def validate_age_group(model, replicate):
# set random seed for reproducibility
mc.np.random.seed(1234567 + replicate)
N = 30
delta_true = 5.0
pi_true = true_rate_function
m = simulate_age_group_data(N=N, delta_true=delta_true, pi_true=pi_true)
if model == "midpoint_covariate":
fit_midpoint_covariate_model(m)
if model == "alt_midpoint_covariate":
fit_alt_midpoint_covariate_model(m)
elif model == "age_standardizing":
fit_age_standardizing_model(m)
elif model == "age_integrating":
fit_age_integrating_model(m)
elif model == "midpoint_model":
fit_midpoint_model(m)
elif model == "disaggregation_model":
fit_disaggregation_model(m)
else:
raise TypeError, 'Unknown model type: "%s"' % model
# compare estimate to ground truth
import data_simulation
m.mu = pandas.DataFrame(
dict(
true=[pi_true(a) for a in range(101)],
mu_pred=m.vars["mu_age"].stats()["mean"],
sigma_pred=m.vars["mu_age"].stats()["standard deviation"],
)
)
data_simulation.add_quality_metrics(m.mu)
print "\nparam prediction bias: %.5f, MARE: %.3f, coverage: %.2f" % (
m.mu["abs_err"].mean(),
pl.median(pl.absolute(m.mu["rel_err"].dropna())),
m.mu["covered?"].mean(),
)
print
data_simulation.add_quality_metrics(m.mu)
data_simulation.initialize_results(m)
data_simulation.add_to_results(m, "mu")
data_simulation.finalize_results(m)
return m
def fit(model):
emp_priors = model.emp_priors
## Then fit the model and compare the estimates to the truth
model.vars = {}
model.vars['p'] = data_model.data_model('p', model, 'p', 'all', 'total', 'all', None, emp_priors['p', 'mu'], emp_priors['p', 'sigma'])
model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'], iter=5000, burn=2000, thin=25, tune_interval=100)
#model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'], iter=101, burn=0, thin=1, tune_interval=100)
#graphics.plot_one_ppc(model.vars['p'], 'p')
#graphics.plot_convergence_diag(model.vars)
graphics.plot_one_type(model, model.vars['p'], emp_priors, 'p')
pl.plot(model.a, model.pi_age_true, 'b--', linewidth=3, alpha=.5, label='Truth')
pl.legend(fancybox=True, shadow=True, loc='upper left')
pl.title('Heterogeneity %s'%model.parameters['p']['heterogeneity'])
pl.show()
model.input_data['mu_pred'] = model.vars['p']['p_pred'].stats()['mean']
model.input_data['sigma_pred'] = model.vars['p']['p_pred'].stats()['standard deviation']
data_simulation.add_quality_metrics(model.input_data)
model.delta = pandas.DataFrame(dict(true=[model.delta_true]))
model.delta['mu_pred'] = pl.exp(model.vars['p']['eta'].trace()).mean()
model.delta['sigma_pred'] = pl.exp(model.vars['p']['eta'].trace()).std()
data_simulation.add_quality_metrics(model.delta)
print 'delta'
print model.delta
print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (model.input_data['abs_err'].mean(),
pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
model.input_data['covered?'].mean())
model.mu = pandas.DataFrame(dict(true=model.pi_age_true,
mu_pred=model.vars['p']['mu_age'].stats()['mean'],
sigma_pred=model.vars['p']['mu_age'].stats()['standard deviation']))
data_simulation.add_quality_metrics(model.mu)
data_simulation.initialize_results(model)
data_simulation.add_to_results(model, 'delta')
data_simulation.add_to_results(model, 'mu')
data_simulation.add_to_results(model, 'input_data')
data_simulation.finalize_results(model)
print model.results
def validate_age_group(model, replicate):
# set random seed for reproducibility
mc.np.random.seed(1234567+replicate)
N = 30
delta_true = 5.
pi_true = true_rate_function
m = simulate_age_group_data(N=N, delta_true=delta_true, pi_true=pi_true)
if model == 'midpoint_covariate':
fit_midpoint_covariate_model(m)
elif model == 'age_standardizing':
fit_age_standardizing_model(m)
elif model == 'age_integrating':
fit_age_integrating_model(m)
elif model == 'midpoint_model':
fit_midpoint_model(m)
elif model == 'disaggregation_model':
fit_disaggregation_model(m)
else:
raise TypeError, 'Unknown model type: "%s"' % model
# compare estimate to ground truth
import data_simulation
m.mu = pandas.DataFrame(dict(true=[pi_true(a) for a in range(101)],
mu_pred=m.vars['mu_age'].stats()['mean'],
lb_pred=m.vars['mu_age'].stats()['95% HPD interval'][:,0],
ub_pred=m.vars['mu_age'].stats()['95% HPD interval'][:,1]))
data_simulation.add_quality_metrics(m.mu)
print '\nparam prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (m.mu['abs_err'].mean(),
pl.median(pl.absolute(m.mu['rel_err'].dropna())),
m.mu['covered?'].mean())
print
data_simulation.add_quality_metrics(m.mu)
data_simulation.initialize_results(m)
data_simulation.add_to_results(m, 'mu')
data_simulation.finalize_results(m)
return m
def store_results(dm, area, sex, year):
types_to_plot = 'p i r rr'.split()
graphics.plot_convergence_diag(dm.vars)
pl.clf()
for i, t in enumerate(types_to_plot):
pl.subplot(len(types_to_plot), 1, i+1)
graphics.plot_data_bars(dm.model.get_data(t))
pl.plot(range(101), dm.emp_priors[t, 'mu'], linestyle='dashed', color='grey', label='Emp. Prior', linewidth=3)
pl.plot(range(101), dm.true[t], 'b-', label='Truth', linewidth=3)
pl.plot(range(101), dm.posteriors[t].mean(0), 'r-', label='Estimate', linewidth=3)
pl.errorbar(range(101), dm.posteriors[t].mean(0), yerr=1.96*dm.posteriors[t].std(0), fmt='r-', linewidth=1, capsize=0)
pl.ylabel(t)
graphics.expand_axis()
pl.legend(loc=(0.,-.95), fancybox=True, shadow=True)
pl.subplots_adjust(hspace=0, left=.1, right=.95, bottom=.2, top=.95)
pl.xlabel('Age (Years)')
pl.show()
model = dm
model.mu = pandas.DataFrame()
for t in types_to_plot:
model.mu = model.mu.append(pandas.DataFrame(dict(true=dm.true[t],
mu_pred=dm.posteriors[t].mean(0),
sigma_pred=dm.posteriors[t].std(0))),
ignore_index=True)
data_simulation.add_quality_metrics(model.mu)
print '\nparam prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (model.mu['abs_err'].mean(),
pl.median(pl.absolute(model.mu['rel_err'].dropna())),
model.mu['covered?'].mean())
print
data_simulation.initialize_results(model)
data_simulation.add_to_results(model, 'mu')
data_simulation.finalize_results(model)
print model.results
return model
def validate_ai_re(N=500, delta_true=.15, sigma_true=[.1,.1,.1,.1,.1], pi_true=quadratic, smoothness='Moderately', heterogeneity='Slightly'):
## generate simulated data
a = pl.arange(0, 101, 1)
pi_age_true = pi_true(a)
import dismod3
import simplejson as json
model = data.ModelData.from_gbd_jsons(json.loads(dismod3.disease_json.DiseaseJson().to_json()))
gbd_hierarchy = model.hierarchy
model = data_simulation.simple_model(N)
model.hierarchy = gbd_hierarchy
model.parameters['p']['parameter_age_mesh'] = range(0, 101, 10)
model.parameters['p']['smoothness'] = dict(amount=smoothness)
model.parameters['p']['heterogeneity'] = heterogeneity
age_start = pl.array(mc.runiform(0, 100, size=N), dtype=int)
age_end = pl.array(mc.runiform(age_start, 100, size=N), dtype=int)
age_weights = pl.ones_like(a)
sum_pi_wt = pl.cumsum(pi_age_true*age_weights)
sum_wt = pl.cumsum(age_weights*1.)
p = (sum_pi_wt[age_end] - sum_pi_wt[age_start]) / (sum_wt[age_end] - sum_wt[age_start])
# correct cases where age_start == age_end
i = age_start == age_end
if pl.any(i):
p[i] = pi_age_true[age_start[i]]
model.input_data['age_start'] = age_start
model.input_data['age_end'] = age_end
model.input_data['effective_sample_size'] = mc.runiform(100, 10000, size=N)
from validate_covariates import alpha_true_sim
area_list = pl.array(['all', 'super-region_3', 'north_africa_middle_east', 'EGY', 'KWT', 'IRN', 'IRQ', 'JOR', 'SYR'])
alpha = alpha_true_sim(model, area_list, sigma_true)
print alpha
model.input_data['true'] = pl.nan
model.input_data['area'] = area_list[mc.rcategorical(pl.ones(len(area_list)) / float(len(area_list)), N)]
for i, a in model.input_data['area'].iteritems():
model.input_data['true'][i] = p[i] * pl.exp(pl.sum([alpha[n] for n in nx.shortest_path(model.hierarchy, 'all', a) if n in alpha]))
p = model.input_data['true']
n = model.input_data['effective_sample_size']
model.input_data['value'] = mc.rnegative_binomial(n*p, delta_true*n*p) / n
## Then fit the model and compare the estimates to the truth
model.vars = {}
model.vars['p'] = data_model.data_model('p', model, 'p', 'north_africa_middle_east', 'total', 'all', None, None, None)
#model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'], iter=1005, burn=500, thin=5, tune_interval=100)
model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'], iter=10000, burn=5000, thin=25, tune_interval=100)
graphics.plot_one_ppc(model.vars['p'], 'p')
graphics.plot_convergence_diag(model.vars)
graphics.plot_one_type(model, model.vars['p'], {}, 'p')
pl.plot(range(101), pi_age_true, 'r:', label='Truth')
pl.legend(fancybox=True, shadow=True, loc='upper left')
pl.show()
model.input_data['mu_pred'] = model.vars['p']['p_pred'].stats()['mean']
model.input_data['sigma_pred'] = model.vars['p']['p_pred'].stats()['standard deviation']
data_simulation.add_quality_metrics(model.input_data)
model.delta = pandas.DataFrame(dict(true=[delta_true]))
model.delta['mu_pred'] = pl.exp(model.vars['p']['eta'].trace()).mean()
model.delta['sigma_pred'] = pl.exp(model.vars['p']['eta'].trace()).std()
data_simulation.add_quality_metrics(model.delta)
model.alpha = pandas.DataFrame(index=[n for n in nx.traversal.dfs_preorder_nodes(model.hierarchy)])
model.alpha['true'] = pandas.Series(dict(alpha))
model.alpha['mu_pred'] = pandas.Series([n.stats()['mean'] for n in model.vars['p']['alpha']], index=model.vars['p']['U'].columns)
model.alpha['sigma_pred'] = pandas.Series([n.stats()['standard deviation'] for n in model.vars['p']['alpha']], index=model.vars['p']['U'].columns)
model.alpha = model.alpha.dropna()
data_simulation.add_quality_metrics(model.alpha)
model.sigma = pandas.DataFrame(dict(true=sigma_true))
model.sigma['mu_pred'] = [n.stats()['mean'] for n in model.vars['p']['sigma_alpha']]
model.sigma['sigma_pred']=[n.stats()['standard deviation'] for n in model.vars['p']['sigma_alpha']]
data_simulation.add_quality_metrics(model.sigma)
print 'delta'
print model.delta
print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (model.input_data['abs_err'].mean(),
pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
model.input_data['covered?'].mean())
model.mu = pandas.DataFrame(dict(true=pi_age_true,
mu_pred=model.vars['p']['mu_age'].stats()['mean'],
sigma_pred=model.vars['p']['mu_age'].stats()['standard deviation']))
data_simulation.add_quality_metrics(model.mu)
data_simulation.initialize_results(model)
data_simulation.add_to_results(model, 'delta')
data_simulation.add_to_results(model, 'mu')
data_simulation.add_to_results(model, 'input_data')
data_simulation.add_to_results(model, 'alpha')
data_simulation.add_to_results(model, 'sigma')
data_simulation.finalize_results(model)
print model.results
return model
def validate_ai_re(N=500,
delta_true=.15,
sigma_true=[.1, .1, .1, .1, .1],
pi_true=quadratic,
smoothness='Moderately',
heterogeneity='Slightly'):
## generate simulated data
a = pl.arange(0, 101, 1)
pi_age_true = pi_true(a)
import dismod3
import simplejson as json
model = data.ModelData.from_gbd_jsons(
json.loads(dismod3.disease_json.DiseaseJson().to_json()))
gbd_hierarchy = model.hierarchy
model = data_simulation.simple_model(N)
model.hierarchy = gbd_hierarchy
model.parameters['p']['parameter_age_mesh'] = range(0, 101, 10)
model.parameters['p']['smoothness'] = dict(amount=smoothness)
model.parameters['p']['heterogeneity'] = heterogeneity
age_start = pl.array(mc.runiform(0, 100, size=N), dtype=int)
age_end = pl.array(mc.runiform(age_start, 100, size=N), dtype=int)
age_weights = pl.ones_like(a)
sum_pi_wt = pl.cumsum(pi_age_true * age_weights)
sum_wt = pl.cumsum(age_weights * 1.)
p = (sum_pi_wt[age_end] - sum_pi_wt[age_start]) / (sum_wt[age_end] -
sum_wt[age_start])
# correct cases where age_start == age_end
i = age_start == age_end
if pl.any(i):
p[i] = pi_age_true[age_start[i]]
model.input_data['age_start'] = age_start
model.input_data['age_end'] = age_end
model.input_data['effective_sample_size'] = mc.runiform(100, 10000, size=N)
from validate_covariates import alpha_true_sim
area_list = pl.array([
'all', 'super-region_3', 'north_africa_middle_east', 'EGY', 'KWT',
'IRN', 'IRQ', 'JOR', 'SYR'
])
alpha = alpha_true_sim(model, area_list, sigma_true)
print alpha
model.input_data['true'] = pl.nan
model.input_data['area'] = area_list[mc.rcategorical(
pl.ones(len(area_list)) / float(len(area_list)), N)]
for i, a in model.input_data['area'].iteritems():
model.input_data['true'][i] = p[i] * pl.exp(
pl.sum([
alpha[n] for n in nx.shortest_path(model.hierarchy, 'all', a)
if n in alpha
]))
p = model.input_data['true']
n = model.input_data['effective_sample_size']
model.input_data['value'] = mc.rnegative_binomial(n * p,
delta_true * n * p) / n
## Then fit the model and compare the estimates to the truth
model.vars = {}
model.vars['p'] = data_model.data_model('p', model, 'p',
'north_africa_middle_east',
'total', 'all', None, None, None)
#model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'], iter=1005, burn=500, thin=5, tune_interval=100)
model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'],
iter=10000,
burn=5000,
thin=25,
tune_interval=100)
graphics.plot_one_ppc(model.vars['p'], 'p')
graphics.plot_convergence_diag(model.vars)
graphics.plot_one_type(model, model.vars['p'], {}, 'p')
pl.plot(range(101), pi_age_true, 'r:', label='Truth')
pl.legend(fancybox=True, shadow=True, loc='upper left')
pl.show()
model.input_data['mu_pred'] = model.vars['p']['p_pred'].stats()['mean']
model.input_data['sigma_pred'] = model.vars['p']['p_pred'].stats(
)['standard deviation']
data_simulation.add_quality_metrics(model.input_data)
model.delta = pandas.DataFrame(dict(true=[delta_true]))
model.delta['mu_pred'] = pl.exp(model.vars['p']['eta'].trace()).mean()
model.delta['sigma_pred'] = pl.exp(model.vars['p']['eta'].trace()).std()
data_simulation.add_quality_metrics(model.delta)
model.alpha = pandas.DataFrame(
index=[n for n in nx.traversal.dfs_preorder_nodes(model.hierarchy)])
model.alpha['true'] = pandas.Series(dict(alpha))
model.alpha['mu_pred'] = pandas.Series(
[n.stats()['mean'] for n in model.vars['p']['alpha']],
index=model.vars['p']['U'].columns)
model.alpha['sigma_pred'] = pandas.Series(
[n.stats()['standard deviation'] for n in model.vars['p']['alpha']],
index=model.vars['p']['U'].columns)
model.alpha = model.alpha.dropna()
data_simulation.add_quality_metrics(model.alpha)
model.sigma = pandas.DataFrame(dict(true=sigma_true))
model.sigma['mu_pred'] = [
n.stats()['mean'] for n in model.vars['p']['sigma_alpha']
]
model.sigma['sigma_pred'] = [
n.stats()['standard deviation'] for n in model.vars['p']['sigma_alpha']
]
data_simulation.add_quality_metrics(model.sigma)
print 'delta'
print model.delta
print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (
model.input_data['abs_err'].mean(),
pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
model.input_data['covered?'].mean())
model.mu = pandas.DataFrame(
dict(true=pi_age_true,
mu_pred=model.vars['p']['mu_age'].stats()['mean'],
sigma_pred=model.vars['p']['mu_age'].stats()
['standard deviation']))
data_simulation.add_quality_metrics(model.mu)
data_simulation.initialize_results(model)
data_simulation.add_to_results(model, 'delta')
data_simulation.add_to_results(model, 'mu')
data_simulation.add_to_results(model, 'input_data')
data_simulation.add_to_results(model, 'alpha')
data_simulation.add_to_results(model, 'sigma')
data_simulation.finalize_results(model)
print model.results
return model
def validate_rate_model(rate_type='neg_binom',
data_type='epilepsy',
replicate=0):
# set random seed for reproducibility
mc.np.random.seed(1234567 + replicate)
# load data
model = dismod3.data.load('/home/j/Project/dismod/output/dm-32377/')
data = model.get_data('p')
#data = data.ix[:20, :]
# replace data with synthetic data if requested
if data_type == 'epilepsy':
# no replacement needed
pass
elif data_type == 'schiz':
import pandas as pd
data = pd.read_csv('/homes/abie/gbd_dev/gbd/tests/schiz.csv')
elif data_type == 'binom':
N = 1.e6
data['effective_sample_size'] = N
mu = data['value'].mean()
data['value'] = mc.rbinomial(N, mu, size=len(data.index)) / N
elif data_type == 'poisson':
N = 1.e6
data['effective_sample_size'] = N
mu = data['value'].mean()
data['value'] = mc.rpoisson(N * mu, size=len(data.index)) / N
elif data_type == 'normal':
mu = data['value'].mean()
sigma = .125 * mu
data['standard_error'] = sigma
data['value'] = mc.rnormal(mu, sigma**-2, size=len(data.index))
elif data_type == 'log_normal':
mu = data['value'].mean()
sigma = .25
data['standard_error'] = sigma * mu
data['value'] = pl.exp(
mc.rnormal(pl.log(mu), sigma**-2, size=len(data.index)))
else:
raise TypeError, 'Unknown data type "%s"' % data_type
# sample prevalence data
i_test = mc.rbernoulli(.25, size=len(data.index))
i_nan = pl.isnan(data['effective_sample_size'])
data['lower_ci'] = pl.nan
data['upper_ci'] = pl.nan
data.ix[i_nan, 'effective_sample_size'] = 0.
data['standard_error'] = pl.sqrt(
data['value'] * (1 - data['value'])) / data['effective_sample_size']
data.ix[pl.isnan(data['standard_error']), 'standard_error'] = pl.inf
data['standard_error'][i_test] = pl.inf
data['effective_sample_size'][i_test] = 0.
data['value'] = pl.maximum(data['value'], 1.e-12)
model.input_data = data
# create model
# TODO: set parameters in model.parameters['p'] dict
# then have simple method to create age specific rate model
#model.parameters['p'] = ...
#model.vars += dismod3.ism.age_specific_rate(model, 'p')
model.parameters['p']['parameter_age_mesh'] = [0, 100]
model.parameters['p']['heterogeneity'] = 'Very'
model.vars['p'] = dismod3.data_model.data_model(
'p',
model,
'p',
'all',
'total',
'all',
None,
None,
None,
rate_type=rate_type,
interpolation_method='zero',
include_covariates=False)
# add upper bound on sigma in log normal model to help convergence
#if rate_type == 'log_normal':
# model.vars['p']['sigma'].parents['upper'] = 1.5
# add upper bound on sigma, zeta in offset log normal
#if rate_type == 'offset_log_normal':
# model.vars['p']['sigma'].parents['upper'] = .1
# model.vars['p']['p_zeta'].value = 5.e-9
# model.vars['p']['p_zeta'].parents['upper'] = 1.e-8
# fit model
dismod3.fit.fit_asr(model, 'p', iter=20000, thin=10, burn=10000)
#dismod3.fit.fit_asr(model, 'p', iter=100, thin=1, burn=0)
# compare estimate to hold-out
data['mu_pred'] = model.vars['p']['p_pred'].stats()['mean']
data['lb_pred'] = model.vars['p']['p_pred'].stats()['95% HPD interval'][:,
0]
data['ub_pred'] = model.vars['p']['p_pred'].stats()['95% HPD interval'][:,
1]
import data_simulation
model.test = data[i_test]
data = model.test
data['true'] = data['value']
data_simulation.add_quality_metrics(data)
data_simulation.initialize_results(model)
data_simulation.add_to_results(model, 'test')
data_simulation.finalize_results(model)
return model
def validate_consistent_re(N=500, delta_true=.15, sigma_true=[.1,.1,.1,.1,.1],
true=dict(i=quadratic, f=constant, r=constant)):
types = pl.array(['i', 'r', 'f', 'p'])
## generate simulated data
model = data_simulation.simple_model(N)
model.input_data['effective_sample_size'] = 1.
model.input_data['value'] = 0.
# coarse knot spacing for fast testing
for t in types:
model.parameters[t]['parameter_age_mesh'] = range(0, 101, 20)
sim = consistent_model.consistent_model(model, 'all', 'total', 'all', {})
for t in 'irf':
for i, k_i in enumerate(sim[t]['knots']):
sim[t]['gamma'][i].value = pl.log(true[t](k_i))
age_start = pl.array(mc.runiform(0, 100, size=N), dtype=int)
age_end = pl.array(mc.runiform(age_start, 100, size=N), dtype=int)
data_type = types[mc.rcategorical(pl.ones(len(types), dtype=float) / float(len(types)), size=N)]
a = pl.arange(101)
age_weights = pl.ones_like(a)
sum_wt = pl.cumsum(age_weights)
p = pl.zeros(N)
for t in types:
mu_t = sim[t]['mu_age'].value
sum_mu_wt = pl.cumsum(mu_t*age_weights)
p_t = (sum_mu_wt[age_end] - sum_mu_wt[age_start]) / (sum_wt[age_end] - sum_wt[age_start])
# correct cases where age_start == age_end
i = age_start == age_end
if pl.any(i):
p_t[i] = mu_t[age_start[i]]
# copy part into p
p[data_type==t] = p_t[data_type==t]
# add covariate shifts
import dismod3
import simplejson as json
gbd_model = data.ModelData.from_gbd_jsons(json.loads(dismod3.disease_json.DiseaseJson().to_json()))
model.hierarchy = gbd_model.hierarchy
from validate_covariates import alpha_true_sim
area_list = pl.array(['all', 'super-region_3', 'north_africa_middle_east', 'EGY', 'KWT', 'IRN', 'IRQ', 'JOR', 'SYR'])
alpha = {}
for t in types:
alpha[t] = alpha_true_sim(model, area_list, sigma_true)
print json.dumps(alpha, indent=2)
model.input_data['area'] = area_list[mc.rcategorical(pl.ones(len(area_list)) / float(len(area_list)), N)]
for i, a in model.input_data['area'].iteritems():
t = data_type[i]
p[i] = p[i] * pl.exp(pl.sum([alpha[t][n] for n in nx.shortest_path(model.hierarchy, 'all', a) if n in alpha]))
n = mc.runiform(100, 10000, size=N)
model.input_data['data_type'] = data_type
model.input_data['age_start'] = age_start
model.input_data['age_end'] = age_end
model.input_data['effective_sample_size'] = n
model.input_data['true'] = p
model.input_data['value'] = mc.rnegative_binomial(n*p, delta_true) / n
# coarse knot spacing for fast testing
for t in types:
model.parameters[t]['parameter_age_mesh'] = range(0, 101, 20)
## Then fit the model and compare the estimates to the truth
model.vars = {}
model.vars = consistent_model.consistent_model(model, 'all', 'total', 'all', {})
#model.map, model.mcmc = fit_model.fit_consistent_model(model.vars, iter=101, burn=0, thin=1, tune_interval=100)
model.map, model.mcmc = fit_model.fit_consistent_model(model.vars, iter=10000, burn=5000, thin=25, tune_interval=100)
graphics.plot_convergence_diag(model.vars)
graphics.plot_fit(model, model.vars, {}, {})
for i, t in enumerate('i r f p rr pf'.split()):
pl.subplot(2, 3, i+1)
pl.plot(range(101), sim[t]['mu_age'].value, 'w-', label='Truth', linewidth=2)
pl.plot(range(101), sim[t]['mu_age'].value, 'r-', label='Truth', linewidth=1)
pl.show()
model.input_data['mu_pred'] = 0.
model.input_data['sigma_pred'] = 0.
for t in types:
model.input_data['mu_pred'][data_type==t] = model.vars[t]['p_pred'].stats()['mean']
model.input_data['sigma_pred'][data_type==t] = model.vars[t]['p_pred'].stats()['standard deviation']
data_simulation.add_quality_metrics(model.input_data)
model.delta = pandas.DataFrame(dict(true=[delta_true for t in types if t != 'rr']))
model.delta['mu_pred'] = [pl.exp(model.vars[t]['eta'].trace()).mean() for t in types if t != 'rr']
model.delta['sigma_pred'] = [pl.exp(model.vars[t]['eta'].trace()).std() for t in types if t != 'rr']
data_simulation.add_quality_metrics(model.delta)
model.alpha = pandas.DataFrame()
model.sigma = pandas.DataFrame()
for t in types:
alpha_t = pandas.DataFrame(index=[n for n in nx.traversal.dfs_preorder_nodes(model.hierarchy)])
alpha_t['true'] = pandas.Series(dict(alpha[t]))
alpha_t['mu_pred'] = pandas.Series([n.stats()['mean'] for n in model.vars[t]['alpha']], index=model.vars[t]['U'].columns)
alpha_t['sigma_pred'] = pandas.Series([n.stats()['standard deviation'] for n in model.vars[t]['alpha']], index=model.vars[t]['U'].columns)
alpha_t['type'] = t
model.alpha = model.alpha.append(alpha_t.dropna(), ignore_index=True)
sigma_t = pandas.DataFrame(dict(true=sigma_true))
sigma_t['mu_pred'] = [n.stats()['mean'] for n in model.vars[t]['sigma_alpha']]
sigma_t['sigma_pred'] = [n.stats()['standard deviation'] for n in model.vars[t]['sigma_alpha']]
model.sigma = model.sigma.append(sigma_t.dropna(), ignore_index=True)
data_simulation.add_quality_metrics(model.alpha)
data_simulation.add_quality_metrics(model.sigma)
print 'delta'
print model.delta
print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (model.input_data['abs_err'].mean(),
pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
model.input_data['covered?'].mean())
model.mu = pandas.DataFrame()
for t in types:
model.mu = model.mu.append(pandas.DataFrame(dict(true=sim[t]['mu_age'].value,
mu_pred=model.vars[t]['mu_age'].stats()['mean'],
sigma_pred=model.vars[t]['mu_age'].stats()['standard deviation'])),
ignore_index=True)
data_simulation.add_quality_metrics(model.mu)
print '\nparam prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (model.mu['abs_err'].mean(),
pl.median(pl.absolute(model.mu['rel_err'].dropna())),
model.mu['covered?'].mean())
print
data_simulation.initialize_results(model)
data_simulation.add_to_results(model, 'delta')
data_simulation.add_to_results(model, 'mu')
data_simulation.add_to_results(model, 'input_data')
data_simulation.add_to_results(model, 'alpha')
data_simulation.add_to_results(model, 'sigma')
data_simulation.finalize_results(model)
print model.results
return model
def validate_rate_model(rate_type='neg_binom', data_type='epilepsy', replicate=0):
# set random seed for reproducibility
mc.np.random.seed(1234567 + replicate)
# load data
model = dismod3.data.load('/home/j/Project/dismod/output/dm-32377/')
data = model.get_data('p')
#data = data.ix[:20, :]
# replace data with synthetic data if requested
if data_type == 'epilepsy':
# no replacement needed
pass
elif data_type == 'schiz':
import pandas as pd
data = pd.read_csv('/homes/abie/gbd_dev/gbd/tests/schiz.csv')
elif data_type == 'binom':
N = 1.e6
data['effective_sample_size'] = N
mu = data['value'].mean()
data['value'] = mc.rbinomial(N, mu, size=len(data.index)) / N
elif data_type == 'poisson':
N = 1.e6
data['effective_sample_size'] = N
mu = data['value'].mean()
data['value'] = mc.rpoisson(N*mu, size=len(data.index)) / N
elif data_type == 'normal':
mu = data['value'].mean()
sigma = .125*mu
data['standard_error'] = sigma
data['value'] = mc.rnormal(mu, sigma**-2, size=len(data.index))
elif data_type == 'log_normal':
mu = data['value'].mean()
sigma = .25
data['standard_error'] = sigma*mu
data['value'] = pl.exp(mc.rnormal(pl.log(mu), sigma**-2, size=len(data.index)))
else:
raise TypeError, 'Unknown data type "%s"' % data_type
# sample prevalence data
i_test = mc.rbernoulli(.25, size=len(data.index))
i_nan = pl.isnan(data['effective_sample_size'])
data['lower_ci'] = pl.nan
data['upper_ci'] = pl.nan
data.ix[i_nan, 'effective_sample_size'] = 0.
data['standard_error'] = pl.sqrt(data['value']*(1-data['value'])) / data['effective_sample_size']
data.ix[pl.isnan(data['standard_error']), 'standard_error'] = pl.inf
data['standard_error'][i_test] = pl.inf
data['effective_sample_size'][i_test] = 0.
data['value'] = pl.maximum(data['value'], 1.e-12)
model.input_data = data
# create model
# TODO: set parameters in model.parameters['p'] dict
# then have simple method to create age specific rate model
#model.parameters['p'] = ...
#model.vars += dismod3.ism.age_specific_rate(model, 'p')
model.parameters['p']['parameter_age_mesh'] = [0,100]
model.parameters['p']['heterogeneity'] = 'Very'
model.vars['p'] = dismod3.data_model.data_model(
'p', model, 'p',
'all', 'total', 'all',
None, None, None,
rate_type=rate_type,
interpolation_method='zero',
include_covariates=False)
# add upper bound on sigma in log normal model to help convergence
#if rate_type == 'log_normal':
# model.vars['p']['sigma'].parents['upper'] = 1.5
# add upper bound on sigma, zeta in offset log normal
#if rate_type == 'offset_log_normal':
# model.vars['p']['sigma'].parents['upper'] = .1
# model.vars['p']['p_zeta'].value = 5.e-9
# model.vars['p']['p_zeta'].parents['upper'] = 1.e-8
# fit model
dismod3.fit.fit_asr(model, 'p', iter=20000, thin=10, burn=10000)
#dismod3.fit.fit_asr(model, 'p', iter=100, thin=1, burn=0)
# compare estimate to hold-out
data['mu_pred'] = model.vars['p']['p_pred'].stats()['mean']
data['lb_pred'] = model.vars['p']['p_pred'].stats()['95% HPD interval'][:,0]
data['ub_pred'] = model.vars['p']['p_pred'].stats()['95% HPD interval'][:,1]
import data_simulation
model.test = data[i_test]
data = model.test
data['true'] = data['value']
data_simulation.add_quality_metrics(data)
data_simulation.initialize_results(model)
data_simulation.add_to_results(model, 'test')
data_simulation.finalize_results(model)
return model
def validate_consistent_model_sim(N=500,
delta_true=.5,
true=dict(i=quadratic,
f=constant,
r=constant)):
types = pl.array(['i', 'r', 'f', 'p'])
## generate simulated data
model = data_simulation.simple_model(N)
model.input_data['effective_sample_size'] = 1.
model.input_data['value'] = 0.
for t in types:
model.parameters[t]['parameter_age_mesh'] = range(0, 101, 20)
sim = consistent_model.consistent_model(model, 'all', 'total', 'all', {})
for t in 'irf':
for i, k_i in enumerate(sim[t]['knots']):
sim[t]['gamma'][i].value = pl.log(true[t](k_i))
age_start = pl.array(mc.runiform(0, 100, size=N), dtype=int)
age_end = pl.array(mc.runiform(age_start, 100, size=N), dtype=int)
data_type = types[mc.rcategorical(pl.ones(len(types), dtype=float) /
float(len(types)),
size=N)]
a = pl.arange(101)
age_weights = pl.ones_like(a)
sum_wt = pl.cumsum(age_weights)
p = pl.zeros(N)
for t in types:
mu_t = sim[t]['mu_age'].value
sum_mu_wt = pl.cumsum(mu_t * age_weights)
p_t = (sum_mu_wt[age_end] - sum_mu_wt[age_start]) / (sum_wt[age_end] -
sum_wt[age_start])
# correct cases where age_start == age_end
i = age_start == age_end
if pl.any(i):
p_t[i] = mu_t[age_start[i]]
# copy part into p
p[data_type == t] = p_t[data_type == t]
n = mc.runiform(100, 10000, size=N)
model.input_data['data_type'] = data_type
model.input_data['age_start'] = age_start
model.input_data['age_end'] = age_end
model.input_data['effective_sample_size'] = n
model.input_data['true'] = p
model.input_data['value'] = mc.rnegative_binomial(n * p,
delta_true * n * p) / n
# coarse knot spacing for fast testing
for t in types:
model.parameters[t]['parameter_age_mesh'] = range(0, 101, 20)
## Then fit the model and compare the estimates to the truth
model.vars = {}
model.vars = consistent_model.consistent_model(model, 'all', 'total',
'all', {})
model.map, model.mcmc = fit_model.fit_consistent_model(model.vars,
iter=10000,
burn=5000,
thin=25,
tune_interval=100)
graphics.plot_convergence_diag(model.vars)
graphics.plot_fit(model, model.vars, {}, {})
for i, t in enumerate('i r f p rr pf'.split()):
pl.subplot(2, 3, i + 1)
pl.plot(a, sim[t]['mu_age'].value, 'w-', label='Truth', linewidth=2)
pl.plot(a, sim[t]['mu_age'].value, 'r-', label='Truth', linewidth=1)
#graphics.plot_one_type(model, model.vars['p'], {}, 'p')
#pl.legend(fancybox=True, shadow=True, loc='upper left')
pl.show()
model.input_data['mu_pred'] = 0.
model.input_data['sigma_pred'] = 0.
for t in types:
model.input_data['mu_pred'][
data_type == t] = model.vars[t]['p_pred'].stats()['mean']
model.input_data['sigma_pred'][data_type == t] = model.vars['p'][
'p_pred'].stats()['standard deviation']
data_simulation.add_quality_metrics(model.input_data)
model.delta = pandas.DataFrame(
dict(true=[delta_true for t in types if t != 'rr']))
model.delta['mu_pred'] = [
pl.exp(model.vars[t]['eta'].trace()).mean() for t in types if t != 'rr'
]
model.delta['sigma_pred'] = [
pl.exp(model.vars[t]['eta'].trace()).std() for t in types if t != 'rr'
]
data_simulation.add_quality_metrics(model.delta)
print 'delta'
print model.delta
print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (
model.input_data['abs_err'].mean(),
pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
model.input_data['covered?'].mean())
model.mu = pandas.DataFrame()
for t in types:
model.mu = model.mu.append(pandas.DataFrame(
dict(true=sim[t]['mu_age'].value,
mu_pred=model.vars[t]['mu_age'].stats()['mean'],
sigma_pred=model.vars[t]['mu_age'].stats()
['standard deviation'])),
ignore_index=True)
data_simulation.add_quality_metrics(model.mu)
print '\nparam prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (
model.mu['abs_err'].mean(),
pl.median(pl.absolute(
model.mu['rel_err'].dropna())), model.mu['covered?'].mean())
print
data_simulation.initialize_results(model)
data_simulation.add_to_results(model, 'delta')
data_simulation.add_to_results(model, 'mu')
data_simulation.add_to_results(model, 'input_data')
data_simulation.finalize_results(model)
print model.results
return model