04-Intro to Coding with Spatial Data.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "93b0e141-9afd-41e6-a16e-0b3d03d18b73",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "## Geospatial Coding With Cleveland's Open Data Portal\n",
    "**This notebook will teach you the following:**\n",
    "* How to programatically access data using the [ArcGIS Online API for Python](https://developers.arcgis.com/python/latest/).\n",
    "* How to convert that data into a [geopandas GeoDataFrame](https://geopandas.org/en/stable/docs/reference/api/geopandas.GeoDataFrame.html).\n",
    "* How to plot spatial data on a map using the [`.plot`](https://geopandas.org/en/stable/docs/user_guide/mapping.html) function.\n",
    "* How to perform a spatial join using the [`.sjoin`](https://geopandas.org/en/stable/docs/reference/api/geopandas.sjoin.html) function.\n",
    "* Analyze and visualize your data using `geopandas` and `seaborn`."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "cd21478d-f2a1-4de3-88e4-ae6e14abe508",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "#### Step 1: Setup your environment\n",
    "Before you start, you'll the following packages:\n",
    "* [`geopandas`](https://geopandas.org/en/stable/)\n",
    "* [`arcgis`](https://developers.arcgis.com/python/latest/)\n",
    "* [`seaborn`](https://seaborn.pydata.org/index.html)  \n",
    "\n",
    "`geopandas` is a package that allows you to work with spatial data in Python. `geopandas` is built off of the `pandas` package, which is most commonly used data analysis package for Python. `pandas` uses what are called `DataFrames` to store data. [Click here](https://www.w3schools.com/python/pandas/pandas_dataframes.asp) to learn more about `DataFrames`. `geopandas` takes the concept of a `DataFrame` a step further, by introducing what is known as a [`GeoDataFrame`](https://geopandas.org/en/stable/docs/reference/api/geopandas.GeoDataFrame.html). `GeoDataFrames` are capable of storing spatial information (i.e Points, Polygons, and Lines) in addition to other data.\n",
    "\n",
    "`arcgis` is a wrapper for the [ArcGIS Online REST API](https://developers.arcgis.com/rest/). Since Cleveland's Open Data Portal is built on ArcGIS Online, we can use this package to programatically connect to and access data from the service.\n",
    "\n",
    "If you don't already have these packages installed, you can install them using the following code in the command line:  \n",
    "\n",
    "```\n",
    "pip install geopandas\n",
    "pip install arcgis\n",
    "pip install seaborn\n",
    "```  \n",
    "\n",
    "[Click here](https://packaging.python.org/en/latest/tutorials/installing-packages/) to learn more about installing packages in Python."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "e2f3e285-1bcf-42e3-af30-2e4675dc99da",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "data": {
      "application/vnd.databricks.v1+h3_hint": "",
      "text/plain": []
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import geopandas as gpd\n",
    "import arcgis\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "4ff8e2e7-5c13-4f75-97ee-822c18d7c94f",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "#### Step 2: Load in data using the `arcgis` package\n",
    "We will be using two datasets from [Cleveland Open Data](data.clevelandohio.gov) for this analysis:  \n",
    "\n",
    "[**Cleveland Traffic Crashes**](https://data.clevelandohio.gov/datasets/44239d50c4f448dc9789ff4f7739e524_62/explore?location=41.510315%2C-81.727496%2C9.76)\n",
    ">Point layer of all Cleveland crash locations exported from Ohio Department of Transportation (ODOT) GIS Crash Analysis Tool (GCAT).\n",
    "\n",
    "[**Cleveland Neighborhoods**](https://data.clevelandohio.gov/datasets/b2a2da54401a41e78dd71563f01f5273_0/explore?location=41.504856%2C-81.709890%2C11.84)\n",
    ">Reference boundaries of Cleveland neighborhoods, which are also referred to as Statisical Planning Areas (SPAs).\n",
    "\n",
    "As previously mentioned, we will access this data using the [ArcGIS Online API for Python](https://developers.arcgis.com/python/latest/). This will be achieved in 5 steps.\n",
    "\n",
    "First, load in the [*FeatureService*](https://developers.arcgis.com/rest/services-reference/enterprise/feature-service/) for the dataset using the service's REST URL:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "83d5147d-51ca-4f6a-b452-a4025822d888",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<FeatureLayer url:\"https://services3.arcgis.com/dty2kHktVXHrqO8i/arcgis/rest/services/Cleveland_Traffic_Crashes_view/FeatureServer/62\">\n"
     ]
    }
   ],
   "source": [
    "# First we will need the URL to the FeatureService\n",
    "crashes_service_url = \"https://services3.arcgis.com/dty2kHktVXHrqO8i/arcgis/rest/services/Cleveland_Traffic_Crashes_view/FeatureServer/62/\"\n",
    "\n",
    "# Then we will connect to the service using the ArcGIS Online API\n",
    "crashes_featureservice = arcgis.features.FeatureLayer(url=crashes_service_url)\n",
    "print(crashes_featureservice)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "449e473a-9fdf-4431-b063-154d0b99e93c",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "Query the *FeatureService* to access its underlying data. In ArcGIS, this data structure is called a [*FeatureSet*](https://developers.arcgis.com/rest/services-reference/enterprise/featureset-object/), which is a collection of [*Features*](https://developers.arcgis.com/rest/services-reference/enterprise/feature-object/):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "2190b915-612e-4c0c-ab25-3463bc010c9e",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "IOStream.flush timed out\n"
     ]
    }
   ],
   "source": [
    "# Once we've connected to the FeatureService, we can query it to get the actual data.\n",
    "crashes_featureset = crashes_featureservice.query()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "3ac21a85-0b8c-4576-b3fb-d236b284c805",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "Extract the [*Coordinate Reference System*](https://en.wikipedia.org/wiki/Spatial_reference_system) (CRS) from the *FeatureSet*. This will allow for us to know *how* the data is mapped on the Earth's surface:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "8b8db2c1-4a5e-44ef-b362-1dfa1bca704f",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The EPSG ID of the CRS is 3734\n"
     ]
    }
   ],
   "source": [
    "# Let's get the Coordinate Reference System (CRS) from the above FeatureSet\n",
    "crashes_crs = crashes_featureset.spatial_reference['latestWkid']\n",
    "print(f\"The EPSG ID of the CRS is {crashes_crs}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "157b1af6-ff3e-4549-a8b7-3cefcb64fb47",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "Extract a `DataFrame` from the *FeatureSet* using the *FeatureSet*'s `.sdf` property:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "bce1e7c9-0f45-43da-ba77-e2f8691e5be4",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\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>DOCUMENT_NBR</th>\n",
       "      <th>CRASH_YR</th>\n",
       "      <th>CRASH_MONTH_YEAR</th>\n",
       "      <th>DISTRICT_NBR</th>\n",
       "      <th>NLFID</th>\n",
       "      <th>NLF_JUR_CD</th>\n",
       "      <th>NLF_COUNTY_CD</th>\n",
       "      <th>COUNTY_LOG_NBR</th>\n",
       "      <th>ODOT_LATITUDE_NBR</th>\n",
       "      <th>ODOT_LONGITUDE_NBR</th>\n",
       "      <th>ODOT_FIPS_CD</th>\n",
       "      <th>AREA_CODE</th>\n",
       "      <th>CRASH_DATE</th>\n",
       "      <th>CRASH_SEVERITY_CD</th>\n",
       "      <th>CRASH_TYPE_CD</th>\n",
       "      <th>DAY_IN_WEEK_CD</th>\n",
       "      <th>DISTRACTED_DRIVER_IND</th>\n",
       "      <th>FACILITY_TYPE_CD</th>\n",
       "      <th>FHWA_RDWY_DEPARTURE_IND</th>\n",
       "      <th>FREEWAY_IND</th>\n",
       "      <th>FUNCTIONAL_CLASS_CD</th>\n",
       "      <th>HOUR_OF_CRASH</th>\n",
       "      <th>INCAPAC_INJURIES_NBR</th>\n",
       "      <th>INTERCHANGE_ID</th>\n",
       "      <th>INTERSECTION_ID_CURRENT</th>\n",
       "      <th>INTERSECTION_LEG_ID</th>\n",
       "      <th>INTERSTATE_IND</th>\n",
       "      <th>INV_LOG_NBR</th>\n",
       "      <th>INV_NLFID</th>\n",
       "      <th>IS_COMMERCIAL_RELATED</th>\n",
       "      <th>LIGHT_COND_PRIMARY_CD</th>\n",
       "      <th>LOCAL_REPORT_NUMBER_ID</th>\n",
       "      <th>MAINTENANCE_AUTHORITY_CD</th>\n",
       "      <th>MONTH_OF_CRASH</th>\n",
       "      <th>NHS_CD</th>\n",
       "      <th>NO_INJURY_REPORTED_NBR</th>\n",
       "      <th>NON_INCAPAC_INJURIES_NBR</th>\n",
       "      <th>NUMBER_OF_UNITS_NBR</th>\n",
       "      <th>ODOT_CITY_VILLAGE_TWP_NME</th>\n",
       "      <th>...</th>\n",
       "      <th>U1_TRAFFIC_CONTROL_CD</th>\n",
       "      <th>U1_TURN_CD</th>\n",
       "      <th>U1_TYPE_OF_UNIT_CD</th>\n",
       "      <th>U1_UNIT_SPEED_NBR</th>\n",
       "      <th>U2_AGE_NBR</th>\n",
       "      <th>U2_CONT_CIR_PRIMARY_CD</th>\n",
       "      <th>U2_DIRECTION_FROM_CD</th>\n",
       "      <th>U2_DIRECTION_TO_CD</th>\n",
       "      <th>U2_DISTRACTED_BY_1_CD</th>\n",
       "      <th>U2_GENDER_CD</th>\n",
       "      <th>U2_NON_MOTORIST_LOC_CD</th>\n",
       "      <th>U2_ODPS_UNIT_NBR</th>\n",
       "      <th>U2_POSTED_SPEED_NBR</th>\n",
       "      <th>U2_PRECRASH_ACTION_CD</th>\n",
       "      <th>U2_SEQ_OF_EVENTS_1_CD</th>\n",
       "      <th>U2_SEQ_OF_EVENTS_2_CD</th>\n",
       "      <th>U2_SEQ_OF_EVENTS_3_CD</th>\n",
       "      <th>U2_SEQ_OF_EVENTS_4_CD</th>\n",
       "      <th>U2_SEQ_OF_EVENTS_5_CD</th>\n",
       "      <th>U2_SEQ_OF_EVENTS_6_CD</th>\n",
       "      <th>U2_SPECIAL_FUNCTION_CD</th>\n",
       "      <th>U2_TRAFFIC_CONTROL_CD</th>\n",
       "      <th>U2_TURN_CD</th>\n",
       "      <th>U2_TYPE_OF_UNIT_CD</th>\n",
       "      <th>U2_UNIT_SPEED_NBR</th>\n",
       "      <th>U3_CONT_CIR_PRIMARY_CD</th>\n",
       "      <th>U3_ODPS_UNIT_NBR</th>\n",
       "      <th>U3_PRECRASH_ACTION_CD</th>\n",
       "      <th>U3_SEQ_OF_EVENTS_1_CD</th>\n",
       "      <th>U3_SEQ_OF_EVENTS_2_CD</th>\n",
       "      <th>U3_SEQ_OF_EVENTS_3_CD</th>\n",
       "      <th>U3_SEQ_OF_EVENTS_4_CD</th>\n",
       "      <th>U3_SEQ_OF_EVENTS_5_CD</th>\n",
       "      <th>U3_SEQ_OF_EVENTS_6_CD</th>\n",
       "      <th>U3_SPECIAL_FUNCTION_CD</th>\n",
       "      <th>U3_TRAFFIC_CONTROL_CD</th>\n",
       "      <th>U3_TYPE_OF_UNIT_CD</th>\n",
       "      <th>UNRESTRAIN_OCCUPANTS</th>\n",
       "      <th>WEATHER_COND_CD</th>\n",
       "      <th>SHAPE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>20174001939.0</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>1/1/2017 12:00:00 AM</td>\n",
       "      <td>12.0</td>\n",
       "      <td>CCUYCR00398**C</td>\n",
       "      <td>C</td>\n",
       "      <td>CUY</td>\n",
       "      <td>0.844</td>\n",
       "      <td>41.451878</td>\n",
       "      <td>-81.621368</td>\n",
       "      <td>16000</td>\n",
       "      <td>17668</td>\n",
       "      <td>1/19/2017 12:00:00 AM</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>N</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>N</td>\n",
       "      <td>N</td>\n",
       "      <td>4.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>97fca815-7530-4e41-89fc-f3d30d184b47</td>\n",
       "      <td>5603e287-f6d5-46d4-b8f1-de3082166e10</td>\n",
       "      <td>N</td>\n",
       "      <td>0.844</td>\n",
       "      <td>CCUYCR00398**C</td>\n",
       "      <td>Y</td>\n",
       "      <td>1.0</td>\n",
       "      <td>00912</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>CLEVELAND</td>\n",
       "      <td>...</td>\n",
       "      <td>6.0</td>\n",
       "      <td>NT</td>\n",
       "      <td>19.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>55.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>F</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>1.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>4.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>NT</td>\n",
       "      <td>19.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>{\"x\": 2209355.6854842156, \"y\": 651613.02818214...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>20174001941.0</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>1/1/2017 12:00:00 AM</td>\n",
       "      <td>12.0</td>\n",
       "      <td>CCUYCR00721**C</td>\n",
       "      <td>C</td>\n",
       "      <td>CUY</td>\n",
       "      <td>0.579</td>\n",
       "      <td>41.499732</td>\n",
       "      <td>-81.680842</td>\n",
       "      <td>16000</td>\n",
       "      <td>17668</td>\n",
       "      <td>1/20/2017 12:00:00 AM</td>\n",
       "      <td>3.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>N</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>N</td>\n",
       "      <td>N</td>\n",
       "      <td>5.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>5fe1d5c8-fa09-4373-8d94-334e1fd2392d</td>\n",
       "      <td>58b206d5-f2d5-4b30-b01a-2d379cf3a123</td>\n",
       "      <td>N</td>\n",
       "      <td>0.579</td>\n",
       "      <td>CCUYCR00721**C</td>\n",
       "      <td>Y</td>\n",
       "      <td>2.0</td>\n",
       "      <td>00911</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>CLEVELAND</td>\n",
       "      <td>...</td>\n",
       "      <td>2.0</td>\n",
       "      <td>NT</td>\n",
       "      <td>23.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>48.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>M</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>1.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>LT</td>\n",
       "      <td>15.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>{\"x\": 2192889.1357402205, \"y\": 668889.97066231...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>20174001952.0</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>1/1/2017 12:00:00 AM</td>\n",
       "      <td>12.0</td>\n",
       "      <td>CCUYCR00009**C</td>\n",
       "      <td>C</td>\n",
       "      <td>CUY</td>\n",
       "      <td>4.978</td>\n",
       "      <td>41.536373</td>\n",
       "      <td>-81.620804</td>\n",
       "      <td>16000</td>\n",
       "      <td>17668</td>\n",
       "      <td>1/15/2017 12:00:00 AM</td>\n",
       "      <td>3.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>N</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>Y</td>\n",
       "      <td>N</td>\n",
       "      <td>4.0</td>\n",
       "      <td>21.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>ac3b359f-342c-4419-a6c3-408eb5bb9f2a</td>\n",
       "      <td>d182e433-67d6-4712-8b92-38e8c7f883f1</td>\n",
       "      <td>N</td>\n",
       "      <td>4.978</td>\n",
       "      <td>CCUYCR00009**C</td>\n",
       "      <td>N</td>\n",
       "      <td>3.0</td>\n",
       "      <td>00914</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>CLEVELAND</td>\n",
       "      <td>...</td>\n",
       "      <td>6.0</td>\n",
       "      <td>NT</td>\n",
       "      <td>23.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>56.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>M</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>1.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>44.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>1.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>LT</td>\n",
       "      <td>3.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>{\"x\": 2209199.9312025607, \"y\": 682400.34685672...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>20174001969.0</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>1/1/2017 12:00:00 AM</td>\n",
       "      <td>12.0</td>\n",
       "      <td>SCUYUS00322**C</td>\n",
       "      <td>S</td>\n",
       "      <td>CUY</td>\n",
       "      <td>0.86</td>\n",
       "      <td>41.503394</td>\n",
       "      <td>-81.678955</td>\n",
       "      <td>16000</td>\n",
       "      <td>17668</td>\n",
       "      <td>1/24/2017 12:00:00 AM</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>N</td>\n",
       "      <td>2.0</td>\n",
       "      <td>N</td>\n",
       "      <td>N</td>\n",
       "      <td>3.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>503a8f60-7e92-4a56-9913-998a5d3ae7e2</td>\n",
       "      <td>62b5f64e-baf8-48c0-afb7-4729fee60f5a</td>\n",
       "      <td>N</td>\n",
       "      <td>0.86</td>\n",
       "      <td>SCUYUS00322**C</td>\n",
       "      <td>N</td>\n",
       "      <td>1.0</td>\n",
       "      <td>00942</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>N</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>CLEVELAND</td>\n",
       "      <td>...</td>\n",
       "      <td>2.0</td>\n",
       "      <td>NT</td>\n",
       "      <td>99.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>66.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>F</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>1.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>1.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>NT</td>\n",
       "      <td>3.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>{\"x\": 2193393.4559258074, \"y\": 670229.09298406...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>20174001970.0</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>1/1/2017 12:00:00 AM</td>\n",
       "      <td>12.0</td>\n",
       "      <td>CCUYCR00009**C</td>\n",
       "      <td>C</td>\n",
       "      <td>CUY</td>\n",
       "      <td>5.765</td>\n",
       "      <td>41.540792</td>\n",
       "      <td>-81.607019</td>\n",
       "      <td>16000</td>\n",
       "      <td>17668</td>\n",
       "      <td>1/23/2017 12:00:00 AM</td>\n",
       "      <td>5.0</td>\n",
       "      <td>19.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>N</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>N</td>\n",
       "      <td>N</td>\n",
       "      <td>4.0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>f8e1afec-0a14-40dd-ac7b-66b664bb2e8e</td>\n",
       "      <td>eecbdef6-adf7-4adf-95a5-d74b65171c72</td>\n",
       "      <td>N</td>\n",
       "      <td>5.765</td>\n",
       "      <td>CCUYCR00009**C</td>\n",
       "      <td>Y</td>\n",
       "      <td>1.0</td>\n",
       "      <td>00934</td>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>CLEVELAND</td>\n",
       "      <td>...</td>\n",
       "      <td>6.0</td>\n",
       "      <td>RT</td>\n",
       "      <td>5.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>82.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>F</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>1.0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>1.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>NT</td>\n",
       "      <td>1.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>&lt;NA&gt;</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>{\"x\": 2212957.254068464, \"y\": 684048.772037565...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 149 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   OBJECTID  ...                                              SHAPE\n",
       "0         1  ...  {\"x\": 2209355.6854842156, \"y\": 651613.02818214...\n",
       "1         2  ...  {\"x\": 2192889.1357402205, \"y\": 668889.97066231...\n",
       "2         3  ...  {\"x\": 2209199.9312025607, \"y\": 682400.34685672...\n",
       "3         4  ...  {\"x\": 2193393.4559258074, \"y\": 670229.09298406...\n",
       "4         5  ...  {\"x\": 2212957.254068464, \"y\": 684048.772037565...\n",
       "\n",
       "[5 rows x 149 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Lastly, lets get the DataFrame from the FeatureSet, this is contained in the .sdf property of the FeatureSet. \n",
    "crashes_sdf = crashes_featureset.sdf\n",
    "crashes_sdf.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "bce32e41-5e27-4e1a-95d5-f8bfc7a9e9ce",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "Convert the `DataFrame` into a `GeoDataFrame`, using the `DataFrame` from the previous step, alongside the *CRS* from two steps ago. We will also only select the columns we need for later analysis."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "55935220-319e-477e-9d88-06f607521ac7",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\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>CRASH_YR</th>\n",
       "      <th>FUNCTIONAL_CLASS_CD</th>\n",
       "      <th>geometry</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>POINT (2209355.685 651613.028)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>POINT (2192889.136 668889.971)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>POINT (2209199.931 682400.347)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>POINT (2193393.456 670229.093)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>POINT (2212957.254 684048.772)</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   OBJECTID  CRASH_YR  FUNCTIONAL_CLASS_CD                        geometry\n",
       "0         1    2017.0                  4.0  POINT (2209355.685 651613.028)\n",
       "1         2    2017.0                  5.0  POINT (2192889.136 668889.971)\n",
       "2         3    2017.0                  4.0  POINT (2209199.931 682400.347)\n",
       "3         4    2017.0                  3.0  POINT (2193393.456 670229.093)\n",
       "4         5    2017.0                  4.0  POINT (2212957.254 684048.772)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# We will then convert the DataFrame to a GeoDataFrame, so we can perform spatial analysis with geopandas.\n",
    "columns = ['OBJECTID','CRASH_YR','FUNCTIONAL_CLASS_CD','geometry']\n",
    "crashes_gdf = gpd.GeoDataFrame(data=crashes_sdf,\n",
    "                               geometry=crashes_sdf.SHAPE,\n",
    "                               crs=crashes_crs)[columns] # Only grab the columns we define above\n",
    "crashes_gdf.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "de5287ee-2e8f-408a-a93b-6cb234f7c020",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "Now we will repeat this process for the Neighborhoods dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "077348e7-40cf-453f-bd18-6d64d9a974be",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>SPANM</th>\n",
       "      <th>geometry</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>North Shore Collinwood</td>\n",
       "      <td>MULTIPOLYGON (((2228297.801 705482.512, 222832...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Collinwood-Nottingham</td>\n",
       "      <td>MULTIPOLYGON (((2217876.552 692522.199, 221897...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Euclid-Green</td>\n",
       "      <td>MULTIPOLYGON (((2227403.225 691768.527, 222742...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Glenville</td>\n",
       "      <td>MULTIPOLYGON (((2217208.150 688382.125, 221724...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>St.Clair-Superior</td>\n",
       "      <td>MULTIPOLYGON (((2205138.324 684299.803, 220515...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                    SPANM                                           geometry\n",
       "0  North Shore Collinwood  MULTIPOLYGON (((2228297.801 705482.512, 222832...\n",
       "1   Collinwood-Nottingham  MULTIPOLYGON (((2217876.552 692522.199, 221897...\n",
       "2            Euclid-Green  MULTIPOLYGON (((2227403.225 691768.527, 222742...\n",
       "3               Glenville  MULTIPOLYGON (((2217208.150 688382.125, 221724...\n",
       "4       St.Clair-Superior  MULTIPOLYGON (((2205138.324 684299.803, 220515..."
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Now, repeat the above process for Neighborhoods\n",
    "neighborhoods_service_url = \"https://www.clevelandgis.org/arcgis/rest/services/ReferenceLayers/SPA/FeatureServer/0\"\n",
    "neighborhoods_featureservice = arcgis.features.FeatureLayer(neighborhoods_service_url)\n",
    "neighborhoods_featureset = neighborhoods_featureservice.query()\n",
    "neighborhoods_crs = neighborhoods_featureset.spatial_reference['latestWkid']\n",
    "neighborhoods_sdf = neighborhoods_featureset.sdf\n",
    "neighborhoods_gdf = gpd.GeoDataFrame(data=neighborhoods_sdf,\n",
    "                                     geometry=neighborhoods_sdf.SHAPE,\n",
    "                                     crs=neighborhoods_crs)[['SPANM','geometry']] # Only select neighborhood name and the geometry\n",
    "neighborhoods_gdf['geometry'] = neighborhoods_gdf.make_valid()\n",
    "neighborhoods_gdf.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "f19639f8-995c-42a1-8fec-7206d211c471",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "Now that we've loaded in the data, we can plot it on a map using the `GeoDataFrame.plot()` function. This allows us to quickly visualize our data and make sure we loaded everything in correctly."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "c9d11154-e153-4eba-87cc-cb90c3b90adf",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: >"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Let's plot the data we just retreived, since there are hundreds of thousands of records, we will only map the first 100.\n",
    "base_plot = neighborhoods_gdf.plot(color='white',\n",
    "                                   edgecolor='black')\n",
    "crashes_gdf.head(100).plot(ax=base_plot,\n",
    "                           color='red',\n",
    "                           markersize=5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "61e5f7e6-8916-4ff6-a8e6-ec03ab577dd0",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "#### Step 3: Perform a spatial join between crashes and neighborhoods\n",
    "Say we want to know how many crashes happen in each neighborhood. Currently, the `crashes_gdf` GeoDataFrame does not contain any information about what neighborhood it's in. Furthermore, the `neighborhoods_gdf` doesn't have any information about the number of crashes in each neighborhood. Therefore, we have to combine these datasets together using what is known as a [*spatial join*](https://en.wikipedia.org/wiki/Spatial_join).  \n",
    "\n",
    "With `geopandas`, we can perform a spatial join using the [`geopandas.sjoin()`](https://geopandas.org/en/stable/docs/reference/api/geopandas.sjoin.html) function. The `sjoin` function works similarly to a standard table join. We input two `GeoDataFrames` that we want to join together as either a *left*, *right*, or *inner* join. \n",
    "\n",
    "Next, we define the *predicate* we want to use for the join. The *predicate* is effectively the spatial operation we use to link the two datasets together. In the case of this example, we want to know how many crashes are *inside* each neighborhood. Therefore, we will use the *contains* predicate. The *contains* predicate will only join a crash point to a neighborhood polygon if it is completely inside the neighborhood polygon.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "4836cdf0-7e3b-43fa-bb78-4f07e5b77e5d",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>SPANM</th>\n",
       "      <th>geometry</th>\n",
       "      <th>index_right</th>\n",
       "      <th>OBJECTID</th>\n",
       "      <th>CRASH_YR</th>\n",
       "      <th>FUNCTIONAL_CLASS_CD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>North Shore Collinwood</td>\n",
       "      <td>MULTIPOLYGON (((2228297.801 705482.512, 222832...</td>\n",
       "      <td>7154</td>\n",
       "      <td>7155</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>North Shore Collinwood</td>\n",
       "      <td>MULTIPOLYGON (((2228297.801 705482.512, 222832...</td>\n",
       "      <td>126967</td>\n",
       "      <td>126968</td>\n",
       "      <td>2016.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>North Shore Collinwood</td>\n",
       "      <td>MULTIPOLYGON (((2228297.801 705482.512, 222832...</td>\n",
       "      <td>152275</td>\n",
       "      <td>310661</td>\n",
       "      <td>2022.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>North Shore Collinwood</td>\n",
       "      <td>MULTIPOLYGON (((2228297.801 705482.512, 222832...</td>\n",
       "      <td>130754</td>\n",
       "      <td>130755</td>\n",
       "      <td>2016.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>North Shore Collinwood</td>\n",
       "      <td>MULTIPOLYGON (((2228297.801 705482.512, 222832...</td>\n",
       "      <td>113359</td>\n",
       "      <td>113360</td>\n",
       "      <td>2015.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                    SPANM  ... FUNCTIONAL_CLASS_CD\n",
       "0  North Shore Collinwood  ...                 1.0\n",
       "0  North Shore Collinwood  ...                 1.0\n",
       "0  North Shore Collinwood  ...                 1.0\n",
       "0  North Shore Collinwood  ...                 1.0\n",
       "0  North Shore Collinwood  ...                 1.0\n",
       "\n",
       "[5 rows x 6 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Perform the spatial join with `.sjoin` method of geopandas\n",
    "crash_neighborhood_join = gpd.sjoin(left_df=neighborhoods_gdf,\n",
    "                                    right_df=crashes_gdf,\n",
    "                                    how='left',\n",
    "                                    predicate='contains')\n",
    "\n",
    "crash_neighborhood_join.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "3743aa27-3c0c-40be-9d16-dc3ebc296480",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "#### Step 4: Map the data by neighborhood\n",
    "Now that we've spatially joined the crashes dataset to the neighborhoods dataset, we can begin to answer the question \"how many crashes occurred in each neighborhood\". One good way to approach this question is through creating a [choropleth map](https://venngage.com/blog/choropleth-map/#:~:text=A%20choropleth%20map%20is%20a,relation%20to%20a%20data%20variable.). Choropleth maps are commonly used to represent numeric data in a geographic space.  \n",
    "\n",
    "Before we create the choropleth, we have to organize our data by neighborhood. We can achieve this by using the `DataFrame.groupby()`, and then the `.count()` function.  \n",
    "\n",
    "*Note*: When you use `groupby()` on a `GeoDataFrame`, the `GeoDataFrame` will be converted back to a regular pandas `DataFrame`. Therefore, we have to \"re-convert\" the `DataFrame` back into a `GeoDataFrame`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "62340283-ff1f-4f3b-9f81-84c3b5785034",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>SPANM</th>\n",
       "      <th>geometry</th>\n",
       "      <th>index_right</th>\n",
       "      <th>OBJECTID</th>\n",
       "      <th>CRASH_YR</th>\n",
       "      <th>FUNCTIONAL_CLASS_CD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Bellaire-Puritas</td>\n",
       "      <td>MULTIPOLYGON (((2166865.373 648881.199, 216750...</td>\n",
       "      <td>6235</td>\n",
       "      <td>6235</td>\n",
       "      <td>6235</td>\n",
       "      <td>5926</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Broadway-Slavic Village</td>\n",
       "      <td>MULTIPOLYGON (((2200991.024 662326.916, 220100...</td>\n",
       "      <td>7882</td>\n",
       "      <td>7882</td>\n",
       "      <td>7882</td>\n",
       "      <td>7464</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Brooklyn Centre</td>\n",
       "      <td>MULTIPOLYGON (((2189462.787 655578.785, 218936...</td>\n",
       "      <td>5372</td>\n",
       "      <td>5372</td>\n",
       "      <td>5372</td>\n",
       "      <td>5168</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Buckeye-Shaker Square</td>\n",
       "      <td>MULTIPOLYGON (((2214621.091 667218.541, 221679...</td>\n",
       "      <td>3180</td>\n",
       "      <td>3180</td>\n",
       "      <td>3180</td>\n",
       "      <td>2937</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Buckeye-Woodhill</td>\n",
       "      <td>MULTIPOLYGON (((2214257.275 663095.179, 221426...</td>\n",
       "      <td>2327</td>\n",
       "      <td>2327</td>\n",
       "      <td>2327</td>\n",
       "      <td>2203</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     SPANM  ... FUNCTIONAL_CLASS_CD\n",
       "0         Bellaire-Puritas  ...                5926\n",
       "1  Broadway-Slavic Village  ...                7464\n",
       "2          Brooklyn Centre  ...                5168\n",
       "3    Buckeye-Shaker Square  ...                2937\n",
       "4         Buckeye-Woodhill  ...                2203\n",
       "\n",
       "[5 rows x 6 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "neighborhoods_aggregated = crash_neighborhood_join.groupby(['SPANM','geometry'],\n",
    "                                                            as_index=False).count() # Get the count of rows for each neighborhood group\n",
    "neighborhoods_counts_gdf = gpd.GeoDataFrame(data=neighborhoods_aggregated,\n",
    "                                             geometry='geometry')\n",
    "neighborhoods_counts_gdf.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {},
     "inputWidgets": {},
     "nuid": "03fd4143-8920-44f5-a330-f62315789a39",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "Now that we've prepped our data, we can create a choropleth map using the [`GeoDataFrame.plot()`](https://geopandas.org/en/stable/docs/user_guide/mapping.html) function."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "96a5ea66-1b6e-4c3c-8a35-beb596010b3a",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: >"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "neighborhoods_counts_gdf.plot(column=\"index_right\", legend=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {},
     "inputWidgets": {},
     "nuid": "088957f0-6d27-44c6-ad9d-79f0cf9f458e",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "Based on the results from the choropleth, we can see that Downtown experiences the most crashes."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {},
     "inputWidgets": {},
     "nuid": "f635e9e1-f9f1-436b-9f46-2f1d2508a58c",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "#### Step 5: Plot trends in data over time\n",
    "Since we know which crashes happened in which neighborhood, we can perform some additional analysis on the data. Let's say we want to learn more about how trends in crash frequency has changed over time. We can use the `seaborn` package to easily visualize this information on a line chart.  \n",
    "\n",
    "Before we visualize the data, we need to prepare it into the appropriate shape. We will do this in the following steps:\n",
    "1. Filter for records where `FUNCTIONAL_CLASS_CD != 1`. The `FUNCTIONAL_CLASS_CD` column represents the type of road on which the crash occurred. In this case, we are only interested in crashes that ocurred on local streets. A `FUNCTIONAL_CLASS_CD` value of 1 means that the street is a highway. Therefore, we want to filter out these records.\n",
    "2. Group the data by the year and neighborhood in which the crash ocurred. This is done with the `CRASH_YR` and `SPANM` columns respectively. \n",
    "3. Count the number of records in each group."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "3b232912-57b3-4832-a6de-e9060aaa43b8",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>CRASH_YR</th>\n",
       "      <th>SPANM</th>\n",
       "      <th>geometry</th>\n",
       "      <th>index_right</th>\n",
       "      <th>OBJECTID</th>\n",
       "      <th>FUNCTIONAL_CLASS_CD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2012.0</td>\n",
       "      <td>Bellaire-Puritas</td>\n",
       "      <td>266</td>\n",
       "      <td>266</td>\n",
       "      <td>266</td>\n",
       "      <td>266</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2012.0</td>\n",
       "      <td>Broadway-Slavic Village</td>\n",
       "      <td>354</td>\n",
       "      <td>354</td>\n",
       "      <td>354</td>\n",
       "      <td>354</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2012.0</td>\n",
       "      <td>Brooklyn Centre</td>\n",
       "      <td>223</td>\n",
       "      <td>223</td>\n",
       "      <td>223</td>\n",
       "      <td>223</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2012.0</td>\n",
       "      <td>Buckeye-Shaker Square</td>\n",
       "      <td>178</td>\n",
       "      <td>178</td>\n",
       "      <td>178</td>\n",
       "      <td>178</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2012.0</td>\n",
       "      <td>Buckeye-Woodhill</td>\n",
       "      <td>147</td>\n",
       "      <td>147</td>\n",
       "      <td>147</td>\n",
       "      <td>147</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   CRASH_YR                    SPANM  ...  OBJECTID  FUNCTIONAL_CLASS_CD\n",
       "0    2012.0         Bellaire-Puritas  ...       266                  266\n",
       "1    2012.0  Broadway-Slavic Village  ...       354                  354\n",
       "2    2012.0          Brooklyn Centre  ...       223                  223\n",
       "3    2012.0    Buckeye-Shaker Square  ...       178                  178\n",
       "4    2012.0         Buckeye-Woodhill  ...       147                  147\n",
       "\n",
       "[5 rows x 6 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "neighborhood_analysis =(\n",
    "# Filter for crashes not occuring on interstates irrelevant to local context\n",
    "crash_neighborhood_join[crash_neighborhood_join[\"FUNCTIONAL_CLASS_CD\"] != 1]\\\n",
    ".groupby([\"CRASH_YR\",'SPANM'], as_index=False)\\\n",
    ".count()\n",
    ")\n",
    "\n",
    "neighborhood_analysis.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {},
     "inputWidgets": {},
     "nuid": "9cdb6436-9475-4fbe-981f-51b4c091a349",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "For the sake of simplicity, we will only look at the trends for 3 specific neighborhoods: Downtown, Glenville, and Old Brooklyn."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "aa627ac4-fdb8-46d9-b8d3-925027042bff",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [],
   "source": [
    "focus_df = neighborhood_analysis[neighborhood_analysis['SPANM'].isin(['Downtown', 'Glenville', 'Old Brooklyn'])]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {},
     "inputWidgets": {},
     "nuid": "ccd6ef47-1119-4cb2-847c-cbbaeadaef12",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "Now that we've prepped the data, we can plot it using the [`seaborn.lineplot()`](https://seaborn.pydata.org/generated/seaborn.lineplot.html) function. We will tune the chart using the following parameters:\n",
    "1. `data = focus_df`, this is the dataset we want to build the chart off of.\n",
    "2. `x='CRASH_YEAR'` is the column that will create the X axis. In this case, it is the year the crash ocurred.\n",
    "3. `y='OBJECTID'` is the column that will create the Y axis. In this case, it is the count of crashes that ocurred. Since we used `groupby` and `count` earlier in the process, the `OBJECTID` column is an aggregated count of all crashes by year and neighborhood.\n",
    "4. `hue='SPANM'` is the value by which each line will be colored. In this case, it is the neighborhood in which each crash ocurred."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "a5b7b306-4a77-4745-837e-4f8a43475276",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='CRASH_YR', ylabel='OBJECTID'>"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.lineplot(data=focus_df,\n",
    "             x='CRASH_YR',\n",
    "             y='OBJECTID',\n",
    "             hue='SPANM')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {},
     "inputWidgets": {},
     "nuid": "d004e80d-363b-4013-a6c7-960ec6c99cdd",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "Based on the results of the analysis, we can see that crashes were increasing across the board from 2012 to 2020. Then, when COVID hit, crashes both in Downtown and Old Brooklyn plummeted. However, in Glenville, the number of crashes actually increased. Since then, crash numbers have generally increased back to or beyond pre-pandemic levels. I think there are some interesting questions that come from these results:\n",
    "1. Why did crashes in Glenville increase during COVID? And why did they fall between 2021 and 2022?\n",
    "2. Why have crashes Downtown increased significantly post-COVID?"
   ]
  }
 ],
 "metadata": {
  "application/vnd.databricks.v1+notebook": {
   "dashboards": [],
   "environmentMetadata": null,
   "language": "python",
   "notebookMetadata": {
    "pythonIndentUnit": 4
   },
   "notebookName": "Intro to Coding with Spatial Data",
   "widgets": {}
  },
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}