def export_dataframe_to_csv(name: str, dataframe):
filename = os.path.join(CSV_FOLDER, f'{name}.csv')
old_hash = sha1sum(filename)
dataframe.replace({
0: None
}).astype('Int64').to_csv(filename, line_terminator='\r\n')
write_timestamp_file(filename=filename, old_hash=old_hash)
old_hash = sha1sum(municipality_deceased_csv_path)
with open(file=municipality_deceased_csv_path, encoding='utf-8') as f:
rows = [row for row in csv.DictReader(f)]
latest_date = str([val for val in df.index.values][-1]).split('T')[0]
latest_date = datetime.strptime(latest_date, '%Y-%m-%d').date()
while (date := datetime.strptime(rows[-1]['date'], '%Y-%m-%d').date()) < latest_date:
rows.append(copy.deepcopy(rows[-1]))
rows[-1]['date'] = str(date + timedelta(days=1))
# Write the rows collection back to the csv
with open(municipality_deceased_csv_path, 'w', newline='', encoding='utf-8') as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=rows[0].keys())
writer.writeheader()
for row in rows:
writer.writerow(row)
write_timestamp_file(filename=municipality_deceased_csv_path, old_hash=old_hash)
# --- region-confirmed.csv | region-active.csv ---
df = pd.read_excel(io=SOURCE_FILE, sheet_name='Tabela 4', engine='openpyxl', skiprows=[0, 2])[:-1]
df.drop(['SKUPAJ'], inplace=True, axis=1) # axis=1 means columns
def get_region_header(region: str):
return {
'Pomurska': 'region.ms.todate',
'Podravska': 'region.mb.todate',
'Koroška': 'region.sg.todate',
'Savinjska': 'region.ce.todate',
'Zasavska': 'region.za.todate',
'Posavska': 'region.kk.todate',
'Jugovzhodna Slovenija': 'region.nm.todate',
for key in [
'kranj', 'ljubljana', 'domzale', 'saleske', 'koper', 'celje',
'maribor'
]:
if key in components:
return key
raise Exception('No location key found: ', components)
mapping = {}
for column in df.columns:
if column == 'NIB Measurements':
mapping['NIB Measurements'] = 'measurements.nib'
continue
components = column.lower().split('_')
location = get_location_key(components=components)
components.remove(location)
location = {
'saleske': 'velenje'
}.get(location, location) # transform some of the location names
mapping[column] = f'sewage.{location}.{"-".join(components)}'
df.rename(mapper=mapping, axis='columns', inplace=True)
# export to csv
filename = os.path.join(CSV_FOLDER, 'sewage.csv')
old_hash = sha1sum(filename)
df.to_csv(filename)
write_timestamp_file(filename=filename, old_hash=old_hash)
old_hash = sha1sum(deceased_regions_csv_path)
with open(deceased_regions_csv_path) as f:
rows = [row for row in csv.DictReader(f)]
latest_date = str([val for val in df.index.values][-1]).split('T')[0]
latest_date = datetime.strptime(latest_date, '%Y-%m-%d').date()
while (date := datetime.strptime(rows[-1]['date'], '%Y-%m-%d').date()) < latest_date:
rows.append(copy.deepcopy(rows[-1]))
rows[-1]['date'] = str(date + timedelta(days=1))
# Write the rows collection back to the csv
with open(deceased_regions_csv_path, 'w', newline='') as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=rows[0].keys())
writer.writeheader()
for row in rows:
writer.writerow(row)
write_timestamp_file(filename=deceased_regions_csv_path, old_hash=old_hash)
# --- regions-cases.csv | regions-cases-active.csv ---
df = pd.read_excel(io=SOURCE_FILE, sheet_name='Tabela 4', engine='openpyxl', skiprows=[0, 2])[:-1]
df.drop(['SKUPAJ'], inplace=True, axis=1) # axis=1 means columns
def get_region_header(region: str):
return {
'Pomurska': 'region.ms.todate',
'Podravska': 'region.mb.todate',
'Koroška': 'region.sg.todate',
'Savinjska': 'region.ce.todate',
'Zasavska': 'region.za.todate',
'Posavska': 'region.kk.todate',
'Jugovzhodna Slovenija': 'region.nm.todate',
