def custom_age_weights(age_group_ids, gbdrid=4):
"""Get age weights scaled to age group start and end"""
t = qry.get_age_weights(gbdrid)
t = t.query('age_group_id in {}'.format(age_group_ids))
# scale weights to 1
t['age_group_weight_value'] = \
t['age_group_weight_value'] / \
t['age_group_weight_value'].sum()
return t[['age_group_id', 'age_group_weight_value']]
def get_custom_age_weights(age_group_years_start, age_group_years_end):
"""Get age weights scaled to age group start and end"""
t = qry.get_age_weights()
t = t.query(
'age_group_years_start >= {start} & age_group_years_end <= {end}'.
format(start=age_group_years_start, end=age_group_years_end))
# scale weights to 1
t['age_group_weight_value'] = t['age_group_weight_value'] / t[
'age_group_weight_value'].sum()
return t[['age_group_id', 'age_group_weight_value']]
def custom_age_weights(age_group_id_start, age_group_id_end):
"""Get age weights scaled to age group start and end"""
t = qry.get_age_weights(3) # default is gbd 2010? Why?
t = t.query('age_group_id >= {start} & age_group_id <= {end}'.format(
start=age_group_id_start, end=age_group_id_end))
# scale weights to 1
t['age_group_weight_value'] = \
t['age_group_weight_value'] / \
t['age_group_weight_value'].sum()
return t
def age_standardize(df):
""" Age standardize. """
age_weights = qry.get_age_weights(4)
age_weights = age_weights[['age_group_id', 'age_group_weight_value']]
df = df.merge(age_weights, on=['age_group_id'], how='left')
assert df.age_group_weight_value.notnull().values.all(), 'age weights merg'
# make weighted product and sum
df = pd.concat([
df[dw.EPI_GROUP_COLS],
df[dw.DRAW_COLS].apply(lambda x: x * df['age_group_weight_value'])
],
axis=1)
df['age_group_id'] = 27
df = df.groupby(dw.EPI_GROUP_COLS, as_index=False)[dw.DRAW_COLS].sum()
return df
def process_location_risk_burden_draws(location_id, test=False):
''' Given a list of rei_ids, use gopher to get attributable burden draws
and save to out directory.
'''
dfs = []
for rei_id in dw.RISK_BURDEN_REI_IDS + dw.RISK_BURDEN_DALY_REI_IDS:
print(rei_id)
if rei_id in dw.RISK_BURDEN_REI_IDS:
measure_id = 1
elif rei_id in dw.RISK_BURDEN_DALY_REI_IDS:
measure_id = 2
else:
raise ValueError("no measure found")
print('Getting draws')
df = get_draws(gbd_id_field=['cause_id', 'rei_id'],
gbd_id=[294, rei_id],
source='burdenator',
version=dw.BURDENATOR_VERS,
location_ids=location_id,
year_ids=[],
age_group_ids=[],
sex_ids=[],
num_workers=3,
n_draws=1000,
resample=True)
# keep years we want
df = df.query('measure_id == {}'.format(measure_id))
df = df.query('metric_id == 1')
df = df.query('age_group_id in {} and sex_id in [1, 2]'.format(
range(2, 21) + range(30, 33) + [235]))
df = df.query('year_id in {}'.format(range(1990, 2011, 5) + [2016]))
# aggregate to both sexes
df['sex_id'] = 3
df = df.groupby(dw.RISK_BURDEN_GROUP_COLS,
as_index=False)[dw.DRAW_COLS].sum()
pops = qry.get_pops(both_sexes=True)
df = df.merge(pops,
how='left',
on=['location_id', 'age_group_id', 'sex_id', 'year_id'])
df = pd.concat([
df[dw.RISK_BURDEN_GROUP_COLS],
df[dw.DRAW_COLS].apply(lambda x: x / df['population'])
],
axis=1)
df['metric_id'] = 3
# keep the right columns
df = df[dw.RISK_BURDEN_GROUP_COLS + dw.DRAW_COLS]
# interpolate years
print('Interpolating')
df = custom_interpolate(df)
# age-standardize
age_weights = qry.get_age_weights(4)
df = df.merge(age_weights)
df = pd.concat([
df[dw.RISK_BURDEN_GROUP_COLS],
df[dw.DRAW_COLS].apply(lambda x: x * df['age_group_weight_value'])
],
axis=1)
df['age_group_id'] = 27
df = df.groupby(dw.RISK_BURDEN_GROUP_COLS,
as_index=False)[dw.DRAW_COLS].sum()
dfs.append(df)
df = pd.concat(dfs)
write_output(df, 'risk_burden', location_id)
return df
def load_location_file(iso):
df = pd.read_csv(os.path.join(dw.HIV_DIR, iso + '.csv'))
df = df.query('year_id >= 1990 and year_id <= 2030 and variable == "Incidence"')
df['run_num'] = 'draw_' + (df['run_num'] - 1).astype(str)
df = pd.pivot_table(df,
values='value',
index=['location_id', 'year_id', 'age_group_id', 'sex_id'],
columns='run_num')
df = df.reset_index()
return df
if __name__ == '__main__':
# Supplementary datasets
print('Collecting supplementary datasets')
age_weights = qry.get_age_weights(4)
age_weights.loc[age_weights.age_group_id.isin([30, 31, 32, 235]), 'age_group_id'] = 21
age_weights = age_weights.groupby(['age_group_id'], as_index=False)['age_group_weight_value'].sum()
gbd_popdf = qry.get_pops()
gbd_popdf.loc[gbd_popdf.age_group_id.isin([30, 31, 32, 235]), 'age_group_id'] = 21
gbd_popdf = gbd_popdf.groupby(['location_id', 'year_id', 'age_group_id', 'sex_id'], as_index=False)['population'].sum()
wpp_popdf = pd.read_csv('FILEPATH/wpp2015_to2063.csv')
wpp_popdf = wpp_popdf.loc[wpp_popdf.year_id >= 2016]
wpp_popdf = wpp_popdf.rename(index=str, columns={'pop':'population'})
locsdf = qry.get_sdg_reporting_locations()
locsdf['L3_loc'] = [loc[3] for loc in locsdf.path_to_top_parent.str.split(',').tolist()]
# Compile all countries
import sdg_utils.draw_files as dw
import sdg_utils.queries as qry
# read asfr file
print 'reading input file...'
df = pd.read_csv("{d}/asfr_10_19.csv".format(d=dw.ASFR_DIR))
# DRAW NAME STANDARDS
# rename asfr_draw_X to draw_X like others
print 'cleaning...'
df = df.rename(columns=lambda x: x.replace('asfr_draw', 'draw'))
# shift from 1-1000 to 0-999
df = df.rename(columns={'draw_1000': 'draw_0'})
# AGE STANDARDIZE
weights = qry.get_age_weights(ref_pop=3)
weights = weights.ix[weights['age_group_id'].isin([7, 8])]
weights['age_group_weight_value'] = weights['age_group_weight_value'] / \
weights.age_group_weight_value.sum()
df = df.merge(weights, how='left')
assert df.age_group_weight_value.notnull().values.all(), \
'merge failed'
id_cols = [
'location_id', 'year_id', 'sex_id', 'age_group_id', 'measure_id',
'metric_id'
]
# just call this a continuous rate? idk
df['measure_id'] = 18
df['metric_id'] = 3
df['age_group_id'] = 27