def load_forecast_data(key: EntityKey, location: str):
location_id = extract.get_location_id(location)
path = paths.forecast_data_path(key)
data = extract.load_forecast_from_xarray(path, location_id)
data = data[data.scenario == project_globals.FORECASTING_SCENARIO].drop(
columns='scenario')
if key == EntityKey('etiology.shigellosis.incidence'):
# Only one draw for incidence
data = pd.concat(project_globals.NUM_DRAWS * [
data.set_index(
['location_id', 'age_group_id', 'sex_id', 'year_id']).value
],
axis=1)
else:
data = data.set_index(
['location_id', 'age_group_id', 'sex_id', 'year_id',
'draw']).unstack()
if len(data.columns) == 100: # Not 1000 draws for everything
data = pd.concat([data] * 10, axis=1)
data.columns = pd.Index([f'draw_{i}' for i in range(1000)])
data = data.reset_index()
data = standardize.normalize(data)
data = utilities.reshape(data)
data = utilities.scrub_gbd_conventions(data, location)
data = utilities.split_interval(data,
interval_column='age',
split_column_prefix='age')
data = utilities.split_interval(data,
interval_column='year',
split_column_prefix='year')
return utilities.sort_hierarchical_data(data)
def _load_diarrhea_sequela_disability_weight(sequela, location_id: int):
logger.info(f'Loading disability weight for {sequela.name} from GBD 2016.')
data = extract.get_auxiliary_data('disability_weight', 'sequela', 'all',
location_id)
data = data.loc[data.healthstate_id == sequela.healthstate.gbd_id, :]
data = standardize.normalize(data)
data = utilities.clear_disability_weight_outside_restrictions(
data, causes.diarrheal_diseases, 0.0, utility_data.get_age_group_ids())
data = data.filter(vi_globals.DEMOGRAPHIC_COLUMNS +
vi_globals.DRAW_COLUMNS)
return utilities.reshape(data)
def _load_prevalence(entity, location_id: int, entity_type: str):
logger.info(f'Loading prevalence for {entity.name} from GBD 2016.')
data = extract.get_como_draws(entity.gbd_id, location_id, entity_type)
data = data[data.measure_id == vi_globals.MEASURES['Prevalence']]
data = utilities.filter_data_by_restrictions(
data, causes.diarrheal_diseases, 'yld',
utility_data.get_age_group_ids())
data = data[data.year_id == 2016].drop(
columns='year_id') # Use latest GBD results for all data
data = standardize.normalize(data, fill_value=0)
data = data.filter(vi_globals.DEMOGRAPHIC_COLUMNS +
vi_globals.DRAW_COLUMNS)
return utilities.reshape(data)
def _get_raw_demographic_dimensions(location: str):
location_id = extract.get_location_id(location)
ages = utility_data.get_age_group_ids()
years = range(project_globals.MIN_YEAR, project_globals.MAX_YEAR + 1)
sexes = [vi_globals.SEXES['Male'], vi_globals.SEXES['Female']]
location_id = [location_id]
values = [location_id, sexes, ages, years]
names = ['location_id', 'sex_id', 'age_group_id', 'year_id']
data = (pd.MultiIndex.from_product(values,
names=names).to_frame(index=False))
data = standardize.normalize(data)
data = utilities.reshape(data)
return data
def load_shigella_remission_rate(key: EntityKey, location: str):
location_id = extract.get_location_id(location)
data = extract.get_modelable_entity_draws(
causes.diarrheal_diseases.dismod_id, location_id)
data = data[data.measure_id == vi_globals.MEASURES['Remission rate']]
data = utilities.filter_data_by_restrictions(
data, causes.diarrheal_diseases, 'yld',
utility_data.get_age_group_ids())
data = data[data.year_id == 2016].drop(
columns='year_id') # Use latest GBD results for all data
data = standardize.normalize(data, fill_value=0)
data = data.filter(vi_globals.DEMOGRAPHIC_COLUMNS +
vi_globals.DRAW_COLUMNS)
data = utilities.reshape(data)
data = utilities.scrub_gbd_conventions(data, location)
data = utilities.split_interval(data,
interval_column='age',
split_column_prefix='age')
data = utilities.split_interval(data,
interval_column='year',
split_column_prefix='year')
return utilities.sort_hierarchical_data(data)
def load_live_births_by_year(key: EntityKey, location: str):
location_id = extract.get_location_id(location)
asfr_key = EntityKey('covariate.age_specific_fertility_rate.estimate')
pop_key = EntityKey(project_globals.POPULATION_STRUCTURE)
asfr_data = extract.load_forecast_from_xarray(
paths.forecast_data_path(asfr_key), location_id)
asfr_data = asfr_data[
(asfr_data.scenario == project_globals.FORECASTING_SCENARIO)
& (asfr_data.year_id >= project_globals.MIN_YEAR)].drop(
columns='scenario')
asfr_data = asfr_data.set_index(
['location_id', 'age_group_id', 'sex_id', 'year_id',
'draw']).unstack()
asfr_data.columns = pd.Index([f'draw_{i}' for i in range(1000)])
pop_data = extract.load_forecast_from_xarray(
paths.forecast_data_path(pop_key), location_id)
pop_data = pop_data[(
pop_data.scenario == project_globals.FORECASTING_SCENARIO)].drop(
columns='scenario')
pop_data = pop_data.set_index(
['location_id', 'age_group_id', 'sex_id', 'year_id',
'draw']).unstack()
pop_data.columns = pd.Index([f'draw_{i}' for i in range(1000)])
pop_data = pop_data.loc[asfr_data.index]
live_births = asfr_data * pop_data
live_births = (live_births.reset_index().drop(
columns=['sex_id', 'age_group_id']).groupby(['location_id', 'year_id'
]).sum().reset_index())
data = standardize.normalize(live_births)
data = utilities.reshape(data)
data = utilities.scrub_gbd_conventions(data, location)
data = utilities.split_interval(data,
interval_column='year',
split_column_prefix='year')
return utilities.sort_hierarchical_data(data)