if self.df.equals(df_existing):
exists = True
logger.info("Current data frame already exists")
break
if not exists:
self.df.to_csv(
f"{self.daily_folder}/{self.country.lower()}_covid19_{self.date}_{self.hour:0.0f}_{self.minute:02.0f}.csv",
index=False)
if __name__ == "__main__":
column_converter = {"authority": "nuts_3"}
daily_files = retrieve_files(ENGLAND_DAILY_FOLDER)
daily_files.sort()
for file in daily_files:
file_path = os.path.join(ENGLAND_DAILY_FOLDER, file)
file_transformation = DailyTransformation(
file_path=file_path, column_converter=column_converter)
file_transformation.workflow()
cov_england = SARSCOV2England()
cov_england.workflow()
da_england = DailyAggregator(base_folder="dataset",
daily_folder=ENGLAND_DAILY_FOLDER,
country="England")
da_england.workflow()
def post_processing(self):
self.df.sort_values(by="cases", inplace=True)
self.df.drop(self.df.loc[(self.df['nuts_3'] == 'TOTAL') |
(self.df['nuts_3'] == 'Total')].index,
inplace=True)
self.df.replace("Wales Total", "Wales", inplace=True)
if __name__ == "__main__":
column_converter = {"authority": "nuts_3"}
daily_files = retrieve_files(WALES_DAILY_FOLDER)
daily_files.sort()
for file in daily_files:
file_path = os.path.join(WALES_DAILY_FOLDER, file)
file_transformation = DailyTransformation(
file_path=file_path, column_converter=column_converter)
file_transformation.workflow()
cov_wales = SARSCOV2Wales()
cov_wales.workflow()
logger.info(cov_wales.df)
da_wales = DailyAggregator(base_folder="dataset",
daily_folder=WALES_DAILY_FOLDER,
def post_processing(self):
self.df.sort_values(by="cases", inplace=True)
if __name__ == "__main__":
column_converter = {
"state": "nuts_2"
}
drop_rows = {
"state": "sum"
}
daily_files = retrieve_files(DAILY_FOLDER)
daily_files.sort()
for file in daily_files:
file_path = os.path.join(DAILY_FOLDER, file)
file_transformation = DailyTransformation(
file_path=file_path,
column_converter=column_converter,
drop_rows=drop_rows
)
file_transformation.workflow()
cov_at = SARSCOV2AT()
cov_at.workflow()
print(cov_at.df)
dt_from_re = dt_from_re[0]
dt_from_re = dateutil.parser.parse(dt_from_re, dayfirst=True)
self.dt = dt_from_re
def post_processing(self):
self.df.sort_values(by="cases", inplace=True)
if __name__ == "__main__":
column_converter = {
"nuts_2": "nuts_3"
}
daily_files = retrieve_files(SCOTLAND_DAILY_FOLDER)
daily_files.sort()
for file in daily_files:
file_path = os.path.join(SCOTLAND_DAILY_FOLDER, file)
file_transformation = DailyTransformation(
file_path=file_path,
column_converter=column_converter
)
file_transformation.workflow()
cov_scotland = SARSCOV2Scotland()
cov_scotland.workflow()
da_scotland = DailyAggregator(
base_folder="dataset",
