# run formatter = Formatter(args) ## First, we load the data and identify some counties we're interested in ## Let's go with King County, WA (where the first US case was identified), and WESTCHESTER infections = pd.read_csv( join(formatter.raw_data_dir, 'national/USAfacts_infections/covid_confirmed_usafacts_aligned.csv')) deaths = pd.read_csv( join(formatter.raw_data_dir, 'national/USAfacts_infections/covid_deaths_usafacts_aligned.csv')) fips = [53033, 36119] ## Extract the features from those counties national_data = formatter.parse_national_data() king_data = national_data[str(fips[0])] westchester_data = national_data[str(fips[1])] king_population = int(king_data['population'][6]) * susceptible_factor westchester_population = int( westchester_data['population'][6]) * susceptible_factor ## To get a general overview of the data, we can first plot them #timeseries.plot_timeseries(infections, fips=fips, label='Infections') #timeseries.plot_timeseries(deaths, fips=fips, label='Deaths') ## Let's take a deeper look at the data and see how the growth in these two counties compare ## Read out the timeseries in each county and we can calculate the growth rate king_time, king_infections, king_deaths = utils.get_timeseries( infections, deaths, fips[0])