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(bs,
posterior,
kernel,
burnin_niters,
skip,
ntries,
nsamples,
kl_places):
N = bs.nentities()
start = time.time()
last = start
for i in xrange(burnin_niters):
kernel(bs)
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(permutation_iter(N))}
def sample_fn():
for _ in xrange(skip):
kernel(bs)
return idmap[tuple(permutation_canonical(bs.assignments()))]
assert_discrete_dist_approx(
sample_fn, posterior,
ntries=ntries, nsamples=nsamples, kl_places=kl_places)
def _test_convergence(bs, posterior, kernel, burnin_niters, skip, ntries,
nsamples, kl_places):
N = bs.nentities()
start = time.time()
last = start
for i in xrange(burnin_niters):
kernel(bs)
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(permutation_iter(N))}
def sample_fn():
for _ in xrange(skip):
kernel(bs)
return idmap[tuple(permutation_canonical(bs.assignments()))]
assert_discrete_dist_approx(sample_fn,
posterior,
ntries=ntries,
nsamples=nsamples,
kl_places=kl_places)
def test_runner_multiprocessing_convergence():
N, D = 4, 5
defn = model_definition(N, [bb] * D)
prng = rng()
Y, posterior = data_with_posterior(defn, r=prng)
view = numpy_dataview(Y)
latents = [model.initialize(defn, view, prng)
for _ in xrange(mp.cpu_count())]
runners = [runner.runner(defn, view, latent, ['assign'])
for latent in latents]
r = parallel.runner(runners)
r.run(r=prng, niters=1000) # burnin
idmap = {C: i for i, C in enumerate(permutation_iter(N))}
def sample_iter():
r.run(r=prng, niters=10)
for latent in r.get_latents():
yield idmap[tuple(permutation_canonical(latent.assignments()))]
ref = [None]
def sample_fn():
if ref[0] is None:
ref[0] = sample_iter()
try:
return next(ref[0])
except StopIteration:
ref[0] = None
return sample_fn()
assert_discrete_dist_approx(sample_fn, posterior, ntries=100, kl_places=2)
def permutations(doclengths):
"""Generate a permutation of XXX
WARNING: very quickly becomes intractable
"""
perms = [permutation_iter(length) for length in doclengths]
for prod in it.product(*perms):
dishes = sum([max(x) + 1 for x in prod])
for p in permutation_iter(dishes):
idx = 0
ret = []
for d in prod:
ntables = max(d) + 1
ret.append(tuple(p[idx:idx+ntables]))
idx += ntables
yield prod, tuple(ret)
def permutations(doclengths):
"""Generate a permutation of XXX
WARNING: very quickly becomes intractable
"""
perms = [permutation_iter(length) for length in doclengths]
for prod in it.product(*perms):
dishes = sum([max(x) + 1 for x in prod])
for p in permutation_iter(dishes):
idx = 0
ret = []
for d in prod:
ntables = max(d) + 1
ret.append(tuple(p[idx:idx+ntables]))
idx += ntables
yield prod, tuple(ret)
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_crp(initialize_fn, dataview, alpha, r):
N = 6
defn = model_definition(N, [bb])
Y = np.array([(True,)] * N, dtype=[('', bool)])
view = dataview(Y)
def crp_score(assignment):
latent = initialize_fn(
defn, view, r=r,
cluster_hp={'alpha': alpha}, assignment=assignment)
return latent.score_assignment()
dist = np.array(list(map(crp_score, permutation_iter(N))))
dist = np.exp(dist)
assert_almost_equals(dist.sum(), 1.0, places=3)
def test_runner_convergence():
N, D = 4, 5
defn = model_definition(N, [bb] * D)
prng = rng()
Y, posterior = data_with_posterior(defn, r=prng)
view = numpy_dataview(Y)
latent = model.initialize(defn, view, prng)
r = runner.runner(defn, view, latent, ['assign'])
r.run(r=prng, niters=1000) # burnin
idmap = {C: i for i, C in enumerate(permutation_iter(N))}
def sample_fn():
r.run(r=prng, niters=10)
new_latent = r.get_latent()
return idmap[tuple(permutation_canonical(new_latent.assignments()))]
assert_discrete_dist_approx(sample_fn, posterior, ntries=100)
def _test_crp(initialize_fn, dataview, alpha, r):
N = 6
defn = model_definition(N, [bb])
Y = np.array([(True, )] * N, dtype=[('', bool)])
view = dataview(Y)
def crp_score(assignment):
latent = initialize_fn(defn,
view,
r=r,
cluster_hp={'alpha': alpha},
assignment=assignment)
return latent.score_assignment()
dist = np.array(list(map(crp_score, permutation_iter(N))))
dist = np.exp(dist)
assert_almost_equals(dist.sum(), 1.0, places=3)
def test_compare_to_mixture_model():
r = rng()
N, D = 4, 5
Y = np.random.uniform(size=(N, D)) > 0.8
Y_rec = np.array([tuple(y) for y in Y], dtype=[('', bool)] * D)
mm_view = rec_numpy_dataview(Y_rec)
irm_view = relation_numpy_dataview(Y)
mm_def = mm_definition(N, [bb] * D)
irm_def = irm_definition([N, D], [((0, 1), bb)])
perms = list(permutation_iter(N))
assignment = perms[np.random.randint(0, len(perms))]
mm_s = mm_initialize(mm_def, mm_view, r=r, assignment=assignment)
irm_s = irm_initialize(irm_def,
[irm_view],
r=r,
domain_assignments=[
assignment,
range(D),
])
def assert_suff_stats_equal():
assert set(mm_s.groups()) == set(irm_s.groups(0))
assert irm_s.groups(1) == range(D)
groups = mm_s.groups()
for g in groups:
for i in xrange(D):
a = mm_s.get_suffstats(g, i)
b = irm_s.get_suffstats(0, [g, i])
if b is None:
b = {'heads': 0L, 'tails': 0L}
assert a['heads'] == b['heads'] and a['tails'] == b['tails']
assert_suff_stats_equal()
assert_almost_equals(
mm_s.score_assignment(), irm_s.score_assignment(0), places=3)
bound_mm_s = mm_bind(mm_s, mm_view)
bound_irm_s = irm_bind(irm_s, 0, [irm_view])
# XXX: doesn't really have to be true, just is true of impl
assert not bound_mm_s.empty_groups()
assert not bound_irm_s.empty_groups()
bound_mm_s.create_group(r)
bound_irm_s.create_group(r)
gid_a = bound_mm_s.remove_value(0, r)
gid_b = bound_irm_s.remove_value(0, r)
assert gid_a == gid_b
assert_suff_stats_equal()
x0, y0 = bound_mm_s.score_value(0, r)
x1, y1 = bound_irm_s.score_value(0, r)
assert x0 == x1 # XXX: not really a requirement
# XXX: should really normalize and then check
for a, b in zip(y0, y1):
assert_almost_equals(a, b, places=2)
def test_compare_to_mixture_model():
r = rng()
N, D = 4, 5
Y = np.random.uniform(size=(N, D)) > 0.8
Y_rec = np.array([tuple(y) for y in Y], dtype=[('', bool)] * D)
mm_view = rec_numpy_dataview(Y_rec)
irm_view = relation_numpy_dataview(Y)
mm_def = mm_definition(N, [bb] * D)
irm_def = irm_definition([N, D], [((0, 1), bb)])
perms = list(permutation_iter(N))
assignment = perms[np.random.randint(0, len(perms))]
mm_s = mm_initialize(mm_def, mm_view, r=r, assignment=assignment)
irm_s = irm_initialize(irm_def, [irm_view],
r=r,
domain_assignments=[
assignment,
range(D),
])
def assert_suff_stats_equal():
assert set(mm_s.groups()) == set(irm_s.groups(0))
assert irm_s.groups(1) == range(D)
groups = mm_s.groups()
for g in groups:
for i in xrange(D):
a = mm_s.get_suffstats(g, i)
b = irm_s.get_suffstats(0, [g, i])
if b is None:
b = {'heads': 0L, 'tails': 0L}
assert a['heads'] == b['heads'] and a['tails'] == b['tails']
assert_suff_stats_equal()
assert_almost_equals(mm_s.score_assignment(),
irm_s.score_assignment(0),
places=3)
bound_mm_s = mm_bind(mm_s, mm_view)
bound_irm_s = irm_bind(irm_s, 0, [irm_view])
# XXX: doesn't really have to be true, just is true of impl
assert not bound_mm_s.empty_groups()
assert not bound_irm_s.empty_groups()
bound_mm_s.create_group(r)
bound_irm_s.create_group(r)
gid_a = bound_mm_s.remove_value(0, r)
gid_b = bound_irm_s.remove_value(0, r)
assert gid_a == gid_b
assert_suff_stats_equal()
x0, y0 = bound_mm_s.score_value(0, r)
x1, y1 = bound_irm_s.score_value(0, r)
assert x0 == x1 # XXX: not really a requirement
# XXX: should really normalize and then check
for a, b in zip(y0, y1):
assert_almost_equals(a, b, places=2)
