def records_main(self):
"""
Return records of the main datasets as a dataframe.
Raises:
NotRegisteredMainError: JHUData was not registered
SubsetNotFoundError: failed in subsetting because of lack of data
Returns:
pandas.DataFrame:
Index
reset index
Columns:
- Date (pd.Timestamp): Observation date
- Confirmed (int): the number of confirmed cases
- Infected (int): the number of currently infected cases
- Fatal (int): the number of fatal cases
- Recovered (int): the number of recovered cases ( > 0)
- Susceptible (int): the number of susceptible cases
"""
jhu_data = self._data_dict[self.__NAME_JHU]
# Main datasets should be registered
if jhu_data is None:
raise NotRegisteredMainError(".register(jhu_data)")
# Subsetting
df, self._complemented = jhu_data.records(
**self._area_dict,
start_date=self._first_date,
end_date=self._last_date,
population=self._population,
**self._complement_dict,
)
# Columns which are included in the main dataset except for 'Date'
self._main_cols = list(set(df.columns) - set([self.DATE]))
return df
def population(self):
"""
int: population value
Raises:
NotRegisteredMainError: no information because JHUData was not registered
"""
if self._population is None:
raise NotRegisteredMainError(".register(jhu_data)")
return self._population
def complemented(self):
"""
bool or str: whether complemented or not and the details, None when not confirmed
Raises:
NotRegisteredMainError: no information because JHUData was not registered
"""
if self._complemented is None:
raise NotRegisteredMainError(".register(jhu_data)")
return self._complemented
def records_extras(self):
"""
Return records of the extra datasets as a dataframe.
Raises:
NotRegisteredMainError: either JHUData or PopulationData was not registered
NotRegisteredExtraError: no extra datasets were registered
Returns:
pandas.DataFrame:
Index
reset index
Columns:
- Date(pd.Timestamp): Observation date
- columns defined in the extra datasets
"""
if None in self._data_dict.values():
raise NotRegisteredMainError(
".register(jhu_data, population_data)")
if not set(self._data_dict) - set(self.MAIN_DICT):
raise NotRegisteredExtraError(
".register(jhu_data, population_data, extras=[...])",
message="with extra datasets")
# Get all subset
df = pd.DataFrame(columns=[self.DATE])
for (name, data) in self._data_dict.items():
if name in self.MAIN_DICT:
continue
try:
subset_df = data.subset(**self._area_dict)
except TypeError:
subset_df = data.subset(country=self._area_dict["country"])
except SubsetNotFoundError:
continue
new_cols = (set(subset_df) - set(df.columns)) | set([self.DATE])
subset_df = subset_df.loc[:, subset_df.columns.isin(new_cols)]
df = df.merge(subset_df, how="outer", on=self.DATE)
# Remove columns which is included in the main datasets
df = df.loc[:, ~df.columns.isin(self._main_cols)]
# Data cleaning
df = df.set_index(self.DATE).resample("D").last()
df = df.fillna(method="ffill").fillna(0)
# Subsetting by dates
df = df.loc[pd.to_datetime(self._first_date):pd.
to_datetime(self._last_date)]
# Convert float values to integer if values will not be changed
for col in df.columns:
converted2int = df[col].astype(np.int64)
if np.array_equal(converted2int, df[col]):
df[col] = converted2int
return df.reset_index()
def recovery_period(self):
"""
Return representative value of recovery period of all countries.
Raises:
NotRegisteredMainError: JHUData was not registered
Returns:
int: recovery period [days]
"""
jhu_data = self._data_dict[self.__NAME_JHU]
if jhu_data is None:
raise NotRegisteredMainError(".register(jhu_data)")
return jhu_data.recovery_period
def show_complement(self):
"""
Show the details of complement that was (or will be) performed for the records.
Raises:
NotRegisteredMainError: JHUData was not registered
Returns:
pandas.DataFrame: as the same as JHUData.show_complement()
Note:
Keyword arguments of JHUData,subset_complement() can be specified with DataHandler.switch_complement().
"""
jhu_data = self._data_dict[self.__NAME_JHU]
if jhu_data is None:
raise NotRegisteredMainError(".register(jhu_data)")
comp_dict = self._complement_dict.copy()
comp_dict.pop("auto_complement")
return jhu_data.show_complement(start_date=self._first_date,
end_date=self._last_date,
**self._area_dict,
**comp_dict)
