def _check_marginal_samples_match_scores(server, row, fi):
row = loom.query.protobuf_to_data_row(row.diff)
row[fi] = None
to_sample = [i == fi for i in range(len(row))]
samples = server.sample(to_sample, row, SAMPLE_COUNT)
val = samples[0][fi]
base_score = server.score(row)
if isinstance(val, bool) or isinstance(val, int):
probs_dict = {}
samples = [sample[fi] for sample in samples]
for sample in set(samples):
row[fi] = sample
probs_dict[sample] = numpy.exp(
server.score(row) - base_score)
if len(probs_dict) == 1:
assert_almost_equal(probs_dict[sample], 1., places=SCORE_PLACES)
return
if min(probs_dict.values()) < MIN_CATEGORICAL_PROB:
return
gof = discrete_goodness_of_fit(samples, probs_dict, plot=True)
elif isinstance(val, float):
probs = numpy.exp([
server.score(sample) - base_score
for sample in samples
])
samples = [sample[fi] for sample in samples]
gof = density_goodness_of_fit(samples, probs, plot=True)
assert_greater(gof, MIN_GOODNESS_OF_FIT)
def _check_marginal_samples_match_scores(server, row, fi):
row = loom.query.protobuf_to_data_row(row.diff)
row[fi] = None
to_sample = [i == fi for i in range(len(row))]
samples = server.sample(to_sample, row, SAMPLE_COUNT)
val = samples[0][fi]
base_score = server.score(row)
if isinstance(val, bool) or isinstance(val, (int, long)):
probs_dict = {}
samples = [sample[fi] for sample in samples]
for sample in set(samples):
row[fi] = sample
probs_dict[sample] = numpy.exp(server.score(row) - base_score)
if len(probs_dict) == 1:
assert_almost_equal(probs_dict[sample], 1., places=SCORE_PLACES)
return
if min(probs_dict.values()) < MIN_CATEGORICAL_PROB:
return
gof = discrete_goodness_of_fit(samples, probs_dict, plot=True)
elif isinstance(val, float):
probs = numpy.exp(
[server.score(sample) - base_score for sample in samples])
samples = [sample[fi] for sample in samples]
gof = density_goodness_of_fit(samples, probs, plot=True)
assert_greater(gof, MIN_GOODNESS_OF_FIT)
def test_sample_value(module, EXAMPLE):
seed_all(0)
shared = module.Shared.from_dict(EXAMPLE['shared'])
shared.realize()
for values in [[], EXAMPLE['values']]:
group = module.Group.from_values(shared, values)
sample_count = SAMPLE_COUNT
if module.Value == numpy.ndarray:
sample_count *= 10
samples = [group.sample_value(shared) for _ in xrange(sample_count)]
if module.Value in [bool, int]:
probs_dict = {
value: math.exp(group.score_value(shared, value))
for value in set(samples)
}
gof = discrete_goodness_of_fit(samples, probs_dict, plot=True)
elif module.Value == float:
probs = numpy.exp(
[group.score_value(shared, value) for value in samples])
gof = density_goodness_of_fit(samples, probs, plot=True)
elif module.Value == numpy.ndarray:
if module.__name__ == 'distributions.lp.models.niw':
raise SkipTest('FIXME known sampling bug')
probs = numpy.exp(
[group.score_value(shared, value) for value in samples])
gof = vector_density_goodness_of_fit(samples, probs, plot=True)
else:
raise SkipTest('Not implemented for {}'.format(module.Value))
print '{} gof = {:0.3g}'.format(module.__name__, gof)
assert_greater(gof, MIN_GOODNESS_OF_FIT)
def test_sample_value(module, EXAMPLE):
seed_all(0)
shared = module.Shared.from_dict(EXAMPLE['shared'])
shared.realize()
for values in [[], EXAMPLE['values']]:
group = module.Group.from_values(shared, values)
sample_count = SAMPLE_COUNT
if module.Value == numpy.ndarray:
sample_count *= 10
samples = [group.sample_value(shared) for _ in xrange(sample_count)]
if module.Value in [bool, int]:
probs_dict = {
value: math.exp(group.score_value(shared, value))
for value in set(samples)
}
gof = discrete_goodness_of_fit(samples, probs_dict, plot=True)
elif module.Value == float:
probs = numpy.exp([
group.score_value(shared, value)
for value in samples
])
gof = density_goodness_of_fit(samples, probs, plot=True)
elif module.Value == numpy.ndarray:
if module.__name__ == 'distributions.lp.models.niw':
raise SkipTest('FIXME known sampling bug')
probs = numpy.exp([
group.score_value(shared, value)
for value in samples
])
gof = vector_density_goodness_of_fit(samples, probs, plot=True)
else:
raise SkipTest('Not implemented for {}'.format(module.Value))
print '{} gof = {:0.3g}'.format(module.__name__, gof)
assert_greater(gof, MIN_GOODNESS_OF_FIT)
