def get_full_envelope(self):
'''
(self) -> None
For models with age restrictions, the all-ages group should use envelope
for all ages. This function replaces the age-restricted envelope for the
full envelope for each location-year, country-year, region-year,
super-region-year, and global-year
'''
print "We're definitely pulling the full envelope."
for df_type in [
'age_location', 'age_country', 'age_region',
'age_super_region', 'global'
]:
self.agg_dfs[df_type].drop('envelope', inplace=True, axis=1)
locs = self.agg_dfs[df_type].location_id.values.tolist()
years = self.agg_dfs[df_type].year.values.tolist()
# get the envelope, then merge in with the aggregated dfs
env_df = get_envelope(age_group_id=22,
gbd_round_id=self.gbd_round_id,
location_id=locs,
sex_id=self.sex_id,
year_id=years)
env_df = env_df[['location_id', 'year_id', 'mean']]
env_df.rename(columns={
'mean': 'envelope',
'year_id': 'year'
},
inplace=True)
self.agg_dfs[df_type] = self.agg_dfs[df_type].merge(
env_df, on=['location_id', 'year'])
def get_data(self, id_template_df):
locs = id_template_df.location_id.tolist()
ages = id_template_df.age_group_id.tolist()
sexes = id_template_df.sex_id.tolist()
years = id_template_df.year_id.tolist()
# get deaths and pop
env_df = get_envelope(
age_group_id=ages, location_id=locs, year_id=years, sex_id=sexes,
with_hiv=1, with_shock=0)
pop_df = get_population(
age_group_id=ages, location_id=locs, year_id=years, sex_id=sexes)
df = env_df.merge(
pop_df, on=["location_id", "year_id", "age_group_id", "sex_id"])
# convert to rates
for col in ["mean", "lower", "upper"]:
df[col] = df[col] / df["population"]
df = self.drop_zeros_nulls(df, "mean", "lower", "upper")
# add input_data_key
df = df.merge(id_template_df,
on=["location_id", "year_id", "age_group_id", "sex_id"])
if df.empty:
raise NoNonZeroValues
# aggregate
df = self.calc_se_from_ui(df, "mean", "lower", "upper")
df = self.calc_aggregate_se(df, self._data_key, "mean", "se")
df = df.set_index(self._data_key)
return df
def get_full_envelope(self):
"""
For models with age restrictions, the all-ages group should use envelope
for all ages. Replace the age-restricted envelope for the full envelope for
each location-year, country-year, region-year, super-region-year, and global-year.
"""
logger.info("Pulling in the full envelope in order to have a correct"
"envelope for age-restricted causes.")
for df_type in self.age_aggregate_dfs:
self.agg_dfs[df_type].drop('envelope', inplace=True, axis=1)
locs = self.agg_dfs[df_type].location_id.values.tolist()
years = self.agg_dfs[df_type].year_id.values.tolist()
# get the envelope, then merge in with the aggregated dfs
env_df = get_envelope(
age_group_id=self.model_metadata.
model_parameters['all_age_group_id'],
gbd_round_id=self.model_metadata.
model_parameters['gbd_round_id'],
location_id=locs,
sex_id=self.model_metadata.model_parameters['sex_id'],
year_id=years,
decomp_step=self.model_metadata.
model_parameters['decomp_step'],
run_id=self.model_metadata.model_parameters['env_run_id'])
env_df = env_df[['location_id', 'year_id', 'mean']]
env_df.rename(columns={'mean': 'envelope'}, inplace=True)
self.agg_dfs[df_type] = self.agg_dfs[df_type].merge(
env_df, on=['location_id', 'year_id'])
def mortQuery(sex, start_year, start_age, end_age, location_set_version_id,
gbd_round, db_connection):
'''
Strings indicating model parameters -> Pandas Data Frame
Given a set of model parameters will query from the mortality database and
return a pandas data frame. The data frame contains the base variables
used in the CODEm process.
'''
loc_df = locQuery(location_set_version_id, db_connection)
loc_list = loc_df.location_id.values.tolist()
age_df = createAgeDF(db_connection)
age_restrict = "all_ages >= {0} & all_ages <= {1}".format(start_age,
end_age)
age_list = age_df.query(age_restrict).all_ages.values.tolist()
env = get_envelope(age_group_id=age_list,
sex_id=sex,
year_id=range(start_year, gbd_round+1),
location_set=35,
location_id=loc_list)
pop = get_population(age_group_id=age_list,
sex_id=sex,
year_id=range(start_year, gbd_round+1),
location_set=35,
location_id=loc_list)
df = pd.merge(env, pop, on=['age_group_id', 'location_id', 'year_id',
'sex_id'])
df.drop(['upper', 'lower', 'run_id_x', 'run_id_y'], axis=1, inplace=True)
df.rename(columns={'age_group_id': 'age', 'year_id': 'year',
'sex_id': 'sex', 'mean': 'envelope',
'population': 'pop'}, inplace=True)
return df
def _get_envelope_summary(version: MachineParameters) -> pd.DataFrame:
"""
Wrapper around get_envelope; used to unpack arguments from version object
as well as rename columns and sub-select dataframe columns.
Arguments:
version (FauxCorrectParameters): object containing all the demographic
and fauxcorrect configuration data needed to query envelope
estimates.
Return:
pd.DataFrame
"""
env = get_envelope(age_group_id=version.all_age_group_ids,
location_id=version.location_ids,
year_id=version.year_ids,
sex_id=version.all_sex_ids,
decomp_step=version.decomp_step,
gbd_round_id=version.gbd_round_id,
run_id=version.envelope_version_id,
with_shock=0,
with_hiv=0)
env.rename(columns={constants.Columns.MEAN: constants.Columns.ENVELOPE},
inplace=True)
keep_cols = (constants.Columns.DEMOGRAPHIC_INDEX +
[constants.Columns.ENVELOPE])
return env[keep_cols]
def __init__(self,
gbd_round_id: int = gbd.GBD_ROUND_ID,
decomp_step: str = gbd.decomp_step.ONE):
self.gbd_round_id: int = gbd_round_id
self.decomp_step: str = decomp_step
self._run_id: int = get_envelope(
gbd_round_id=self.gbd_round_id,
decomp_step=self.decomp_step).run_id.item()
def get_all_cause_mortality():
dems = db.get_demographics(gbd_team = "epi", gbd_round_id = 6)
mortality = db.get_envelope(age_group_id = dems["age_group_id"],
location_id = dems["location_id"], year_id = dems["year_id"], sex_id = dems["sex_id"], with_hiv = 1, rates = 1, decomp_step = ds, gbd_round_id = gbd_round_id)
# calculate the standard error
mortality["std"] = (mortality["upper"] - mortality["lower"])/3.92
mortality.drop(['run_id'], axis = 1, inplace = True)
filename = "all_cause_mortality.csv"
mortality.to_csv(os.path.join(out_dir_rate, "02_temp/03_data", filename), index = False)
def pull_mort_vers(gbd_round_id):
##############################################################
## Returns the current best with shock life table version
##############################################################
env = get_envelope(gbd_round_id=gbd_round_id,
with_shock=1,
with_hiv=1,
location_id=1,
sex_id=1,
age_group_id=10,
year_id=gbdr(gbd_round_id))
lt_vers = env['run_id'].item()
return lt_vers
def get_env():
''' returns current gbd envelope
'''
d_step = utils.get_gbd_parameter('current_decomp_step')
gbd_id = utils.get_gbd_parameter('current_gbd_round')
yr_range = range(1980,2030)
yr_list = list(yr_range)
env_df = get_envelope(age_group_id=-1, location_id=-1, location_set_id=8,
year_id=yr_list,
sex_id = -1,
decomp_step = d_step,
gbd_round_id = gbd_id)
env_df.rename(columns={"mean": "mean_env"}, inplace=True)
return env_df
def load_mortality_envelope(location_id_list, age_group_list, year_list):
''' Returns the current all-cause mortality envelope
'''
env = get_envelope(sex_id=[1, 2],
location_id=location_id_list,
year_id=year_list,
age_group_id=age_group_list)
env.rename(columns={'mean': 'envelope'}, inplace=True)
pop = get_population(sex_id=[1, 2],
location_id=location_id_list,
year_id=year_list,
age_group_id=age_group_list)
env = env.merge(pop,
on=['location_id', 'year_id', 'sex_id', 'age_group_id'])
env['death_rate'] = env['envelope'] / env['population']
env = env[[
'location_id', 'year_id', 'sex_id', 'age_group_id', 'death_rate'
]]
return (env)
def combined_get_model_results(prev_filepath=None, inc_filepath=None, model_version_id=152216):
age_ids = [2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,30,31,32,33]
year_ids = [1990,1995,2000,2005,2010,2016]
sex_ids = [1,2]
location_id = [6, 7, 8, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 29, 30, 33, 34,
35, 36, 37, 38, 39, 40, 41, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 57, 58, 59, 60, 61, 62, 63, 66,
67, 68, 69, 71, 72, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 97,
98, 99, 101, 102, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 121, 122, 123, 125,
126, 127, 128, 129, 130, 131, 132, 133, 135, 136, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150,
151, 152, 153, 154, 155, 156, 157, 160, 161, 162, 163, 164, 165, 168, 169, 170, 171, 172, 173, 175, 176, 177,
178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 189, 190, 191, 193, 194, 195, 196, 197, 198, 200, 201, 202,
203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 215, 216, 217, 218, 298, 305, 349, 351, 354, 376,
385, 422, 433, 434, 435, 521, 522, 523, 524, 525, 526, 527, 528, 529, 530, 531, 532, 533, 534, 535, 536, 537,
538, 539, 540, 541, 542, 543, 544, 545, 546, 547, 548, 549, 550, 551, 552, 553, 554, 555, 556, 557, 558,
559, 560, 561, 562, 563, 564, 565, 566, 567, 568, 569, 570, 571, 572, 573, 4636, 4643, 4644, 4645, 4646,
4647, 4648, 4650, 4651, 4652, 4653, 4655, 4656, 4657, 4658, 4659, 4660, 4661, 4662, 4663, 4664, 4665, 4666,
4667, 4668, 4669, 4670, 4671, 4672, 4673, 4674, 4753, 4756, 4757, 4758, 4760, 4761, 4762, 4765, 4768, 4770,
4771, 4772, 4773, 4775, 4940, 4944, 35424, 35425, 35426, 35427, 35428, 35429, 35430, 35431, 35432, 35433,
35434, 35435, 35436, 35437, 35438, 35439, 35440, 35441, 35442, 35443, 35444, 35445, 35446, 35447, 35448,
35449, 35450, 35451, 35452, 35453, 35454, 35455, 35456, 35457, 35458, 35459, 35460, 35461, 35462, 35463,
35464, 35465, 35466, 35467, 35468, 35469, 35470, 44643, 44644, 44645, 44646, 44647, 44648, 44649, 44650,
44651, 44652, 44653, 44654, 44655, 44656, 44657, 44658, 44659, 44660, 44661, 44662, 44663, 44664, 44665,
44666, 44667, 44668, 44669, 44670, 44671, 44672, 44673, 44674, 44675, 44676, 44677, 44678, 44679, 44680,
44681, 44682, 44683, 44684, 44685, 44686, 44687, 44688, 44689, 44690, 44691, 44692, 44693, 44694, 44695,
44696, 44697, 44698, 44699, 44700, 44701, 44702, 44703, 44704, 44705, 44706, 44707, 44708, 44709, 44710,
44711, 44712, 44713, 44714, 44715, 44716, 44717, 44718, 44719, 44720, 44721, 44722, 44723, 44724, 44725,
44726, 44727, 44728, 44729, 44730, 44731, 44732, 44733, 44734, 44735, 44736, 44737, 44738, 44739, 44740,
44741, 44742, 44743, 44744, 44745, 44746, 44747, 44748, 44749, 44750, 44751, 44752, 44753, 44754, 44755,
44756, 44757, 44758, 44759, 44760, 44761, 44762, 44763, 44764, 44765, 44766, 44767, 44768, 44769, 44770,
44771, 44772, 44773, 44774, 44775, 44776, 44777, 44778, 44779, 44780, 44781, 44782, 44783, 44784,
44785, 44786, 44787, 44788, 44789, 44790, 44791, 44792]
#get incidence and prevalence data
if (prev_filepath):
print("Using file {} for prev" % prev_filepath)
prev = pd.read_excel(prev_filepath)
# get excel
else:
print("querying epi database for prev...")
all_covariate_adjusted_data = get_cov_adjusted_data(model_version_id)
prev = all_covariate_adjusted_data.loc[all_covariate_adjusted_data['measure_id']==5]
if (inc_filepath):
print("Using file {} for inc" % inc_filepath)
inc = pd.read_excel(inc_filepath)
# get excel
else:
print("querying epi database for inc...")
all_covariate_adjusted_data = get_cov_adjusted_data(model_version_id)
inc = all_covariate_adjusted_data.loc[all_covariate_adjusted_data['measure_id']==6].copy()
prev = prev.loc[prev['location_id'].isin(location_id)]
prev = prev.loc[prev['outlier_type_id'] == 0]
prev['prev_se'] = (prev["upper"] - prev["lower"]) / (2*1.96)
prev = prev.rename(columns={'mean':'prev_mean', 'lower':'prev_lower', 'upper':'prev_upper'})
prev = adj_data_template(df=prev)
inc = inc.loc[inc['location_id'].isin(location_id)]
inc = all_fourplus_locs(inc)
inc = inc.loc[inc['outlier_type_id'] == 0]
inc['inc_se'] = (inc["upper"] - inc["lower"]) / (2*1.96)
inc = inc.rename(columns={'mean':'inc_mean', 'lower':'inc_lower', 'upper':'inc_upper'})
inc = adj_data_template(df=inc)
#load custom (HIV-neg + HIV-pos) csmr
print("loading custom csmr data...")
csmr = pd.read_csv("FILEPATH")
csmr['csmr_se'] = (csmr["upper"] - csmr["lower"]) / (2*1.96)
csmr = csmr.rename(columns={'mean':'csmr_mean', 'lower':'csmr_lower', 'upper':'csmr_upper'})
csmr = csmr[['age_group_id', 'location_id', 'year_id', 'sex_id', 'csmr_mean', 'csmr_se', 'csmr_lower', 'csmr_upper']].copy()
#get acmr data
print("querying get_envelope for acmr...")
acmr = get_envelope(age_group_id=age_ids, location_id=location_id, year_id=year_ids, sex_id=sex_ids, gbd_round_id=4, status='best', rates=1)
acmr['acmr_se'] = (acmr["upper"] - acmr["lower"]) / (2*1.96)
acmr = acmr.rename(columns={'mean':'acmr_mean', 'lower':'acmr_lower', 'upper':'acmr_upper'})
#get emr-predicted data
print('pulling global emr-pred numbers...')
emrpred = get_emr_pred(model_version_id)
print('merging dataframes...')
merge_inc = pd.merge(left=inc, right=csmr, on=['age_group_id', 'sex_id', 'year_id', 'location_id'], how='inner')
merge_inc = pd.merge(left=merge_inc, right=acmr, on=['age_group_id', 'sex_id', 'year_id', 'location_id'], how='inner')
merge_inc = pd.merge(left=merge_inc, right=emrpred, on=['age_group_id', 'sex_id', 'year_id'], how='inner')
merge_inc['location_id']=merge_inc['location_id_x']
#required since emr-pred is only global, location_id=1
#remission should equal 2. upper and lower bounds 1.8-2.2
merge_inc['rem_mean'] = 2
merge_inc['rem_se'] = .1020408
#merge data required for incidence-based emr calculation
merge_prev = pd.merge(left=prev, right=csmr, on=['age_group_id', 'sex_id', 'year_id', 'location_id'], how='inner')
#merge data required for prevalence-based emr calculation
return (merge_prev, merge_inc)
def get_mortality(dems, shock):
"""Pull all-cause mortality."""
print("Getting mortality")
df = db.get_envelope(age_group_id=dems["age_group_id"], location_id=dems["location_id"], year_id=dems['year_id'],
sex_id=dems['sex_id'], with_hiv=1, with_shock=shock, rates=1, gbd_round_id=help.GBD_ROUND)
return df
def get_best_version():
temp = db.get_envelope(gbd_round_id=help.GBD_ROUND, year_id=help.LAST_YEAR, with_hiv=True, with_shock=False)
return temp.loc[0,'run_id']
def combined_get_model_results(gbd_id=None,
location_id='all',
prev_filepath=None,
inc_filepath=None,
model_version_id=263738):
age_ids = [2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,30,31,32,235]
year_ids = [1990,1995,2000,2005,2010,2017]
sex_ids = [1,2]
#get incidence and prevalence data
if (prev_filepath):
print("Using file for prev")
prev = pd.read_excel(prev_filepath)
# get excel
else:
print("querying get_model_results for prev...")
prev = get_model_results('epi',
gbd_id=gbd_id,
measure_id=5,
location_id='all',
year_id=year_ids,
age_group_id=age_ids,
sex_id=sex_ids,
status='best',
gbd_round_id=4)
if (inc_filepath):
print("Using file for inc")
inc = pd.read_excel(inc_filepath)
# get excel
else:
print("querying get_model_results for inc...")
inc = get_model_results('epi',
gbd_id=gbd_id,
measure_id=6,
location_id='all',
year_id=year_ids,
age_group_id=age_ids,
sex_id=sex_ids,
status='best',
gbd_round_id=4)
#prev['prev_se'] = (prev["upper"] - prev["lower"]) / (2*1.96)
#inc['inc_se'] = (inc["upper"] - inc["lower"]) / (2*1.96)
prev = prev.rename(columns={'mean':'prev_mean',
'lower':'prev_lower',
'upper':'prev_upper',
'standard_error':'prev_se'})
inc = inc.rename(columns={'mean':'inc_mean',
'lower':'inc_lower',
'upper':'inc_upper',
'standard_error':'inc_se'})
#prev = adj_data_template(df=prev)
#inc = adj_data_template(df=inc)
#load custom (HIV-neg + HIV-pos) csmr
print("loading custom csmr data...")
csmr = pd.read_csv("FILEPATH")
#csmr['csmr_se'] = (csmr["upper"] - csmr["lower"]) / (2*1.96)
csmr = csmr.rename(columns={'mean':'csmr_mean',
'lower':'csmr_lower',
'upper':'csmr_upper',
'standard_error':'csmr_se'})
csmr = csmr[['age_group_id',
'location_id',
'year_id',
'sex_id',
'csmr_mean',
'csmr_se',
'csmr_lower',
'csmr_upper']].copy()
#get acmr data
print("querying get_envelope for acmr...")
acmr = get_envelope(age_group_id=age_ids,
location_id='all',
year_id=year_ids,
sex_id=sex_ids,
gbd_round_id=5,
with_shock=1,
with_hiv=1,
rates=1)
acmr['acmr_se'] = (acmr["upper"] - acmr["lower"]) / (2*1.96)
acmr = acmr.rename(columns={'mean':'acmr_mean',
'lower':'acmr_lower',
'upper':'acmr_upper'})
#get remission data
#remission should equal 2. upper and lower bounds 1.8-2.2
#get emr-predicted data
emrpred = get_emr_pred(model_version_id)
merge_inc = pd.merge(left=inc,
right=csmr,
on=['age_group_id', 'sex_id', 'year_id', 'location_id'],
how='left')
merge_inc = pd.merge(left=merge_inc,
right=acmr,
on=['age_group_id', 'sex_id', 'year_id', 'location_id'],
how='left')
merge_inc = pd.merge(left=merge_inc,
right=emrpred,
on=['age_group_id', 'sex_id', 'year_id'],
how='left')
merge_inc['rem_mean'] = 2
merge_inc['rem_se'] = .1020408
merge_inc = merge_inc.rename(columns={'location_id_x':'location_id'})
#merge data required for incidence-based emr calculation
merge_prev = pd.merge(left=prev,
right=csmr,
on=['age_group_id', 'sex_id', 'year_id', 'location_id'],
how='left')
#merge data required for prevalence-based emr calculation
return (merge_prev, merge_inc)
env.set_index(index_cols, inplace=True)
env.sort_index(inplace=True)
prop.set_index(index_cols, inplace=True)
prop.sort_index(inplace=True)
# subset to columns that need to be adjusted
final = env.join(prop)
final.loc[final['adj'] == 0, 'prop'] = 1
final[draw_cols] = final[draw_cols].multiply(final['prop'], axis="index")
# pull in mortality draws
mort = get_envelope(
location_id=locs, location_set_id=25,
age_group_id=list(range(7, 16)), sex_id=2,
year_id=list(range(1980, 2020)),
decomp_step=decomp.decomp_step_from_decomp_step_id(decomp_step_id),
gbd_round_id=maternal_fns.GBD_ROUND_ID)
mort = mort[index_cols + ['mean']]
mort.set_index(index_cols, inplace=True)
final = final.join(mort)
final[draw_cols] = final[draw_cols].multiply(final['mean'], axis="index")
final['cause_id'] = 366
final['measure_id'] = 1
final.reset_index(inplace=True)
logger.info("Exporting to %s" % out_dir)
final.to_hdf('%s/late_corrected_maternal_envelope.h5' % out_dir, key='draws',
env.set_index(index_cols, inplace=True)
env.sort_index(inplace=True)
prop.set_index(index_cols, inplace=True)
prop.sort_index(inplace=True)
# subset to columns that need to be adjusted
final = env.join(prop)
final.loc[final['adj'] == 0, 'prop'] = 1
final[draw_cols] = final[draw_cols].multiply(final['prop'], axis="index")
# pull in mortality draws
mort = get_envelope(location_id=locs,
location_set_id=25,
age_group_id=list(range(7, 16)),
sex_id=2,
year_id=list(range(1980, 2018)))
mort = mort[index_cols + ['mean']]
mort.set_index(index_cols, inplace=True)
final = final.join(mort)
final[draw_cols] = final[draw_cols].multiply(final['mean'], axis="index")
final['cause_id'] = 366
final['measure_id'] = 1
final.reset_index(inplace=True)
logger.info("Exporting to %s" % out_dir)
final.to_hdf('%s/FILEPATH.h5' % out_dir,
def get_mortality_data(sex, start_year, start_age, end_age,
location_set_version_id, gbd_round_id, gbd_round,
decomp_step_id, db_connection, env_run_id, pop_run_id,
standard_location_set_version_id):
"""
strings indicating model parameters -> Pandas Data Frame
Given a set of model parameters will query from the mortality database and
return a pandas data frame. The data frame contains the base variables
used in the CODEm process.
Also calculates the weights for subnationals of standard locations.
"""
logger.info("Querying mortality and population.")
loc_df = get_location_info(
location_set_version_id=location_set_version_id,
standard_location_set_version_id=standard_location_set_version_id,
db_connection=db_connection)
loc_list = loc_df.location_id.values.tolist()
age_df = create_age_df(db_connection)
age_restrict = "all_ages >= {0} & all_ages <= {1}".format(
start_age, end_age)
age_list = age_df.query(age_restrict).all_ages.values.tolist()
env = get_envelope(
age_group_id=age_list,
sex_id=sex,
year_id=list(range(start_year, gbd_round + 1)),
location_set_id=35,
location_id=loc_list,
gbd_round_id=gbd_round_id,
decomp_step=decomp_step_from_decomp_step_id(decomp_step_id),
run_id=env_run_id)
pop = get_population(
age_group_id=age_list,
sex_id=sex,
year_id=list(range(start_year, gbd_round + 1)),
location_set_id=35,
location_id=loc_list,
gbd_round_id=gbd_round_id,
decomp_step=decomp_step_from_decomp_step_id(decomp_step_id),
run_id=pop_run_id)
df = pd.merge(env,
pop,
on=['age_group_id', 'location_id', 'year_id', 'sex_id'])
df.drop(['upper', 'lower', 'run_id_x', 'run_id_y'], axis=1, inplace=True)
df = population_weights(
df,
loc_df,
age_group_id=age_list,
sex_id=sex,
year_id=list(range(start_year, gbd_round + 1)),
decomp_step_id=decomp_step_id,
gbd_round_id=gbd_round_id,
pop_run_id=pop_run_id,
location_set_version_id=location_set_version_id,
standard_location_set_version_id=standard_location_set_version_id)
df = df[[
'age_group_id', 'location_id', 'year_id', 'sex_id', 'mean',
'population', 'weight'
]]
df.rename(columns={
'age_group_id': 'age',
'year_id': 'year',
'sex_id': 'sex',
'mean': 'envelope',
'population': 'pop'
},
inplace=True)
return df
# This retrieves mortality rates from IHME's database.
# Run this first in order to get access to db_queries.
# source /ihme/code/central_comp/miniconda/bin/activate gbd_env
from db_queries import get_envelope, get_age_metadata
gbd_round = 5
population = get_envelope(age_group_id="all",
location_id="all",
sex_id=1,
gbd_round_id=gbd_round)
mortality_rate = get_envelope(age_group_id="all",
location_id="all",
sex_id=1,
gbd_round_id=gbd_round,
rates=1)
ages = get_age_metadata(age_group_set_id=12, gbd_round_id=gbd_round)
mortality_rate.to_hdf("mortality.h5",
"mortality",
format="table",
append=False)
mortality_rate.to_csv("mortality.csv", index=False)
population.to_hdf("mortality.h5", "population", format="table", append=False)
population.to_csv("population.csv", index=False)
ages.to_hdf("mortality.h5", "ages", format="table", append=False)
ages.to_csv("ages.csv", index=False)
