Output per-county tab-separated information

calculate_liveability.py

#!/bin/env python

#data downloaded from https://data.opendatasoft.com/explore/dataset/usa-2016-presidential-election-by-county@public/download/?format=json&timezone=America/New_York

import json

def get_liveability_info(db, county_state_to_recordid_map, state_county):

    record_ids = county_state_to_recordid_map[state_county]
    if len(record_ids) != 1:
            print 'not a 1:1 mapping between state, county to record'

    county = record_ids[0]
    if 'white_not_latino_population' not in db[county]['fields']:
        white_not_latino_population = 50
    else:
        white_not_latino_population = db[county]['fields']['white_not_latino_population']

    return (db[county]['fields']['rep16_frac'], white_not_latino_population)

def main():
    db = {}
    county_state_to_recordid_map = {}
    for record in json.load(open('usa-2016-presidential-election-by-county.json')):
        if 'st' in record['fields']:
            st = record['fields']['st']
        else:
            st = ''

        county_state_to_recordid_map.setdefault((st, record['fields']['county']), []).append(record['recordid'])
        db[record['recordid']] = record

    liveability_info_all_counties = []
    for state_county in county_state_to_recordid_map:
        liveability_info = get_liveability_info(db, county_state_to_recordid_map, state_county)
        liveability_info_all_counties.append((
                liveability_info[0],
                liveability_info[1],
                state_county[0],
                state_county[1]))

    for liveability_info in liveability_info_all_counties:
        print '%s\t%s\t%s\t%s' % liveability_info

if __name__ == "__main__":
        main()