def interpolate_year(data):
# Hide the central comp dependency unless required.
from core_maths.interpolate import pchip_interpolate
id_cols = list(set(data.columns).difference(DRAW_COLUMNS))
fillin_data = pchip_interpolate(data, id_cols, DRAW_COLUMNS)
return pd.concat([data, fillin_data], sort=True)
def read_single_en_injury(self,
modelable_entity_id,
model_version_id,
measure_id=[
measures.YLD, measures.INCIDENCE,
measures.ST_PREVALENCE,
measures.LT_PREVALENCE
]):
injury_source = (
self._ss_factory.get_en_injuries_modelable_entity_source(
modelable_entity_id, model_version_id))
dim = self.dimensions.get_simulation_dimensions(measure_id=measure_id,
at_birth=False)
# get filters w/ added years if interpolation is needed
filters = dim.index_dim.to_dict()["levels"]
req_years = filters["year_id"]
if not set(req_years).issubset(set(self._estim_years)):
filters["year_id"] = list(set(req_years + self._estim_years))
# read data
df = injury_source.content(filters=filters)
if df.empty:
raise Exception(f"No data returned for ME {modelable_entity_id}, "
f"model version {model_version_id}.")
draw_cols = [col for col in df.columns if "draw_" in col]
# add indices to dimensions object from draw source transforms
dim.index_dim.add_level("sequela_id", df.sequela_id.unique().tolist())
dim.index_dim.add_level("cause_id", df.cause_id.unique().tolist())
dim.index_dim.add_level("healthstate_id",
df.healthstate_id.unique().tolist())
dim.index_dim.add_level("rei_id", df.rei_id.unique().tolist())
# interpolate missing years
if not set(df.year_id.unique()).issuperset(set(req_years)):
interp_df = pchip_interpolate(df=df,
id_cols=dim.index_names,
value_cols=draw_cols,
time_col="year_id",
time_vals=req_years)
df = df[df.year_id.isin(req_years)]
df = df.append(interp_df)
else:
df = df[df.year_id.isin(req_years)]
# resample
if len(dim.data_list()) != len(draw_cols):
gbdizer = gbdize.GBDizeDataFrame(dim)
df = gbdizer.correlated_percentile_resample(df)
return df
def to_como(como_dir, location_set_id, gbd_round_id):
df = pd.read_csv("FILEPATH/urolith_symp_dws.csv")
# fill for new locs
lt = dbtrees.loctree(location_set_id=location_set_id,
gbd_round_id=gbd_round_id)
locmap = lt.flatten()
reg_avgs = df.merge(locmap[['leaf_node', 'level_2']],
left_on='location_id',
right_on='leaf_node')
reg_avgs = reg_avgs[['level_2', 'year_id', 'healthstate_id'] +
list(df.filter(like='draw').columns)]
reg_avgs = reg_avgs.groupby(['level_2', 'year_id'])
reg_avgs = reg_avgs.mean().reset_index()
reg_avgs.rename(columns={'level_2': 'location_id'}, inplace=True)
df = df.append(reg_avgs)
filllen = 0
for ln in list(locmap.leaf_node.unique()):
if ln not in list(df.location_id):
for i in reversed(range(6)):
fill_loc = locmap.loc[locmap.leaf_node == ln,
'level_%s' % i].squeeze()
filldf = df[df.location_id == fill_loc]
if len(filldf) > 0:
filldf['location_id'] = ln
df = df.append(filldf)
filllen = filllen + 1
break
df = df[df.location_id.isin([l.id for l in lt.leaves()])]
# fill in missing years
extra = df.query("year_id == 2013")
extra['year_id'] = 2019
df = df.append(extra)
df = df.filter(regex='(.*_id|draw_)')
interp = pchip_interpolate(df=df,
id_cols=['location_id', 'healthstate_id'],
value_cols=['draw_%s' % d for d in range(1000)],
time_col="year_id",
time_vals=list(range(1990, 2020)))
df = df.append(interp)
df = df[df.year_id.isin(list(range(1990, 2020)))]
# save for como run
df.to_hdf(f"{como_dir}/info/urolith_dws.h5",
'draws',
mode='w',
format='table',
data_columns=['location_id', 'year_id'])
def read_single_en_injury(self,
modelable_entity_id,
model_version_id,
measure_id=[3, 6, 35, 36]):
injury_source = (
self._ss_factory.get_en_injuries_modelable_entity_source(
modelable_entity_id, model_version_id))
dim = self.dimensions.get_simulation_dimensions(measure_id)
# get filters w/ added years if interpolation is needed
filters = dim.index_dim.to_dict()["levels"]
req_years = filters["year_id"]
if not set(req_years).issubset(set(self._estim_years)):
filters["year_id"] = list(set(req_years + self._estim_years))
# read data
df = injury_source.content(filters=filters)
if df.empty:
raise Exception("No data returned for meid:{} and mvid:{}".format(
modelable_entity_id, model_version_id))
# add indices to dimensions object from draw source transforms
dim.index_dim.add_level("sequela_id", df.sequela_id.unique().tolist())
dim.index_dim.add_level("cause_id", df.cause_id.unique().tolist())
dim.index_dim.add_level("healthstate_id",
df.healthstate_id.unique().tolist())
dim.index_dim.add_level("rei_id", df.rei_id.unique().tolist())
# interpolate missing years
if not set(df.year_id.unique()).issuperset(set(req_years)):
interp_df = pchip_interpolate(df=df,
id_cols=dim.index_names,
value_cols=self._draw_cols,
time_col="year_id",
time_vals=req_years)
df = df[df.year_id.isin(req_years)]
df = df.append(interp_df)
else:
df = df[df.year_id.isin(req_years)]
# resample if ndraws is less than 1000
if len(dim.data_list()) != 1000:
gbdizer = gbdize.GBDizeDataFrame(dim)
df = gbdizer.correlated_percentile_resample(df)
return df
def _get_inj_dws(self):
draw_cols = ["draw_{}".format(i) for i in range(1000)]
loc_id = self.dims.index_dim.get_level("location_id")[0]
year_id = self.dims.index_dim.get_level("year_id")
fp = ("FILEPATH/inputs/lt_dw.h5")
inj_dws = read_hdf(fp, "draws", hdf_filters={"location_id": loc_id})
inj_dws = inj_dws.reset_index()
# interpolate
interp = pchip_interpolate(df=inj_dws,
id_cols=["location_id", "ncode"],
value_cols=draw_cols,
time_col="year_id",
time_vals=year_id)
inj_dws = inj_dws.append(interp)
inj_dws = inj_dws[inj_dws.year_id.isin(year_id)]
seq_map = self.cv.injury_dws_by_sequela[[
"sequela_id", "healthstate_id", "n_code"
]].drop_duplicates()
inj_dws = inj_dws.merge(seq_map, left_on="ncode", right_on="n_code")
inj_dws = inj_dws[['sequela_id', 'healthstate_id'] + draw_cols]
return inj_dws
def epilepsy_any(cv):
standard_dws = pd.read_csv(
"FILEPATH/dw.csv")
standard_dws.rename(
columns={d: d.replace("draw", "dw") for d in DRAWCOLS},
inplace=True)
healthstates = cv.sequela_list[["modelable_entity_id", "healthstate_id"]]
# Get country-year specific prevalences for back-calculation
locations = cv.simulation_index['location_id']
years = estimation_years_from_gbd_round_id(cv.gbd_round_id)
ages = cv.simulation_index['age_group_id']
args = [(l, y, ages, cv.gbd_round_id, cv.decomp_step_id)
for l in locations for y in years]
pool = Pool(20)
prop_dfs = pool.map(get_props, args)
pool.close()
pool.join()
prop_dfs = pd.concat(prop_dfs)
prop_dfs = prop_dfs.merge(healthstates)
prop_dfs.rename(
columns={d: d.replace("draw", "prop") for d in DRAWCOLS},
inplace=True)
# Combine DWs
dws_to_weight = prop_dfs.merge(
standard_dws, on='healthstate_id', how='left')
dws_to_weight = dws_to_weight.join(pd.DataFrame(
data=(
dws_to_weight.filter(like='dw_').values *
dws_to_weight.filter(like='prop_').values),
index=dws_to_weight.index,
columns=DRAWCOLS))
def combine_dws(df):
draws_to_combine = df.filter(like='draw_')
combined_draws = 1 - (1 - draws_to_combine).prod()
return combined_draws
# healthstate_id 772 - Epilepsy
epilepsy_id = 772
combined_dws = dws_to_weight.groupby(['location_id', 'year_id']).apply(
combine_dws).reset_index()
combined_dws['healthstate_id'] = epilepsy_id
combined_dws = combined_dws[
['location_id', 'year_id', 'healthstate_id'] + DRAWCOLS]
combined_dws.to_hdf(
f"{cv.como_dir}/info/epilepsy_any_dws.h5",
'draws',
mode='w',
format='table',
data_columns=['location_id', 'year_id'])
# fill in missing years
year_id = list(range(1990,2020))
interp = pchip_interpolate(
df=combined_dws,
id_cols=['location_id', 'healthstate_id'],
value_cols=DRAWCOLS,
time_col="year_id",
time_vals=year_id)
combined_dws = combined_dws.append(interp)
combined_dws = combined_dws[combined_dws.year_id.isin(year_id)]
combined_dws.to_hdf(
f"{cv.como_dir}/info/epilepsy_any_dws.h5",
'draws',
mode='w',
format='table',
data_columns=['location_id', 'year_id'])
"""
df_19 = df[df.year_id == 2017].copy().reset_index(drop=True)
df_19["year_id"] = 2019
draw_cols = df.columns[df.columns.str.contains("draw")]
df_19[draw_cols] = df_19[draw_cols] * 1.00001
return df_19
if __name__ == "__main__":
# Draws pulled via gbd17 archive env prior (see docs), draws dir hardcode for now.
meid = ADDRESS0
print(f"Reading csv {time.time()}")
draws = pd.read_csv(f'{draws_dir}/{meid}_gbd_17/{location_id}.csv')
print(f"read csv {time.time()}")
draws_15 = pchip_interpolate(draws, [
'measure_id', 'modelable_entity_id', 'location_id', 'sex_id',
'age_group_id'
], ['draw_{}'.format(x) for x in range(1000)],
time_vals=[2015])
print(f"Interp complete: {time.time()}")
draws = draws.append(draws_15)
# draws_19 = linear_extrap(draws)
draws_19 = carry_19(draws)
print(f"extrap complete: {time.time()}")
draws = draws.append(draws_19)
print(f"draws complete: {time.time()}")
draws["metric_id"] = 3
draws.to_csv(f"{draws_dir}/{meid}/{location_id}.csv", index=False)