def test_get_testing_df_by_state():
positive_field = CovidTrackingDataSource.Fields.POSITIVE_TESTS
negative_field = CovidTrackingDataSource.Fields.NEGATIVE_TESTS
df = build_processed_dataset.get_testing_timeseries_by_state("MA")
assert positive_field in df.columns
assert negative_field in df.columns
# TODO(tom): have build_processed_dataset return a real datetime dtype so callers don't need to parse a string.
df[CommonFields.DATE] = pd.to_datetime(df[CommonFields.DATE],
format="%m/%d/%y")
df.set_index(CommonFields.DATE, inplace=True)
# No joke, our only source of state-level timeseries testing data is CDSDataset and it has NaN for MA until April 6.
assert 0 < df.at["2020-04-10", positive_field] < df.at["2020-05-01",
positive_field]
assert 0 < df.at["2020-04-10", negative_field] < df.at["2020-05-01",
negative_field]
def generate_state_timeseries(
projection_row, intervention, input_dir
) -> CovidActNowStateTimeseries:
state = US_STATE_ABBREV[projection_row[rc.STATE_FULL_NAME]]
fips = projection_row[rc.FIPS]
raw_dataseries = get_can_projection.get_can_raw_data(
input_dir, state, fips, AggregationLevel.STATE, intervention
)
# join in state testing data onto the timeseries
# left join '%m/%d/%y', so the left join gracefully handles
# missing state testing data (i.e. NE)
testing_df = get_testing_timeseries_by_state(state)
new_df = pd.DataFrame(raw_dataseries).merge(testing_df, on="date", how="left")
can_dataseries = new_df.to_dict(orient="records")
timeseries = []
for data_series in can_dataseries:
timeseries.append(_generate_state_timeseries_row(data_series))
projections = _generate_api_for_projections(projection_row)
if len(timeseries) < 1:
raise Exception(f"State time series empty for {intervention.name}")
state_intervention = get_can_projection.get_intervention_for_state(state)
actuals_ts = combined_datasets.build_us_timeseries_with_all_fields()
actual_latest = combined_datasets.build_us_latest_with_all_fields()
state_latest = actual_latest.get_record_for_state(state)
return CovidActNowStateTimeseries(
population=state_latest[CommonFields.POPULATION],
lat=projection_row[rc.LATITUDE],
long=projection_row[rc.LONGITUDE],
actuals=_generate_actuals(
state_latest, state_intervention
),
stateName=projection_row[rc.STATE_FULL_NAME],
fips=projection_row[rc.FIPS],
lastUpdatedDate=_format_date(projection_row[rc.LAST_UPDATED]),
projections=projections,
timeseries=timeseries,
actuals_timeseries=_generate_actuals_timeseries(
actuals_ts.get_records_for_state(state), state_intervention
),
)
def test_get_testing_df():
testing_df = build_processed_dataset.get_testing_timeseries_by_state('MA')
assert testing_df is not None