def read_json_data() -> dict:
"""
reads downloaded cached json file contents
renames some country names according to ref database
calls prepare_time_series
adds _Per_Million fields
NO LONGER exports as json file
returns as a dict
"""
d_json_downloaded = helper.read_json_file(file_cache)
# rename some countries
d_countries_to_rename = {}
d_countries_to_rename['US'] = 'United States'
d_countries_to_rename['Korea, South'] = 'South Korea'
d_countries_to_rename['Taiwan*'] = 'Taiwan'
d_countries_to_rename['Burma'] = 'Myanmar'
d_countries_to_rename['Cote d\'Ivoire'] = 'Ivory Coast'
d_countries_to_rename['West Bank and Gaza'] = 'Palestinian Territory'
d_countries_to_rename['Timor-Leste'] = 'Timor Leste'
d_countries_to_rename['Holy See'] = 'Vatican'
for country_name_old, country_name_new in d_countries_to_rename.items():
d_json_downloaded[country_name_new] = d_json_downloaded[
country_name_old]
del d_json_downloaded[country_name_old]
d_countries = {}
# re-format date using my date_format(y,m,d) function
for country in d_json_downloaded.keys():
country_data = d_json_downloaded[country]
l_time_series = []
pop = read_population(country)
if pop != None:
pop_in_million = pop / 1000000
else:
pop_in_million = None
for entry in country_data:
d = {}
# entry in country_data:
s = entry['date']
l = s.split("-")
d['Date'] = helper.date_format(int(l[0]), int(l[1]), int(l[2]))
d['Cases'] = int(entry['confirmed'])
d['Deaths'] = int(entry['deaths'])
l_time_series.append(d)
l_time_series = helper.prepare_time_series(l_time_series)
for i in range(len(l_time_series)):
d = l_time_series[i]
# _Per_Million
d = helper.add_per_million(d, pop_in_million)
d_countries[country] = l_time_series
return d_countries
def read_csv_to_dict() -> dict:
"""
read and convert the source csv file, containing: federalstate,infections,deaths,date,newinfections,newdeaths
re-calc _New via helper.prepare_time_series
add _Per_Million via helper.add_per_million_via_lookup
"""
global d_ref_states
# Preparations
d_states_data = {'BW': [], 'BY': [], 'BE': [], 'BB': [], 'HB': [], 'HH': [], 'HE': [], 'MV': [
], 'NI': [], 'NW': [], 'RP': [], 'SL': [], 'SN': [], 'ST': [], 'SH': [], 'TH': []}
# add German sum
d_states_data['DE-total'] = []
d_german_sums = {} # date -> 'infections', 'deaths', 'new infections', 'new deaths'
# data body
with open(download_file, mode='r', encoding='utf-8') as f:
csv_reader = csv.DictReader(f, delimiter=",")
for row in csv_reader:
d = {}
s = row['date']
l = s.split("-")
d['Date'] = helper.date_format(
int(l[0]), int(l[1]), int(l[2]))
d['Cases'] = int(row["infections"])
d['Deaths'] = int(row["deaths"])
if row["federalstate"] == 'Baden-Württemberg':
d_states_data['BW'].append(d)
elif row["federalstate"] == 'Bavaria':
d_states_data['BY'].append(d)
elif row["federalstate"] == 'Berlin':
d_states_data['BE'].append(d)
elif row["federalstate"] == 'Brandenburg':
d_states_data['BB'].append(d)
elif row["federalstate"] == 'Bremen':
d_states_data['HB'].append(d)
elif row["federalstate"] == 'Hamburg':
d_states_data['HH'].append(d)
elif row["federalstate"] == 'Hesse':
d_states_data['HE'].append(d)
elif row["federalstate"] == 'Lower Saxony':
d_states_data['NI'].append(d)
elif row["federalstate"] == 'North Rhine-Westphalia':
d_states_data['NW'].append(d)
elif row["federalstate"] == 'Mecklenburg-Western Pomerania':
d_states_data['MV'].append(d)
elif row["federalstate"] == 'Rhineland-Palatinate':
d_states_data['RP'].append(d)
elif row["federalstate"] == 'Saarland':
d_states_data['SL'].append(d)
elif row["federalstate"] == 'Saxony':
d_states_data['SN'].append(d)
elif row["federalstate"] == 'Saxony-Anhalt':
d_states_data['ST'].append(d)
elif row["federalstate"] == 'Schleswig-Holstein':
d_states_data['SH'].append(d)
elif row["federalstate"] == 'Thuringia':
d_states_data['TH'].append(d)
else:
assert 1 == 2, f"ERROR: unknown state: {row['federalstate']}"
# add to German sum
if d['Date'] not in d_german_sums:
d2 = {}
d2['Cases'] = d['Cases']
d2['Deaths'] = d['Deaths']
else:
d2 = d_german_sums[d['Date']]
d2['Cases'] += d['Cases']
d2['Deaths'] += d['Deaths']
d_german_sums[d['Date']] = d2
del d2
# German sum -> same dict
for datum in d_german_sums.keys():
d = d_german_sums[datum]
d['Date'] = datum # add date field
d_states_data['DE-total'].append(d)
del d_german_sums, d
# check if DE-total of today and yesterday are equal, if so: remove last date
if d_states_data['DE-total'][-1]['Cases'] == d_states_data['DE-total'][-2]['Cases']:
print("WARNING: DE cases sum is unchanged")
for code in d_states_data:
d_states_data[code].pop()
print(f"DE-States Last Date: {d_states_data['DE-total'][-1]['Date']}")
for code in d_states_data.keys():
l_time_series = d_states_data[code]
# add days past, _New, _Last_Week, etc
l_time_series = helper.prepare_time_series(l_time_series)
for i in range(len(l_time_series)):
d = l_time_series[i]
# add per Million rows
d = helper.add_per_million_via_lookup(d, d_ref_states, code)
# # fit cases data
# dataCases = []
# dataDeaths = []
# for i in range(1, len(l_time_series)):
# # x= day , y = cases
# dataCases.append(
# (
# l_time_series[i]['Days_Past'],
# l_time_series[i]['Cases']
# )
# )
# dataDeaths.append(
# (
# l_time_series[i]['Days_Past'],
# l_time_series[i]['Deaths']
# )
# )
# fit_series_res = helper.series_of_fits(
# dataCases, fit_range=7, max_days_past=60)
# for i in range(0, len(l_time_series)):
# this_Doubling_Time = ""
# this_days_past = l_time_series[i]['Days_Past']
# if this_days_past in fit_series_res:
# this_Doubling_Time = fit_series_res[this_days_past]
# l_time_series[i]['Cases_Doubling_Time'] = this_Doubling_Time
# fit_series_res = helper.series_of_fits(
# dataDeaths, fit_range=7, max_days_past=60)
# for i in range(0, len(l_time_series)):
# this_Doubling_Time = ""
# this_days_past = l_time_series[i]['Days_Past']
# if this_days_past in fit_series_res:
# this_Doubling_Time = fit_series_res[this_days_past]
# l_time_series[i]['Deaths_Doubling_Time'] = this_Doubling_Time
d_states_data[code] = l_time_series
return d_states_data