def test_multi_region_get_one_region():
ts = timeseries.MultiRegionTimeseriesDataset.from_csv(
io.StringIO(
"location_id,county,aggregate_level,date,m1,m2\n"
"iso1:us#fips:97111,Bar County,county,2020-04-02,2,\n"
"iso1:us#fips:97222,Foo County,county,2020-04-01,,10\n"
"iso1:us#fips:97111,Bar County,county,,3,\n"
"iso1:us#fips:97222,Foo County,county,,,11\n"
)
)
region_97111_ts = ts.get_one_region(Region.from_fips("97111"))
assert to_dict(["date"], region_97111_ts.data[["date", "m1", "m2"]]) == {
pd.to_datetime("2020-04-02"): {"m1": 2}
}
assert region_97111_ts.latest["m1"] == 3
region_97222_ts = ts.get_one_region(Region.from_fips("97222"))
assert to_dict(["date"], region_97222_ts.data) == {
pd.to_datetime("2020-04-01"): {
"m2": 10,
"county": "Foo County",
"fips": "97222",
"location_id": "iso1:us#fips:97222",
"aggregate_level": "county",
}
}
assert region_97222_ts.latest["m2"] == 11
def test_dataclass_include_exclude():
orig_data_source_cls = CANScraperUSAFactsProvider
orig_ds = orig_data_source_cls.make_dataset()
assert "iso1:us#iso2:us-tx" in orig_ds.static.index
assert "iso1:us#iso2:us-ny" in orig_ds.static.index
ny_source = combined_datasets.datasource_regions(
orig_data_source_cls, RegionMask(states=["NY"])
)
assert ny_source.SOURCE_NAME == orig_data_source_cls.SOURCE_NAME
assert ny_source.EXPECTED_FIELDS == orig_data_source_cls.EXPECTED_FIELDS
ny_ds = ny_source.make_dataset()
assert "iso1:us#iso2:us-tx" not in ny_ds.static.index
assert "iso1:us#iso2:us-ny" in ny_ds.static.index
ca_counties_without_la_source = combined_datasets.datasource_regions(
orig_data_source_cls,
RegionMask(AggregationLevel.COUNTY, states=["CA"]),
exclude=Region.from_fips("06037"),
)
ds = ca_counties_without_la_source.make_dataset()
assert "iso1:us#iso2:us-tx" not in ds.static.index
assert "iso1:us#iso2:us-ca" not in ds.static.index
assert "iso1:us#iso2:us-ca#fips:06045" in ds.static.index
assert "iso1:us#iso2:us-ca#fips:06037" not in ds.static.index
# Just Cook County, IL
ds = combined_datasets.datasource_regions(
orig_data_source_cls, include=Region.from_fips("17031")
).make_dataset()
assert ds.static.index.to_list() == ["iso1:us#iso2:us-il#fips:17031"]
def test_provenance():
region_as = Region.from_state("AS")
region_tx = Region.from_state("TX")
metrics_as = {
CommonFields.POSITIVE_TESTS: TimeseriesLiteral([0, 2, 4, 6], provenance="pt_src1"),
CommonFields.TOTAL_TESTS: [100, 200, 300, 400],
}
metrics_tx = {
CommonFields.POSITIVE_TESTS: TimeseriesLiteral([1, 2, 3, 4], provenance="pt_src2"),
CommonFields.POSITIVE_TESTS_VIRAL: TimeseriesLiteral(
[10, 20, 30, 40], provenance="pos_viral"
),
CommonFields.TOTAL_TESTS: [100, 200, 300, 400],
}
dataset_in = test_helpers.build_dataset({region_as: metrics_as, region_tx: metrics_tx})
methods = [
DivisionMethod(
DatasetName("method1"), CommonFields.POSITIVE_TESTS_VIRAL, CommonFields.TOTAL_TESTS
),
DivisionMethod(
DatasetName("method2"), CommonFields.POSITIVE_TESTS, CommonFields.TOTAL_TESTS
),
]
all_methods = AllMethods.run(dataset_in, methods, diff_days=3)
expected_as = {CommonFields.TEST_POSITIVITY: TimeseriesLiteral([0.02], provenance=["pt_src1"])}
expected_tx = {CommonFields.TEST_POSITIVITY: TimeseriesLiteral([0.1], provenance="pos_viral")}
expected_positivity = test_helpers.build_dataset(
{region_as: expected_as, region_tx: expected_tx}, start_date="2020-04-04"
)
test_helpers.assert_dataset_like(all_methods.test_positivity, expected_positivity)
def test_multi_region_to_from_timeseries_and_latest_values(tmp_path: pathlib.Path):
ts = timeseries.TimeseriesDataset(
read_csv_and_index_fips_date(
"fips,county,aggregate_level,date,m1,m2\n"
"97111,Bar County,county,2020-04-02,2,\n"
"97222,Foo County,county,2020-04-01,,10\n"
"01,,state,2020-04-01,,20\n"
).reset_index()
)
latest_values = timeseries.LatestValuesDataset(
read_csv_and_index_fips(
"fips,county,aggregate_level,c1,c2\n"
"97111,Bar County,county,3,\n"
"97222,Foo County,county,4,10.5\n"
"01,,state,,123.4\n"
).reset_index()
)
multiregion = timeseries.MultiRegionTimeseriesDataset.from_timeseries_and_latest(
ts, latest_values
)
region_97111 = multiregion.get_one_region(Region.from_fips("97111"))
assert region_97111.date_indexed.at["2020-04-02", "m1"] == 2
assert region_97111.latest["c1"] == 3
assert multiregion.get_one_region(Region.from_fips("01")).latest["c2"] == 123.4
csv_path = tmp_path / "multiregion.csv"
multiregion.to_csv(csv_path)
multiregion_loaded = timeseries.MultiRegionTimeseriesDataset.from_csv(csv_path)
region_97111 = multiregion_loaded.get_one_region(Region.from_fips("97111"))
assert region_97111.date_indexed.at["2020-04-02", "m1"] == 2
assert region_97111.latest["c1"] == 3
assert multiregion_loaded.get_one_region(Region.from_fips("01")).latest["c2"] == 123.4
def get_run_artifact_path(region: Region,
artifact: RunArtifact,
output_dir=None) -> str:
"""
Get an artifact path for a given locale and artifact type.
Parameters
----------
fips: str
State or county fips code. Can also be a 2 character state abbreviation.
If arbitrary string (e.g. for tests) then passed through
artifact: RunArtifact
The artifact type to retrieve the pointer for.
output_dir: str or NoneType
Output directory to obtain the path for.
Returns
-------
path: str
Location of the artifact.
"""
output_dir = output_dir or OUTPUT_DIR
if region.level is AggregationLevel.COUNTY:
state_name = region.get_state_region().state_obj().name
county = combined_datasets.get_county_name(region)
readable_name = f"{state_name}__{county}__{region.fips}"
folder = REPORTS_FOLDER(output_dir, state_name)
elif region.level is AggregationLevel.STATE:
state_name = region.state_obj().name
readable_name = f"{state_name}__{region.fips}"
folder = os.path.join(STATE_SUMMARY_FOLDER(output_dir), "reports")
elif region.level is AggregationLevel.CBSA:
readable_name = f"CBSA__{region.fips}"
folder = os.path.join(STATE_SUMMARY_FOLDER(output_dir), "reports")
elif region.level is AggregationLevel.PLACE:
state_name = region.get_state_region().state_obj().name
readable_name = f"{state_name}__{region.fips}"
folder = os.path.join(STATE_SUMMARY_FOLDER(output_dir), "reports")
elif region.level is AggregationLevel.COUNTRY:
readable_name = region.country
folder = os.path.join(output_dir, "pyseir", "reports")
else:
raise AssertionError(f"Unsupported aggregation level {region.level}")
artifact = RunArtifact(artifact)
if artifact is RunArtifact.RT_INFERENCE_REPORT:
path = os.path.join(folder, f"Rt_results__{readable_name}.pdf")
elif artifact is RunArtifact.RT_SMOOTHING_REPORT:
path = os.path.join(folder, f"Rt_smoothing__{readable_name}.pdf")
else:
raise ValueError(f"No paths available for artifact {RunArtifact}")
os.makedirs(os.path.dirname(path), exist_ok=True)
return path
def test_regions_in_states_basic():
whitelist_df = read_csv_and_index_fips(
"fips,state,county,inference_ok\n"
"45111,TX,Bar County,True\n"
"06222,CA,Foo County,True\n").reset_index()
regions = regions_in_states(
[pipeline.Region.from_state(s) for s in ["CA", "TX"]], whitelist_df)
assert set(regions) == {
Region.from_fips("45111"),
Region.from_fips("06222")
}
def test_aggregate():
df_in = read_csv_and_index_fips_date(
"fips,state,aggregate_level,county,m1,date,foo\n"
"55005,ZZ,county,North County,1,2020-05-01,11\n"
"55005,ZZ,county,North County,2,2020-05-02,22\n"
"55005,ZZ,county,North County,3,2020-05-03,33\n"
"55005,ZZ,county,North County,0,2020-05-04,0\n"
"55006,ZZ,county,South County,0,2020-05-01,0\n"
"55006,ZZ,county,South County,0,2020-05-02,0\n"
"55006,ZZ,county,South County,3,2020-05-03,44\n"
"55006,ZZ,county,South County,4,2020-05-04,55\n"
"55,ZZ,state,Grand State,41,2020-05-01,66\n"
"55,ZZ,state,Grand State,43,2020-05-03,77\n"
).reset_index()
ts_in = MultiRegionDataset.from_fips_timeseries_df(df_in)
agg = statistical_areas.CountyToCBSAAggregator(
county_map={"55005": "10001", "55006": "10001"},
cbsa_title_map={"10001": "Stat Area 1"},
aggregations=[],
)
ts_out = agg.aggregate(ts_in)
assert ts_out.groupby_region().ngroups == 1
ts_cbsa = ts_out.get_one_region(Region.from_cbsa_code("10001"))
assert ts_cbsa.date_indexed["m1"].to_dict() == {
pd.to_datetime("2020-05-01"): 1,
pd.to_datetime("2020-05-02"): 2,
pd.to_datetime("2020-05-03"): 6,
pd.to_datetime("2020-05-04"): 4,
}
def test_top_level_metrics_with_rt():
region = Region.from_fips("36")
data = (
"date,fips,cases,positive_tests,negative_tests,contact_tracers_count"
",current_icu,current_icu_total,icu_beds\n"
"2020-08-17,36,10,10,90,1,,,\n"
"2020-08-18,36,20,20,180,2,,,\n"
"2020-08-19,36,,,,3,,,\n"
"2020-08-20,36,40,40,360,4,,,\n")
one_region = _fips_csv_to_one_region(data, region)
data = ("date,fips,Rt_MAP_composite,Rt_ci95_composite\n"
"2020-08-17,36,1.1,1.2\n"
"2020-08-18,36,1.2,1.3\n"
"2020-08-19,36,1.1,1.3\n"
"2020-08-20,36,1.1,1.2\n")
rt_data = _fips_csv_to_one_region(data, region)
latest = {
CommonFields.POPULATION: 100_000,
CommonFields.FIPS: "36",
CommonFields.STATE: "NY",
CommonFields.ICU_TYPICAL_OCCUPANCY_RATE: 0.5,
CommonFields.ICU_BEDS: 25,
}
def test_aggregate():
ts = TimeseriesDataset.load_csv(
io.StringIO("fips,state,aggregate_level,county,m1,date,foo\n"
"55005,ZZ,county,North County,1,2020-05-01,ab\n"
"55005,ZZ,county,North County,2,2020-05-02,cd\n"
"55005,ZZ,county,North County,3,2020-05-03,ef\n"
"55006,ZZ,county,South County,3,2020-05-03,ef\n"
"55006,ZZ,county,South County,4,2020-05-04,gh\n"
"55,ZZ,state,Grand State,41,2020-05-01,ij\n"
"55,ZZ,state,Grand State,43,2020-05-03,kl\n"))
ts_in = MultiRegionTimeseriesDataset.from_timeseries_and_latest(
ts, ts.latest_values_object())
agg = statistical_areas.CountyToCBSAAggregator(
county_map={
"55005": "10001",
"55006": "10001"
},
cbsa_title_map={"10001": "Stat Area 1"})
ts_out = agg.aggregate(ts_in)
assert ts_out.groupby_region().ngroups == 1
ts_cbsa = ts_out.get_one_region(Region.from_cbsa_code("10001"))
assert ts_cbsa.date_indexed["m1"].to_dict() == {
pd.to_datetime("2020-05-01"): 1,
pd.to_datetime("2020-05-02"): 2,
pd.to_datetime("2020-05-03"): 6,
pd.to_datetime("2020-05-04"): 4,
}
def test_combined_county_has_some_data(fips):
region_data = combined_datasets.load_us_timeseries_dataset().get_one_region(
Region.from_fips(fips)
)
assert region_data.data[CommonFields.POSITIVE_TESTS].all()
assert region_data.data[CommonFields.NEGATIVE_TESTS].all()
assert region_data.latest[CommonFields.DEATHS] > 1
def test_calculate_icu_capacity():
region = Region.from_fips("36")
latest = {
CommonFields.POPULATION: 100_000,
CommonFields.FIPS: "36",
CommonFields.STATE: "NY",
}
def test_annotation(rt_dataset, icu_dataset):
region = Region.from_state("IL")
tag = test_helpers.make_tag(date="2020-04-01", original_observation=10.0)
death_url = UrlStr("http://can.com/death_source")
cases_urls = [UrlStr("http://can.com/one"), UrlStr("http://can.com/two")]
new_cases_url = UrlStr("http://can.com/new_cases")
ds = test_helpers.build_default_region_dataset(
{
CommonFields.CASES:
TimeseriesLiteral(
[100, 200, 300], provenance="NYTimes", source_url=cases_urls),
# NEW_CASES has only source_url set, to make sure that an annotation is still output.
CommonFields.NEW_CASES:
TimeseriesLiteral([100, 100, 100], source_url=new_cases_url),
CommonFields.CONTACT_TRACERS_COUNT: [10] * 3,
CommonFields.ICU_BEDS:
TimeseriesLiteral([20, 20, 20], provenance="NotFound"),
CommonFields.CURRENT_ICU: [5, 5, 5],
CommonFields.DEATHS:
TimeseriesLiteral(
[2, 3, 2], annotation=[tag], source_url=death_url),
},
region=region,
static={
CommonFields.POPULATION: 100_000,
CommonFields.STATE: "IL",
CommonFields.CAN_LOCATION_PAGE_URL:
"http://covidactnow.org/foo/bar",
},
)
def modify_dataset(ds: MultiRegionDataset) -> MultiRegionDataset:
ts_copy = ds.timeseries.copy()
# Test positivity should be a ratio
ts_copy.loc[:, CommonFields.TEST_POSITIVITY_7D] = (
ts_copy.loc[:, CommonFields.TEST_POSITIVITY_7D] / 100.0)
levels = set(
Region.from_location_id(l).level for l in
ds.timeseries.index.get_level_values(CommonFields.LOCATION_ID))
# Should only be picking up county all_df for now. May need additional logic if states
# are included as well
assert levels == {AggregationLevel.COUNTY}
# Duplicating DC County results as state results because of a downstream
# use of how dc state data is used to override DC county data.
dc_results = ts_copy.xs(DC_COUNTY_LOCATION_ID,
axis=0,
level=CommonFields.LOCATION_ID,
drop_level=False)
dc_results = dc_results.rename(
index={DC_COUNTY_LOCATION_ID: DC_STATE_LOCATION_ID},
level=CommonFields.LOCATION_ID)
ts_copy = ts_copy.append(dc_results, verify_integrity=True).sort_index()
return dataclasses.replace(ds,
timeseries=remove_trailing_zeros(ts_copy),
timeseries_bucketed=None)
def test_dataclass_include_exclude():
"""Tests datasource_regions using mock data for speed."""
region_data = {CommonFields.CASES: [100, 200, 300], CommonFields.DEATHS: [0, 1, 2]}
regions_orig = [Region.from_state(state) for state in "AZ CA NY IL TX".split()] + [
Region.from_fips(fips) for fips in "06037 06045 17031 17201".split()
]
dataset_orig = test_helpers.build_dataset({region: region_data for region in regions_orig})
# Make a new subclass to keep this test separate from others in the make_dataset lru_cache.
class DataSourceForTest(data_source.DataSource):
EXPECTED_FIELDS = [CommonFields.CASES, CommonFields.DEATHS]
SOURCE_TYPE = "DataSourceForTest"
@classmethod
def make_dataset(cls) -> timeseries.MultiRegionDataset:
return dataset_orig
orig_data_source_cls = DataSourceForTest
orig_ds = orig_data_source_cls.make_dataset()
assert "iso1:us#iso2:us-tx" in orig_ds.location_ids
assert "iso1:us#iso2:us-ny" in orig_ds.location_ids
ny_source = combined_datasets.datasource_regions(
orig_data_source_cls, RegionMask(states=["NY"])
)
ny_ds = ny_source.make_dataset()
assert "iso1:us#iso2:us-tx" not in ny_ds.location_ids
assert "iso1:us#iso2:us-ny" in ny_ds.location_ids
ca_counties_without_la_source = combined_datasets.datasource_regions(
orig_data_source_cls,
RegionMask(AggregationLevel.COUNTY, states=["CA"]),
exclude=Region.from_fips("06037"),
)
ds = ca_counties_without_la_source.make_dataset()
assert "iso1:us#iso2:us-tx" not in ds.location_ids
assert "iso1:us#iso2:us-ca" not in ds.location_ids
assert "iso1:us#iso2:us-ca#fips:06045" in ds.location_ids
assert "iso1:us#iso2:us-ca#fips:06037" not in ds.location_ids
# Just Cook County, IL
ds = combined_datasets.datasource_regions(
orig_data_source_cls, include=Region.from_fips("17031")
).make_dataset()
assert ds.location_ids.to_list() == ["iso1:us#iso2:us-il#fips:17031"]
def il_regional_input(rt_dataset, icu_dataset):
region = Region.from_state("IL")
regional_data = combined_datasets.load_us_timeseries_dataset(
).get_regions_subset([region])
# TODO(tom): add test positivity back in after PR 728 is merged.
# test_positivity_results = test_positivity.AllMethods.run(regional_data)
# regional_data = regional_data.join_columns(test_positivity_results.test_positivity)
return api_v2_pipeline.RegionalInput.from_region_and_model_output(
region, regional_data, rt_dataset, icu_dataset)
def iter_one_regions(
self) -> Iterable[Tuple[Region, OneRegionTimeseriesDataset]]:
"""Iterates through all the regions in this object"""
for location_id, data_group in self.data_with_fips.groupby(
CommonFields.LOCATION_ID):
latest_dict = self._location_id_latest_dict(location_id)
yield Region(location_id=location_id,
fips=None), OneRegionTimeseriesDataset(
data_group, latest_dict)
def il_regional_input(rt_dataset, icu_dataset):
region = Region.from_state("IL")
regional_data = combined_datasets.load_us_timeseries_dataset(
).get_regions_subset([region])
regional_data = test_positivity.run_and_maybe_join_columns(
regional_data, structlog.get_logger())
return api_v2_pipeline.RegionalInput.from_region_and_model_output(
region, regional_data, rt_dataset, icu_dataset)
def test_pyseir_end_to_end_dc(tmp_path):
# Runs over a single state which tests state filtering + running over more than
# a single fips.
with unittest.mock.patch("pyseir.utils.OUTPUT_DIR", str(tmp_path)):
region = Region.from_state("DC")
pipelines = cli._build_all_for_states(states=["DC"])
# Checking to make sure that build all for states properly filters and only
# returns DC data
assert len(pipelines) == 2
def test_top_level_metrics_with_rt():
region = Region.from_fips("36")
latest = {
CommonFields.POPULATION: 100_000,
CommonFields.FIPS: "36",
CommonFields.STATE: "NY",
CommonFields.ICU_TYPICAL_OCCUPANCY_RATE: 0.5,
CommonFields.ICU_BEDS: 25,
}
def test_load_hospitalization_data():
t0 = datetime(year=2020, month=1, day=1)
region = Region.from_fips("33")
hospitalization_df = load_data.get_hospitalization_data_for_region(region)
_, _, hosp_type = load_data.calculate_hospitalization_data(
hospitalization_df, t0, category=HospitalizationCategory.ICU
)
# Double check that data loads and it went throughh the cumulative hosps
assert hosp_type is HospitalizationDataType.CUMULATIVE_HOSPITALIZATIONS
def from_state_region(region: pipeline.Region) -> "RegionalInput":
"""Creates a RegionalInput for given state region."""
assert region.is_state()
hospitalization_df = load_data.get_hospitalization_data_for_region(
region)
return RegionalInput(
region=region,
_combined_data=combined_datasets.RegionalData.from_region(region),
_hospitalization_df=hospitalization_df,
)
def test_preserve_tags():
region_as = Region.from_state("AS")
region_tx = Region.from_state("TX")
tag1 = test_helpers.make_tag(type=TagType.CUMULATIVE_LONG_TAIL_TRUNCATED, date="2020-04-04")
tag2 = test_helpers.make_tag(type=TagType.CUMULATIVE_TAIL_TRUNCATED, date="2020-04-04")
tag_drop = test_helpers.make_tag(type=TagType.ZSCORE_OUTLIER, date="2020-04-01")
tag3 = test_helpers.make_tag(type=TagType.ZSCORE_OUTLIER, date="2020-04-04")
tag4 = test_helpers.make_tag(type=TagType.ZSCORE_OUTLIER, date="2020-04-03")
metrics_as = {
CommonFields.POSITIVE_TESTS: TimeseriesLiteral(
[1, 2, 3, 4], annotation=[tag1], provenance="pos"
),
CommonFields.TOTAL_TESTS: TimeseriesLiteral([100, 200, 300, 400], annotation=[tag2]),
}
metrics_tx = {
CommonFields.POSITIVE_TESTS: TimeseriesLiteral([None, None, 3, 4], annotation=[tag_drop]),
CommonFields.POSITIVE_TESTS_VIRAL: [10, 20, 30, 40],
CommonFields.TOTAL_TESTS: TimeseriesLiteral([100, 200, 300, 400], annotation=[tag3, tag4]),
}
dataset_in = test_helpers.build_dataset({region_as: metrics_as, region_tx: metrics_tx})
methods = [
DivisionMethod(
DatasetName("method1"), CommonFields.POSITIVE_TESTS, CommonFields.TOTAL_TESTS
),
DivisionMethod(
DatasetName("method2"), CommonFields.POSITIVE_TESTS_VIRAL, CommonFields.TOTAL_TESTS
),
]
all_methods = AllMethods.run(dataset_in, methods, diff_days=3)
expected_as = {
CommonFields.TEST_POSITIVITY: TimeseriesLiteral(
[0.01], provenance="pos", annotation=[tag1, tag2]
)
}
expected_tx = {CommonFields.TEST_POSITIVITY: TimeseriesLiteral([0.1], annotation=[tag3, tag4])}
expected_positivity = test_helpers.build_dataset(
{region_as: expected_as, region_tx: expected_tx}, start_date="2020-04-04"
)
test_helpers.assert_dataset_like(all_methods.test_positivity, expected_positivity)
def test_make_latest_from_timeseries_simple():
data = read_csv_and_index_fips_date(
"fips,county,state,country,date,aggregate_level,m1,m2\n"
"97123,Smith County,ZZ,USA,2020-04-01,county,1,\n"
"97123,Smith County,ZZ,USA,2020-04-02,county,,2\n"
).reset_index()
ds = timeseries.MultiRegionDataset.from_fips_timeseries_df(data)
region = ds.get_one_region(Region.from_fips("97123"))
# Compare 2 values in region.latest
expected = {"m1": 1, "m2": 2}
actual = {key: region.latest[key] for key in expected.keys()}
assert actual == expected
def test_combined_county_has_some_timeseries_data(fips):
region = Region.from_fips(fips)
latest = combined_datasets.load_us_timeseries_dataset().get_one_region(
region)
df = latest.data.set_index(CommonFields.DATE)
assert df.loc["2020-05-01", CommonFields.CASES] > 0
assert df.loc["2020-05-01", CommonFields.DEATHS] > 0
if fips.startswith(
"06"
): # TODO(tom): Remove this condition when we have county data in TX too.
assert df.loc["2020-05-01", CommonFields.POSITIVE_TESTS] > 0
assert df.loc["2020-05-01", CommonFields.NEGATIVE_TESTS] > 0
assert df.loc["2020-05-01", CommonFields.CURRENT_ICU] > 0
def test_persist_and_load_dataset(tmp_path, nyc_fips):
region = Region.from_fips(nyc_fips)
dataset = combined_datasets.load_us_timeseries_dataset()
timeseries_nyc = dataset.get_regions_subset([region])
pointer = combined_dataset_utils.persist_dataset(timeseries_nyc, tmp_path)
downloaded_dataset = MultiRegionDataset.read_from_pointer(pointer)
differ_l = DatasetDiff.make(downloaded_dataset.timeseries)
differ_r = DatasetDiff.make(timeseries_nyc.timeseries)
differ_l.compare(differ_r)
assert not len(differ_l.my_ts)
def update_test_combined_data(truncate_dates: bool, state: List[str]):
us_dataset = combined_datasets.load_us_timeseries_dataset()
# Keep only a small subset of the regions so we have enough to exercise our code in tests.
test_subset = us_dataset.get_regions_subset([
RegionMask(states=[s.strip() for s in state]),
Region.from_fips("48201"),
Region.from_fips("48301"),
Region.from_fips("20161"),
Region.from_state("TX"),
Region.from_state("KS"),
])
if truncate_dates:
dates = test_subset.timeseries_bucketed.index.get_level_values(
CommonFields.DATE)
date_range_mask = (dates >= "2021-01-01") & (dates < "2021-04-01")
test_subset = dataclasses.replace(
test_subset,
timeseries_bucketed=test_subset.timeseries_bucketed.
loc[date_range_mask])
test_subset.write_to_wide_dates_csv(
dataset_utils.TEST_COMBINED_WIDE_DATES_CSV_PATH,
dataset_utils.TEST_COMBINED_STATIC_CSV_PATH)
def test_top_level_metrics_no_pos_neg_tests_has_positivity_ratio():
ny_region = Region.from_state("NY")
metrics = {
CommonFields.CASES: [10, 20, 30, 40],
CommonFields.NEW_CASES: [10, 10, 10, 10],
CommonFields.TEST_POSITIVITY: [0.02, 0.03, 0.04, 0.05],
}
latest = {
CommonFields.POPULATION: 100_000,
CommonFields.FIPS: "36",
CommonFields.STATE: "NY",
CommonFields.ICU_BEDS: 10,
}
def test_persist_and_load_dataset(tmp_path, nyc_fips):
region = Region.from_fips(nyc_fips)
dataset = combined_datasets.load_us_timeseries_dataset()
timeseries_nyc = TimeseriesDataset(dataset.get_one_region(region).data)
pointer = combined_dataset_utils.persist_dataset(timeseries_nyc, tmp_path)
downloaded_dataset = pointer.load_dataset()
differ_l = DatasetDiff.make(downloaded_dataset.data)
differ_r = DatasetDiff.make(timeseries_nyc.data)
differ_l.compare(differ_r)
assert not len(differ_l.my_ts)
def _transform_one_override(
override: Mapping,
cbsa_to_counties_map: Mapping[Region, List[Region]]) -> Filter:
region_str = override["region"]
if re.fullmatch(r"[A-Z][A-Z]", region_str):
region = Region.from_state(region_str)
elif re.fullmatch(r"\d{5}", region_str):
region = Region.from_fips(region_str)
else:
raise ValueError(f"Invalid region: {region_str}")
include_str = override["include"]
if include_str == "region":
regions_included = [region]
elif include_str == "region-and-subregions":
if region.is_state():
regions_included = [RegionMask(states=[region.state])]
elif region.level == AggregationLevel.CBSA:
regions_included = [region] + cbsa_to_counties_map[region]
else:
raise ValueError(
"region-and-subregions only valid for a state and CBSA")
elif include_str == "subregions":
if not region.is_state():
raise ValueError("subregions only valid for a state")
regions_included = [
RegionMask(AggregationLevel.COUNTY, states=[region.state])
]
else:
raise ValueError(f"Invalid include: {include_str}")
return Filter(
regions_included=regions_included,
fields_included=_METRIC_TO_FIELDS[override["metric"]],
internal_note=override["context"],
public_note=override.get("disclaimer", ""),
drop_observations=bool(override["blocked"]),
)
def test_basic():
region_tx = Region.from_state("TX")
region_sf = Region.from_fips("06075")
region_hi = Region.from_state("HI")
# Add a timeseries with a tag to make sure they are preserved.
ts_with_tag = TimeseriesLiteral(
[0, 0, 0], annotation=[test_helpers.make_tag(date="2020-04-01")])
ds_in = test_helpers.build_dataset({
region_tx: {
CommonFields.VACCINES_DISTRIBUTED: [0, 0, 0]
},
region_sf: {
CommonFields.VACCINES_DISTRIBUTED: [0, 0, 1]
},
region_hi: {
CommonFields.VACCINES_DISTRIBUTED: [0, 0, None],
CommonFields.CASES: ts_with_tag,
},
})
with structlog.testing.capture_logs() as logs:
ds_out = zeros_filter.drop_all_zero_timeseries(
ds_in, [CommonFields.VACCINES_DISTRIBUTED])
ds_expected = test_helpers.build_dataset({
region_sf: {
CommonFields.VACCINES_DISTRIBUTED: [0, 0, 1]
},
region_hi: {
CommonFields.CASES: ts_with_tag
},
})
log = more_itertools.one(logs)
assert log["event"] == zeros_filter.DROPPING_TIMESERIES_WITH_ONLY_ZEROS
assert pd.MultiIndex.from_tuples([
(region_hi.location_id, CommonFields.VACCINES_DISTRIBUTED),
(region_tx.location_id, CommonFields.VACCINES_DISTRIBUTED),
]).equals(log["dropped"])
test_helpers.assert_dataset_like(ds_expected, ds_out)
