def write_dataframes(dataframes):
for key, df in dataframes.items():
path = c('directories.export.data') + key + '.json'
df.to_json(path, orient='records', date_format='iso')
key = 'district-hoexter-ages'
path = c('directories.export.data') + key + '.json'
df.to_json(path, orient='records', date_format='iso')
def write_configuration():
path = c('directories.export.data') + 'configuration.json'
with open(path, 'w') as outfile:
json.dump(c(''), outfile)
idents = c('names.communes')
path = c('directories.export.data') + 'ident.json'
with open(path, 'w') as outfile:
json.dump(idents, outfile)
def concat(dfs):
cdfs = {}
for district in c('names.districts'):
frames = []
keys = []
for commune, parent in c('parents.communes').items():
if parent == district:
frames.append(dfs['commune-' + commune].transpose())
keys.append(commune)
df = pd.concat(frames, keys=keys)
cdfs['district-' + district] = df
return cdfs
def run():
for key, name in c('names.districts').items():
df = load(key)
df = shorten_df(df)
df = process_manual_data(df, 'district', key)
write_imported_dataframe(df, 'district-' + key)
def process_disctricts(dfs, cdfs, args):
print('Districts argument list:', str(args))
for district in c('names.districts'):
map.plot(dfs['district-' + district], cdfs['district-' + district],
'district', 'commune', district)
for count in counts:
StackedSupervisor(dfs, count, 'district', district).run()
ComparisonSupervisor(cdfs, count, 'confirmed', 'district', 'commune', district,
'Absolute Fallzahlen', 'absolute-comparison').run()
ComparisonSupervisor(cdfs, count, 'density_of_cases', 'district', 'commune',
district, 'Relative Fallzahlen',
'relative-comparison').run()
ComparisonSupervisor(cdfs, count, 'density_of_illness', 'district', 'commune',
district, 'Infektionsrisiko',
'risc-comparison').run()
ComparisonSupervisor(cdfs, count, 'last_weeks_incidence',
'district', 'commune',
district, 'Wocheninzidenzen',
'incidence-comparison').run()
IncidenceSupervisor(dfs, count, 'district', district).run()
VerticalComparisonSupervisor(dfs, count, 'last_weeks_incidence',
'district',
district, 'Risikovergleich',
# 'Aktiv Infizierte je 100.000 Einwohner',
'Wocheninzidenz',
'vertical-risc-comparison').run()
def process_ages(dfs, args):
print('Ages argument List:', str(args))
ages = dfs['district-hoexter-ages']
for key, group in ages.groupby(['Jahr', 'Monat']):
AgesPlotter(group).run()
name = 'district-hoexter-ages-' \
+ str(key[0]) + '-' + str(key[1]) + '.png'
path = c('directories.export.plots') + name
plt.savefig(path)
plt.close()
def process_communes(dfs, args):
print('Communes argument List:', str(args))
if len(args) > 0:
communes = args
else:
communes = c('names.communes')
for commune in communes:
for count in counts:
StackedSupervisor(dfs, count, 'commune', commune).run()
IncidenceSupervisor(dfs, count, 'commune', commune).run()
VerticalComparisonSupervisor(dfs, count, 'last_weeks_incidence',
'commune',
commune, 'Risikovergleich',
'Wocheninzidenz',
'vertical-risc-comparison').run()
def export_data():
source = c('directories.export.data')
destination = c('directories.published.data')
copy(source, destination)
def export_plots():
source = c('directories.export.plots')
destination = c('directories.published.plots')
copy(source, destination)
def load(district):
path = c('files.raw.districts')[district]
return pd.read_csv(path, sep=';')
def f(row):
r = lakh * row.last_weeks_incidence / c('populations')[p(type)][key]
return round(r, 3)
from urllib.request import urlopen
import geopandas
import pandas as pd
from configuration import get as c
import pathlib
import datetime
from lib import write_imported_dataframe
cache = c('files.cache.rki_kreis_hoexter')
url = "https://services7.arcgis.com/mOBPykOjAyBO2ZKk/arcgis/rest/services" \
"/RKI_COVID19/FeatureServer/0/query?where=IdLandkreis%20%3D%20'05762" \
"'&outFields=IdBundesland,Bundesland,Landkreis,Altersgruppe," \
"Geschlecht,AnzahlFall,AnzahlTodesfall,ObjectId,Meldedatum," \
"IdLandkreis,Datenstand,NeuerFall,NeuerTodesfall,Refdatum,NeuGenesen," \
"AnzahlGenesen,IstErkrankungsbeginn&returnGeometry=false&outSR=4326&f" \
"=json"
data_download_interval_in_minutes = 600
def load():
def download():
with urlopen(url) as reader:
content = reader.read().decode('utf-8')
with open(cache, 'w') as writer:
writer.write(content)
def read_df():
data = geopandas.read_file(cache)
data['Refdatum'] = pd.to_datetime(data['Refdatum'], unit='ms')
def density_of_cases(row):
r = lakh * row.confirmed / c('populations')[p(type)][key]
return round(r, 3)
def run():
for key, name in c('names.communes').items():
df = load('hoexter', key)
df = shorten_df(df)
df = process_manual_data(df, 'commune', key)
write_imported_dataframe(df, 'commune-' + key)
def load_jhu_data():
df_confirmed = pd.read_csv(c('files.jhu_confirmed'))
df_deaths = pd.read_csv(c('files.jhu_deaths'))
df_recovered = pd.read_csv(c('files.jhu_recovered'))
return df_confirmed, df_deaths, df_recovered
def run():
dfs = load_jhu_data()
for key, names in c('names.countries').items():
df = process_jhu_data(*dfs, country=names['jhu'], key=key)
write_imported_dataframe(df, 'country-' + key)
def read_children(self):
for k, v in c('names')[p(self.child_type)].items():
self.keys.append(k)
self.labels.append(v)
def density_of_death(row):
r = lakh * row.dead / c('populations')[p(type)][key]
return round(r, 3)
def process_countries(dfs, args):
print('Countries argument list:', str(args))
for country in c('names.countries'):
for count in counts:
StackedSupervisor(dfs, count, 'country', country).run()
IncidenceSupervisor(dfs, count, 'country', country).run()
def load(district, commune):
path = c('directories.raw.districts')[district]
path += 'district-' + commune + '.csv'
return pd.read_csv(path, sep=';')
def plot(district_df, cdf, type, child_type, key):
# load data
def get_latest_incidences():
incidences = list()
for k, v in c('names')[p(child_type)].items():
incidences.append((v, cdf.loc[(k, 'last_weeks_incidence')][-1]))
return incidences
df = pd.DataFrame(
columns=['commune', 'last_weeks_incidence'],
data=get_latest_incidences(),
)
df['last_weeks_incidence'] = round(df['last_weeks_incidence'], 1)
date = cdf.keys()[-1] # last date
meta = district_df[district_df['date'] == date]
if meta['STI-LZG'].notnull().bool():
total_incidence = meta['STI-LZG']
total_incidence_source = 'LZG NRW, amtlich'
elif meta['STI-RKI'].notnull().bool():
total_incidence = meta['STI-RKI']
total_incidence_source = 'RKI, vorläufig'
elif meta['STI-Kreis'].notnull().bool():
total_incidence = meta['STI-Kreis']
total_incidence_source = 'Kreis, vorläufig'
else:
total_incidence = None
total_incidence_source = ''
if total_incidence is not None:
total_incidence = float(total_incidence)
# load map
file = c('files.shapefile')
communes = geopandas.read_file(file)
communes['Name'] = communes['GN']
# create layer dataframes
communes = communes.set_index('GN').join(df.set_index('commune'))
communes['helper'] = 0
district = communes.dissolve(by='helper')
shadow = district.copy()
shadow = shadow.translate(xoff=7000, yoff=2000)
# create figure objects
figure = plt.figure()
axes = plt.axes()
# start plotting
# shadow
if total_incidence is not None:
shadow.plot(
color=get_color(total_incidence),
ax=axes,
alpha=0.3,
linewidth=0,
)
shadow.boundary.plot(ax=axes, color='#aaa', linewidth=0.1)
# communes
district.plot(ax=axes, color='white', linewidth=0) # white background for
# alpha
communes.plot(
norm=Normalize(0,
len(colors) - 1),
ax=axes,
column='last_weeks_incidence',
legend=False,
scheme="user_defined",
cmap=cmap,
classification_kwds={'bins': bins},
alpha=0.88,
linewidth=0,
)
district.boundary.plot(ax=axes, color='#ddd', linewidth=0.3)
# style
figure.set_size_inches(mapsize)
if total_incidence is not None:
bbox_props = dict(
boxstyle="round,pad=0.45",
fc="white",
# ec="black",
ec=get_color(total_incidence),
lw=0.3,
alpha=0.7)
plt.annotate(
('Kreis Höxter: ' + str(total_incidence).replace('.', ',') + ' (' +
total_incidence_source + ')'),
xy=(0.65, 0.78),
xycoords='figure fraction',
ha='center',
bbox=bbox_props,
size=10.5,
color='#666',
fontfamily='sans-serif',
fontweight='bold',
fontstyle='italic',
)
bbox_props = dict(boxstyle="round,pad=0.35",
fc="#484848",
ec="white",
lw=0.2,
alpha=1)
communes.apply(
lambda x: axes.annotate(
# ugly, but works for now
text=x.Name + ': ' + str(x.last_weeks_incidence).replace('.', ','),
size=9.5,
xy=x.geometry.centroid.coords[0],
ha='center',
bbox=bbox_props,
color='white',
fontfamily='sans-serif',
fontweight='bold',
fontstyle='italic',
),
axis=1)
plt.suptitle('7-Tage-Inzidenzen im Kreis Höxter', fontsize=18, y=0.93)
day = date.strftime("%d.%m.%Y")
axes.set_title(label='je 100.000 Einwohnern am ' + day, fontsize=16)
plt.axis('off')
# go
save(type, key, 'last_weeks_incidence-map')
def density_of_illness(row):
r = lakh * row.ill / c('populations')[p(type)][key]
return round(r, 3)
def get_latest_incidences():
incidences = list()
for k, v in c('names')[p(child_type)].items():
incidences.append((v, cdf.loc[(k, 'last_weeks_incidence')][-1]))
return incidences
def density_of_recoverance(row):
r = lakh * row.recovered / c('populations')[p(type)][key]
return round(r, 3)
