def test_simulated_disease(): """ Test fit for simulated disease data""" # load model to test fitting dm = DiseaseJson(file('tests/test_disease_1.json').read()) # filter and noise up data cov = .5 data = [] for d in dm.data: d['truth'] = d['value'] if dismod3.utils.clean(d['gbd_region']) == 'north_america_high_income': if d['data_type'] == 'all-cause mortality data': data.append(d) else: se = (cov * d['value']) d['value'] = mc.rtruncnorm(d['truth'], se**-2, 0, np.inf) d['age_start'] -= 5 d['age_end'] = d['age_start']+9 d['age_weights'] = np.ones(d['age_end']-d['age_start']+1) d['age_weights'] /= float(len(d['age_weights'])) d['standard_error'] = se data.append(d) dm.data = data # fit empirical priors and compare fit to data from dismod3 import neg_binom_model for rate_type in 'prevalence incidence remission excess-mortality'.split(): neg_binom_model.fit_emp_prior(dm, rate_type, '/dev/null') check_emp_prior_fits(dm) # fit posterior delattr(dm, 'vars') # remove vars so that gbd_disease_model creates its own version from dismod3 import gbd_disease_model keys = dismod3.utils.gbd_keys(region_list=['north_america_high_income'], year_list=[1990], sex_list=['male']) gbd_disease_model.fit(dm, method='map', keys=keys, verbose=1) ## first generate decent initial conditions gbd_disease_model.fit(dm, method='mcmc', keys=keys, iter=1000, thin=5, burn=5000, verbose=1, dbname='/dev/null') ## then sample the posterior via MCMC print 'error compared to the noisy data (coefficient of variation = %.2f)' % cov check_posterior_fits(dm) for d in dm.data: d['value'] = d['truth'] d['age_start'] += 5 d['age_end'] = d['age_start'] d['age_weights'] = np.ones(d['age_end']-d['age_start']+1) d['age_weights'] /= float(len(d['age_weights'])) print 'error compared to the truth' check_posterior_fits(dm) return dm
def test_dismoditis_wo_prevalence(): """ Test fit for simple example""" # load model to test fitting dm = DiseaseJson(file('tests/dismoditis.json').read()) # remove all prevalence data dm.data = [d for d in dm.data if d['parameter'] != 'prevalence data'] # fit empirical priors neg_binom_model.fit_emp_prior(dm, 'incidence', '/dev/null') check_emp_prior_fits(dm) neg_binom_model.fit_emp_prior(dm, 'excess-mortality', '/dev/null') check_emp_prior_fits(dm) # fit posterior delattr(dm, 'vars') # remove vars so that gbd_disease_model creates its own version from dismod3 import gbd_disease_model keys = dismod3.utils.gbd_keys(region_list=['asia_southeast'], year_list=[1990], sex_list=['male']) #gbd_disease_model.fit(dm, method='map', keys=keys, verbose=1) ## first generate decent initial conditions gbd_disease_model.fit(dm, method='mcmc', keys=keys, iter=1000, thin=5, burn=5000, verbose=1, dbname='/dev/null') ## then sample the posterior via MCMC # compare fit to data check_posterior_fits(dm)
def fit_simulated_disease(n=300, cv=2.): """ Test fit for simulated disease data with noise and missingness""" # load model to test fitting dm = DiseaseJson(file('tests/simulation_gold_standard.json').read()) # adjust any priors and covariates as desired dm.set_param_age_mesh(arange(0,101,2)) for type in 'incidence prevalence remission excess_mortality'.split(): dm.params['global_priors']['heterogeneity'][type] = 'Very' dm.params['covariates']['Country_level']['LDI_id']['rate']['value'] = 0 # filter and noise up data mort_data = [] all_data = [] for d in dm.data: d['truth'] = d['value'] d['age_weights'] = array([1.]) if d['data_type'] == 'all-cause mortality data': mort_data.append(d) else: if d['value'] > 0: se = (cv / 100.) * d['value'] Y_i = mc.rtruncnorm(d['truth'], se**-2, 0, np.inf) d['value'] = Y_i d['standard_error'] = se d['effective_sample_size'] = Y_i * (1-Y_i) / se**2 all_data.append(d) sampled_data = random.sample(all_data, n) + mort_data dm.data = sampled_data # fit empirical priors and compare fit to data from dismod3 import neg_binom_model for rate_type in 'prevalence incidence remission excess-mortality'.split(): #neg_binom_model.fit_emp_prior(dm, rate_type, iter=1000, thin=1, burn=0, dbname='/dev/null') neg_binom_model.fit_emp_prior(dm, rate_type, iter=30000, thin=15, burn=15000, dbname='/dev/null') check_emp_prior_fits(dm) # fit posterior delattr(dm, 'vars') # remove vars so that gbd_disease_model creates its own version from dismod3 import gbd_disease_model keys = dismod3.utils.gbd_keys(region_list=['north_america_high_income'], year_list=[1990], sex_list=['male']) gbd_disease_model.fit(dm, method='map', keys=keys, verbose=1) ## first generate decent initial conditions gbd_disease_model.fit(dm, method='mcmc', keys=keys, iter=30000, thin=15, burn=15000, verbose=1, dbname='/dev/null') ## then sample the posterior via MCMC #gbd_disease_model.fit(dm, method='mcmc', keys=keys, iter=1000, thin=1, burn=0, verbose=1, dbname='/dev/null') ## fast for dev print 'error compared to the noisy data (coefficient of variation = %.2f)' % cv check_posterior_fits(dm) dm.data = all_data for d in dm.data: if d['data_type'] != 'all-cause mortality data': d['noisy_data'] = d['value'] d['value'] = d['truth'] print 'error compared to the truth' are, coverage = check_posterior_fits(dm) print print 'Median Absolute Relative Error of Posterior Predictions:', median(are) print 'Pct coverage:', 100*mean(coverage) f = open('score_%d_%f.txt' % (n, cv), 'a') f.write('%10.10f,%10.10f\n' % (median(are), mean(coverage))) f.close() dm.all_data = all_data dm.data = sampled_data for d in dm.data: if d['data_type'] != 'all-cause mortality data': d['value'] = d['noisy_data'] generate_figure(dm, n, cv) return dm