def __init__(
self,
state,
output_interval_days=4,
run_mode="can-before",
output_dir=None,
jhu_dataset=None,
cds_dataset=None,
include_imputed=False,
):
self.output_interval_days = output_interval_days
self.state = state
self.run_mode = RunMode(run_mode)
self.include_imputed = include_imputed
self.state_abbreviation = us.states.lookup(state).abbr
self.population_data = FIPSPopulation.local().population()
self.output_dir = output_dir
self.jhu_local = jhu_dataset or JHUDataset.local()
self.cds_dataset = cds_dataset or CDSDataset.local()
self.county_timeseries = build_aggregate_county_data_frame(self.jhu_local, self.cds_dataset)
self.county_timeseries["date"] = self.county_timeseries["date"].dt.normalize()
self.state_timeseries = self.jhu_local.timeseries().state_data
self.state_timeseries["date"] = self.state_timeseries["date"].dt.normalize()
self.df_whitelist = load_data.load_whitelist()
self.df_whitelist = self.df_whitelist[self.df_whitelist["inference_ok"] == True]
def __init__(
self,
state,
output_interval_days=4,
run_mode="can-before",
output_dir=None,
jhu_dataset=None,
cds_dataset=None,
include_imputed=False,
):
self.output_interval_days = output_interval_days
self.state = state
self.run_mode = RunMode(run_mode)
self.include_imputed = include_imputed
self.state_abbreviation = us.states.lookup(state).abbr
self.population_data = FIPSPopulation.local().population()
self.output_dir = output_dir
self.jhu_local = jhu_dataset or JHUDataset.local()
self.cds_dataset = cds_dataset or CDSDataset.local()
self.county_timeseries = build_aggregate_county_data_frame(
self.jhu_local, self.cds_dataset)
self.county_timeseries["date"] = self.county_timeseries[
"date"].dt.normalize()
state_timeseries = self.jhu_local.timeseries().get_subset(
AggregationLevel.STATE)
self.state_timeseries = state_timeseries.data["date"].dt.normalize()
def _cache_global_datasets():
# Populate cache for combined latest and timeseries. Caching pre-fork
# will make sure cache is populated for subprocesses. Return value
# is not needed as the only goal is to populate the cache.
combined_datasets.build_us_latest_with_all_fields()
combined_datasets.build_us_timeseries_with_all_fields()
global nyt_dataset, cds_dataset
if cds_dataset is None:
cds_dataset = CDSDataset.local()
if nyt_dataset is None:
nyt_dataset = NYTimesDataset.local()
def _cache_global_datasets():
global nyt_dataset, cds_dataset
if cds_dataset is None:
cds_dataset = CDSDataset.local()
if nyt_dataset is None:
nyt_dataset = NYTimesDataset.load()
def get_cds():
cds_df = CDSDataset.local().data
cds_df["date"] = cds_df.date.apply(lambda x: x.strftime("%m/%d/%y"))
cds_df = cds_df[CDSDataset.TEST_FIELDS]
return cds_df