covid masks in US states

gistfile1.py

import datetime
import requests
import requests_cache
import re
import pprint
import numpy as np
import matplotlib.pyplot as plt


pp = pprint.PrettyPrinter()

requests_cache.install_cache('c')


us_state_abbrev = {
    'Alabama': 'AL',
    'Alaska': 'AK',
    'American Samoa': 'AS',
    'Arizona': 'AZ',
    'Arkansas': 'AR',
    'California': 'CA',
    'Colorado': 'CO',
    'Connecticut': 'CT',
    'Delaware': 'DE',
    'District of Columbia': 'DC',
    'Florida': 'FL',
    'Georgia': 'GA',
    'Guam': 'GU',
    'Hawaii': 'HI',
    'Idaho': 'ID',
    'Illinois': 'IL',
    'Indiana': 'IN',
    'Iowa': 'IA',
    'Kansas': 'KS',
    'Kentucky': 'KY',
    'Louisiana': 'LA',
    'Maine': 'ME',
    'Maryland': 'MD',
    'Massachusetts': 'MA',
    'Michigan': 'MI',
    'Minnesota': 'MN',
    'Mississippi': 'MS',
    'Missouri': 'MO',
    'Montana': 'MT',
    'Nebraska': 'NE',
    'Nevada': 'NV',
    'New Hampshire': 'NH',
    'New Jersey': 'NJ',
    'New Mexico': 'NM',
    'New York': 'NY',
    'North Carolina': 'NC',
    'North Dakota': 'ND',
    'Northern Mariana Islands':'MP',
    'Ohio': 'OH',
    'Oklahoma': 'OK',
    'Oregon': 'OR',
    'Pennsylvania': 'PA',
    'Puerto Rico': 'PR',
    'Rhode Island': 'RI',
    'South Carolina': 'SC',
    'South Dakota': 'SD',
    'Tennessee': 'TN',
    'Texas': 'TX',
    'Utah': 'UT',
    'Vermont': 'VT',
    'Virgin Islands': 'VI',
    'Virginia': 'VA',
    'Washington': 'WA',
    'West Virginia': 'WV',
    'Wisconsin': 'WI',
    'Wyoming': 'WY'
}


def get_state_population(state_name):
    f = open('pop.tsv')
    for line in f:
        n, pop = line.split('\t')
        n = n.strip()
        pop = pop.strip().replace(',', '')
        print(n, pop)
        if n == state_name:
            return int(pop)
    raise Exception(state_name)


def get_data(state, dt, days_around, field):
    # print(state, dt, field)
    print('.', end='')
    url = 'https://api.covidtracking.com/v1/states/%s/daily.json' % (state.lower())
    data = requests.get(url).json()
    before = []
    after = []
    for day in data:
        day_date_str = day['date']
        m = re.search(r'(\d\d\d\d)(\d\d)(\d\d)', str(day_date_str))
        day_dt = datetime.datetime(year=int(m.group(1)), month=int(m.group(2)), day=int(m.group(3)))
        delta = (dt - day_dt).days
        if delta < 0 and delta >= -days_around:
            before.append(day[field])
        if delta >= 0 and delta < days_around:
            after.append(day[field])
    return before, after


def get_dates():
    # Source for dates.tsv: https://masks4all.co/what-states-require-masks/
    f = open('dates.tsv')
    dates = {}
    pops = {}
    for line in f:
        # print(line)
        state, _, _, date_str = line.split('\t')
        parts = [int(x) for x in date_str.split('/')]
        dt = datetime.datetime(year=parts[2], month=parts[0], day=parts[1])
        dates[us_state_abbrev[state]] = dt
        pops[us_state_abbrev[state]] = get_state_population(state)
    return dates, pops


def run():
    dates, pops = get_dates()
    # print(dates)
    cases_total_before, cases_total_after = 0, 0
    death_total_before, death_total_after = 0, 0

    n = 35
    cases_series = np.array([0.] * n * 2)
    death_series = np.array([0.] * n * 2)
    for state, dt in dates.items():
        cases_before, cases_after = get_data(state, dt, n, 'positiveIncrease')
        death_before, death_after = get_data(state, dt, n, 'deathIncrease')

        cases_total_before += sum(cases_before) / pops[state]
        cases_total_after += sum(cases_after) / pops[state]
        death_total_before += sum(death_before) / pops[state]
        death_total_after += sum(death_after) / pops[state]

        state_cases_series = np.array(cases_before + cases_after) / float(pops[state])
        state_death_series = np.array(death_before + death_after) / float(pops[state])
        cases_series += state_cases_series
        death_series += state_death_series
        plt.plot(state_cases_series * len(dates), alpha=.1, c='g')
        plt.plot(state_death_series * len(dates) * 15, alpha=.1, c='b')


    print('--')
    print('cases_total_before', cases_total_before)
    print('cases_total_after ', cases_total_after)
    print('death_total_before', death_total_before)
    print('death_total_after ', death_total_after)

    print(cases_series)
    plt.plot(cases_series, label='cases per pop')
    plt.plot(death_series * 30, label='deaths per pop')
    plt.axvline(x=n, c='r', label='mask mandate')
    plt.title('cases and deaths per population %s days \nbefore/after mask mandate in US states' % n)
    plt.show()

run()