def _eval_bmlingam(n_trials, gen_data_params, hparamss, show_progress,
sampling_mode):
"""Evaluate BMLiNGAM model selection.
"""
# ---- Loop over trials ----
n_corrects = 0
for t in range(n_trials):
# ---- Generate samples ----
gen_data_params.seed = t
data = gen_samples(gen_data_params)
xs = data['xs']
causality_true = data['causality_true']
# ---- Estimate causality ----
results = find_best_model(xs, hparamss, sampling_mode)
hparams_best = results[0]
posterior = results[1]
causality_est = hparams_best['causality']
# ---- Check result ----
if causality_est == causality_true:
n_corrects += 1
if show_progress:
print('causality (true/pred), p(M_MAP|D): (%s/%s), %e' %
(str(causality_true), str(causality_est), posterior))
return n_corrects
def infer_causality(xs, infer_params, varnames=None, verbose=1):
"""Infer causality based on samples given pair of columns in data.
"""
assert (type(infer_params) == InferParams)
if varnames is None:
varnames = ['var1', 'var2']
hparamss = define_hparam_searchspace(infer_params)
sampling_mode = infer_params.sampling_mode
hparams_best, post_prob, ll, hparams_rev, post_prob_rev, ll_rev = \
find_best_model(xs, hparamss, sampling_mode)
causality = hparams_best['causality']
x1_name = varnames[0]
x2_name = varnames[1]
if causality == [1, 2]:
src, dst = x1_name, x2_name
else:
src, dst = x2_name, x1_name
result = {
'Infered causality': '{} -> {}'.format(src, dst),
'2 * log(p(M)) - log(p(M_rev))': '{}'.format(2 * (ll - ll_rev))
}
if 1 <= verbose:
print(json.dumps(result, indent=2, sort_keys=True))
if 2 <= verbose:
print('---- Inference for variables "%s" and "%s" ----' %
(x1_name, x2_name))
print(
'Inferred : %s -> %s (posterior prob: %1.3f, loglikelihood: %1.3f)'
% (src, dst, post_prob, ll))
print(
'(best_rev): %s -> %s (posterior prob: %1.3f, loglikelihood: %1.3f)'
% (dst, src, post_prob_rev, ll_rev))
print('')
print('Hyper parameters of the optimal model:')
show_hparams(hparams_best)
print('')
print('Hyper parameters of the reverse optimal model:')
show_hparams(hparams_rev)
print('')
return {
'x1_name': x1_name,
'x2_name': x2_name,
'xs': xs,
'causality': causality,
'causality_str': ('%s -> %s' % (src, dst)),
'post_prob': post_prob,
'hparams': hparams_best,
'post_prob_rev': post_prob_rev,
'hparams_rev': hparams_rev
}
def _estimate_hparams(xs, infer_params):
assert (type(infer_params) == InferParams)
sampling_mode = infer_params.sampling_mode
hparamss = define_hparam_searchspace(infer_params)
results = find_best_model(xs, hparamss, sampling_mode)
hparams_best = results[0]
bf = results[2] - results[5] # Bayes factor
return hparams_best, bf
def test_find_best_model(verbose=False):
gen_data_params = GenDataParams(n_samples=200,
mu1_dist=5.0,
mu2_dist=10.0,
f1_coef=[1.0, 1.0, 1.5],
f2_coef=[1.0, 2.0, 0.5],
conf_dist=[['laplace'], ['exp'],
['uniform']],
e1_dist=['laplace'],
e2_dist=['laplace'],
e1_std=3.0,
e2_std=3.0,
fix_causality=False,
seed=0)
# gen_data_params = deepcopy(gen_data_params_default)
gen_data_params.n_samples = 200
gen_data_params.n_confounders = 3
gen_data_params.dists_e1 = ['laplace']
gen_data_params.dists_e2 = ['laplace']
gen_data_params.dist_be1 = 'be1=9.0'
gen_data_params.dist_be2 = 'be2=9.0'
gen_data_params.dist_bf1s = '1., 1., 1.5'
gen_data_params.dist_bf2s = '1., 2., 0.5'
gen_data_params.dists_conf = [['laplace'], ['exp'], ['uniform']]
gen_data_params.dist_mu1 = 'mu1=5.0'
gen_data_params.dist_mu2 = 'mu2=10.0'
data = gen_artificial_data(gen_data_params)
xs = data['xs']
infer_params = infer_params1()
sampling_mode = infer_params.sampling_mode
hparamss = define_hparam_searchspace(infer_params)
result1 = find_best_model(xs, hparamss, sampling_mode)
print(result1)
infer_params = infer_params2()
sampling_mode = infer_params.sampling_mode
hparamss = define_hparam_searchspace(infer_params)
result2 = find_best_model(xs, hparamss, sampling_mode)
print(result2)
def estimate_hparams(xs, infer_params):
"""Estimate hyperparameters with the largest marginal likelihood value.
"""
assert (type(infer_params) == InferParams)
sampling_mode = infer_params.sampling_mode
hparamss = define_hparam_searchspace(infer_params)
results = find_best_model(xs, hparamss, sampling_mode)
hparams_best = results[0]
bf = results[2] - results[5] # Bayes factor
return hparams_best, bf
def _eval_bmlingam(comp_logP_func,
n_confounders,
n_trials,
n_samples,
hparamss,
rng,
show_result,
tied_sampling=False,
normalize_samples=False):
"""Evaluate BMLiNGAM model selection.
This function is invoked from _test_bmlingam_main().
"""
# ---- Loop over trials ----
n_corrects = 0
for t in xrange(n_trials):
# ---- Generate samples ----
data = gen_samples(n_confounders,
n_samples,
rng,
normalize_samples=normalize_samples)
xs = data['xs']
causality_true = data['causality_true']
# ---- Estimate causality ----
if tied_sampling:
causality_est, _ = bayesmixedlingam_np(xs, hparamss, rng)
posterior = np.nan
else:
hparams_best, posterior = find_best_model(xs, hparamss, rng)
causality_est = hparams_best['causality']
# ---- Check result ----
if causality_est == causality_true:
n_corrects += 1
if show_result:
print('causality (true/pred), p(M_MAP|D): (%s/%s), %e' %
(str(causality_true), str(causality_est), posterior))
return n_corrects