def test_unique_timeseries(data_source_cls):
data_source = data_source_cls.local()
timeseries = TimeseriesDataset.build_from_data_source(data_source)
timeseries = combined_datasets.US_STATES_FILTER.apply(timeseries)
timeseries_data = timeseries.data.set_index(timeseries.INDEX_FIELDS)
duplicates = timeseries_data.index.duplicated()
assert not sum(duplicates)
def test_unique_timeseries(data_source_cls):
data_source = data_source_cls.local()
timeseries = TimeseriesDataset.build_from_data_source(data_source)
timeseries = combined_datasets.US_STATES_FILTER.apply(timeseries)
# Check for duplicate rows with the same INDEX_FIELDS. Sort by index so duplicates are next to
# each other in the message if the assert fails.
timeseries_data = timeseries.data.set_index(timeseries.INDEX_FIELDS).sort_index()
duplicates = timeseries_data.index.duplicated(keep=False)
assert not sum(duplicates), str(timeseries_data.loc[duplicates])
def build_from_data_source(cls, source):
from libs.datasets.timeseries import TimeseriesDataset
if set(source.INDEX_FIELD_MAP.keys()) == set(TimeseriesDataset.INDEX_FIELDS):
timeseries = TimeseriesDataset.build_from_data_source(source)
return timeseries.to_latest_values_dataset()
if set(source.INDEX_FIELD_MAP.keys()) != set(cls.INDEX_FIELDS):
raise ValueError("Index fields must match")
return cls.from_source(source)
def build_from_data_source(cls, source):
from libs.datasets.timeseries import TimeseriesDataset
if set(source.INDEX_FIELD_MAP.keys()) == set(
TimeseriesDataset.INDEX_FIELDS):
timeseries = TimeseriesDataset.build_from_data_source(source)
return timeseries.to_latest_values_dataset()
if set(source.INDEX_FIELD_MAP.keys()) != set(cls.INDEX_FIELDS):
raise ValueError("Index fields must match")
return cls.from_source(
source, fill_missing_state=source.FILL_MISSING_STATE_LEVEL_DATA)
def timeseries(self) -> TimeseriesDataset:
"""Builds generic beds dataset"""
return TimeseriesDataset.build_from_data_source(self)