def test_operations():
N = 10
R = rng(12)
def mkrow():
return (np.random.choice([False,
True]), np.random.choice([False, True]),
np.random.random(), np.random.choice([False, True]))
dtype = [('', bool), ('', bool), ('', float), ('', bool)]
# non-masked data
data = [mkrow() for _ in xrange(N)]
data = np.array(data, dtype=dtype)
defn = model_definition(N, [bb, bb, nich, bb])
init_args = {
'defn':
defn,
'cluster_hp': {
'alpha': 2.0
},
'feature_hps': [
dist_bb.EXAMPLES[0]['shared'],
dist_bb.EXAMPLES[0]['shared'],
dist_nich.EXAMPLES[0]['shared'],
dist_bb.EXAMPLES[0]['shared'],
],
'r':
R,
}
cxx_s = cxx_initialize(data=cxx_numpy_dataview(data), **init_args)
# *_initialize() randomly assigns all entities to a group, so we'll have to
# unset this assignment for this test
unset(cxx_s, data, R)
ensure_k_groups(cxx_s, 3, R)
assert cxx_s.nentities() == N
cxx_s.dcheck_consistency()
assert cxx_s.ngroups() == 3 and set(cxx_s.empty_groups()) == set([0, 1, 2])
for i, yi in enumerate(data):
egid = i % 2
cxx_s.add_value(egid, i, yi, R)
cxx_s.dcheck_consistency()
for i, yi in it.islice(enumerate(data), 2):
cxx_s.remove_value(i, yi, R)
cxx_s.dcheck_consistency()
newrow = mkrow()
newdata = np.array([newrow], dtype=dtype)
cxx_score = cxx_s.score_value(newdata[0], R)
assert cxx_score is not None
cxx_s.dcheck_consistency()
def test_sample_post_pred():
N = 10
R = rng(5483932)
D = 4
def randombool():
return np.random.choice([False, True])
def mkrow():
return tuple(randombool() for _ in xrange(D))
dtype = [('', bool)] * D
data = [mkrow() for _ in xrange(N)]
data = np.array(data, dtype=dtype)
defn = model_definition(N, [bb] * D)
init_args = {
'defn': defn,
'cluster_hp': {
'alpha': 2.0
},
'feature_hps': [dist_bb.EXAMPLES[0]['shared']] * D,
'r': R,
}
cxx_s = cxx_initialize(data=cxx_numpy_dataview(data), **init_args)
G = 3
unset(cxx_s, data, R)
ensure_k_groups(cxx_s, 3, R)
for i, yi in enumerate(data):
egid = i % G
cxx_s.add_value(egid, i, yi, R)
# sample
y_new_data = mkrow()
y_new_mask = tuple(randombool() for _ in xrange(D))
y_new = ma.masked_array(np.array([y_new_data], dtype=dtype),
mask=[y_new_mask])[0]
n_samples = 1000
cxx_samples = np.hstack(
[cxx_s.sample_post_pred(y_new, R)[1] for _ in xrange(n_samples)])
idmap = {C: i for i, C in enumerate(it.product([False, True], repeat=D))}
def todist(samples):
dist = np.zeros(len(idmap))
for s in samples:
dist[idmap[tuple(s)]] += 1.0
dist /= dist.sum()
return dist
cxx_dist = todist(cxx_samples)
assert cxx_dist is not None
def test_operations():
N = 10
R = rng(12)
def mkrow():
return (np.random.choice([False, True]),
np.random.choice([False, True]),
np.random.random(),
np.random.choice([False, True]))
dtype = [('', bool), ('', bool), ('', float), ('', bool)]
# non-masked data
data = [mkrow() for _ in xrange(N)]
data = np.array(data, dtype=dtype)
defn = model_definition(N, [bb, bb, nich, bb])
init_args = {
'defn': defn,
'cluster_hp': {'alpha': 2.0},
'feature_hps': [
dist_bb.EXAMPLES[0]['shared'],
dist_bb.EXAMPLES[0]['shared'],
dist_nich.EXAMPLES[0]['shared'],
dist_bb.EXAMPLES[0]['shared'],
],
'r': R,
}
cxx_s = cxx_initialize(data=cxx_numpy_dataview(data), **init_args)
# *_initialize() randomly assigns all entities to a group, so we'll have to
# unset this assignment for this test
unset(cxx_s, data, R)
ensure_k_groups(cxx_s, 3, R)
assert cxx_s.nentities() == N
cxx_s.dcheck_consistency()
assert cxx_s.ngroups() == 3 and set(cxx_s.empty_groups()) == set([0, 1, 2])
for i, yi in enumerate(data):
egid = i % 2
cxx_s.add_value(egid, i, yi, R)
cxx_s.dcheck_consistency()
for i, yi in it.islice(enumerate(data), 2):
cxx_s.remove_value(i, yi, R)
cxx_s.dcheck_consistency()
newrow = mkrow()
newdata = np.array([newrow], dtype=dtype)
cxx_score = cxx_s.score_value(newdata[0], R)
assert cxx_score is not None
cxx_s.dcheck_consistency()
def test_sample_post_pred():
N = 10
R = rng(5483932)
D = 4
def randombool():
return np.random.choice([False, True])
def mkrow():
return tuple(randombool() for _ in xrange(D))
dtype = [('', bool)] * D
data = [mkrow() for _ in xrange(N)]
data = np.array(data, dtype=dtype)
defn = model_definition(N, [bb] * D)
init_args = {
'defn': defn,
'cluster_hp': {'alpha': 2.0},
'feature_hps': [dist_bb.EXAMPLES[0]['shared']] * D,
'r': R,
}
cxx_s = cxx_initialize(data=cxx_numpy_dataview(data), **init_args)
G = 3
unset(cxx_s, data, R)
ensure_k_groups(cxx_s, 3, R)
for i, yi in enumerate(data):
egid = i % G
cxx_s.add_value(egid, i, yi, R)
# sample
y_new_data = mkrow()
y_new_mask = tuple(randombool() for _ in xrange(D))
y_new = ma.masked_array(
np.array([y_new_data], dtype=dtype),
mask=[y_new_mask])[0]
n_samples = 1000
cxx_samples = np.hstack(
[cxx_s.sample_post_pred(y_new, R)[1] for _ in xrange(n_samples)])
idmap = {C: i for i, C in enumerate(it.product([False, True], repeat=D))}
def todist(samples):
dist = np.zeros(len(idmap))
for s in samples:
dist[idmap[tuple(s)]] += 1.0
dist /= dist.sum()
return dist
cxx_dist = todist(cxx_samples)
assert cxx_dist is not None
def score_dataset(counts):
M, K = counts.shape
Y = np.array([(y, ) for y in counts], dtype=[('', np.int, (K, ))])
view = cxx_numpy_dataview(Y)
r = rng()
defn = model_definition(M, [dm(K)])
prior = {'alphas': [1.] * K}
s = cxx_initialize(defn,
view,
r,
feature_hps=[prior],
assignment=[0] * M)
assert_equals(s.groups(), [0])
return s.score_data(None, None, r)
def test_masked_operations():
N = 10
R = rng(2347785)
dtype = [('', bool), ('', int), ('', float)]
def randombool():
return np.random.choice([False, True])
def mkrow():
return (randombool(), np.random.randint(1, 10), np.random.random())
def mkmask():
return (randombool(), randombool(), randombool())
data = [mkrow() for _ in xrange(N)]
data = np.array(data, dtype=dtype)
mask = [mkmask() for _ in xrange(N)]
data = ma.masked_array(data, mask=mask)
defn = model_definition(N, [bb, bnb, nich])
init_args = {
'defn':
defn,
'cluster_hp': {
'alpha': 10.0
},
'feature_hps': [
dist_bb.EXAMPLES[0]['shared'],
dist_bnb.EXAMPLES[0]['shared'],
dist_nich.EXAMPLES[0]['shared'],
],
'r':
R,
}
cxx_s = cxx_initialize(data=cxx_numpy_dataview(data), **init_args)
# see comment above
unset(cxx_s, data, R)
ensure_k_groups(cxx_s, 3, R)
for i, yi in enumerate(data):
egid = i % 2
cxx_s.add_value(egid, i, yi, R)
cxx_s.dcheck_consistency()
for i, yi in enumerate(data):
cxx_s.remove_value(i, yi, R)
cxx_s.dcheck_consistency()
def score_dataset(counts):
M, K = counts.shape
Y = np.array([(y,) for y in counts], dtype=[('', np.int, (K,))])
view = cxx_numpy_dataview(Y)
r = rng()
defn = model_definition(M, [dm(K)])
prior = {'alphas': [1.] * K}
s = cxx_initialize(
defn,
view,
r,
feature_hps=[prior],
assignment=[0] * M)
assert_equals(s.groups(), [0])
return s.score_data(None, None, r)
def test_masked_operations():
N = 10
R = rng(2347785)
dtype = [('', bool), ('', int), ('', float)]
def randombool():
return np.random.choice([False, True])
def mkrow():
return (randombool(), np.random.randint(1, 10), np.random.random())
def mkmask():
return (randombool(), randombool(), randombool())
data = [mkrow() for _ in xrange(N)]
data = np.array(data, dtype=dtype)
mask = [mkmask() for _ in xrange(N)]
data = ma.masked_array(data, mask=mask)
defn = model_definition(N, [bb, bnb, nich])
init_args = {
'defn': defn,
'cluster_hp': {'alpha': 10.0},
'feature_hps': [
dist_bb.EXAMPLES[0]['shared'],
dist_bnb.EXAMPLES[0]['shared'],
dist_nich.EXAMPLES[0]['shared'],
],
'r': R,
}
cxx_s = cxx_initialize(data=cxx_numpy_dataview(data), **init_args)
# see comment above
unset(cxx_s, data, R)
ensure_k_groups(cxx_s, 3, R)
for i, yi in enumerate(data):
egid = i % 2
cxx_s.add_value(egid, i, yi, R)
cxx_s.dcheck_consistency()
for i, yi in enumerate(data):
cxx_s.remove_value(i, yi, R)
cxx_s.dcheck_consistency()
def test_dm_cxx():
K = 4
Y = np.array([
([0, 1, 2, 5], ),
([1, 0, 1, 2], ),
([0, 2, 9, 9], ),
],
dtype=[('', np.int, (K, ))])
Y_np = np.vstack(y[0] for y in Y)
cxx_view = cxx_numpy_dataview(Y)
r = rng()
defn = model_definition(Y.shape[0], [dm(K)])
prior = {'alphas': [1.] * K}
cxx_s = cxx_initialize(defn,
cxx_view,
r,
feature_hps=[prior],
assignment=[0] * Y.shape[0])
counts = cxx_s.get_suffstats(0, 0)['counts']
assert_sequence_equal(counts, list(Y_np.sum(axis=0)))
def test_dm_cxx():
K = 4
Y = np.array([
([0, 1, 2, 5],),
([1, 0, 1, 2],),
([0, 2, 9, 9],),
], dtype=[('', np.int, (K,))])
Y_np = np.vstack(y[0] for y in Y)
cxx_view = cxx_numpy_dataview(Y)
r = rng()
defn = model_definition(Y.shape[0], [dm(K)])
prior = {'alphas': [1.] * K}
cxx_s = cxx_initialize(
defn,
cxx_view,
r,
feature_hps=[prior],
assignment=[0] * Y.shape[0])
counts = cxx_s.get_suffstats(0, 0)['counts']
assert_sequence_equal(counts, list(Y_np.sum(axis=0)))
def test_betabin_equiv():
# https://github.com/pymc-devs/pymc/blob/
# a7ab153f2b58d81824a56166747c678d7f421bde/pymc/distributions/discrete.py#L84
def betabin_like(value, alpha, beta, n):
return (gammaln(alpha + beta) - gammaln(alpha) - gammaln(beta) +
gammaln(n + 1) - gammaln(value + 1) - gammaln(n - value + 1) +
gammaln(alpha + value) + gammaln(n + beta - value) -
gammaln(beta + alpha + n))
# this N refers to the number of trials in the binomial distribution
N = 10
# this refers to the dataset size
M = 100
# hyperparams of the beta dist
alpha, beta = 1., 2.
heads = np.random.randint(low=0, high=N + 1, size=M)
tails = N - heads
data = np.vstack((heads, tails)).T
Y = np.array([(y, ) for y in data], dtype=[('', np.int, (2, ))])
view = cxx_numpy_dataview(Y)
r = rng()
defn = model_definition(Y.shape[0], [dm(2)])
prior = {'alphas': [alpha, beta]}
s = cxx_initialize(defn,
view,
r,
feature_hps=[prior],
assignment=[0] * Y.shape[0])
assert_equals(s.groups(), [0])
def all_indices(N):
for i, j in it.product(range(0, N + 1), repeat=2):
if (i + j) == N:
yield i, j
all_data = [(list(ij), ) for ij in all_indices(N)]
Y_test = np.array(all_data, dtype=[('', np.int, (2, ))])
# the actual score is simply a betabin using the updated alpha, beta
alpha1, beta1 = np.array([alpha, beta]) + data.sum(axis=0)
def model_score(Y_value):
_, (score, ) = s.score_value(Y_value, r)
return score
def test_score(Y_value):
score = betabin_like(Y_value[0][0], alpha1, beta1, N)
return score
model_scores = np.array(map(model_score, Y_test))
test_scores = np.array(map(test_score, Y_test))
assert_almost_equals(np.exp(model_scores).sum(), 1., places=2)
assert_almost_equals(np.exp(test_scores).sum(), 1., places=2)
assert_almost_equals(np.abs(model_scores - test_scores).max(),
0.,
places=1)
def test_betabin_equiv():
# https://github.com/pymc-devs/pymc/blob/
# a7ab153f2b58d81824a56166747c678d7f421bde/pymc/distributions/discrete.py#L84
def betabin_like(value, alpha, beta, n):
return (gammaln(alpha + beta) - gammaln(alpha) - gammaln(beta) +
gammaln(n + 1) - gammaln(value + 1) - gammaln(n - value + 1) +
gammaln(alpha + value) + gammaln(n + beta - value) -
gammaln(beta + alpha + n))
# this N refers to the number of trials in the binomial distribution
N = 10
# this refers to the dataset size
M = 100
# hyperparams of the beta dist
alpha, beta = 1., 2.
heads = np.random.randint(low=0, high=N + 1, size=M)
tails = N - heads
data = np.vstack((heads, tails)).T
Y = np.array([(y,) for y in data], dtype=[('', np.int, (2,))])
view = cxx_numpy_dataview(Y)
r = rng()
defn = model_definition(Y.shape[0], [dm(2)])
prior = {'alphas': [alpha, beta]}
s = cxx_initialize(
defn,
view,
r,
feature_hps=[prior],
assignment=[0] * Y.shape[0])
assert_equals(s.groups(), [0])
def all_indices(N):
for i, j in it.product(range(0, N + 1), repeat=2):
if (i + j) == N:
yield i, j
all_data = [(list(ij),) for ij in all_indices(N)]
Y_test = np.array(all_data, dtype=[('', np.int, (2,))])
# the actual score is simply a betabin using the updated alpha, beta
alpha1, beta1 = np.array([alpha, beta]) + data.sum(axis=0)
def model_score(Y_value):
_, (score,) = s.score_value(Y_value, r)
return score
def test_score(Y_value):
score = betabin_like(Y_value[0][0], alpha1, beta1, N)
return score
model_scores = np.array(map(model_score, Y_test))
test_scores = np.array(map(test_score, Y_test))
assert_almost_equals(np.exp(model_scores).sum(), 1., places=2)
assert_almost_equals(np.exp(test_scores).sum(), 1., places=2)
assert_almost_equals(
np.abs(model_scores - test_scores).max(), 0., places=1)