def get_data(
self,
aggregation_level,
country=None,
fips: Optional[str] = None,
state: Optional[str] = None,
states: Optional[List[str]] = None,
on: Optional[str] = None,
after: Optional[str] = None,
before: Optional[str] = None,
columns_slice: Optional[List[str]] = None,
) -> pd.DataFrame:
rows_binary_array = dataset_utils.make_binary_array(
self.data,
aggregation_level=aggregation_level,
country=country,
fips=fips,
state=state,
states=states,
on=on,
after=after,
before=before,
)
if columns_slice is None:
columns_slice = slice(None, None, None)
return self.data.loc[rows_binary_array, columns_slice]
def get_subset(
self,
aggregation_level,
country=None,
fips: Optional[str] = None,
state: Optional[str] = None,
states: Optional[List[str]] = None,
on: Optional[str] = None,
after: Optional[str] = None,
before: Optional[str] = None,
) -> "TimeseriesDataset":
"""Fetch a new TimeseriesDataset with a subset of the data in `self`.
Some parameters are only used in ipython notebooks."""
row_binary_array = dataset_utils.make_binary_array(
self.data,
aggregation_level=aggregation_level,
country=country,
fips=fips,
state=state,
states=states,
on=on,
after=after,
before=before,
)
return self.__class__(self.data.loc[row_binary_array, :])
def column_as_set(
df: pd.DataFrame,
column: str,
aggregation_level,
state=None,
states=None,
on=None,
after=None,
before=None,
):
"""Return values in selected rows and column of df.
Exists to call `make_binary_array` without listing all the parameters.
"""
rows_binary_array = dataset_utils.make_binary_array(
df,
aggregation_level,
country=None,
fips=None,
state=state,
states=states,
on=on,
after=after,
before=before,
)
return set(df.loc[rows_binary_array][column])
def get_subset(
self,
aggregation_level=None,
country=None,
fips: Optional[str] = None,
state: Optional[str] = None,
states: Optional[List[str]] = None,
on: Optional[str] = None,
after: Optional[str] = None,
before: Optional[str] = None,
) -> "LatestValuesDataset":
rows_binary_array = make_binary_array(
self.data,
aggregation_level=aggregation_level,
country=country,
fips=fips,
state=state,
states=states,
on=on,
after=after,
before=before,
)
return self.__class__(self.data.loc[rows_binary_array, :])