def _agg_age_std_ages(self):
age_tree = agetree(age.AGE_STANDARDIZED)
# make the source and sink
source = self.gen_draw_source()
source.add_transform(
fill_square,
index_cols=[
col for col in self.dimensions.index_names
if col != "age_group_id"
],
square_col="age_group_id",
square_col_vals=[node.id for node in age_tree.leaves()])
sink = self.gen_draw_sink()
# constuct aggregator obj
operator = WtdSum(index_cols=[
col for col in self.dimensions.index_names if col != "age_group_id"
],
value_cols=self.dimensions.data_list(),
weight_df=self.std_age_weights,
weight_name="age_group_weight_value",
merge_cols=["age_group_id"])
aggregator = AggSynchronous(draw_source=source,
draw_sink=sink,
index_cols=[
col
for col in self.dimensions.index_names
if col != "age_group_id"
],
aggregate_col="age_group_id",
operator=operator)
# run the tree
aggregator.run(age_tree)
def compute_sex_aggregates(self):
sex_tree = sextree()
# make the source and sink
source = self.gen_draw_source()
source.add_transform(
fill_square,
index_cols=[
col for col in self.dimensions.index_names if col != "sex_id"
],
square_col="sex_id",
square_col_vals=[node.id for node in sex_tree.leaves()])
sink = self.gen_draw_sink()
# construct aggregator obj
operator = WtdSum(
index_cols=[
col for col in self.dimensions.index_names if col != "sex_id"
],
value_cols=self.dimensions.data_list(),
weight_df=self.population,
weight_name="population",
merge_cols=["location_id", "year_id", "age_group_id", "sex_id"])
aggregator = AggSynchronous(draw_source=source,
draw_sink=sink,
index_cols=[
col
for col in self.dimensions.index_names
if col != "sex_id"
],
aggregate_col="sex_id",
operator=operator)
# run the tree
aggregator.run(sex_tree)
def run_task(self, location_set_version_id, component):
source = self.get_source(component)
sink = self.get_sink(component)
dimensions = self.dimensions.get_dimension_by_component(
component, self.measure_id)
# get the tree we are aggregating
loc_trees = dbtrees.loctree(
location_set_version_id=location_set_version_id, return_many=True)
for loc_tree in loc_trees:
# get the weight vals
pop = get_population(
self.como_version,
age_group_id=dimensions.index_dim.get_level("age_group_id"),
location_id=[node.id for node in loc_tree.nodes],
year_id=dimensions.index_dim.get_level("year_id"),
sex_id=dimensions.index_dim.get_level("sex_id"))
pop = pop[[
"age_group_id", "location_id", "year_id", "sex_id",
"population"
]]
# set up our aggregation operator
operator = WtdSum(index_cols=[
col for col in dimensions.index_names if col != "location_id"
],
value_cols=dimensions.data_list(),
weight_df=pop,
weight_name="population",
merge_cols=[
"location_id", "year_id", "age_group_id",
"sex_id"
])
# run our aggregation
aggregator = AggMemEff(draw_source=source,
draw_sink=sink,
index_cols=[
col for col in dimensions.index_names
if col != "location_id"
],
aggregate_col="location_id",
operator=operator,
chunksize=self.chunksize[component])
# run the tree
aggregator.run(loc_tree,
draw_filters={
"measure_id": [self.measure_id],
"year_id":
dimensions.index_dim.get_level("year_id"),
"sex_id":
dimensions.index_dim.get_level("sex_id")
},
n_processes=self.chunksize[component])
write_func=partial(standard_write_func, index=False))
index_cols = [
'rei_id', 'year_id', 'age_group_id', 'sex_id', 'measure_id',
'metric_id'
]
draw_cols = ['draw_{}'.format(i) for i in range(n_draws)]
for lsid in location_set_id:
popfile = os.path.join(drawdir, 'population_{}.csv'.format(lsid))
population = pd.read_csv(popfile)
# aggregation operator
operator = WtdSum(
index_cols=index_cols,
value_cols=draw_cols,
weight_df=population,
weight_name='population',
merge_cols=['location_id', 'year_id', 'age_group_id', 'sex_id'])
# run aggregation
aggregator = AggMemEff(draw_source=source,
draw_sink=sink,
index_cols=index_cols,
aggregate_col='location_id',
operator=operator)
if lsid == 40:
loc_trees = loctree(location_set_id=lsid,
gbd_round_id=gbd_round_id,
return_many=True)
for tree in loc_trees:
aggregator.run(tree, draw_filters={'rei_id': rei_id})