def test_dense_vs_sparse():
# XXX: really belongs in irm test cases, but kernels has a nice cluster
# enumeration iterator
r = rng()
n = 5
raw = ma.array(np.random.choice(np.arange(20), size=(n, n)),
mask=np.random.choice([False, True], size=(n, n)))
dense = [relation_numpy_dataview(raw)]
sparse = [sparse_relation_dataview(_tocsr(raw))]
domains = [n]
relations = [((0, 0), gp)]
defn = irm_definition(domains, relations)
def score_fn(data):
def f(assignments):
s = irm_initialize(defn, data, r=r, domain_assignments=assignments)
assign = sum(
s.score_assignment(i) for i in xrange(len(assignments)))
likelihood = s.score_likelihood(r)
return assign + likelihood
return f
product_assignments = tuple(map(list, map(permutation_iter, domains)))
dense_posterior = scores_to_probs(
np.array(map(score_fn(dense), it.product(*product_assignments))))
sparse_posterior = scores_to_probs(
np.array(map(score_fn(sparse), it.product(*product_assignments))))
assert_1d_lists_almost_equals(dense_posterior, sparse_posterior, places=3)
def test_dense_vs_sparse():
# XXX: really belongs in irm test cases, but kernels has a nice cluster
# enumeration iterator
r = rng()
n = 5
raw = ma.array(
np.random.choice(np.arange(20), size=(n, n)),
mask=np.random.choice([False, True], size=(n, n)))
dense = [relation_numpy_dataview(raw)]
sparse = [sparse_relation_dataview(_tocsr(raw))]
domains = [n]
relations = [((0, 0), gp)]
defn = irm_definition(domains, relations)
def score_fn(data):
def f(assignments):
s = irm_initialize(defn, data, r=r, domain_assignments=assignments)
assign = sum(s.score_assignment(i)
for i in xrange(len(assignments)))
likelihood = s.score_likelihood(r)
return assign + likelihood
return f
product_assignments = tuple(map(list, map(permutation_iter, domains)))
dense_posterior = scores_to_probs(
np.array(map(score_fn(dense), it.product(*product_assignments))))
sparse_posterior = scores_to_probs(
np.array(map(score_fn(sparse), it.product(*product_assignments))))
assert_1d_lists_almost_equals(dense_posterior, sparse_posterior, places=3)
def test_crp_empirical():
N = 4
alpha = 2.5
defn = model_definition(N, [bb])
Y = np.array([(True, )] * N, dtype=[('', bool)])
view = numpy_dataview(Y)
r = rng()
def crp_score(assignment):
latent = initialize(defn,
view,
r=r,
cluster_hp={'alpha': alpha},
assignment=assignment)
return latent.score_assignment()
scores = np.array(list(map(crp_score, permutation_iter(N))))
dist = scores_to_probs(scores)
idmap = {C: i for i, C in enumerate(permutation_iter(N))}
def sample_fn():
sample = permutation_canonical(_sample_crp(N, alpha))
return idmap[tuple(sample)]
assert_discrete_dist_approx(sample_fn, dist, ntries=100)
def test_convergence_simple():
N, V = 2, 10
defn = model_definition(N, V)
data = [
np.array([5, 6]),
np.array([0, 1, 2]),
]
view = numpy_dataview(data)
prng = rng()
scores = []
idmap = {}
for i, (tables, dishes) in enumerate(permutations([2, 3])):
latent = model.initialize(
defn, view, prng,
table_assignments=tables,
dish_assignments=dishes)
scores.append(
latent.score_assignment() +
latent.score_data(prng))
idmap[(tables, dishes)] = i
true_dist = scores_to_probs(scores)
def kernel(latent):
# mutates latent in place
doc_model = model.bind(latent, data=view)
kernels.assign2(doc_model, prng)
for did in xrange(latent.nentities()):
table_model = model.bind(latent, document=did)
kernels.assign(table_model, prng)
latent = model.initialize(defn, view, prng)
skip = 10
def sample_fn():
for _ in xrange(skip):
kernel(latent)
table_assignments = latent.table_assignments()
canon_table_assigments = tuple(
map(tuple, map(permutation_canonical, table_assignments)))
dish_maps = latent.dish_assignments()
dish_assignments = []
for dm, (ta, ca) in zip(dish_maps, zip(table_assignments, canon_table_assigments)):
dish_assignment = []
for t, c in zip(ta, ca):
if c == len(dish_assignment):
dish_assignment.append(dm[t])
dish_assignments.append(dish_assignment)
canon_dish_assigments = tuple(
map(tuple, map(permutation_canonical, dish_assignments)))
return idmap[(canon_table_assigments, canon_dish_assigments)]
assert_discrete_dist_approx(
sample_fn, true_dist,
ntries=100, nsamples=10000, kl_places=2)
def _test_convergence(domains,
data,
reg_relations,
brute_relations,
kernel,
burnin_niters=10000,
skip=10,
ntries=50,
nsamples=1000,
places=2):
r = rng()
reg_defn = irm_definition(domains, reg_relations)
brute_defn = irm_definition(domains, brute_relations)
def score_fn(assignments):
s = irm_initialize(
brute_defn, data, r=r,
domain_assignments=assignments)
assign = sum(s.score_assignment(i) for i in xrange(len(assignments)))
likelihood = s.score_likelihood(r)
return assign + likelihood
product_assignments = tuple(map(list, map(permutation_iter, domains)))
posterior = scores_to_probs(
np.array(map(score_fn, it.product(*product_assignments))))
s = irm_initialize(reg_defn, data, r=r)
bounded_states = [irm_bind(s, i, data) for i in xrange(len(domains))]
# burnin
start = time.time()
last = start
for i in xrange(burnin_niters):
for bs in bounded_states:
kernel(bs, r)
if not ((i + 1) % 1000):
print 'burning finished iteration', (i + 1), \
'in', (time.time() - last), 'seconds'
last = time.time()
print 'finished burnin of', burnin_niters, \
'iters in', (time.time() - start), 'seconds'
idmap = {C: i for i, C in enumerate(it.product(*product_assignments))}
#print idmap
def sample_fn():
for _ in xrange(skip):
for bs in bounded_states:
kernel(bs, r)
key = tuple(tuple(permutation_canonical(bs.assignments()))
for bs in bounded_states)
return idmap[key]
assert_discrete_dist_approx(
sample_fn, posterior,
ntries=ntries, nsamples=nsamples,
kl_places=places)
def data_with_posterior(defn, r=None):
# XXX(stephentu): should only accept conjugate models
if r is None:
r = rng()
relations = toy_dataset(defn)
views = map(numpy_dataview, relations)
def score_fn(assignments):
s = model.initialize(defn, views, r=r, domain_assignments=assignments)
assign = sum(s.score_assignment(i) for i in xrange(len(assignments)))
likelihood = s.score_likelihood(r)
return assign + likelihood
domains = defn.domains()
product_assignments = tuple(map(list, map(permutation_iter, domains)))
posterior = scores_to_probs(
np.array(map(score_fn, it.product(*product_assignments))))
return relations, posterior
def data_with_posterior(defn, r=None):
# XXX(stephentu): should only accept conjugate models
if r is None:
r = rng()
relations = toy_dataset(defn)
views = map(numpy_dataview, relations)
def score_fn(assignments):
s = model.initialize(defn, views, r=r, domain_assignments=assignments)
assign = sum(s.score_assignment(i) for i in xrange(len(assignments)))
likelihood = s.score_likelihood(r)
return assign + likelihood
domains = defn.domains()
product_assignments = tuple(map(list, map(permutation_iter, domains)))
posterior = scores_to_probs(
np.array(map(score_fn, it.product(*product_assignments))))
return relations, posterior
def test_crp_empirical():
N = 4
alpha = 2.5
defn = model_definition(N, [bb])
Y = np.array([(True,)] * N, dtype=[('', bool)])
view = numpy_dataview(Y)
r = rng()
def crp_score(assignment):
latent = initialize(
defn, view, r=r,
cluster_hp={'alpha': alpha}, assignment=assignment)
return latent.score_assignment()
scores = np.array(list(map(crp_score, permutation_iter(N))))
dist = scores_to_probs(scores)
idmap = {C: i for i, C in enumerate(permutation_iter(N))}
def sample_fn():
sample = permutation_canonical(_sample_crp(N, alpha))
return idmap[tuple(sample)]
assert_discrete_dist_approx(sample_fn, dist, ntries=100)
def _test_convergence(domains,
data,
reg_relations,
brute_relations,
kernel,
burnin_niters=10000,
skip=10,
ntries=50,
nsamples=1000,
places=2):
r = rng()
reg_defn = irm_definition(domains, reg_relations)
brute_defn = irm_definition(domains, brute_relations)
def score_fn(assignments):
s = irm_initialize(brute_defn,
data,
r=r,
domain_assignments=assignments)
assign = sum(s.score_assignment(i) for i in xrange(len(assignments)))
likelihood = s.score_likelihood(r)
return assign + likelihood
product_assignments = tuple(map(list, map(permutation_iter, domains)))
posterior = scores_to_probs(
np.array(map(score_fn, it.product(*product_assignments))))
s = irm_initialize(reg_defn, data, r=r)
bounded_states = [irm_bind(s, i, data) for i in xrange(len(domains))]
# burnin
start = time.time()
last = start
for i in xrange(burnin_niters):
for bs in bounded_states:
kernel(bs, r)
if not ((i + 1) % 1000):
print 'burning finished iteration', (i + 1), \
'in', (time.time() - last), 'seconds'
last = time.time()
print 'finished burnin of', burnin_niters, \
'iters in', (time.time() - start), 'seconds'
idmap = {C: i for i, C in enumerate(it.product(*product_assignments))}
#print idmap
def sample_fn():
for _ in xrange(skip):
for bs in bounded_states:
kernel(bs, r)
key = tuple(
tuple(permutation_canonical(bs.assignments()))
for bs in bounded_states)
return idmap[key]
assert_discrete_dist_approx(sample_fn,
posterior,
ntries=ntries,
nsamples=nsamples,
kl_places=places)
def test_convergence_simple():
N, V = 2, 10
defn = model_definition(N, V)
data = [
np.array([5, 6]),
np.array([0, 1, 2]),
]
view = numpy_dataview(data)
prng = rng()
scores = []
idmap = {}
for i, (tables, dishes) in enumerate(permutations([2, 3])):
latent = model.initialize(defn,
view,
prng,
table_assignments=tables,
dish_assignments=dishes)
scores.append(latent.score_assignment() + latent.score_data(prng))
idmap[(tables, dishes)] = i
true_dist = scores_to_probs(scores)
def kernel(latent):
# mutates latent in place
doc_model = model.bind(latent, data=view)
kernels.assign2(doc_model, prng)
for did in xrange(latent.nentities()):
table_model = model.bind(latent, document=did)
kernels.assign(table_model, prng)
latent = model.initialize(defn, view, prng)
skip = 10
def sample_fn():
for _ in xrange(skip):
kernel(latent)
table_assignments = latent.table_assignments()
canon_table_assigments = tuple(
map(tuple, map(permutation_canonical, table_assignments)))
dish_maps = latent.dish_assignments()
dish_assignments = []
for dm, (ta, ca) in zip(dish_maps,
zip(table_assignments,
canon_table_assigments)):
dish_assignment = []
for t, c in zip(ta, ca):
if c == len(dish_assignment):
dish_assignment.append(dm[t])
dish_assignments.append(dish_assignment)
canon_dish_assigments = tuple(
map(tuple, map(permutation_canonical, dish_assignments)))
return idmap[(canon_table_assigments, canon_dish_assigments)]
assert_discrete_dist_approx(sample_fn,
true_dist,
ntries=100,
nsamples=10000,
kl_places=2)