Quick and dirty geocoding and mapping of KAP Project metadata

kap-geocoding.ipynb

{
 "metadata": {
  "name": "kap-geocoding"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "from csv import DictReader\nfrom geopy import geocoders\nimport geojson\nimport requests\n\n# Use data from KAP Project master spreadsheet\u2014exported as CSV\nkap_metadata = '/Users/libraries/Code/kap-data/KAP.Metadata-master.csv'\n\n# Set up a connection to a geocoding web service \u2014 in this case, Geonames\ngn = geocoders.GeoNames(username='trevormunoz')\n\nplaces = {}\nwith open(kap_metadata, 'rU') as csvfile:\n    reader = DictReader(csvfile)\n    for row in reader:\n        # Skip rows with no geographic information\n        if row['Settlement (City)'] is not '':\n            places[\"{0}, {1}, {2}, {3}\".format(row['Settlement (City)'], row['Region (State)'], row['Country'], row['Continent'])] = 0\n  \n\n#print(\"{0} places found in the data set\".format(len(places.keys())))\nfeature_list = []\n\n# Send each string representing a place to the geocoding service.\nfor p in places.keys():\n    try:\n        name, coords = gn.geocode(p)\n        \n        # Need to flip Lat and Long to render correctly as GeoJSON, \n        # see: http://gis.stackexchange.com/questions/54065/leaflet-geojson-coordinate-problem\n        geoJSON_coords = (coords[1], coords[0])\n        \n        map_point = geojson.Point(geoJSON_coords)\n        map_feature = geojson.Feature(geometry=map_point, properties={\"Name\" : name, \"popupContent\": p})\n        feature_list.append(map_feature)\n    \n    #Insert blank features where geocoding returns None\n    except TypeError:\n        map_feature = geojson.Feature(geometry=[], properties={\"Name\" : \"null\", \"popupContent\": p})\n        feature_list.append(map_feature)\n\n# Dump the GeoJSON and write to a file        \ndata_dump = geojson.dumps(geojson.FeatureCollection(feature_list))\nwith open('/Users/libraries/Code/kap-data/KAP.Locations.json', 'w') as outfile:\n    outfile.write(data_dump)",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "# Check that the generated GeoJSON is valid using GeoJSON Lint\nvalidate_endpoint = 'http://geojsonlint.com/validate'\ntest_request = requests.post(validate_endpoint, data=data_dump)\n\nprint test_request.json()",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "{u'status': u'ok'}\n"
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "",
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}