def test_multinmoial_goodness_of_fit():
thresh = 1e-3
n = int(1e5)
ds = [3, 10, 20]
for d in ds:
for _ in range(5):
probs = np.random.dirichlet([1] * d)
counts = np.random.multinomial(n, probs)
p_good = mgof(probs, counts, n)
assert_greater(p_good, thresh)
unif_counts = np.random.multinomial(n, [1. / d] * d)
p_bad = mgof(probs, unif_counts, n)
assert_less(p_bad, thresh)
def test_multinmoial_goodness_of_fit():
thresh = 1e-3
n = int(1e5)
ds = [3, 10, 20]
for d in ds:
for _ in range(5):
probs = np.random.dirichlet([1] * d)
counts = np.random.multinomial(n, probs)
p_good = mgof(probs, counts, n)
assert_greater(p_good, thresh)
unif_counts = np.random.multinomial(n, [1. / d] * d)
p_bad = mgof(probs, unif_counts, n)
assert_less(p_bad, thresh)
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_nich(impl, data_count, mean, std):
check_cm(impl)
ss = None
if data_count:
data = np.random.normal(mean, std, size=data_count)
ss = {'count': data_count, 'mean': data.mean(), 'variance': data.var()}
cm = ComponentModel(impl, ss=ss)
samples = cm.sample_data(SAMPS)
counts, bin_ranges = bin_samples(samples)
#use of quadrature is unfortunate but for now
#it's the easiest way to score bins and seems to work
pdf = lambda x: np.exp(cm.pred_prob(x))
probs = [quad(pdf, m, M, epsabs=0., epsrel=1e-6)[0] for m, M in bin_ranges]
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_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_nich(impl, data_count, mean, std):
check_cm(impl)
ss = None
if data_count:
data = np.random.normal(mean, std, size=data_count)
ss = {
'count': data_count,
'mean': data.mean(),
'variance': data.var()
}
cm = ComponentModel(impl, ss=ss)
samples = cm.sample_data(SAMPS)
counts, bin_ranges = bin_samples(samples)
#use of quadrature is unfortunate but for now
#it's the easiest way to score bins and seems to work
pdf = lambda x: np.exp(cm.pred_prob(x))
probs = [quad(pdf, m, M, epsabs=0., epsrel=1e-6)[0] for m, M in bin_ranges]
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)
