def timeseries(self) -> TimeseriesDataset:
"""Build TimeseriesDataset from this data source."""
if set(self.INDEX_FIELD_MAP.keys()) != set(
TimeseriesDataset.INDEX_FIELDS):
raise ValueError("Index fields must match")
return TimeseriesDataset.from_source(
self, fill_missing_state=self.FILL_MISSING_STATE_LEVEL_DATA)
def test_summarize_timeseries_fields_with_some_real_data():
data_source = CovidCountyDataDataSource.local()
ts = TimeseriesDataset.from_source(data_source)
summary = summarize_timeseries_fields(
ts.data.loc[lambda df: df[CommonFields.FIPS].str.startswith("06")])
assert not summary.empty
cases_summary = summary.loc[("06025", "cases"), :]
assert summary.loc[("06025", "cases"), "max_value"] > 7000
assert summary.loc[("06025", "cases"),
"max_date"] > pd.to_datetime("2020-08-01")
assert summary.loc[("06025", "cases"),
"largest_delta_date"] > pd.to_datetime("2020-04-01")
assert cases_summary["has_value"] == True
assert cases_summary["num_observations"] > 100
def test_expected_field_in_sources(data_source_cls):
data_source = data_source_cls.local()
ts = TimeseriesDataset.from_source(data_source)
# Extract the USA data from the raw DF. Replace this with cleaner access when the DataSource makes it easy.
rename_columns = {source: common for common, source in data_source.all_fields_map().items()}
renamed_data = data_source.data.rename(columns=rename_columns)
usa_data = renamed_data.loc[renamed_data["country"] == "USA"]
assert not usa_data.empty
states = set(usa_data["state"])
if data_source.SOURCE_NAME == "NHA":
assert states == {"NV"}
else:
good_state = set()
for state in states:
if re.fullmatch(r"[A-Z]{2}", state):
good_state.add(state)
else:
logging.info(f"Ignoring {state} in {data_source.SOURCE_NAME}")
assert len(good_state) >= 48
def timeseries(self) -> "TimeseriesDataset":
"""Builds generic beds dataset"""
return TimeseriesDataset.from_source(self)