Created
March 29, 2020 19:52
-
-
Save John-K/4244c42c6cfb986857e66b77597ca18c to your computer and use it in GitHub Desktop.
parse NYT covid data into python dictionaries
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env python | |
| # run from the NYT data directory: | |
| # python covid.py | |
| import csv | |
| import pprint | |
| # data structures | |
| by_date = {} | |
| by_state = {} | |
| # use prettyprint so anything we print looks nice | |
| pp = pprint.PrettyPrinter(indent=4) | |
| # Load the data into two maps, one organized by date, the other by state | |
| with open('us-states.csv', newline='') as csvfile: | |
| # DictReader uses the first row as data labels | |
| reader = csv.DictReader(csvfile) | |
| for line in reader: | |
| no_date = {k: v for k, v in line.items() if not k.startswith('date')} | |
| no_state = {k: v for k, v in line.items() if not k.startswith('state')} | |
| # create the first record or append to an existing one | |
| if line['date'] in by_date.keys(): | |
| by_date[line['date']].append(no_date) | |
| else: | |
| by_date[line['date']] = [no_date] | |
| # create the first record or append to an existing one | |
| if line['state'] in by_state.keys(): | |
| by_state[line['state']].append(no_state) | |
| else: | |
| by_state[line['state']] = [no_state] | |
| # print data structures to see what's in them | |
| pp.pprint(by_state) | |
| pp.pprint(by_date) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
to get all entries for a given date:
pp.pprint(by_date['2020-03-03'])
to get all dates for a given state:
pp.pprint(by_state['California'])