geopandas_spatial_join.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h1>Introduction and Set Up</h1>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p>This notebook will demonstrate how to assign trip starting points to Michigan census tracts and plot tracts that a trip has travelled through. It has been tested on:</p>\n",
    "<ul>\n",
    "    <li>geopandas: 0.2.1 </li>\n",
    "    <li>pandas: 0.19.2</li>\n",
    "    <li>shapely: 1.5.17</li>\n",
    "    <li>pysal: 1.14.2</li>\n",
    "</ul>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 306,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import geopandas as gpd\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from shapely.geometry import *\n",
    "import pysal as ps\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h3>Read In Data and Create GeoDataFrame</h3>\n",
    "<p>In general, GeoPandas read spatial data into GeoDataFrame (or GeoSeries) while Pandas read text data (most often) into DataFrame (or Series). GeoDataFrame and DataFrame are highly comparable because common methods available to DataFrame can also be applied to GeoDataFrame.</p>\n",
    "<p>One major difference between GeoDataFrame and DataFrame is that GeoDataFrame must have a column <strong>geometry</strong> which stores Shapely geometric objects. Common Shapely geometric objects include Point, Polygon, LineString. Less common geometric objects are collection of objects like MultiPoint, MultiPolygon, MultiLineString.</p>\n",
    "<p>Geopandas can read almost any vector-based spatial data formate including widely used <strong>ESRI shapefile</strong>, <strong>GeoJSON</strong> by command: gpd.read_file().\n",
    "<p>First we read in the Michigan census tract shape file, which can be found on <a href=\"\"http://gis-michigan.opendata.arcgis.com/datasets/172a00f7218b455299682f4d76562757_13>Michigan GIS Data Portal</a>.</p>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "filename = \"2010_Census_Tracts_v17a.geojson\"\n",
    "mi_census = gpd.read_file(filename)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The geometry column  shows that most of the census tracts are polygons."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>OBJECTID</th>\n",
       "      <th>NAME</th>\n",
       "      <th>LABEL</th>\n",
       "      <th>TYPE</th>\n",
       "      <th>LINK</th>\n",
       "      <th>CNTY_CODE</th>\n",
       "      <th>SQKM</th>\n",
       "      <th>SQMILES</th>\n",
       "      <th>ACRES</th>\n",
       "      <th>VER</th>\n",
       "      <th>LAYOUT</th>\n",
       "      <th>PENINSULA</th>\n",
       "      <th>ShapeSTArea</th>\n",
       "      <th>ShapeSTLength</th>\n",
       "      <th>geometry</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>970100</td>\n",
       "      <td>Tract 9701</td>\n",
       "      <td>Tract</td>\n",
       "      <td>001970100</td>\n",
       "      <td>001</td>\n",
       "      <td>204.621</td>\n",
       "      <td>79.004</td>\n",
       "      <td>50562.495</td>\n",
       "      <td>17A</td>\n",
       "      <td>portrait</td>\n",
       "      <td>lower</td>\n",
       "      <td>2.046214e+08</td>\n",
       "      <td>80225.641570</td>\n",
       "      <td>POLYGON ((-83.40342246796628 44.68502773673926...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>000100</td>\n",
       "      <td>Tract 0001</td>\n",
       "      <td>Tract</td>\n",
       "      <td>001000100</td>\n",
       "      <td>001</td>\n",
       "      <td>168.130</td>\n",
       "      <td>64.915</td>\n",
       "      <td>41545.324</td>\n",
       "      <td>17A</td>\n",
       "      <td>landscape</td>\n",
       "      <td>lower</td>\n",
       "      <td>1.681298e+08</td>\n",
       "      <td>52639.870882</td>\n",
       "      <td>(POLYGON ((-83.58911532322678 44.8053156248352...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>970500</td>\n",
       "      <td>Tract 9705</td>\n",
       "      <td>Tract</td>\n",
       "      <td>001970500</td>\n",
       "      <td>001</td>\n",
       "      <td>920.748</td>\n",
       "      <td>355.501</td>\n",
       "      <td>227519.309</td>\n",
       "      <td>17A</td>\n",
       "      <td>portrait</td>\n",
       "      <td>lower</td>\n",
       "      <td>9.207479e+08</td>\n",
       "      <td>143070.374716</td>\n",
       "      <td>POLYGON ((-83.88729210379145 44.614888452553, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>970400</td>\n",
       "      <td>Tract 9704</td>\n",
       "      <td>Tract</td>\n",
       "      <td>001970400</td>\n",
       "      <td>001</td>\n",
       "      <td>428.635</td>\n",
       "      <td>165.496</td>\n",
       "      <td>105916.824</td>\n",
       "      <td>17A</td>\n",
       "      <td>portrait</td>\n",
       "      <td>lower</td>\n",
       "      <td>4.286348e+08</td>\n",
       "      <td>103318.569067</td>\n",
       "      <td>POLYGON ((-83.625013486627 44.59038565417478, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>970600</td>\n",
       "      <td>Tract 9706</td>\n",
       "      <td>Tract</td>\n",
       "      <td>001970600</td>\n",
       "      <td>001</td>\n",
       "      <td>76.424</td>\n",
       "      <td>29.507</td>\n",
       "      <td>18884.615</td>\n",
       "      <td>17A</td>\n",
       "      <td>landscape</td>\n",
       "      <td>lower</td>\n",
       "      <td>7.642415e+07</td>\n",
       "      <td>34597.247127</td>\n",
       "      <td>POLYGON ((-83.33373829371767 44.51176424727763...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   OBJECTID    NAME       LABEL   TYPE       LINK CNTY_CODE     SQKM  SQMILES  \\\n",
       "0         1  970100  Tract 9701  Tract  001970100       001  204.621   79.004   \n",
       "1         2  000100  Tract 0001  Tract  001000100       001  168.130   64.915   \n",
       "2         3  970500  Tract 9705  Tract  001970500       001  920.748  355.501   \n",
       "3         4  970400  Tract 9704  Tract  001970400       001  428.635  165.496   \n",
       "4         5  970600  Tract 9706  Tract  001970600       001   76.424   29.507   \n",
       "\n",
       "        ACRES  VER     LAYOUT PENINSULA   ShapeSTArea  ShapeSTLength  \\\n",
       "0   50562.495  17A   portrait     lower  2.046214e+08   80225.641570   \n",
       "1   41545.324  17A  landscape     lower  1.681298e+08   52639.870882   \n",
       "2  227519.309  17A   portrait     lower  9.207479e+08  143070.374716   \n",
       "3  105916.824  17A   portrait     lower  4.286348e+08  103318.569067   \n",
       "4   18884.615  17A  landscape     lower  7.642415e+07   34597.247127   \n",
       "\n",
       "                                            geometry  \n",
       "0  POLYGON ((-83.40342246796628 44.68502773673926...  \n",
       "1  (POLYGON ((-83.58911532322678 44.8053156248352...  \n",
       "2  POLYGON ((-83.88729210379145 44.614888452553, ...  \n",
       "3  POLYGON ((-83.625013486627 44.59038565417478, ...  \n",
       "4  POLYGON ((-83.33373829371767 44.51176424727763...  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mi_census.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's take a look at Washtenaw county tracts."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 307,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1d19220b8>"
      ]
     },
     "execution_count": 307,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYQAAADvCAYAAADy+aP+AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x116088358>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "washtenaw = mi_census[mi_census.CNTY_CODE == \"161\"]\n",
    "washtenaw.plot(color = \"white\", linewidth = 0.5,edgecolor=\"black\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Read in trip summary data (dataset <a href=\"https://github.com/caocscar/ConnectedVehicleDocs/blob/master/BSMdocumentation.md\">documentation</a>)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 410,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>RxDevice</th>\n",
       "      <th>fileId</th>\n",
       "      <th>TxDevice</th>\n",
       "      <th>firstLatitude</th>\n",
       "      <th>firstLongitude</th>\n",
       "      <th>lastLatitude</th>\n",
       "      <th>lastLongitude</th>\n",
       "      <th>distance</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1104</td>\n",
       "      <td>76</td>\n",
       "      <td>-7029</td>\n",
       "      <td>42.449341</td>\n",
       "      <td>-83.752304</td>\n",
       "      <td>42.516045</td>\n",
       "      <td>-83.757439</td>\n",
       "      <td>4.64</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1104</td>\n",
       "      <td>76</td>\n",
       "      <td>-1792</td>\n",
       "      <td>42.632069</td>\n",
       "      <td>-83.776802</td>\n",
       "      <td>42.630283</td>\n",
       "      <td>-83.853798</td>\n",
       "      <td>3.91</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1104</td>\n",
       "      <td>76</td>\n",
       "      <td>-67</td>\n",
       "      <td>42.323597</td>\n",
       "      <td>-83.715752</td>\n",
       "      <td>42.379303</td>\n",
       "      <td>-83.756821</td>\n",
       "      <td>5.30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1104</td>\n",
       "      <td>76</td>\n",
       "      <td>3543</td>\n",
       "      <td>42.603577</td>\n",
       "      <td>-83.740303</td>\n",
       "      <td>42.632515</td>\n",
       "      <td>-83.766769</td>\n",
       "      <td>3.07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1104</td>\n",
       "      <td>76</td>\n",
       "      <td>11131</td>\n",
       "      <td>42.524647</td>\n",
       "      <td>-83.752205</td>\n",
       "      <td>42.595886</td>\n",
       "      <td>-83.740540</td>\n",
       "      <td>5.08</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   RxDevice  fileId  TxDevice  firstLatitude  firstLongitude  lastLatitude  \\\n",
       "0      1104      76     -7029      42.449341      -83.752304     42.516045   \n",
       "1      1104      76     -1792      42.632069      -83.776802     42.630283   \n",
       "2      1104      76       -67      42.323597      -83.715752     42.379303   \n",
       "3      1104      76      3543      42.603577      -83.740303     42.632515   \n",
       "4      1104      76     11131      42.524647      -83.752205     42.595886   \n",
       "\n",
       "   lastLongitude  distance  \n",
       "0     -83.757439      4.64  \n",
       "1     -83.853798      3.91  \n",
       "2     -83.756821      5.30  \n",
       "3     -83.766769      3.07  \n",
       "4     -83.740540      5.08  "
      ]
     },
     "execution_count": 410,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "metadata = \"umtri_bsm_metadata.txt\"\n",
    "trip_df = pd.read_csv(metadata,usecols=list(range(2,9))+[17])\n",
    "trip_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<p>Before doing spatial join or other sptial operations, it is always a good practice to project GeoDataFrames or GeoSeries to the same Coordinate Reference System.</p>\n",
    "<p>Coordinate Reference System (CRS) are referred to using codes called __proj4__ strings. Commonly used code can be found at http://spatialreference.org.</p>\n",
    "<p>In this example we'll stick to the standard WGS84 coordinate system which is speficed as {'init': 'epsg:4326'}.</p>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First check the tract gdf's crs, which is the standard system."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 411,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'init': 'epsg:4326'}"
      ]
     },
     "execution_count": 411,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mi_census.crs"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Then create Point object using the starting lattitude and longtitude. Remember to specify crs when converting DataFrame to GeoDataFrame."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 434,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "start_point_geometry = [Point(x,y) for x,y in zip(trip_df.firstLongitude, trip_df.firstLatitude)]\n",
    "start_point_gdf = gpd.GeoDataFrame(trip_df, geometry=start_point_geometry,crs={'init': 'epsg:4326'})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 435,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>RxDevice</th>\n",
       "      <th>fileId</th>\n",
       "      <th>TxDevice</th>\n",
       "      <th>firstLatitude</th>\n",
       "      <th>firstLongitude</th>\n",
       "      <th>lastLatitude</th>\n",
       "      <th>lastLongitude</th>\n",
       "      <th>distance</th>\n",
       "      <th>geometry</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>index_left</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1104</td>\n",
       "      <td>76</td>\n",
       "      <td>-7029</td>\n",
       "      <td>42.449341</td>\n",
       "      <td>-83.752304</td>\n",
       "      <td>42.516045</td>\n",
       "      <td>-83.757439</td>\n",
       "      <td>4.64</td>\n",
       "      <td>POINT (-83.75230400000001 42.449341)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1104</td>\n",
       "      <td>76</td>\n",
       "      <td>-1792</td>\n",
       "      <td>42.632069</td>\n",
       "      <td>-83.776802</td>\n",
       "      <td>42.630283</td>\n",
       "      <td>-83.853798</td>\n",
       "      <td>3.91</td>\n",
       "      <td>POINT (-83.776802 42.632069)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1104</td>\n",
       "      <td>76</td>\n",
       "      <td>-67</td>\n",
       "      <td>42.323597</td>\n",
       "      <td>-83.715752</td>\n",
       "      <td>42.379303</td>\n",
       "      <td>-83.756821</td>\n",
       "      <td>5.30</td>\n",
       "      <td>POINT (-83.71575199999999 42.323597)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1104</td>\n",
       "      <td>76</td>\n",
       "      <td>3543</td>\n",
       "      <td>42.603577</td>\n",
       "      <td>-83.740303</td>\n",
       "      <td>42.632515</td>\n",
       "      <td>-83.766769</td>\n",
       "      <td>3.07</td>\n",
       "      <td>POINT (-83.740303 42.603577)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1104</td>\n",
       "      <td>76</td>\n",
       "      <td>11131</td>\n",
       "      <td>42.524647</td>\n",
       "      <td>-83.752205</td>\n",
       "      <td>42.595886</td>\n",
       "      <td>-83.740540</td>\n",
       "      <td>5.08</td>\n",
       "      <td>POINT (-83.752205 42.52464699999999)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            RxDevice  fileId  TxDevice  firstLatitude  firstLongitude  \\\n",
       "index_left                                                              \n",
       "0               1104      76     -7029      42.449341      -83.752304   \n",
       "1               1104      76     -1792      42.632069      -83.776802   \n",
       "2               1104      76       -67      42.323597      -83.715752   \n",
       "3               1104      76      3543      42.603577      -83.740303   \n",
       "4               1104      76     11131      42.524647      -83.752205   \n",
       "\n",
       "            lastLatitude  lastLongitude  distance  \\\n",
       "index_left                                          \n",
       "0              42.516045     -83.757439      4.64   \n",
       "1              42.630283     -83.853798      3.91   \n",
       "2              42.379303     -83.756821      5.30   \n",
       "3              42.632515     -83.766769      3.07   \n",
       "4              42.595886     -83.740540      5.08   \n",
       "\n",
       "                                        geometry  \n",
       "index_left                                        \n",
       "0           POINT (-83.75230400000001 42.449341)  \n",
       "1                   POINT (-83.776802 42.632069)  \n",
       "2           POINT (-83.71575199999999 42.323597)  \n",
       "3                   POINT (-83.740303 42.603577)  \n",
       "4           POINT (-83.752205 42.52464699999999)  "
      ]
     },
     "execution_count": 435,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "start_point_gdf.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Check the number of census tracts and starting points."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 414,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2773, 15)"
      ]
     },
     "execution_count": 414,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mi_census.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 415,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4643842, 9)"
      ]
     },
     "execution_count": 415,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "start_point_gdf.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h3>Assigning Points to Correct Census Tract Using Spatial Join</h3>\n",
    "<p><strong>Spatial join</strong> is to join two geometric object based on their sptial locations. GeoPandas can readily spatial join two geometric obejcts using the <strong>sjoin</strong> function. The example below shows how to spatial join census tracts with starting points.</p>\n",
    "<p>The <strong>\"op\"</strong> parameter specifies the relationship between the first and second geometric object. The options can be <strong>\"within\", \"contains\" or \"intersects\"</strong>. Pay attention to the sequence of objects and the option when doing spatial join.</p>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We'll use 10000 randomly selected points in this example."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 314,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "start_point_sample = start_point_gdf.sample(10000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 315,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>RxDevice</th>\n",
       "      <th>fileId</th>\n",
       "      <th>TxDevice</th>\n",
       "      <th>firstLatitude</th>\n",
       "      <th>firstLongitude</th>\n",
       "      <th>lastLatitude</th>\n",
       "      <th>lastLongitude</th>\n",
       "      <th>geometry</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3018029</th>\n",
       "      <td>9536</td>\n",
       "      <td>7241519</td>\n",
       "      <td>9536</td>\n",
       "      <td>42.243221</td>\n",
       "      <td>-83.745514</td>\n",
       "      <td>42.282330</td>\n",
       "      <td>-83.732155</td>\n",
       "      <td>POINT (-83.745514 42.24322100000001)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>665590</th>\n",
       "      <td>2620</td>\n",
       "      <td>1382369</td>\n",
       "      <td>2620</td>\n",
       "      <td>42.254864</td>\n",
       "      <td>-83.680885</td>\n",
       "      <td>42.247990</td>\n",
       "      <td>-83.738197</td>\n",
       "      <td>POINT (-83.680885 42.254864)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2877271</th>\n",
       "      <td>11101</td>\n",
       "      <td>6223677</td>\n",
       "      <td>11101</td>\n",
       "      <td>42.493263</td>\n",
       "      <td>-83.409782</td>\n",
       "      <td>42.282360</td>\n",
       "      <td>-83.750946</td>\n",
       "      <td>POINT (-83.40978199999999 42.493263)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1076178</th>\n",
       "      <td>11501</td>\n",
       "      <td>2308176</td>\n",
       "      <td>11501</td>\n",
       "      <td>42.253788</td>\n",
       "      <td>-83.679161</td>\n",
       "      <td>42.316444</td>\n",
       "      <td>-83.648849</td>\n",
       "      <td>POINT (-83.67916099999999 42.253788)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>252066</th>\n",
       "      <td>6659</td>\n",
       "      <td>911988</td>\n",
       "      <td>6659</td>\n",
       "      <td>42.293972</td>\n",
       "      <td>-83.718185</td>\n",
       "      <td>42.322983</td>\n",
       "      <td>-83.840309</td>\n",
       "      <td>POINT (-83.71818499999999 42.293972)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         RxDevice   fileId  TxDevice  firstLatitude  firstLongitude  \\\n",
       "3018029      9536  7241519      9536      42.243221      -83.745514   \n",
       "665590       2620  1382369      2620      42.254864      -83.680885   \n",
       "2877271     11101  6223677     11101      42.493263      -83.409782   \n",
       "1076178     11501  2308176     11501      42.253788      -83.679161   \n",
       "252066       6659   911988      6659      42.293972      -83.718185   \n",
       "\n",
       "         lastLatitude  lastLongitude                              geometry  \n",
       "3018029     42.282330     -83.732155  POINT (-83.745514 42.24322100000001)  \n",
       "665590      42.247990     -83.738197          POINT (-83.680885 42.254864)  \n",
       "2877271     42.282360     -83.750946  POINT (-83.40978199999999 42.493263)  \n",
       "1076178     42.316444     -83.648849  POINT (-83.67916099999999 42.253788)  \n",
       "252066      42.322983     -83.840309  POINT (-83.71818499999999 42.293972)  "
      ]
     },
     "execution_count": 315,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "start_point_sample.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Find trips that start in Washtenaw county."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 316,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "start_in_washtenaw = gpd.sjoin(start_point_sample, washtenaw, op= \"within\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 317,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>RxDevice</th>\n",
       "      <th>fileId</th>\n",
       "      <th>TxDevice</th>\n",
       "      <th>firstLatitude</th>\n",
       "      <th>firstLongitude</th>\n",
       "      <th>lastLatitude</th>\n",
       "      <th>lastLongitude</th>\n",
       "      <th>geometry</th>\n",
       "      <th>index_right</th>\n",
       "      <th>OBJECTID</th>\n",
       "      <th>...</th>\n",
       "      <th>LINK</th>\n",
       "      <th>CNTY_CODE</th>\n",
       "      <th>SQKM</th>\n",
       "      <th>SQMILES</th>\n",
       "      <th>ACRES</th>\n",
       "      <th>VER</th>\n",
       "      <th>LAYOUT</th>\n",
       "      <th>PENINSULA</th>\n",
       "      <th>ShapeSTArea</th>\n",
       "      <th>ShapeSTLength</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3018029</th>\n",
       "      <td>9536</td>\n",
       "      <td>7241519</td>\n",
       "      <td>9536</td>\n",
       "      <td>42.243221</td>\n",
       "      <td>-83.745514</td>\n",
       "      <td>42.282330</td>\n",
       "      <td>-83.732155</td>\n",
       "      <td>POINT (-83.745514 42.24322100000001)</td>\n",
       "      <td>2099</td>\n",
       "      <td>2100</td>\n",
       "      <td>...</td>\n",
       "      <td>161404500</td>\n",
       "      <td>161</td>\n",
       "      <td>3.787</td>\n",
       "      <td>1.462</td>\n",
       "      <td>935.865</td>\n",
       "      <td>17A</td>\n",
       "      <td>portrait</td>\n",
       "      <td>lower</td>\n",
       "      <td>3.787353e+06</td>\n",
       "      <td>8536.074039</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3108384</th>\n",
       "      <td>11101</td>\n",
       "      <td>6227529</td>\n",
       "      <td>11101</td>\n",
       "      <td>42.242775</td>\n",
       "      <td>-83.739403</td>\n",
       "      <td>42.287998</td>\n",
       "      <td>-83.692696</td>\n",
       "      <td>POINT (-83.739403 42.242775)</td>\n",
       "      <td>2099</td>\n",
       "      <td>2100</td>\n",
       "      <td>...</td>\n",
       "      <td>161404500</td>\n",
       "      <td>161</td>\n",
       "      <td>3.787</td>\n",
       "      <td>1.462</td>\n",
       "      <td>935.865</td>\n",
       "      <td>17A</td>\n",
       "      <td>portrait</td>\n",
       "      <td>lower</td>\n",
       "      <td>3.787353e+06</td>\n",
       "      <td>8536.074039</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3985772</th>\n",
       "      <td>2023</td>\n",
       "      <td>8213929</td>\n",
       "      <td>2023</td>\n",
       "      <td>42.243290</td>\n",
       "      <td>-83.742165</td>\n",
       "      <td>42.232075</td>\n",
       "      <td>-83.741516</td>\n",
       "      <td>POINT (-83.742165 42.24329)</td>\n",
       "      <td>2099</td>\n",
       "      <td>2100</td>\n",
       "      <td>...</td>\n",
       "      <td>161404500</td>\n",
       "      <td>161</td>\n",
       "      <td>3.787</td>\n",
       "      <td>1.462</td>\n",
       "      <td>935.865</td>\n",
       "      <td>17A</td>\n",
       "      <td>portrait</td>\n",
       "      <td>lower</td>\n",
       "      <td>3.787353e+06</td>\n",
       "      <td>8536.074039</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>391563</th>\n",
       "      <td>11511</td>\n",
       "      <td>221142</td>\n",
       "      <td>11511</td>\n",
       "      <td>42.254738</td>\n",
       "      <td>-83.751686</td>\n",
       "      <td>42.282795</td>\n",
       "      <td>-83.747162</td>\n",
       "      <td>POINT (-83.75168599999999 42.254738)</td>\n",
       "      <td>2099</td>\n",
       "      <td>2100</td>\n",
       "      <td>...</td>\n",
       "      <td>161404500</td>\n",
       "      <td>161</td>\n",
       "      <td>3.787</td>\n",
       "      <td>1.462</td>\n",
       "      <td>935.865</td>\n",
       "      <td>17A</td>\n",
       "      <td>portrait</td>\n",
       "      <td>lower</td>\n",
       "      <td>3.787353e+06</td>\n",
       "      <td>8536.074039</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4492853</th>\n",
       "      <td>9507</td>\n",
       "      <td>9688949</td>\n",
       "      <td>9507</td>\n",
       "      <td>42.246006</td>\n",
       "      <td>-83.749397</td>\n",
       "      <td>42.235867</td>\n",
       "      <td>-83.727448</td>\n",
       "      <td>POINT (-83.749397 42.246006)</td>\n",
       "      <td>2099</td>\n",
       "      <td>2100</td>\n",
       "      <td>...</td>\n",
       "      <td>161404500</td>\n",
       "      <td>161</td>\n",
       "      <td>3.787</td>\n",
       "      <td>1.462</td>\n",
       "      <td>935.865</td>\n",
       "      <td>17A</td>\n",
       "      <td>portrait</td>\n",
       "      <td>lower</td>\n",
       "      <td>3.787353e+06</td>\n",
       "      <td>8536.074039</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 23 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         RxDevice   fileId  TxDevice  firstLatitude  firstLongitude  \\\n",
       "3018029      9536  7241519      9536      42.243221      -83.745514   \n",
       "3108384     11101  6227529     11101      42.242775      -83.739403   \n",
       "3985772      2023  8213929      2023      42.243290      -83.742165   \n",
       "391563      11511   221142     11511      42.254738      -83.751686   \n",
       "4492853      9507  9688949      9507      42.246006      -83.749397   \n",
       "\n",
       "         lastLatitude  lastLongitude                              geometry  \\\n",
       "3018029     42.282330     -83.732155  POINT (-83.745514 42.24322100000001)   \n",
       "3108384     42.287998     -83.692696          POINT (-83.739403 42.242775)   \n",
       "3985772     42.232075     -83.741516           POINT (-83.742165 42.24329)   \n",
       "391563      42.282795     -83.747162  POINT (-83.75168599999999 42.254738)   \n",
       "4492853     42.235867     -83.727448          POINT (-83.749397 42.246006)   \n",
       "\n",
       "         index_right  OBJECTID      ...            LINK CNTY_CODE   SQKM  \\\n",
       "3018029         2099      2100      ...       161404500       161  3.787   \n",
       "3108384         2099      2100      ...       161404500       161  3.787   \n",
       "3985772         2099      2100      ...       161404500       161  3.787   \n",
       "391563          2099      2100      ...       161404500       161  3.787   \n",
       "4492853         2099      2100      ...       161404500       161  3.787   \n",
       "\n",
       "        SQMILES    ACRES  VER    LAYOUT  PENINSULA   ShapeSTArea ShapeSTLength  \n",
       "3018029   1.462  935.865  17A  portrait      lower  3.787353e+06   8536.074039  \n",
       "3108384   1.462  935.865  17A  portrait      lower  3.787353e+06   8536.074039  \n",
       "3985772   1.462  935.865  17A  portrait      lower  3.787353e+06   8536.074039  \n",
       "391563    1.462  935.865  17A  portrait      lower  3.787353e+06   8536.074039  \n",
       "4492853   1.462  935.865  17A  portrait      lower  3.787353e+06   8536.074039  \n",
       "\n",
       "[5 rows x 23 columns]"
      ]
     },
     "execution_count": 317,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "start_in_washtenaw.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "Plot them on the washtenaw tracts:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 318,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x272da53c8>"
      ]
     },
     "execution_count": 318,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYQAAADvCAYAAADy+aP+AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x272da56a0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "base = washtenaw.plot(color = \"white\", linewidth = 0.5,edgecolor=\"black\")\n",
    "start_in_washtenaw.plot(ax = base,markersize = 1,color=\"red\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h3>Plotting a trip</h3>\n",
    "<p>In the trip summary data, each row represents one trip and only has start and end point locations. To plot a complete trip we need to read in the detailed vehicle activity data (dataset <a href=\"https://github.com/caocscar/ConnectedVehicleDocs/blob/master/BSMdocumentation.md\">documentation</a>). </p>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 465,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>RxDevice</th>\n",
       "      <th>fileId</th>\n",
       "      <th>TxDevice</th>\n",
       "      <th>Gentime</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6512</td>\n",
       "      <td>7125966</td>\n",
       "      <td>6512</td>\n",
       "      <td>323254442760265</td>\n",
       "      <td>43.437309</td>\n",
       "      <td>-83.939384</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6512</td>\n",
       "      <td>7125966</td>\n",
       "      <td>6512</td>\n",
       "      <td>323254442860111</td>\n",
       "      <td>43.437302</td>\n",
       "      <td>-83.939346</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6512</td>\n",
       "      <td>7125966</td>\n",
       "      <td>6512</td>\n",
       "      <td>323254442960170</td>\n",
       "      <td>43.437294</td>\n",
       "      <td>-83.939308</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6512</td>\n",
       "      <td>7125966</td>\n",
       "      <td>6512</td>\n",
       "      <td>323254443060049</td>\n",
       "      <td>43.437290</td>\n",
       "      <td>-83.939270</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6512</td>\n",
       "      <td>7125966</td>\n",
       "      <td>6512</td>\n",
       "      <td>323254443160143</td>\n",
       "      <td>43.437283</td>\n",
       "      <td>-83.939232</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   RxDevice   fileId  TxDevice          Gentime   Latitude  Longitude\n",
       "0      6512  7125966      6512  323254442760265  43.437309 -83.939384\n",
       "1      6512  7125966      6512  323254442860111  43.437302 -83.939346\n",
       "2      6512  7125966      6512  323254442960170  43.437294 -83.939308\n",
       "3      6512  7125966      6512  323254443060049  43.437290 -83.939270\n",
       "4      6512  7125966      6512  323254443160143  43.437283 -83.939232"
      ]
     },
     "execution_count": 465,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "point_df = pd.read_csv(\"TripStart_41728_p038.csv\",header=None,usecols=[0,1,2,3]+[7,8])\n",
    "point_df.columns =['RxDevice','fileId','TxDevice','Gentime','Latitude','Longitude']\n",
    "point_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this dataset each row represents the vehicle's location at that particular moment. Let's merge it with the summary dataset on shared columns to see how many intermediate points a trip has."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 466,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "merge_df=pd.merge(trip_df,point_df,how=\"inner\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 467,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>RxDevice</th>\n",
       "      <th>fileId</th>\n",
       "      <th>TxDevice</th>\n",
       "      <th>firstLatitude</th>\n",
       "      <th>firstLongitude</th>\n",
       "      <th>lastLatitude</th>\n",
       "      <th>lastLongitude</th>\n",
       "      <th>distance</th>\n",
       "      <th>geometry</th>\n",
       "      <th>Gentime</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6512</td>\n",
       "      <td>7125966</td>\n",
       "      <td>6512</td>\n",
       "      <td>43.437309</td>\n",
       "      <td>-83.939384</td>\n",
       "      <td>42.973461</td>\n",
       "      <td>-83.730125</td>\n",
       "      <td>36.72</td>\n",
       "      <td>POINT (-83.93938399999999 43.437309)</td>\n",
       "      <td>323254442760265</td>\n",
       "      <td>43.437309</td>\n",
       "      <td>-83.939384</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6512</td>\n",
       "      <td>7125966</td>\n",
       "      <td>6512</td>\n",
       "      <td>43.437309</td>\n",
       "      <td>-83.939384</td>\n",
       "      <td>42.973461</td>\n",
       "      <td>-83.730125</td>\n",
       "      <td>36.72</td>\n",
       "      <td>POINT (-83.93938399999999 43.437309)</td>\n",
       "      <td>323254442860111</td>\n",
       "      <td>43.437302</td>\n",
       "      <td>-83.939346</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6512</td>\n",
       "      <td>7125966</td>\n",
       "      <td>6512</td>\n",
       "      <td>43.437309</td>\n",
       "      <td>-83.939384</td>\n",
       "      <td>42.973461</td>\n",
       "      <td>-83.730125</td>\n",
       "      <td>36.72</td>\n",
       "      <td>POINT (-83.93938399999999 43.437309)</td>\n",
       "      <td>323254442960170</td>\n",
       "      <td>43.437294</td>\n",
       "      <td>-83.939308</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6512</td>\n",
       "      <td>7125966</td>\n",
       "      <td>6512</td>\n",
       "      <td>43.437309</td>\n",
       "      <td>-83.939384</td>\n",
       "      <td>42.973461</td>\n",
       "      <td>-83.730125</td>\n",
       "      <td>36.72</td>\n",
       "      <td>POINT (-83.93938399999999 43.437309)</td>\n",
       "      <td>323254443060049</td>\n",
       "      <td>43.437290</td>\n",
       "      <td>-83.939270</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6512</td>\n",
       "      <td>7125966</td>\n",
       "      <td>6512</td>\n",
       "      <td>43.437309</td>\n",
       "      <td>-83.939384</td>\n",
       "      <td>42.973461</td>\n",
       "      <td>-83.730125</td>\n",
       "      <td>36.72</td>\n",
       "      <td>POINT (-83.93938399999999 43.437309)</td>\n",
       "      <td>323254443160143</td>\n",
       "      <td>43.437283</td>\n",
       "      <td>-83.939232</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   RxDevice   fileId  TxDevice  firstLatitude  firstLongitude  lastLatitude  \\\n",
       "0      6512  7125966      6512      43.437309      -83.939384     42.973461   \n",
       "1      6512  7125966      6512      43.437309      -83.939384     42.973461   \n",
       "2      6512  7125966      6512      43.437309      -83.939384     42.973461   \n",
       "3      6512  7125966      6512      43.437309      -83.939384     42.973461   \n",
       "4      6512  7125966      6512      43.437309      -83.939384     42.973461   \n",
       "\n",
       "   lastLongitude  distance                              geometry  \\\n",
       "0     -83.730125     36.72  POINT (-83.93938399999999 43.437309)   \n",
       "1     -83.730125     36.72  POINT (-83.93938399999999 43.437309)   \n",
       "2     -83.730125     36.72  POINT (-83.93938399999999 43.437309)   \n",
       "3     -83.730125     36.72  POINT (-83.93938399999999 43.437309)   \n",
       "4     -83.730125     36.72  POINT (-83.93938399999999 43.437309)   \n",
       "\n",
       "           Gentime   Latitude  Longitude  \n",
       "0  323254442760265  43.437309 -83.939384  \n",
       "1  323254442860111  43.437302 -83.939346  \n",
       "2  323254442960170  43.437294 -83.939308  \n",
       "3  323254443060049  43.437290 -83.939270  \n",
       "4  323254443160143  43.437283 -83.939232  "
      ]
     },
     "execution_count": 467,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "merge_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now the merged dataset has all the points we need. We can label the point state."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 468,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def label_point(row):\n",
    "    if (row.Latitude,row.Longitude) == (row.firstLatitude,row.firstLongitude):\n",
    "        return \"start\"\n",
    "    elif (row.Latitude,row.Longitude) == (row.lastLatitude,row.lastLongitude):\n",
    "        return \"end\"\n",
    "    else:\n",
    "        return \"intermediate\"   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 469,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>RxDevice</th>\n",
       "      <th>fileId</th>\n",
       "      <th>TxDevice</th>\n",
       "      <th>firstLatitude</th>\n",
       "      <th>firstLongitude</th>\n",
       "      <th>lastLatitude</th>\n",
       "      <th>lastLongitude</th>\n",
       "      <th>distance</th>\n",
       "      <th>geometry</th>\n",
       "      <th>Gentime</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "      <th>point_label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6512</td>\n",
       "      <td>7125966</td>\n",
       "      <td>6512</td>\n",
       "      <td>43.437309</td>\n",
       "      <td>-83.939384</td>\n",
       "      <td>42.973461</td>\n",
       "      <td>-83.730125</td>\n",
       "      <td>36.72</td>\n",
       "      <td>POINT (-83.93938399999999 43.437309)</td>\n",
       "      <td>323254442760265</td>\n",
       "      <td>43.437309</td>\n",
       "      <td>-83.939384</td>\n",
       "      <td>start</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6512</td>\n",
       "      <td>7125966</td>\n",
       "      <td>6512</td>\n",
       "      <td>43.437309</td>\n",
       "      <td>-83.939384</td>\n",
       "      <td>42.973461</td>\n",
       "      <td>-83.730125</td>\n",
       "      <td>36.72</td>\n",
       "      <td>POINT (-83.93938399999999 43.437309)</td>\n",
       "      <td>323254442860111</td>\n",
       "      <td>43.437302</td>\n",
       "      <td>-83.939346</td>\n",
       "      <td>intermediate</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6512</td>\n",
       "      <td>7125966</td>\n",
       "      <td>6512</td>\n",
       "      <td>43.437309</td>\n",
       "      <td>-83.939384</td>\n",
       "      <td>42.973461</td>\n",
       "      <td>-83.730125</td>\n",
       "      <td>36.72</td>\n",
       "      <td>POINT (-83.93938399999999 43.437309)</td>\n",
       "      <td>323254442960170</td>\n",
       "      <td>43.437294</td>\n",
       "      <td>-83.939308</td>\n",
       "      <td>intermediate</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6512</td>\n",
       "      <td>7125966</td>\n",
       "      <td>6512</td>\n",
       "      <td>43.437309</td>\n",
       "      <td>-83.939384</td>\n",
       "      <td>42.973461</td>\n",
       "      <td>-83.730125</td>\n",
       "      <td>36.72</td>\n",
       "      <td>POINT (-83.93938399999999 43.437309)</td>\n",
       "      <td>323254443060049</td>\n",
       "      <td>43.437290</td>\n",
       "      <td>-83.939270</td>\n",
       "      <td>intermediate</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6512</td>\n",
       "      <td>7125966</td>\n",
       "      <td>6512</td>\n",
       "      <td>43.437309</td>\n",
       "      <td>-83.939384</td>\n",
       "      <td>42.973461</td>\n",
       "      <td>-83.730125</td>\n",
       "      <td>36.72</td>\n",
       "      <td>POINT (-83.93938399999999 43.437309)</td>\n",
       "      <td>323254443160143</td>\n",
       "      <td>43.437283</td>\n",
       "      <td>-83.939232</td>\n",
       "      <td>intermediate</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   RxDevice   fileId  TxDevice  firstLatitude  firstLongitude  lastLatitude  \\\n",
       "0      6512  7125966      6512      43.437309      -83.939384     42.973461   \n",
       "1      6512  7125966      6512      43.437309      -83.939384     42.973461   \n",
       "2      6512  7125966      6512      43.437309      -83.939384     42.973461   \n",
       "3      6512  7125966      6512      43.437309      -83.939384     42.973461   \n",
       "4      6512  7125966      6512      43.437309      -83.939384     42.973461   \n",
       "\n",
       "   lastLongitude  distance                              geometry  \\\n",
       "0     -83.730125     36.72  POINT (-83.93938399999999 43.437309)   \n",
       "1     -83.730125     36.72  POINT (-83.93938399999999 43.437309)   \n",
       "2     -83.730125     36.72  POINT (-83.93938399999999 43.437309)   \n",
       "3     -83.730125     36.72  POINT (-83.93938399999999 43.437309)   \n",
       "4     -83.730125     36.72  POINT (-83.93938399999999 43.437309)   \n",
       "\n",
       "           Gentime   Latitude  Longitude   point_label  \n",
       "0  323254442760265  43.437309 -83.939384         start  \n",
       "1  323254442860111  43.437302 -83.939346  intermediate  \n",
       "2  323254442960170  43.437294 -83.939308  intermediate  \n",
       "3  323254443060049  43.437290 -83.939270  intermediate  \n",
       "4  323254443160143  43.437283 -83.939232  intermediate  "
      ]
     },
     "execution_count": 469,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "merge_df['point_label'] = merge_df.apply (lambda row: label_point (row),axis=1)\n",
    "merge_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's look at the number of points each trip has."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 470,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RxDevice  fileId   TxDevice\n",
       "6512      7125966  6512         18328\n",
       "6518      7223303  6518          7544\n",
       "6565      7716380  6565          4959\n",
       "          7716382  6565          2062\n",
       "          7716383  6565          1331\n",
       "          7716384  6565          3821\n",
       "          7716385  6565          8700\n",
       "          7716386  6565          6340\n",
       "6567      7126620  6567          3250\n",
       "6576      7417845  6576          4990\n",
       "          7417846  6576         20181\n",
       "          7417849  6576          8682\n",
       "          7417851  6576         17625\n",
       "6577      7126818  6577         75024\n",
       "          7126819  6577        183118\n",
       "6583      7640237  6583         24476\n",
       "6589      6951266  6589          8182\n",
       "          6951267  6589         17832\n",
       "6594      7308870  6594         13918\n",
       "6600      7224320  6600          4228\n",
       "          7224321  6600          4370\n",
       "          7224322  6600          1950\n",
       "          7224323  6600          2671\n",
       "          7224324  6600          5804\n",
       "          7224325  6600          6104\n",
       "6604      6789502  6604          8210\n",
       "          6789508  6604          3062\n",
       "          6789512  6604          3060\n",
       "          6789514  6604         10569\n",
       "          6789516  6604         13066\n",
       "6610      7640829  6610          1652\n",
       "          7640831  6610          1236\n",
       "          7640833  6610          2015\n",
       "          7640835  6610          5874\n",
       "          7640837  6610          5679\n",
       "          7640839  6610          6567\n",
       "6623      6853941  6623         16986\n",
       "6626      6350489  6626         11723\n",
       "          6350491  6626          8837\n",
       "          6350497  6626          1648\n",
       "6631      6538294  6631          4056\n",
       "6637      7392658  6637         11795\n",
       "          7392660  6637          4009\n",
       "          7392662  6637          6212\n",
       "          7392664  6637         18523\n",
       "          7392666  6637         11308\n",
       "dtype: int64"
      ]
     },
     "execution_count": 470,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "merge_df.groupby(['RxDevice','fileId','TxDevice']).size()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Use the longest trip as an example, we can plot out the tracts a trip has been through using the spatial join method covered earlier."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 471,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "idx = merge_df.groupby(['RxDevice','fileId','TxDevice']).groups[(6577, 7126819, 6577)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 475,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "trip_sample = merge_df.iloc[idx]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 477,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "trip_point_geometry = [Point(x,y) for x,y in zip(trip_sample.Longitude, trip_sample.Latitude)]\n",
    "trip_points = gpd.GeoDataFrame(trip_sample, geometry=trip_point_geometry,crs={'init': 'epsg:4326'})\n",
    "trip_tracts = gpd.sjoin(mi_census, trip_points, op= \"contains\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Create different layers we want to plot."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 479,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "start_point = trip_points[trip_points['point_label']==\"start\"]\n",
    "end_point = trip_points[trip_points['point_label']==\"end\"]\n",
    "start_tract = trip_tracts[trip_tracts['point_label']==\"start\"].reset_index()\n",
    "end_tract = trip_tracts[trip_tracts['point_label']==\"end\"].reset_index()\n",
    "inter_tracts = trip_tracts[trip_tracts['point_label']==\"intermediate\"].drop_duplicates(\"OBJECTID\")\n",
    "for i,row in inter_tracts.iterrows():\n",
    "    if row['OBJECTID'] == start_tract.at[0,'OBJECTID'] or row['OBJECTID'] == end_tract.at[0,'OBJECTID']:\n",
    "        inter_tracts.drop(i,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 486,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x3617c75f8>"
      ]
     },
     "execution_count": 486,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABIsAAAD4CAYAAABsdmYSAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nEEIIIYQQUf8PM3PF30230wgAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x43b9c6ba8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "base = mi_census.plot(color = \"white\", linewidth = 0.5,edgecolor=\"black\",figsize=(20,20))\n",
    "minx, miny, maxx, maxy = trip_tracts.total_bounds\n",
    "base.set_xlim(minx, maxx)\n",
    "base.set_ylim(miny, maxy)\n",
    "start_tract.plot(ax=base,color=\"lightgreen\")\n",
    "end_tract.plot(ax=base,color=\"blue\")\n",
    "inter_tracts.plot(ax=base,color=\"pink\")\n",
    "trip_points.plot(ax=base,color=\"yellow\",markersize=10)\n",
    "start_point.plot(ax=base,color=\"red\",markersize=100,marker=\"+\")\n",
    "end_point.plot(ax=base,color=\"red\",markersize=100,marker=\"s\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}