def fit_emp_prior(id, param_type):
""" Fit empirical prior of specified type for specified model
Parameters
----------
id : int
The model id number for the job to fit
param_type : str, one of incidence, prevalence, remission, excess-mortality
The disease parameter to generate empirical priors for
Example
-------
>>> import fit_emp_prior
>>> fit_emp_prior.fit_emp_prior(2552, 'incidence')
"""
#dismod3.log_job_status(id, 'empirical_priors', param_type, 'Running')
# load disease model
dm = dismod3.load_disease_model(id)
#dm.data = [] # remove all data to speed up computation, for test
import dismod3.neg_binom_model as model
dir = dismod3.settings.JOB_WORKING_DIR % id
model.fit_emp_prior(dm, param_type, dbname='%s/empirical_priors/pickle/dm-%d-emp_prior-%s.pickle' % (dir, id, param_type))
# generate empirical prior plots
from pylab import subplot
for sex in dismod3.settings.gbd_sexes:
for year in dismod3.settings.gbd_years:
keys = dismod3.utils.gbd_keys(region_list=['all'], year_list=[year], sex_list=[sex], type_list=[param_type])
dismod3.tile_plot_disease_model(dm, keys, defaults={})
dm.savefig('dm-%d-emp_prior-%s-%s-%s.png' % (id, param_type, sex, year))
# TODO: put this in a separate script, which runs after all empirical priors are computed
for effect in ['alpha', 'beta', 'gamma', 'delta']:
dismod3.plotting.plot_empirical_prior_effects([dm], effect)
dm.savefig('dm-%d-emp-prior-%s-%s.png' % (id, param_type, effect))
# summarize fit quality graphically, as well as parameter posteriors
k0 = keys[0]
dm.vars = {k0: dm.vars} # hack to make posterior predictions plot
dismod3.plotting.plot_posterior_predicted_checks(dm, k0)
dm.savefig('dm-%d-emp-prior-check-%s.png' % (dm.id, param_type))
dm.vars = dm.vars[k0] # undo hack to make posterior predictions plot
# save results (do this last, because it removes things from the disease model that plotting function, etc, might need
dm.save('dm-%d-prior-%s.json' % (id, param_type))
dismod3.try_posting_disease_model(dm, ntries=5)
#dismod3.log_job_status(id, 'empirical_priors', param_type, 'Completed')
return dm
def hep_c_fit(regions, prediction_years, data_year_start=-inf, data_year_end=inf, egypt_flag=False):
""" Fit prevalence for regions and years specified """
print "\n***************************\nfitting %s for %s (using data from years %f to %f)" % (
regions,
prediction_years,
data_year_start,
data_year_end,
)
## load model to fit
# dm = DiseaseJson(file('tests/hep_c.json').read())
id = 8788
dismod3.disease_json.create_disease_model_dir(id)
dm = dismod3.fetch_disease_model(id)
## adjust the expert priors
dm.params["global_priors"]["heterogeneity"]["prevalence"] = "Very"
dm.params["global_priors"]["smoothness"]["prevalence"]["amount"] = "Slightly"
# TODO: construct examples of adjusting other covariates
# ipdb> dm.params['global_priors'].keys()
# [u'increasing', u'unimodal', u'level_bounds', u'y_maximum', u'note', u'level_value', u'decreasing', u'parameter_age_mesh', u'heterogeneity', u'smoothness']
# ipdb> dm.params['global_priors']['smoothness']['prevalence']
# {u'age_start': 0, u'amount': u'Moderately', u'age_end': 100}
# include a study-level covariate for 'bias'
covariates_dict = dm.get_covariates()
covariates_dict["Study_level"]["bias"]["rate"]["value"] = 1
# TODO: construct additional examples of adjusting covariates
## select relevant prevalence data
# TODO: streamline data selection functions
if egypt_flag:
dm.data = [d for d in dm.data if d["country_iso3_code"] == "EGY"]
else:
dm.data = [
d
for d in dm.data
if dismod3.utils.clean(d["gbd_region"]) in regions
and float(d["year_end"]) >= data_year_start
and float(d["year_start"]) <= data_year_end
and d["country_iso3_code"] != "EGY"
]
## create, fit, and save rate model
dm.vars = {}
keys = dismod3.utils.gbd_keys(type_list=["prevalence"], region_list=regions, year_list=prediction_years)
# TODO: consider how to do this for models that use the complete disease model
# TODO: consider adding hierarchical similarity priors for the male and female models
k0 = keys[0] # looks like k0='prevalence+asia_south+1990+male'
dm.vars[k0] = neg_binom_model.setup(dm, k0, dm.data)
dm.mcmc = mc.MCMC(dm.vars)
dm.mcmc.sample(iter=50000, burn=25000, thin=50, verbose=1)
# make map object so we can compute AIC and BIC
dm.map = mc.MAP(dm.vars)
dm.map.fit()
for k in keys:
# save the results in the disease model
dm.vars[k] = dm.vars[k0]
neg_binom_model.store_mcmc_fit(dm, k, dm.vars[k])
# check autocorrelation to confirm chain has mixed
test_model.summarize_acorr(dm.vars[k]["rate_stoch"].trace())
# generate plots of results
dismod3.tile_plot_disease_model(dm, [k], defaults={"ymax": 0.15, "alpha": 0.5})
dm.savefig("dm-%d-posterior-%s.%f.png" % (dm.id, k, random()))
# summarize fit quality graphically, as well as parameter posteriors
dismod3.plotting.plot_posterior_predicted_checks(dm, k0)
dm.savefig("dm-%d-check-%s.%f.png" % (dm.id, k0, random()))
dismod3.post_disease_model(dm)
return dm
for y in [1990, 2005]:
for s in ["male", "female"]:
key = "prevalence+egypt+%d+%s" % (y, s)
prev_1 = neg_binom_model.calc_rate_trace(dm_egypt, key, dm_egypt.vars[key])
pop_1 = neg_binom_model.population_by_age[("EGY", str(y), s)]
key = "prevalence+north_africa_middle_east+%d+%s" % (y, s)
prev_0 = neg_binom_model.calc_rate_trace(dm_na_me, key, dm_na_me.vars[key])
pop_0 = neg_binom_model.regional_population(key)
# generate population weighted average
prev = (prev_0 * (pop_0 - pop_1) + prev_1 * pop_1) / pop_0
neg_binom_model.store_mcmc_fit(dm_na_me, key, None, prev)
# generate plots of results
dismod3.tile_plot_disease_model(dm_na_me, [key], defaults={"ymax": 0.15, "alpha": 0.5})
dm_na_me.savefig("dm-%d-posterior-na_me_w_egypt.%f.png" % (dm_na_me.id, random()))
# save results
dismod3.post_disease_model(dm_na_me)
dm = hep_c_fit(
"caribbean latin_america_tropical latin_america_andean latin_america_central latin_america_southern".split(),
[1990, 2005],
)
dm = hep_c_fit(
"sub-saharan_africa_central sub-saharan_africa_southern sub-saharan_africa_west".split(), [1990, 2005]
)
for (
r
['excess-mortality', 'excess'],
['incidence', 'incidence'],
['mrr', 'risk'],
['prevalence', 'prevalence'],
]:
x = [0]
y = [0]
for age in age_mesh:
x.append(age)
y.append(measure_out.model[index_dict[(dm4_type, year, age)]])
key = dismod3.gbd_key_for(dm3_type, r, year, sex)
est = dismod3.utils.interpolate(x, y, dm.get_estimate_age_mesh())
dm.set_truth(key, est)
dismod3.tile_plot_disease_model(dm, [key], defaults={})
try:
pl.savefig(dismod3.settings.JOB_WORKING_DIR % id + '/dm-%d-posterior-%s-%s-%s.png' % (id, dm3_type, sex, year)) # TODO: refactor naming into its own function
except IOError, e:
print 'Warning: could not create png. Maybe it exists already?\n%s' % e
# save results (do this last, because it removes things from the disease model that plotting function, etc, might need
dismod3.try_posting_disease_model(dm, ntries=5)
print
print '********************'
print 'computation complete'
print '********************'
def main():
import optparse
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
