commoncodes11/) are used to pick specific geographies."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#### select all states in the country\n",
    "#g_unit = 'state'\n",
    "#g_filter = {}\n",
    "#### select Florida\n",
    "#g_unit = 'state:12'\n",
    "#g_filter = {}\n",
    "#### select all counties in Florida\n",
    "#g_unit = 'county'\n",
    "#g_filter = {'state':'12'}\n",
    "#### select all census tracts in Florida\n",
    "#g_unit = 'tract'\n",
    "#g_filter = {'state':'12'}\n",
    "#### select all tracts in Leon County, Florida\n",
    "g_unit = 'tract'\n",
    "g_filter = {'state':'12', 'county':'073'}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3. Attributes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Attributes represent the demographic or economic characteristics that you wish to download."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Select attributes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Attributes in the ACS: 45236\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>concept</th>\n",
       "      <th>label</th>\n",
       "      <th>predicateOnly</th>\n",
       "      <th>predicateType</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>AIANHH</th>\n",
       "      <td>Selectable Geographies</td>\n",
       "      <td>American Indian Area/Alaska Native Area/Hawaii...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AIHHTLI</th>\n",
       "      <td>Selectable Geographies</td>\n",
       "      <td>American Indian Trust Land/Hawaiian Home Land ...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>int</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AITS</th>\n",
       "      <td>Selectable Geographies</td>\n",
       "      <td>American Indian Tribal Subdivision (FIPS)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AITSCE</th>\n",
       "      <td>Selectable Geographies</td>\n",
       "      <td>American Indian Tribal Subdivision (Census)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>int</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ANRC</th>\n",
       "      <td>Selectable Geographies</td>\n",
       "      <td>Alaska Native Regional Corporation (FIPS)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B00001_001E</th>\n",
       "      <td>B00001.  Unweighted Sample Count of the Popula...</td>\n",
       "      <td>Total</td>\n",
       "      <td>NaN</td>\n",
       "      <td>int</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B00001_001M</th>\n",
       "      <td>B00001.  Unweighted Sample Count of the Popula...</td>\n",
       "      <td>Margin Of Error For!!Total</td>\n",
       "      <td>NaN</td>\n",
       "      <td>int</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B00002_001E</th>\n",
       "      <td>B00002.  Unweighted Sample Housing Units</td>\n",
       "      <td>Total</td>\n",
       "      <td>NaN</td>\n",
       "      <td>int</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B00002_001M</th>\n",
       "      <td>B00002.  Unweighted Sample Housing Units</td>\n",
       "      <td>Margin Of Error For!!Total</td>\n",
       "      <td>NaN</td>\n",
       "      <td>int</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B01001A_001E</th>\n",
       "      <td>B01001A.  SEX BY AGE (WHITE ALONE)</td>\n",
       "      <td>Total:</td>\n",
       "      <td>NaN</td>\n",
       "      <td>int</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                        concept  \\\n",
       "AIANHH                                   Selectable Geographies   \n",
       "AIHHTLI                                  Selectable Geographies   \n",
       "AITS                                     Selectable Geographies   \n",
       "AITSCE                                   Selectable Geographies   \n",
       "ANRC                                     Selectable Geographies   \n",
       "B00001_001E   B00001.  Unweighted Sample Count of the Popula...   \n",
       "B00001_001M   B00001.  Unweighted Sample Count of the Popula...   \n",
       "B00002_001E            B00002.  Unweighted Sample Housing Units   \n",
       "B00002_001M            B00002.  Unweighted Sample Housing Units   \n",
       "B01001A_001E                 B01001A.  SEX BY AGE (WHITE ALONE)   \n",
       "\n",
       "                                                          label predicateOnly  \\\n",
       "AIANHH        American Indian Area/Alaska Native Area/Hawaii...           NaN   \n",
       "AIHHTLI       American Indian Trust Land/Hawaiian Home Land ...           NaN   \n",
       "AITS                  American Indian Tribal Subdivision (FIPS)           NaN   \n",
       "AITSCE              American Indian Tribal Subdivision (Census)           NaN   \n",
       "ANRC                  Alaska Native Regional Corporation (FIPS)           NaN   \n",
       "B00001_001E                                               Total           NaN   \n",
       "B00001_001M                          Margin Of Error For!!Total           NaN   \n",
       "B00002_001E                                               Total           NaN   \n",
       "B00002_001M                          Margin Of Error For!!Total           NaN   \n",
       "B01001A_001E                                             Total:           NaN   \n",
       "\n",
       "             predicateType  \n",
       "AIANHH                 NaN  \n",
       "AIHHTLI                int  \n",
       "AITS                   NaN  \n",
       "AITSCE                 int  \n",
       "ANRC                   NaN  \n",
       "B00001_001E            int  \n",
       "B00001_001M            int  \n",
       "B00002_001E            int  \n",
       "B00002_001M            int  \n",
       "B01001A_001E           int  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "print 'Attributes in the ACS:', api_conn.variables.shape[0]\n",
    "api_conn.variables.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Cenpy passes column names the Census API. Therefore, one option is to build a list of column codes. A good resource for these codes is [Social Explorer](http://www.socialexplorer.com/). For example, here is the info for [ACS 2008-2012 5 year tables](http://www.socialexplorer.com/data/ACS2012_5yr/metadata/?ds=ACS12_5yr)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#### total number of children in poverty\n",
    "#cols = ['B17006_002E']\n",
    "#### total number of children in poverty and number of children in pov in female headed households\n",
    "#cols = ['B17006_002E', 'B17006_012E']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "An alternative approach for building the list of column names is to use [regular expressions](https://en.wikipedia.org/wiki/Regular_expression). This approach is handy when you want all the columns from a particular table."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#### all the columns for table B17006 (poverty status for children by family type)\n",
    "#cols = api_conn.varslike('B17006_\\S+')\n",
    "#### all the columns for table B17006 and table B19326 (median income by gender and employment)\n",
    "cols = api_conn.varslike('B17006_\\S+')\n",
    "cols.extend(api_conn.varslike('B19326_\\S+'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "72"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(cols)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You can get a text description of each variable. Some descriptions are more useful than others."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>B17006_001E</th>\n",
       "      <td>Total:</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B17006_001M</th>\n",
       "      <td>Margin Of Error For!!Total:</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B17006_002E</th>\n",
       "      <td>Income in the past 12 months below poverty level:</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B17006_002M</th>\n",
       "      <td>Margin Of Error For!!Income in the past 12 mon...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B17006_003E</th>\n",
       "      <td>Income in the past 12 months below poverty lev...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                         label\n",
       "B17006_001E                                             Total:\n",
       "B17006_001M                        Margin Of Error For!!Total:\n",
       "B17006_002E  Income in the past 12 months below poverty level:\n",
       "B17006_002M  Margin Of Error For!!Income in the past 12 mon...\n",
       "B17006_003E  Income in the past 12 months below poverty lev..."
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cols_detail = pd.DataFrame(api_conn.variables.ix[cols].label)\n",
    "cols_detail.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Note that each estimate in the ACS comes with an accompanying margin of error (MOE). Column headers ending in `E` contain estimates, and headers ending in `M` contain MOEs."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Geographic attributes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In addition to the socioeconomic attributes, by default you will also get columns representing the `geo_unit` and `geo_filter`, which contain FIPS codes. We recommend adding the `NAME` and `GEOID` columns to get the geographies' text names and the full FIPS code in one cell."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "cols.extend(['NAME', 'GEOID'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 4. Pull the data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "With all the pieces in hand, we can now pull the data from the API."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "data = api_conn.query(cols, geo_unit=g_unit, geo_filter=g_filter)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(68, 77)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "It is often useful to make the pandas DataFrame index the full FIPS code. The effect is that any selection from the DataFrame will be accompanied by the Census ID."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "data.index = data.GEOID\n",
    "data.index = data.index.str.replace('14000US','')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can view all the columns, and then select one."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index([u'B17006_001E', u'B17006_001M', u'B17006_002E', u'B17006_002M',\n",
       "       u'B17006_003E', u'B17006_003M', u'B17006_004E', u'B17006_004M',\n",
       "       u'B17006_005E', u'B17006_005M', u'B17006_006E', u'B17006_006M',\n",
       "       u'B17006_007E', u'B17006_007M', u'B17006_008E', u'B17006_008M',\n",
       "       u'B17006_009E', u'B17006_009M', u'B17006_010E', u'B17006_010M',\n",
       "       u'B17006_011E', u'B17006_011M', u'B17006_012E', u'B17006_012M',\n",
       "       u'B17006_013E', u'B17006_013M', u'B17006_014E', u'B17006_014M',\n",
       "       u'B17006_015E', u'B17006_015M', u'B17006_016E', u'B17006_016M',\n",
       "       u'B17006_017E', u'B17006_017M', u'B17006_018E', u'B17006_018M',\n",
       "       u'B17006_019E', u'state', u'county', u'tract', u'B17006_019M',\n",
       "       u'B17006_020E', u'B17006_020M', u'B17006_021E', u'B17006_021M',\n",
       "       u'B17006_022E', u'B17006_022M', u'B17006_023E', u'B17006_023M',\n",
       "       u'B17006_024E', u'B17006_024M', u'B17006_025E', u'B17006_025M',\n",
       "       u'B17006_026E', u'B17006_026M', u'B17006_027E', u'B17006_027M',\n",
       "       u'B17006_028E', u'B17006_028M', u'B17006_029E', u'B17006_029M',\n",
       "       u'B19326_001E', u'B19326_001M', u'B19326_002E', u'B19326_002M',\n",
       "       u'B19326_003E', u'B19326_003M', u'B19326_004E', u'B19326_004M',\n",
       "       u'B19326_005E', u'B19326_005M', u'B19326_006E', u'B19326_006M',\n",
       "       u'B19326_007E', u'B19326_007M', u'NAME', u'GEOID'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>B17006_012E</th>\n",
       "      <th>B17006_012M</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GEOID</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>12073000200</th>\n",
       "      <td>107</td>\n",
       "      <td>109</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12073000301</th>\n",
       "      <td>0</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12073000302</th>\n",
       "      <td>0</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12073000303</th>\n",
       "      <td>147</td>\n",
       "      <td>97</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12073000400</th>\n",
       "      <td>28</td>\n",
       "      <td>26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12073000500</th>\n",
       "      <td>0</td>\n",
       "      <td>14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12073000600</th>\n",
       "      <td>139</td>\n",
       "      <td>129</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12073000700</th>\n",
       "      <td>107</td>\n",
       "      <td>96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12073000800</th>\n",
       "      <td>54</td>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12073000901</th>\n",
       "      <td>154</td>\n",
       "      <td>198</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             B17006_012E  B17006_012M\n",
       "GEOID                                \n",
       "12073000200          107          109\n",
       "12073000301            0           14\n",
       "12073000302            0           14\n",
       "12073000303          147           97\n",
       "12073000400           28           26\n",
       "12073000500            0           14\n",
       "12073000600          139          129\n",
       "12073000700          107           96\n",
       "12073000800           54           61\n",
       "12073000901          154          198"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#### select the count of number of children in poverty, and its MOE\n",
    "data[['B17006_012E','B17006_012M']].head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As an aside, you might notice that the quality of this particular estimate is not very good."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 5. Pull down the geometry"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The Census Bureau API for extracting geometries is separate from the database API."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can view all the available geographic data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{u'name': u'AIANNHA', u'type': u'MapServer'},\n",
       " {u'name': u'CBSA', u'type': u'MapServer'},\n",
       " {u'name': u'Hydro_LargeScale', u'type': u'MapServer'},\n",
       " {u'name': u'Hydro', u'type': u'MapServer'},\n",
       " {u'name': u'Labels', u'type': u'MapServer'},\n",
       " {u'name': u'Legislative', u'type': u'MapServer'},\n",
       " {u'name': u'Places_CouSub_ConCity_SubMCD', u'type': u'MapServer'},\n",
       " {u'name': u'PUMA_TAD_TAZ_UGA_ZCTA', u'type': u'MapServer'},\n",
       " {u'name': u'Region_Division', u'type': u'MapServer'},\n",
       " {u'name': u'School', u'type': u'MapServer'},\n",
       " {u'name': u'Special_Land_Use_Areas', u'type': u'MapServer'},\n",
       " {u'name': u'State_County', u'type': u'MapServer'},\n",
       " {u'name': u'tigerWMS_ACS2013', u'type': u'MapServer'},\n",
       " {u'name': u'tigerWMS_ACS2014', u'type': u'MapServer'},\n",
       " {u'name': u'tigerWMS_ACS2015', u'type': u'MapServer'},\n",
       " {u'name': u'tigerWMS_Census2010', u'type': u'MapServer'},\n",
       " {u'name': u'tigerWMS_Current', u'type': u'MapServer'},\n",
       " {u'name': u'tigerWMS_Econ2012', u'type': u'MapServer'},\n",
       " {u'name': u'tigerWMS_PhysicalFeatures', u'type': u'MapServer'},\n",
       " {u'name': u'Tracts_Blocks', u'type': u'MapServer'},\n",
       " {u'name': u'Transportation_LargeScale', u'type': u'MapServer'},\n",
       " {u'name': u'Transportation', u'type': u'MapServer'},\n",
       " {u'name': u'TribalTracts', u'type': u'MapServer'},\n",
       " {u'name': u'Urban', u'type': u'MapServer'},\n",
       " {u'name': u'USLandmass', u'type': u'MapServer'}]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cen.tiger.available()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Like before, we need to make a connection to the API. In this case there is a `set_mapservice` method that will attached this second connection to the first. Since we are working with ACS data, we will connect to the ACS geometry data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Connection to 2008-2012 American Community Survey - Summarized Data: 5-Year Summary File(ID: http://api.census.gov/data/id/ACSSF5Y2012)\n",
       "With MapServer: Census ACS 2013 WMS"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "api_conn.set_mapservice('tigerWMS_ACS2013')\n",
    "api_conn"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The ACS produces estimates from many different geographies."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{0: (ESRILayer) 2010 Census Public Use Microdata Areas,\n",
       " 1: (ESRILayer) 2010 Census Public Use Microdata Areas Labels,\n",
       " 2: (ESRILayer) 2010 Census ZIP Code Tabulation Areas,\n",
       " 3: (ESRILayer) 2010 Census ZIP Code Tabulation Areas Labels,\n",
       " 4: (ESRILayer) Tribal Census Tracts,\n",
       " 5: (ESRILayer) Tribal Census Tracts Labels,\n",
       " 6: (ESRILayer) Tribal Block Groups,\n",
       " 7: (ESRILayer) Tribal Block Groups Labels,\n",
       " 8: (ESRILayer) Census Tracts,\n",
       " 9: (ESRILayer) Census Tracts Labels,\n",
       " 10: (ESRILayer) Census Block Groups,\n",
       " 11: (ESRILayer) Census Block Groups Labels,\n",
       " 12: (ESRILayer) Unified School Districts,\n",
       " 13: (ESRILayer) Unified School Districts Labels,\n",
       " 14: (ESRILayer) Secondary School Districts,\n",
       " 15: (ESRILayer) Secondary School Districts Labels,\n",
       " 16: (ESRILayer) Elementary School Districts,\n",
       " 17: (ESRILayer) Elementary School Districts Labels,\n",
       " 18: (ESRILayer) Estates,\n",
       " 19: (ESRILayer) Estates Labels,\n",
       " 20: (ESRILayer) County Subdivisions,\n",
       " 21: (ESRILayer) County Subdivisions Labels,\n",
       " 22: (ESRILayer) Subbarrios,\n",
       " 23: (ESRILayer) Subbarrios Labels,\n",
       " 24: (ESRILayer) Consolidated Cities,\n",
       " 25: (ESRILayer) Consolidated Cities Labels,\n",
       " 26: (ESRILayer) Incorporated Places,\n",
       " 27: (ESRILayer) Incorporated Places Labels,\n",
       " 28: (ESRILayer) Census Designated Places,\n",
       " 29: (ESRILayer) Census Designated Places Labels,\n",
       " 30: (ESRILayer) Alaska Native Regional Corporations,\n",
       " 31: (ESRILayer) Alaska Native Regional Corporations Labels,\n",
       " 32: (ESRILayer) Tribal Subdivisions,\n",
       " 33: (ESRILayer) Tribal Subdivisions Labels,\n",
       " 34: (ESRILayer) Federal American Indian Reservations,\n",
       " 35: (ESRILayer) Federal American Indian Reservations Labels,\n",
       " 36: (ESRILayer) Off-Reservation Trust Lands,\n",
       " 37: (ESRILayer) Off-Reservation Trust Lands Labels,\n",
       " 38: (ESRILayer) State American Indian Reservations,\n",
       " 39: (ESRILayer) State American Indian Reservations Labels,\n",
       " 40: (ESRILayer) Hawaiian Home Lands,\n",
       " 41: (ESRILayer) Hawaiian Home Lands Labels,\n",
       " 42: (ESRILayer) Alaska Native Village Statistical Areas,\n",
       " 43: (ESRILayer) Alaska Native Village Statistical Areas Labels,\n",
       " 44: (ESRILayer) Oklahoma Tribal Statistical Areas,\n",
       " 45: (ESRILayer) Oklahoma Tribal Statistical Areas Labels,\n",
       " 46: (ESRILayer) State Designated Tribal Statistical Areas,\n",
       " 47: (ESRILayer) State Designated Tribal Statistical Areas Labels,\n",
       " 48: (ESRILayer) Tribal Designated Statistical Areas,\n",
       " 49: (ESRILayer) Tribal Designated Statistical Areas Labels,\n",
       " 50: (ESRILayer) American Indian Joint-Use Areas,\n",
       " 51: (ESRILayer) American Indian Joint-Use Areas Labels,\n",
       " 52: (ESRILayer) 113th Congressional Districts,\n",
       " 53: (ESRILayer) 113th Congressional Districts Labels,\n",
       " 54: (ESRILayer) 2013 State Legislative Districts - Upper,\n",
       " 55: (ESRILayer) 2013 State Legislative Districts - Upper Labels,\n",
       " 56: (ESRILayer) 2013 State Legislative Districts - Lower,\n",
       " 57: (ESRILayer) 2013 State Legislative Districts - Lower Labels,\n",
       " 58: (ESRILayer) Census Divisions,\n",
       " 59: (ESRILayer) Census Divisions Labels,\n",
       " 60: (ESRILayer) Census Regions,\n",
       " 61: (ESRILayer) Census Regions Labels,\n",
       " 62: (ESRILayer) 2010 Census Urbanized Areas,\n",
       " 63: (ESRILayer) 2010 Census Urbanized Areas Labels,\n",
       " 64: (ESRILayer) 2010 Census Urban Clusters,\n",
       " 65: (ESRILayer) 2010 Census Urban Clusters Labels,\n",
       " 66: (ESRILayer) Combined New England City and Town Areas,\n",
       " 67: (ESRILayer) Combined New England City and Town Areas Labels,\n",
       " 68: (ESRILayer) New England City and Town Area Divisions,\n",
       " 69: (ESRILayer) New England City and Town Area  Divisions Labels,\n",
       " 70: (ESRILayer) Metropolitan New England City and Town Areas,\n",
       " 71: (ESRILayer) Metropolitan New England City and Town Areas Labels,\n",
       " 72: (ESRILayer) Micropolitan New England City and Town Areas,\n",
       " 73: (ESRILayer) Micropolitan New England City and Town Areas Labels,\n",
       " 74: (ESRILayer) Combined Statistical Areas,\n",
       " 75: (ESRILayer) Combined Statistical Areas Labels,\n",
       " 76: (ESRILayer) Metropolitan Divisions,\n",
       " 77: (ESRILayer) Metropolitan Divisions Labels,\n",
       " 78: (ESRILayer) Metropolitan Statistical Areas,\n",
       " 79: (ESRILayer) Metropolitan Statistical Areas Labels,\n",
       " 80: (ESRILayer) Micropolitan Statistical Areas,\n",
       " 81: (ESRILayer) Micropolitan Statistical Areas Labels,\n",
       " 82: (ESRILayer) States,\n",
       " 83: (ESRILayer) States Labels,\n",
       " 84: (ESRILayer) Counties,\n",
       " 85: (ESRILayer) Counties Labels}"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "api_conn.mapservice.layers"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We are working with census tracts."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(ESRILayer) Census Tracts"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "api_conn.mapservice.layers[8]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Similar to setting the geographic constraints when pulling attribute data, you need to select the spatial scale and a bounding geography. However, these are selected entirely differently for the geometry data. The scale is set by passing an integer to the `layer` argument, and the bounding geography is selected by passing SQL to the WHERE argument."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "#### select Florida\n",
    "#geodata = api_conn.mapservice.query(layer=82, where='STATE=12', pkg='geopandas')\n",
    "#### select all counties in Florida\n",
    "#geodata = api_conn.mapservice.query(layer=84, where='STATE=12', pkg='geopandas')\n",
    "#### select all census tracts in Florida\n",
    "#geodata = api_conn.mapservice.query(layer=8, where='STATE=12', pkg='geopandas')\n",
    "#### select all tracts in Leon County, Florida\n",
    "geodata = api_conn.mapservice.query(layer=8, where='STATE=12 and COUNTY=073', pkg='geopandas')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 6. Merge attributes and geometries"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We now have all the pieces to merge the attribute data to the geometries."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "newdata = pd.merge(data, geodata, left_index=True, right_on='GEOID')\n",
    "newdata = gpd.GeoDataFrame(newdata)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We will plot median household income for Leon County, Florida."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1107e0cd0>"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAvQAAAH2CAYAAAAf/BiAAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nPKaEXkREREQkjymhFxERERHJY/8fuabyEK4c+BEAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1107e0910>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "newdata.plot(column='B19326_001E', scheme='QUANTILES', k=5, colormap='OrRd')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}