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_hep_c(): """ Test fit for subset of hep_c data data is filtered to include only prevalence with region == 'europe_western' and sex == 'all' """ # load model to test fitting dm = DiseaseJson(file('tests/hep_c_europe_western.json').read()) # fit empirical priors neg_binom_model.fit_emp_prior(dm, 'prevalence', '/dev/null') # 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=['europe_western'], 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 # check that prevalence is smooth near age zero prediction = dm.get_mcmc('mean', 'prevalence+europe_western+1990+male') print prediction return dm assert prediction[100] < .1, 'prediction should not shoot up in oldest ages'
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 test_dismoditis(): """ Test fit for simple example""" # load model to test fitting dm = DiseaseJson(file('tests/dismoditis.json').read()) for d in dm.data: d['standard_error'] = .01 # fit empirical priors neg_binom_model.fit_emp_prior(dm, 'prevalence', '/dev/null') check_emp_prior_fits(dm) 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 where there is no data 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 check_posterior_fits(dm) # check that prevalence is smooth near age zero prediction = dm.get_mcmc('mean', 'prevalence+north_america_high_income+1990+male') assert prediction[1]-prediction[0] < .01, 'prediction should be smooth near zero'
def test_increasing_prior(): """ Test fit for empirical prior to data showing a linearly increasing age pattern with a fine age mesh""" # load model to test fitting dm = DiseaseJson(file('tests/single_low_noise.json').read()) dm.params['global_priors']['increasing']['incidence']['age_end'] = 100 # create linear age pattern data import copy d = dm.data.pop() for a in range(10, 100, 10): d = copy.copy(d) d['age_start'] = a d['age_end'] = a d['parameter_value'] = .01*a d['value'] = .01*a dm.data.append(d) # fit empirical priors from dismod3 import neg_binom_model neg_binom_model.fit_emp_prior(dm, 'prevalence', '/dev/null') # compare fit to data, and check that it is increasing check_emp_prior_fits(dm) assert np.all(np.diff(dm.get_mcmc('emp_prior_mean', dismod3.utils.gbd_key_for('prevalence', 'asia_southeast', 1990, 'male'))) >= 0), 'expert prior says increasing'
def test_ihd(): """ Test fit for subset of ihd data data is filtered to include only data for region == 'europe_western' and sex == 'male' """ # load model to test fitting dm = DiseaseJson(file('tests/ihd.json').read()) fit_model(dm, 'europe_western', 1990, 'male') # check that prevalence is smooth around age 90 prediction = dm.get_mcmc('mean', 'prevalence+europe_western+1990+male') print prediction assert prediction[89]/prediction[90] < .05, 'prediction should not change greatly at age 90' return dm
def test_opi(): """ Test fit for subset of opi_dep data data is filtered to include only data for region == 'europe_central' and sex == 'male' """ # load model to test fitting dm = DiseaseJson(file('tests/opi.json').read()) dm.params['global_priors']['decreasing']['prevalence']['age_start'] = 60 dm.params['global_priors']['decreasing']['prevalence']['age_end'] = 100 fit_model(dm, 'europe_central', 1990, 'male') # check that prevalence is smooth near age zero prediction = dm.get_mcmc('mean', 'prevalence+europe_central+1990+male') print prediction assert prediction[80] > prediction[100], 'prediction should decrease at oldest ages' return dm
def test_mesh_refinement(): """ Compare fit for coarse and fine age mesh""" # load model and fit it dm1 = DiseaseJson(file('tests/single_low_noise.json').read()) dm1.set_param_age_mesh(arange(0,101,20)) from dismod3 import neg_binom_model neg_binom_model.fit_emp_prior(dm1, 'prevalence', '/dev/null') # load another copy and fit it with a finer age mesh dm2 = DiseaseJson(file('tests/single_low_noise.json').read()) dm2.set_param_age_mesh(arange(0,101,5)) from dismod3 import neg_binom_model neg_binom_model.fit_emp_prior(dm2, 'prevalence', '/dev/null') # compare fits p1 = dm1.get_mcmc('emp_prior_mean', dismod3.utils.gbd_key_for('prevalence', 'asia_southeast', 1990, 'male')) p2 = dm2.get_mcmc('emp_prior_mean', dismod3.utils.gbd_key_for('prevalence', 'asia_southeast', 1990, 'male')) print p1[::20] print p2[::20] assert np.all(abs(p1[::20] / p2[::20] - 1.) < .05), 'Prediction should be closer to data'
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
col_names = sorted(data_dict_for_csv(data[0]).keys()) csv_f.writerow(col_names) for d in data: dd = data_dict_for_csv(d) csv_f.writerow([dd[c] for c in col_names]) f_file.close() except: print "couldn't write file" # create the disease model based on this data dm = DiseaseJson(json.dumps({'params': {"id": 1, "sex": "male", "region": "asia_southeast", "year": "2005", "condition": "type_ii_diabetes"}, "data": data})) for year in [1990, 2005]: for sex in ['male', 'female']: key = dismod3.utils.gbd_key_for('%s', dm.get_region(), year, sex) dm.set_initial_value(key % 'all-cause_mortality', m) # set semi-informative priors on the rate functions dm.set_priors(key % 'remission', ' zero 0 100, ') dm.set_priors(key % 'case-fatality', ' zero 0 10, smooth 100, ') dm.set_priors(key % 'incidence', ' zero 0 2, smooth 100, increasing 50 100, ') dm.set_priors(key % 'prevalence', ' zero 0 2, smooth 100, ')
csv_f.writerow(col_names) for d in data: dd = data_dict_for_csv(d) csv_f.writerow([dd[c] for c in col_names]) f_file.close() except: print "couldn't write file" # create the disease model based on this data dm = DiseaseJson( json.dumps({ 'params': { "id": 1, "sex": "male", "region": "asia_southeast", "year": "2005", "condition": "type_ii_diabetes" }, "data": data })) for year in [1990, 2005]: for sex in ['male', 'female']: key = dismod3.utils.gbd_key_for('%s', dm.get_region(), year, sex) dm.set_initial_value(key % 'all-cause_mortality', m) # set semi-informative priors on the rate functions dm.set_priors(key % 'remission', ' zero 0 100, ') dm.set_priors(key % 'case-fatality', ' zero 0 10, smooth 100, ') dm.set_priors(key % 'incidence',