def test_save_country_level_posterior():
""" Test exporting country level posterior output """
# load model to test fitting
dm = DiseaseJson(file('tests/dismoditis.json').read())
# fit posterior where there is data
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=100, thin=1, burn=0, verbose=1, dbname='/dev/null') ## then sample the posterior via MCMC
# make a rate_type_list
rate_type_list = ['incidence', 'prevalence', 'remission', 'excess-mortality']
# job working directory
job_wd = dismod3.settings.JOB_WORKING_DIR % dm.id
# directory to save the file
dir = job_wd + '/posterior/country_level_posterior_dm-' + str(dm.id) + '/'
import os
from shutil import rmtree
if os.path.exists(dir):
rmtree(dir)
os.makedirs(dir)
# save country level posterior in csv file
from fit_posterior import save_country_level_posterior
save_country_level_posterior(dm, 'asia_southeast', '1990', 'male', rate_type_list)
# zip the csv file
from upload_fits import zip_country_level_posterior_files
zip_country_level_posterior_files(dm.id)
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_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():
""" 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_triangle_pattern():
""" Test fit for empirical prior to data showing a linearly increasing age pattern"""
# load model to test fitting
dm = DiseaseJson(file('tests/single_low_noise.json').read())
# create linear age pattern data
import copy
d = dm.data.pop()
for a in range(10, 100, 20):
d = copy.copy(d)
d['age_start'] = a
d['age_end'] = a
d['parameter_value'] = .01*min(a, 100-a)
d['value'] = .01*min(a, 100-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
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_model(dm, region, year, sex):
""" Fit the empirical priors, and the posterior for a specific region/year/sex
"""
# fit empirical priors
for rate_type in 'prevalence incidence remission excess-mortality'.split():
neg_binom_model.fit_emp_prior(dm, rate_type, '/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=[region],
year_list=[year], sex_list=[sex])
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
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
# store the ground truth values, for plotting (these are _not_ used in fitting the model)
dm.set_truth(key % 'remission', r)
dm.set_truth(key % 'incidence', i)
dm.set_truth(key % 'prevalence', p)
dm.set_truth(key % 'case-fatality', f)
dm.set_truth(key % 'relative-risk', (m + f) / m)
dm.set_truth(key % 'duration', X)
dm.set_truth(key % 'yld', X * i)
print '\nfitting model...'
dm.params['estimate_type'] = 'Borrow strength within each region'
keys = model.gbd_keys(region_list=['asia_southeast'], year_list=[1990, 2005], sex_list=['female', 'male'])
print ' beginning MLE+NA fit...'
model.fit(dm, method='norm_approx', keys=keys, verbose=1)
print '...model fit complete.'
# save relevant statistics of the simulation experiment
total_yld = sum(i * X)
est_yld = sum(dm.get_mcmc('median', key % 'yld'))
est_yld_upper_ui = sum(dm.get_mcmc('upper_ui', key % 'yld'))
est_yld_lower_ui = sum(dm.get_mcmc('lower_ui', key % 'yld'))
total_yld_str = """
Dashed = Truth
Dotted = MLE
Solid = Median
True YLD = %.2f
def fit_posterior(id, region, sex, year):
""" Fit posterior of specified region/sex/year for specified model
Parameters
----------
id : int
The model id number for the job to fit
region : str
From dismod3.settings.gbd_regions, but clean()-ed
sex : str, from dismod3.settings.gbd_sexes
year : str, from dismod3.settings.gbd_years
Example
-------
>>> import fit_posterior
>>> fit_posterior.fit_posterior(2552, 'asia_east', 'male', '2005')
"""
#print 'updating job status on server'
#dismod3.log_job_status(id, 'posterior', '%s--%s--%s' % (region, sex, year), 'Running')
dm = dismod3.load_disease_model(id)
#dm.data = [] # for testing, remove all data
keys = dismod3.utils.gbd_keys(region_list=[region], year_list=[year], sex_list=[sex])
# fit the model
dir = dismod3.settings.JOB_WORKING_DIR % id
import dismod3.gbd_disease_model as model
model.fit(dm, method='map', keys=keys, verbose=1) ## first generate decent initial conditions
## then sample the posterior via MCMC
model.fit(dm, method='mcmc', keys=keys, iter=50000, thin=25, burn=25000, verbose=1,
dbname='%s/posterior/pickle/dm-%d-posterior-%s-%s-%s.pickle' % (dir, id, region, sex, year))
# generate plots of results
dismod3.tile_plot_disease_model(dm, keys, defaults={})
dm.savefig('dm-%d-posterior-%s.png' % (id, '+'.join(['all', region, sex, year]))) # TODO: refactor naming into its own function (disease_json.save_image perhaps)
for param_type in dismod3.settings.output_data_types:
keys = dismod3.utils.gbd_keys(region_list=[region], year_list=[year], sex_list=[sex], type_list=[param_type])
dismod3.tile_plot_disease_model(dm, keys, defaults={})
dm.savefig('dm-%d-posterior-%s-%s-%s-%s.png' % (id, dismod3.utils.clean(param_type), region, sex, year)) # TODO: refactor naming into its own function
# summarize fit quality graphically, as well as parameter posteriors
for k in dismod3.utils.gbd_keys(region_list=[region], year_list=[year], sex_list=[sex]):
if dm.vars[k].get('data'):
dismod3.plotting.plot_posterior_predicted_checks(dm, k)
dm.savefig('dm-%d-check-%s.png' % (dm.id, k))
# save results (do this last, because it removes things from the disease model that plotting function, etc, might need
keys = dismod3.utils.gbd_keys(region_list=[region], year_list=[year], sex_list=[sex])
dm.save('dm-%d-posterior-%s-%s-%s.json' % (id, region, sex, year), keys_to_save=keys)
# make a rate_type_list
rate_type_list = ['incidence', 'prevalence', 'remission', 'excess-mortality',
'mortality', 'relative-risk', 'duration', 'incidence_x_duration']
# save country level posterior
save_country_level_posterior(dm, region, year, sex)
# update job status file
#print 'updating job status on server'
#dismod3.log_job_status(id, 'posterior',
# '%s--%s--%s' % (region, sex, year), 'Completed')
return dm
dm.set_truth(key % 'incidence', i)
dm.set_truth(key % 'prevalence', p)
dm.set_truth(key % 'case-fatality', f)
dm.set_truth(key % 'relative-risk', (m + f) / m)
dm.set_truth(key % 'duration', X)
dm.set_truth(key % 'yld', X * i)
print '\nfitting model...'
dm.params['estimate_type'] = 'Borrow strength within each region'
keys = model.gbd_keys(region_list=['asia_southeast'],
year_list=[1990, 2005],
sex_list=['female', 'male'])
print ' beginning MLE+NA fit...'
model.fit(dm, method='norm_approx', keys=keys, verbose=1)
print '...model fit complete.'
# save relevant statistics of the simulation experiment
total_yld = sum(i * X)
est_yld = sum(dm.get_mcmc('median', key % 'yld'))
est_yld_upper_ui = sum(dm.get_mcmc('upper_ui', key % 'yld'))
est_yld_lower_ui = sum(dm.get_mcmc('lower_ui', key % 'yld'))
total_yld_str = """
Dashed = Truth
Dotted = MLE
Solid = Median
True YLD = %.2f