Python code, takes a list of addresses, runs them through NYS Address Management system, then uses GeoPandas to calculate the municipality and Assembly district from GeoPackages then writes out to a CSV file

Python, the State Geocoder and Outputting Assembly Districts

Python code, takes a list of addresses, runs them through NYS Address Management system, then uses GeoPandas to calculate the municipality and Assembly district from GeoPackages then writes out to a CSV file. Nothing fancy, but it does a job. I could use it with any other shapefile I want. GeoPandas is nice because it’s fast and doesn’t require loading QGIS.

view source
print?
01
#!/usr/bin/python
02
 
03
import requests,sys,json,os,csv
04
 
05
import pandas as pd
06
import geopandas as gpd
07
 
08
lines=[]
09
 
10
# read list of addresses
11
with open(sys.argv[-1], newline='') as csvfile: 
12
    for line in csv.DictReader(csvfile):
13
        lines.append(line)
14
         
15
# build address query
16
query = '{"records": ['
17
i=0
18
for line in lines:
19
    query += '{ "attributes": { "OBJECTID":'+str(i)+', "SINGLELINE": "'+line['Address'].rstrip()+'"} },'+"\n"
20
    i+=1   
21
query += ']}'
22
 
23
post = { 'f':'pjson', 'outSR': 4326, 'addresses': query }
24
url = 'https://gisservices.its.ny.gov/arcgis/rest/services/Locators/Street_and_Address_Composite/GeocodeServer/geocodeAddresses'
25
 
26
# send request to state geocoder
27
req = requests.post(url, data = post)
28
locations = json.loads(req.text)['locations']
29
 
30
# parse response
31
for loc in locations:
32
    i = loc['attributes']['ResultID']
33
    lines[i]['y'] = loc['location']['y']
34
    lines[i]['x'] = loc['location']['x']
35
    lines[i]['Match_addr'] = loc['attributes']['Match_addr']
36
     
37
    # hackish, might cause problems but keeps joins from erroring
38
    if (lines[i]['x'] == 'NaN'):
39
        lines[i]['x'] = 0
40
        lines[i]['y'] = 0
41
 
42
# convert to pandas
43
locPd = pd.DataFrame(lines,columns=lines[0].keys())
44
locPd = gpd.GeoDataFrame(locPd,  geometry=gpd.points_from_xy(locPd.x.astype('float32'), locPd.y.astype('float32')))
45
 
46
# add county municipality column
47
cosub = gpd.read_file(r'/home/andy/Documents/GIS.Data/geocode/cosub.gpkg')
48
locPd = gpd.sjoin(locPd, cosub, op="within")
49
 
50
del locPd['index_right']
51
 
52
# add ads column
53
ad = gpd.read_file(r'/home/andy/Documents/GIS.Data/geocode/ad.gpkg')
54
locPd = gpd.sjoin(locPd, ad, op="within")
55
 
56
del locPd['index_right']
57
 
58
# add sd column
59
sd = gpd.read_file(r'/home/andy/Documents/GIS.Data/geocode/sd.gpkg')
60
locPd = gpd.sjoin(locPd, sd, op="within")
61
 
62
del locPd['index_right']
63
 
64
# add cd column
65
sd = gpd.read_file(r'/home/andy/Documents/GIS.Data/geocode/cd.gpkg')
66
locPd = gpd.sjoin(locPd, sd, op="within")
67
 
68
 
69
# remove added geometery and index columns
70
del locPd['geometry']
71
del locPd['index_right']
72
 
73
# write pandas back to out csv
74
locPd.to_csv (os.path.splitext(sys.argv[-1])[0]+'-output.csv', index = False, header=True)