[M, C] = gpr.gpmodel(cc, rr, data_year, data_mort, data_var, data_category,
prior_year, prior_mort, mse, best_scale, best_amp2x,
predictionyears)
## find mean and standard error, drawing from M and C
draws = 1000
mort_draws = np.zeros((draws, len(predictionyears)))
gpr_seeds = [x + 123456 for x in range(1, 1001)]
for draw in range(draws):
np.random.seed(gpr_seeds[draw])
mort_draws[draw, :] = Realization(M, C)(predictionyears)
# collapse across draws
# note: space transformations need to be performed at the draw level
logit_est = gpr.collapse_sims(mort_draws)
unlogit_est = gpr.collapse_sims(gpr.inv_logit(mort_draws))
if hivsims == 0:
os.chdir('FILEPATH')
all_est = []
for i in range(len(predictionyears)):
all_est.append((cc, predictionyears[i], unlogit_est['med'][i],
unlogit_est['lower'][i], unlogit_est['upper'][i]))
all_est = pl.array(all_est, [('ihme_loc_id', '|S32'), ('year', '<f8'),
('med', '<f8'), ('lower', '<f8'),
('upper', '<f8')])
pl.rec2csv(all_est, 'gpr_%s.txt' % cc)
# save the sims
all_sim = []
for i in range(len(predictionyears)):
mse=mse)
else: # data model
[M, C] = gpr.gpmodel(ihme_loc_id, region_name, data_year, data_mort,
data_var, data_category, prior_year, prior_mort, mse,
best_scale, best_amp2x, predictionyears)
## find mean and standard error, drawing from M and C
draws = 1000
mort_draws = np.zeros((draws, len(predictionyears)))
gpr_seeds = [x + 123456 for x in range(1, 1001)]
for draw in range(draws):
np.random.seed(gpr_seeds[draw])
mort_draws[draw, :] = Realization(M, C)(predictionyears)
# collapse across draws
# note: space transformations need to be performed at the draw level
logit_est = gpr.collapse_sims(mort_draws)
unlogit_est = gpr.collapse_sims(gpr.inv_logit(mort_draws))
# save the sims
all_sim = []
for i in range(len(predictionyears)):
for s in range(draws):
all_sim.append((ihme_loc_id, predictionyears[i], s,
gpr.inv_logit(mort_draws[s][i])))
all_sim = pl.array(all_sim, [('ihme_loc_id', '|S32'), ('year', '<f8'),
('sim', '<f8'), ('mort', '<f8')])
pl.rec2csv(all_sim, "FILEPATH")
print("data model")
[M,C] = gpr.gpmodel(ihme_loc_id,region_name,data_year,data_mort,data_var,data_category,prior_year,prior_mort,mse,best_scale,best_amp2x,predictionyears)
## find mean and standard error, drawing from M and C
draws = 1000
mort_draws = np.zeros((draws, len(predictionyears)))
gpr_seeds = [x+123456 for x in range(1,1001)]
for draw in range(draws):
np.random.seed(gpr_seeds[draw])
mort_draws[draw,:] = Realization(M, C)(predictionyears)
# collapse across draws
# note: space transformations need to be performed at the draw level
print("collapse across draws...")
logit_est = gpr.collapse_sims(mort_draws)
unlogit_est = gpr.collapse_sims(gpr.inv_logit(mort_draws))
# the difference of the mean of the antilogited draws from the antilogit of the mean of the draws
mean_diff = np.subtract(unlogit_est['med'],gpr.inv_logit(logit_est['med']))
all_est = []
for i in range(len(predictionyears)):
all_est.append((ihme_loc_id,ss, predictionyears[i], unlogit_est['med'][i] - mean_diff[i], unlogit_est['lower'][i] - mean_diff[i], unlogit_est['upper'][i] - mean_diff[i]))
labels = ['ihme_loc_id','sex','year','mort_med','mort_lower', 'mort_upper']
all_est_df = pd.DataFrame.from_records(all_est, columns=labels)
est_file = "{}/gpr_{}_{}_not_scaled.csv".format(output_dir, ihme_loc_id,ss)
# all_est_df['sex'] = ss
all_est_df.to_csv(est_file, index = False)
# save the sims
all_sim = []
[M,C] = gpr.gpmodel_nodata(pyear=prior_year,pmort=prior_mort,scale=best_scale,predictionyears=predictionyears,sim=1000,amp2x=best_amp2x,mse=mse)
else: # data model
[M,C] = gpr.gpmodel(cc,rr,data_year,data_mort,data_var,data_category,prior_year,prior_mort,mse,best_scale,best_amp2x,predictionyears)
## find mean and standard error, drawing from M and C
draws = 1000
mort_draws = np.zeros((draws, len(predictionyears)))
gpr_seeds = [x+123456 for x in range(1,1001)]
for draw in range(draws):
np.random.seed(gpr_seeds[draw])
mort_draws[draw,:] = Realization(M, C)(predictionyears)
# collapse across draws
logit_est = gpr.collapse_sims(mort_draws)
mort_draws = gpr.inv_logit(mort_draws)
mort_draws = pd.DataFrame(mort_draws)
mort_draws.columns = predictionyears
mort_draws['ihme_loc_id'] = cc
mort_draws['sim'] = list(range(1000))
mort_draws = pd.melt(mort_draws, id_vars = ['ihme_loc_id','sim'], var_name = 'year', value_name = 'mort')
# Unscale backtransformed draws
upper_logit_bound = bounds[bounds['age'] == int(age)]['upper_bound'].iloc[0]
lower_logit_bound = bounds[bounds['age'] == int(age)]['lower_bound'].iloc[0]
mort_draws['mort'] = mort_draws['mort'] * (upper_logit_bound - lower_logit_bound) + lower_logit_bound
mort_draws = mort_draws.rename(index = str, columns = {"mort" : "val"})
# Collapse unscaled and backtransformed draws
meandf = mort_draws[['ihme_loc_id', 'year', 'val']].groupby(by = ['ihme_loc_id','year']).mean()
else: # data model
[M, C] = gpr.gpmodel(cc, rr, train_year, train_mort, train_var,
train_category, prior_year, prior_mort,
mse, scale, amp2x, predictionyears)
## find mean and standard error, drawing from M and C
draws = 1000
#not setting seed here because the holdouts are random anyway
mort_draws = np.zeros((draws, len(predictionyears)))
for draw in range(draws):
mort_draws[draw, :] = Realization(M, C)(predictionyears)
# collapse across draws
# note: space transformations need to be performed at the draw level
logit_est = gpr.collapse_sims(mort_draws)
unlogit_est = gpr.collapse_sims(gpr.inv_logit(mort_draws))
## save the predictions
for i in range(len(predictionyears)):
all_est.append(
(rr, cc, ho, scale, amp2x, mse * amp2x, predictionyears[i],
unlogit_est['med'][i], unlogit_est['std'][i]))
## calculate error and save this too
for year, mort, var in zip(test_year, test_mort, test_var):
pred_index = (predictionyears == year)
re = (gpr.inv_logit(mort) -
unlogit_est['med'][pred_index]) / (gpr.inv_logit(mort))
total_var = var + logit_est['std'][pred_index]**2
coverage = int(
(logit_est['med'][pred_index] -