def interpolate_country_covariate_values(self, df: pd.DataFrame, cov_dict: Dict[Union[float, str], pd.DataFrame]):
"""
Interpolates the covariate values onto the data
so that the non-standard ages and years match up to meaningful
covariate values.
"""
LOG.info(f"Interpolating and merging the country covariates.")
interp_df = get_interpolated_covariate_values(
data_df=df,
covariate_dict=cov_dict,
population_df=self.population.configure_for_dismod()
)
return interp_df
def calculate_country_covariate_reference_values(
self, parent_location_id: int, sex_id: int) -> CovariateSpecs:
"""
Gets the country covariate reference value for a covariate ID and a
parent location ID. Also gets the maximum difference between the
reference value and covariate values observed.
Run this when you're going to make a DisMod AT database for a specific
parent location and sex ID.
:param: (int)
:param parent_location_id: (int)
:param sex_id: (int)
:return: List[CovariateSpec] list of the covariate specs with the
correct reference values and max diff.
"""
covariate_specs = copy(self.covariate_specs)
age_min = self.dismod_data.age_lower.min()
age_max = self.dismod_data.age_upper.max()
time_min = self.dismod_data.time_lower.min()
time_max = self.dismod_data.time_upper.max()
children = self.location_dag.children(parent_location_id)
for c in covariate_specs.covariate_specs:
if c.study_country == 'study':
if c.name == 's_sex':
c.reference = StudyCovConstants.SEX_COV_VALUE_MAP[
SEX_ID_TO_NAME[sex_id]]
c.max_difference = StudyCovConstants.MAX_DIFFERENCE_SEX_COV
elif c.name == 's_one':
c.reference = StudyCovConstants.ONE_COV_VALUE
c.max_difference = StudyCovConstants.MAX_DIFFERENCE_ONE_COV
else:
raise ValueError(f"The only two study covariates allowed are sex and one, you tried {c.name}.")
elif c.study_country == 'country':
LOG.info(f"Calculating the reference and max difference for country covariate {c.covariate_id}.")
cov_df = self.country_covariate_data[c.covariate_id]
parent_df = (
cov_df.loc[cov_df.location_id == parent_location_id].copy()
)
child_df = cov_df.loc[cov_df.location_id.isin(children)].copy()
all_loc_df = pd.concat([child_df, parent_df], axis=0)
# if there is no data for the parent location at all (which
# there should be provided by Central Comp)
# then we are going to set the reference value to 0.
if cov_df.empty:
reference_value = 0
max_difference = np.nan
else:
pop_df = self.population.configure_for_dismod()
pop_df = (
pop_df.loc[pop_df.location_id == parent_location_id].copy()
)
df_to_interp = pd.DataFrame({
'location_id': parent_location_id,
'sex_id': [sex_id],
'age_lower': [age_min], 'age_upper': [age_max],
'time_lower': [time_min], 'time_upper': [time_max]
})
reference_value = get_interpolated_covariate_values(
data_df=df_to_interp,
covariate_dict={c.name: parent_df},
population_df=pop_df
)[c.name].iloc[0]
max_difference = np.max(
np.abs(all_loc_df.mean_value - reference_value)
) + CascadeConstants.PRECISION_FOR_REFERENCE_VALUES
c.reference = reference_value
c.max_difference = max_difference
covariate_specs.create_covariate_list()
return covariate_specs