def check_dpm(impl, data_count, beta0):
check_cm(impl)
data = histogram(np.random.randint(50, size=data_count))
data = dict([(str(i), obs) for i, obs in enumerate(data)])
betas = dict([(str(i), (1 - beta0) / len(data))
for i, obs in enumerate(data)])
hp = {
'gamma': 1.,
'alpha': 1.,
'beta0': beta0,
'betas': betas
}
ss = {'counts': data}
cm = ComponentModel(
impl,
ss=ss,
hp=hp)
samples = cm.sample_data(SAMPS)
counts = list(histogram([y for y in samples if y != -1]))
probs = list(np.exp([cm.pred_prob(x) for x in range(max(samples) + 1)]))
counts.append(len([y for y in samples if y == -1]))
probs.append(np.exp(cm.pred_prob(-1)))
assert_less(1 - sum(probs), THRESH)
probs, counts = zip(*sorted(zip(probs, counts), reverse=True)[:TOPN])
p = mgof(probs, counts, SAMPS, truncated=True)
assert_greater(p, THRESH)
def _check_discrete(cm):
samples = cm.sample_data(SAMPS)
counts = histogram(samples)
probs = np.exp([cm.pred_prob(x) for x in range(max(samples) + 1)])
assert_less(1 - sum(probs), THRESH)
probs, counts = zip(*sorted(zip(probs, counts), reverse=True)[:TOPN])
p = mgof(probs, counts, SAMPS, truncated=True)
assert_greater(p, THRESH)
def _check_discrete(cm):
samples = cm.sample_data(SAMPS)
counts = histogram(samples)
probs = np.exp([cm.pred_prob(x) for x in range(max(samples) + 1)])
assert_less(1 - sum(probs), THRESH)
probs, counts = zip(*sorted(zip(probs, counts), reverse=True)[:TOPN])
p = mgof(probs, counts, SAMPS, truncated=True)
assert_greater(p, THRESH)
def check_dd(impl, data_count, D):
check_cm(impl)
data = histogram(np.random.randint(D, size=data_count), bin_count=D)
cm = ComponentModel(
impl,
ss={'counts': data},
p={'D': D})
cm.realize_hp()
_check_discrete(cm)
def check_dpm(impl, data_count, beta0):
check_cm(impl)
data = histogram(np.random.randint(50, size=data_count))
data = dict([(str(i), obs) for i, obs in enumerate(data)])
betas = dict([(str(i), (1 - beta0) / len(data))
for i, obs in enumerate(data)])
hp = {'gamma': 1., 'alpha': 1., 'beta0': beta0, 'betas': betas}
ss = {'counts': data}
cm = ComponentModel(impl, ss=ss, hp=hp)
samples = cm.sample_data(SAMPS)
counts = list(histogram([y for y in samples if y != -1]))
probs = list(np.exp([cm.pred_prob(x) for x in range(max(samples) + 1)]))
counts.append(len([y for y in samples if y == -1]))
probs.append(np.exp(cm.pred_prob(-1)))
assert_less(1 - sum(probs), THRESH)
probs, counts = zip(*sorted(zip(probs, counts), reverse=True)[:TOPN])
p = mgof(probs, counts, SAMPS, truncated=True)
assert_greater(p, THRESH)
def check_dd(impl, data_count, D):
check_cm(impl)
data = histogram(np.random.randint(D, size=data_count), bin_count=D)
cm = ComponentModel(impl, ss={'counts': data}, p={'D': D})
cm.realize_hp()
_check_discrete(cm)