def parse_dataframes(
self, dataframes: Dict[str, DataFrame], aux: Dict[str, DataFrame], **parse_opts
) -> DataFrame:
data = dataframes[0]
data["date"] = data.REPORT_DATE.apply(lambda x: datetime_isoformat(x, "%Y-%m-%d"))
# Add level1 keys
subregion1s = country_subregion1s(aux["metadata"], "AU")
data = table_merge([data, subregion1s], left_on="CODE", right_on="subregion1_code", how="left")
# Country-level record has CODE AUS
country_mask = data["CODE"] == "AUS"
data.loc[country_mask, "key"] = "AU"
# Only keep country and subregion1 rows
data = data[data.key != None]
data = table_rename(
data,
{
"date": "date",
"key": "key",
"VACC_DOSE_CNT": "total_vaccine_doses_administered",
"VACC_PEOPLE_CNT": "total_persons_fully_vaccinated",
},
drop=True)
# remove rows without vaccination data
data.dropna(subset=["total_vaccine_doses_administered", "total_persons_fully_vaccinated"], how="all", inplace=True)
# based on the assumption two doses = fully vaccinated(since Australia is using Pfizer and AZ)
data["total_persons_vaccinated"] = estimate_total_persons_vaccinated(data)
return data
def parse(self, sources: Dict[str, str], aux: Dict[str, DataFrame], **parse_opts) -> DataFrame:
subregion1s = country_subregion1s(aux["metadata"], "ID")
subregion2s = country_subregion2s(aux["metadata"], "ID")
data = concat([
_get_data(sources['subregion1_url'], 'subregion1_code', _subregion1_code_to_api_id_map, subregion1s),
_get_data(sources['subregion2_url'], 'subregion2_code', _subregion2_code_to_api_id_map, subregion2s),
])
return data
def parse_dataframes(self, dataframes: Dict[str, DataFrame],
aux: Dict[str, DataFrame], **parse_opts) -> DataFrame:
data = table_rename(dataframes[0], _column_adapter, drop=True)
data.date = data.date.apply(
lambda x: datetime_isoformat(x, "%d/%m/%Y"))
# add location keys
subregion1s = country_subregion1s(aux["metadata"], "IN")
data = table_merge([data, subregion1s[["key", "subregion1_name"]]],
on=["subregion1_name"],
how="inner")
return data
def parse_dataframes(self, dataframes: Dict[str, DataFrame],
aux: Dict[str, DataFrame], **parse_opts) -> DataFrame:
data = dataframes[0]
# Flatten the table
data = melt(data,
id_vars=["State"],
var_name="date",
value_name='total_vaccine_doses_administered')
data.date = data.date.apply(
lambda x: datetime_isoformat(x, "%d/%m/%Y"))
# add location keys
subregion1s = country_subregion1s(aux["metadata"], "IN")
data = table_merge([data, subregion1s[['key', 'subregion1_name']]],
left_on="State",
right_on='subregion1_name',
how="inner")
return data