def test_build_api_output_for_intervention(nyc_fips, nyc_model_output_path,
tmp_path):
county_output = tmp_path / "county"
us_latest = combined_datasets.build_us_latest_with_all_fields()
us_timeseries = combined_datasets.build_us_timeseries_with_all_fields()
nyc_latest = us_latest.get_subset(None, fips=nyc_fips)
nyc_timeseries = us_timeseries.get_subset(None, fips=nyc_fips)
all_timeseries_api = api_pipeline.run_on_all_fips_for_intervention(
nyc_latest, nyc_timeseries, Intervention.STRONG_INTERVENTION,
nyc_model_output_path.parent)
api_pipeline.deploy_single_level(Intervention.STRONG_INTERVENTION,
all_timeseries_api, tmp_path,
county_output)
expected_outputs = [
"counties.STRONG_INTERVENTION.timeseries.json",
"counties.STRONG_INTERVENTION.csv",
"counties.STRONG_INTERVENTION.timeseries.csv",
"counties.STRONG_INTERVENTION.json",
"county/36061.STRONG_INTERVENTION.json",
"county/36061.STRONG_INTERVENTION.timeseries.json",
]
output_paths = [
str(path.relative_to(tmp_path)) for path in tmp_path.glob("**/*")
if not path.is_dir()
]
assert sorted(output_paths) == sorted(expected_outputs)
def generate_api(input_dir, output, summary_output, aggregation_level, state,
fips):
"""The entry function for invocation"""
active_states = [state.abbr for state in us.STATES]
us_latest = combined_datasets.load_us_latest_dataset().get_subset(
aggregation_level, state=state, fips=fips, states=active_states)
us_timeseries = combined_datasets.load_us_timeseries_dataset().get_subset(
aggregation_level, state=state, fips=fips, states=active_states)
for intervention in list(Intervention):
_logger.info(f"Running intervention {intervention.name}")
all_timeseries = api_pipeline.run_on_all_fips_for_intervention(
us_latest, us_timeseries, intervention, input_dir)
county_timeseries = [
output for output in all_timeseries
if output.aggregate_level is AggregationLevel.COUNTY
]
api_pipeline.deploy_single_level(intervention, county_timeseries,
summary_output, output)
state_timeseries = [
output for output in all_timeseries
if output.aggregate_level is AggregationLevel.STATE
]
api_pipeline.deploy_single_level(intervention, state_timeseries,
summary_output, output)
def test_build_api_output_for_intervention(nyc_region, tmp_path, rt_dataset,
icu_dataset):
county_output = tmp_path / "county"
regional_input = api_pipeline.RegionalInput.from_region_and_intervention(
nyc_region,
Intervention.STRONG_INTERVENTION,
rt_dataset,
icu_dataset,
)
all_timeseries_api = api_pipeline.run_on_all_regional_inputs_for_intervention(
[regional_input])
api_pipeline.deploy_single_level(Intervention.STRONG_INTERVENTION,
all_timeseries_api, tmp_path,
county_output)
expected_outputs = [
"counties.STRONG_INTERVENTION.timeseries.json",
"counties.STRONG_INTERVENTION.csv",
# No projections are being generated so
# "counties.STRONG_INTERVENTION.timeseries.csv",
"counties.STRONG_INTERVENTION.json",
"county/36061.STRONG_INTERVENTION.json",
"county/36061.STRONG_INTERVENTION.timeseries.json",
]
output_paths = [
str(path.relative_to(tmp_path)) for path in tmp_path.glob("**/*")
if not path.is_dir()
]
assert sorted(output_paths) == sorted(expected_outputs)
def generate_api(input_dir, output, summary_output, aggregation_level, state,
fips):
"""The entry function for invocation"""
# Caching load of us timeseries dataset
combined_datasets.load_us_timeseries_dataset()
active_states = [state.abbr for state in us.STATES]
active_states = active_states + ["PR", "MP"]
regions = combined_datasets.get_subset_regions(
aggregation_level=aggregation_level,
exclude_county_999=True,
state=state,
fips=fips,
states=active_states,
)
icu_data_path = input_dir / SummaryArtifact.ICU_METRIC_COMBINED.value
icu_data = MultiRegionTimeseriesDataset.from_csv(icu_data_path)
rt_data_path = input_dir / SummaryArtifact.RT_METRIC_COMBINED.value
rt_data = MultiRegionTimeseriesDataset.from_csv(rt_data_path)
for intervention in list(Intervention):
_logger.info(f"Running intervention {intervention.name}")
_load_input = functools.partial(
api_pipeline.RegionalInput.from_region_and_intervention,
intervention=intervention,
rt_data=rt_data,
icu_data=icu_data,
)
with multiprocessing.Pool(maxtasksperchild=1) as pool:
regional_inputs = pool.map(_load_input, regions)
_logger.info(f"Loaded {len(regional_inputs)} regions.")
all_timeseries = api_pipeline.run_on_all_regional_inputs_for_intervention(
regional_inputs)
county_timeseries = [
output for output in all_timeseries
if output.aggregate_level is AggregationLevel.COUNTY
]
api_pipeline.deploy_single_level(intervention, county_timeseries,
summary_output, output)
state_timeseries = [
output for output in all_timeseries
if output.aggregate_level is AggregationLevel.STATE
]
api_pipeline.deploy_single_level(intervention, state_timeseries,
summary_output, output)