def join_with_divi_data(d_districts_data: dict) -> dict:
d_divi_data = helper.read_json_file('cache/de-divi/de-divi-V3.json')
for lk_id, l_lk_time_series in d_districts_data.items():
# all Berlin Districts are in divi at 11000
if lk_id[0:2] == '11':
l_divi_time_series = d_divi_data["11000"]
elif lk_id not in d_divi_data:
continue
# assert lk_id in d_divi_data, f"Error: LK {lk_id} missing in DIVI data"
if lk_id[0:2] != '11':
l_divi_time_series = d_divi_data[lk_id]
d_divi_time_series = {}
for d in l_divi_time_series:
d_divi_time_series[d['Date']] = d
for d in l_lk_time_series:
if d['Date'] not in d_divi_time_series:
continue
d['DIVI_Intensivstationen_Covid_Prozent'] = d_divi_time_series[d['Date']
]['faelle_covid_aktuell_proz']
d['DIVI_Intensivstationen_Betten_belegt_Prozent'] = d_divi_time_series[d['Date']
]['betten_belegt_proz']
d_districts_data[lk_id] = l_lk_time_series
return d_districts_data
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_ref_data_countries() -> dict:
d_countries_ref = {}
d_ref_country_database = helper.read_json_file(
'data/ref_country_database.json')
for key, d in d_ref_country_database.items():
d2 = {}
code = d["ISO"]
name = key
if name == 'Republic of the Congo':
name = 'Congo (Brazzaville)'
elif name == 'Democratic Republic of the Congo':
name = 'Congo (Kinshasa)'
pop = d['Population']
if pop != None:
pop = int(pop)
if pop == 0:
pop = None
continent = d['Continent']
# move Turkey from Asia to Europe
if name == 'Turkey':
continent = 'EU'
if continent != None:
if continent == 'AF':
continent = 'Africa'
elif continent == 'AN':
continent = 'Antarctica'
elif continent == 'AS':
continent = 'Asia'
elif continent == 'EU':
continent = 'Europe'
elif continent == 'NA':
continent = 'North America'
elif continent == 'SA':
continent = 'South America'
elif continent == 'OC':
continent = 'Oceania'
else:
assert 1 == 2, f"E: continent missing for {name}"
d2["Code"] = code
d2['Continent'] = continent
d2["Population"] = pop
d_countries_ref[name] = d2
return d_countries_ref
def join_with_divi_data() -> dict:
d_divi_data = helper.read_json_file('cache/de-divi/de-divi-V3-states.json')
for bl_code, l_time_series in d_states_data.items():
assert bl_code in d_divi_data, f"Error: BL {bl_code} missing in DIVI data"
if bl_code[0:2] != '11':
l_divi_time_series = d_divi_data[bl_code]
d_divi_time_series = {}
for d in l_divi_time_series:
d_divi_time_series[d['Date']] = d
for d in l_time_series:
if d['Date'] not in d_divi_time_series:
continue
d['DIVI_Intensivstationen_Covid_Prozent'] = d_divi_time_series[
d['Date']]['faelle_covid_aktuell_proz']
d['DIVI_Intensivstationen_Betten_belegt_Prozent'] = d_divi_time_series[
d['Date']]['betten_belegt_proz']
d_states_data[bl_code] = l_time_series
return d_states_data
'#52be80',
'#27ae60',
'#229954',
'#1e8449',
'#196f3d',
'#145a32'
]
}
d_all_date_data = {}
l_month = []
count = 0
for f in glob.glob('data/de-districts/de-district_timeseries-*.json'):
count += 1
lk_id = int(re.search('^.*de-district_timeseries\-(\d+)\.json$', f).group(1))
l = helper.read_json_file(f)
for d in l:
date = d['Date']
thisMonth = date[0:7]
# skip old data points
if thisMonth in ('2020-01', '2020-02'):
continue
# add to list of months for later creations of 1 gif per month
if count == 1:
if thisMonth not in l_month:
l_month.append(thisMonth)
if not d['Date'] in d_all_date_data:
d_all_date_data[d['Date']] = {}
del d['Timestamp'], d['Date'], d['Days_Past'], d['Days_Since_2nd_Death']
d_all_date_data[date][lk_id] = d
del f, d, l, count
"""
import sys
import csv
from datetime import datetime
import re
# my helper modules
import helper
filename = 'data/de-divi/de-divi-V2'
datestr = datetime.now().strftime("%Y-%m-%d")
d_data_all = helper.read_json_file(filename + '.json')
del d_data_all['Deutschland'] # this is re-calculated at each run
# check if date is already in data set
if d_data_all['Bayern'][-1]['Date'] == datestr:
print(
f"WARNING: Date: {datestr} already in data file: {filename+'.json'} --> SKIPPING"
)
sys.exit()
def extractAreaTagTitleData(cont: str) -> list:
# Example
# <area shape="RECT" title="Thüringen
# Anzahl COVID-19 Patienten/innen in intensivmedizinischer Behandlung: 63
# my helper modules
import helper
unit = 1000000
meta = {
"colour":
["#fee5d9", "#fcbba1", "#fc9272", "#fb6a4a", "#de2d26", "#a50f15"]
}
# date = datetime.date.today()
# date_str = date.strftime("%F")
values = []
l_data = helper.read_json_file(
'data/de-districts/de-districts-results-V2.json')
date_str = l_data[0]['Date']
main = {}
for d in l_data:
area = int(d['LK_ID'])
pcapita = d['Cases_Last_Week_Per_Million']
main[area] = {'pcapita': pcapita}
values.append(main[area]["pcapita"])
# generate color scale range
q = statistics.quantiles(values, n=100, method="inclusive")
step = math.sqrt(statistics.mean(values) - q[0]) / 3
threshold = [0, 0, 0, 0, 0, 0]
for i in range(1, 6):
elif continent == 'SA':
continent = 'South America'
elif continent == 'OC':
continent = 'Oceania'
return continent
def read_country_code(country_name: str) -> str:
code = None
d = get_ref_country_dict(country_name)
if d != {}:
code = d['ISO']
return code
d_ref_country_database = helper.read_json_file(
'data/ref_country_database.json')
d_selected_countries = read_ref_selected_countries()
if not helper.check_cache_file_available_and_recent(
fname=file_cache, max_age=900, verbose=True):
download_new_data()
d_countries_timeseries = read_json_data()
check_for_further_interesting_countries()
fit_doubling_time()
extract_latest_date_data()