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_probs(a, b):
check_cm(a)
check_cm(b)
a = ComponentModel(a)
a.realize_hp()
b = ComponentModel(b, hp=a.dump_hp())
dps = [a.sample_data() for _ in range(DPS)]
for y in dps:
assert_almost_equal(a.data_prob(), b.data_prob())
assert_almost_equal(a.pred_prob(y), b.pred_prob(y))
a.add_data(y)
b.add_data(y)
def test_crp_equals_pyp():
alphas = [1., 5., 10.]
for alpha in alphas:
n = 1000
crp = ComponentModel('CRP', hp={'alpha': alpha})
pyp = ComponentModel('PYP', hp={'alpha': alpha, 'd': 0.})
y = [0] * n
for i in range(n):
y[i] = crp.sample_data()
assert_almost_equal(crp.pred_prob(y[i]), pyp.pred_prob(y[i]))
crp.add_data(y[i])
pyp.add_data(y[i])
assert_almost_equal(crp.data_prob(), pyp.data_prob())
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_sums(name):
check_cm(name)
cm = ComponentModel(name)
cm.realize_hp()
values = [cm.sample_data() for _ in range(COUNT)]
score = 0.
for value in values:
score += cm.pred_prob(value)
cm.add_data(value)
assert_almost_equal(score, cm.data_prob())
def check_sums(name):
check_cm(name)
cm = ComponentModel(name)
cm.realize_hp()
values = [cm.sample_data() for _ in range(COUNT)]
score = 0.
for value in values:
score += cm.pred_prob(value)
cm.add_data(value)
assert_almost_equal(score, cm.data_prob())
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_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 add_remove_add(name, raw_hps, raw_ss0=None):
'''
This tests add_data, remove_data, pred_prob, data_prob
'''
DATA_COUNT = 20
for raw_hp in raw_hps:
cm = ComponentModel(name, hp=raw_hp, ss=raw_ss0)
cm.realize_hp()
data = []
score = 0
for _ in range(DATA_COUNT):
dp = cm.sample_data()
data.append(dp)
score += cm.pred_prob(dp)
cm.add_data(dp)
cm_all = ComponentModel(name, ss=cm.dump_ss())
assert_close(
score,
cm.data_prob(),
err_msg='p(x1,...,xn) != p(x1) p(x2|x1) p(xn|...)')
random.shuffle(data)
for dp in data:
cm.remove_data(dp)
cm0 = ComponentModel(name, ss=raw_ss0)
assert_close(cm.ss, cm0.ss, err_msg='ss + data - data != ss')
random.shuffle(data)
for dp in data:
cm.add_data(dp)
assert_close(cm.ss, cm_all.ss, err_msg='ss - data + data != ss')
def add_remove_add(name, raw_hps, raw_ss0=None):
'''
This tests add_data, remove_data, pred_prob, data_prob
'''
DATA_COUNT = 20
for raw_hp in raw_hps:
cm = ComponentModel(name, hp=raw_hp, ss=raw_ss0)
cm.realize_hp()
data = []
score = 0
for _ in range(DATA_COUNT):
dp = cm.sample_data()
data.append(dp)
score += cm.pred_prob(dp)
cm.add_data(dp)
cm_all = ComponentModel(name, ss=cm.dump_ss())
assert_close(score,
cm.data_prob(),
err_msg='p(x1,...,xn) != p(x1) p(x2|x1) p(xn|...)')
random.shuffle(data)
for dp in data:
cm.remove_data(dp)
cm0 = ComponentModel(name, ss=raw_ss0)
assert_close(cm.ss, cm0.ss, err_msg='ss + data - data != ss')
random.shuffle(data)
for dp in data:
cm.add_data(dp)
assert_close(cm.ss, cm_all.ss, err_msg='ss - data + data != ss')
