def test_crosscat_two_component_nominal__ci_():
prng = get_prng(10)
integration = pytest.config.getoption('--integration')
# Build CGPM with adversarial initialization.
crosscat = Product([
FlexibleRowMixture(
cgpm_row_divide=CRP([-1], [], rng=prng),
cgpm_components_base=Product([
Normal([0], [], rng=prng),
], rng=prng),
rng=prng),
FlexibleRowMixture(
cgpm_row_divide=CRP([-2], [], rng=prng),
cgpm_components_base=Product([
Normal([1], [], rng=prng),
Categorical([50], [], distargs={'k':4}, rng=prng),
], rng=prng),
rng=prng),
], rng=prng,)
# Fetch data and add a nominal variable.
data_xy = make_bivariate_two_clusters(prng)
data_z = np.zeros(len(data_xy))
data_z[:15] = 0
data_z[15:30] = 1
data_z[30:45] = 2
data_z[45:60] = 3
data = np.column_stack((data_xy, data_z))
# Observe.
for rowid, row in enumerate(data):
crosscat.observe(rowid, {0: row[0], 1: row[1], 50:row[2]})
# Run inference.
synthesizer = GibbsCrossCat(crosscat)
synthesizer.transition(N=(50 if integration else 1), progress=False)
synthesizer.transition(N=(100 if integration else 1),
kernels=['hypers_distributions','hypers_row_divide'],
progress=False)
# Assert views are merged into one.
assert not integration or len(synthesizer.crosscat.cgpms) == 1
crp_output = synthesizer.crosscat.cgpms[0].cgpm_row_divide.outputs[0]
# Check joint samples for all nominals.
samples = synthesizer.crosscat.simulate(None, [crp_output,0,1,50], N=250)
not integration or check_sampled_data(samples, [0, 7], 3, 110)
# Check joint samples for nominals [0, 2].
samples_a = [s for s in samples if s[50] in [0,2]]
not integration or check_sampled_data(samples_a, [0, 7], 3, 45)
# Check joint samples for nominals [1, 3].
samples_b = [s for s in samples if s[50] in [1,3]]
not integration or check_sampled_data(samples_b, [0, 7], 3, 45)
# Check conditional samples in correct quadrants.
means = {0:0, 1:0, 2:7, 3:7}
for z in [0, 1, 2, 3]:
samples = synthesizer.crosscat.simulate(None, [0, 1], {50:z}, N=100)
not integration or check_sampled_data(samples, [means[z]], 3, 90)
def test_transition_hypers_basic():
prng = get_prng(2)
component0 = Product([
Poisson([0], [], hypers={'m': 100}, rng=prng),
Normal([1], [], hypers={'m': 100}, rng=prng)
],
rng=prng)
cgpm_row_divide = CRP([2], [], rng=prng)
infinite_mixture = FlexibleRowMixture(cgpm_row_divide=cgpm_row_divide,
cgpm_components_base=component0,
rng=prng)
# Make normal observations.
infinite_mixture.observe(0, {1: 100})
infinite_mixture.observe(1, {1: 300})
infinite_mixture.observe(2, {1: -300})
# Fetch log score.
log_score0 = infinite_mixture.logpdf_score()
# Run inference.
normal_cgpms = get_cgpms_by_output_index(infinite_mixture, 1)
grids_normal = transition_hyper_grids(normal_cgpms, 30)
hypers_normal = [
transition_hypers(normal_cgpms, grids_normal, prng) for _i in xrange(2)
]
assert not all(hypers == hypers_normal[0] for hypers in hypers_normal)
log_score1 = infinite_mixture.logpdf_score()
assert log_score0 < log_score1
def test_flexible_mixture_three_component__ci_():
prng = get_prng(2)
flexible_mixture = FlexibleRowMixture(cgpm_row_divide=CRP([1], [],
rng=prng),
cgpm_components_base=Normal(
[0], [], rng=prng),
rng=prng)
integration = pytest.config.getoption('--integration')
run_mixture_test(flexible_mixture, integration, prng)
def get_crosscat(prng):
view = FlexibleRowMixture(
cgpm_row_divide=CRP([2], [], rng=prng),
cgpm_components_base=Product([
Normal([0], [], rng=prng),
Normal([1], [], rng=prng),
], rng=prng),
rng=prng)
return Product(cgpms=[view], rng=prng)
def make_random_view(outputs, distributions, rng):
crp_output = rng.randint(2**32 - 1)
cgpm_row_divide = CRP([crp_output], [], rng=rng)
cgpm_base_list = [
make_random_primitive(output, distribution, rng)
for output, distribution in zip(outputs, distributions)
]
view = FlexibleRowMixture(cgpm_row_divide=cgpm_row_divide,
cgpm_components_base=Product(cgpm_base_list,
rng=rng),
rng=rng)
return view
def get_crosscat_synthesizer(prng):
view = FlexibleRowMixture(cgpm_row_divide=CRP([2], [], rng=prng),
cgpm_components_base=Product([
Normal([0], [], rng=prng),
Normal([1], [], rng=prng),
],
rng=prng),
rng=prng)
crosscat = Product(cgpms=[view], rng=prng)
data = make_bivariate_two_clusters(prng)
for rowid, row in enumerate(data):
crosscat.observe(rowid, {0: row[0], 1: row[1]})
return GibbsCrossCat(crosscat)
def get_crosscat(prng):
view0 = FlexibleRowMixture(
cgpm_row_divide=CRP([-1], [], rng=prng),
cgpm_components_base=Product([
Normal([0], [], rng=prng),
Normal([1], [], rng=prng),
], rng=prng),
rng=prng)
view1 = FlexibleRowMixture(
cgpm_row_divide=CRP([-2], [], rng=prng),
cgpm_components_base=Product([
Poisson([2], [], rng=prng),
Normal([3], [], rng=prng),
Normal([4], [], rng=prng),
], rng=prng),
rng=prng)
view2 = FlexibleRowMixture(
cgpm_row_divide=CRP([-3], [], rng=prng),
cgpm_components_base=Product([
Categorical([5], [], distargs={'k':4}, rng=prng),
], rng=prng),
rng=prng)
return Product([view0, view1, view2], rng=prng)
def test_product_mixture_walk():
prng = get_prng(2)
component_base = Product([
Poisson([0], [], hypers={
'a': 10,
'b': 1
}, rng=prng),
Normal([1], [], hypers={'m': 100}, rng=prng)
],
rng=prng)
cgpm_row_divide = CRP([2], [], rng=prng)
infinite_mixture = FlexibleRowMixture(cgpm_row_divide=cgpm_row_divide,
cgpm_components_base=component_base,
rng=prng)
# Only the base CGPMs in the flexible mixture.
cgpm_poisson = get_cgpms_by_output_index(infinite_mixture, 0)
cgpm_normal = get_cgpms_by_output_index(infinite_mixture, 1)
cgpm_crp = get_cgpms_by_output_index(infinite_mixture, 2)
assert cgpm_poisson == [component_base.cgpms[0]]
assert cgpm_normal == [component_base.cgpms[1]]
assert cgpm_crp == [cgpm_row_divide]
infinite_mixture.observe(0, {0: 1})
# New CGPMs in the flexible CGPM after observing.
cgpm_poisson = get_cgpms_by_output_index(infinite_mixture, 0)
cgpm_normal = get_cgpms_by_output_index(infinite_mixture, 1)
assert len(cgpm_poisson) == len(cgpm_normal) == 2
assert [cgpm_poisson[-1]] == [component_base.cgpms[0]]
assert [cgpm_normal[-1]] == [component_base.cgpms[1]]
assert cgpm_poisson[0].N == 1
assert cgpm_normal[0].N == 0
cgpm_crp = get_cgpms_by_output_index(infinite_mixture, 2)
assert len(cgpm_crp) == 1
assert cgpm_crp[0].N == 1
assert cgpm_crp[0].data[0] == 0
# Misc. errors, no such output.
with pytest.raises(Exception):
get_cgpms_by_output_index(infinite_mixture, -1)
def test_add_remove():
prng = get_prng(2)
mixture0 = FlexibleRowMixture(
cgpm_row_divide=CRP([2], [], rng=prng),
cgpm_components_base=Product([
Normal([0], [], rng=prng),
Normal([1], [], rng=prng),
], rng=prng),
rng=prng)
for rowid, row in enumerate([[0,.9] ,[.5, 1], [-.5, 1.2]]):
mixture0.observe(rowid, {0:row[0], 1:row[1]})
mixture1 = remove_cgpm(mixture0, 0)
assert mixture0.outputs == [2, 0, 1]
assert mixture1.outputs == [2, 1]
mixture2 = add_cgpm(mixture1, Normal([0], [], rng=prng))
assert mixture0.outputs == [2, 0, 1]
assert mixture1.outputs == [2, 1]
assert mixture2.outputs == [2, 1, 0]
mixture3 = remove_cgpm(mixture2, 1)
assert mixture0.outputs == [2, 0, 1]
assert mixture1.outputs == [2, 1]
assert mixture2.outputs == [2, 1, 0]
assert mixture3.outputs == [2, 0]
mixture4 = remove_cgpm(mixture3, 0)
assert mixture0.outputs == [2, 0, 1]
assert mixture1.outputs == [2, 1]
assert mixture2.outputs == [2, 1, 0]
assert mixture3.outputs == [2, 0]
assert mixture4.outputs == [2]
with pytest.raises(Exception):
# Cannot remove the cgpm_row_divide for a mixture.
mixture3 = remove_cgpm(mixture2, 2)
def test_crosscat_add_remove():
prng = get_prng(2)
crosscat = get_crosscat(prng)
infinite_mixture4 = FlexibleRowMixture(
cgpm_row_divide=CRP([-4], [], rng=prng),
cgpm_components_base=Product([
Categorical([6], [], distargs={'k':4}, rng=prng),
], rng=prng),
rng=prng)
crosscat = add_cgpm(crosscat, infinite_mixture4)
assert crosscat.outputs == [-1, 0, 1, -2, 2, 3, 4, -3, 5, -4, 6]
crosscat = remove_cgpm(crosscat, -1)
assert crosscat.outputs == [-2, 2, 3, 4, -3, 5, -4, 6]
crosscat = remove_cgpm(crosscat, 5)
assert crosscat.outputs == [-2, 2, 3, 4, -4, 6]
def test_crosscat_three_component_cpp__ci_():
prng = get_prng(12)
integration = pytest.config.getoption('--integration')
view = FlexibleRowMixture(cgpm_row_divide=CRP([1], [], rng=prng),
cgpm_components_base=Product(
cgpms=[Normal([0], [], rng=prng)], rng=prng),
rng=prng)
crosscat = Product(cgpms=[view], rng=prng)
def func_inference(crosscat):
n_step = 1000 if integration else 1
synthesizer = GibbsCrossCat(crosscat)
synthesizer.transition_structure_cpp(N=n_step)
synthesizer.transition_hypers_distributions()
synthesizer.transition_hypers_row_divide()
return synthesizer
run_crosscat_test(crosscat, func_inference, integration, prng)
def test_transition_crp_mixture():
prng = get_prng(2)
data = np.concatenate((
prng.normal(loc=0, scale=2, size=20),
prng.normal(loc=30, scale=1, size=20),
prng.normal(loc=-30, scale=1, size=20),
))
infinite_mixture = FlexibleRowMixture(cgpm_row_divide=CRP([1], [],
rng=prng),
cgpm_components_base=Normal(
[0], [], rng=prng),
rng=prng)
for rowid, value in enumerate(data):
infinite_mixture.observe(rowid, {0: value})
cgpms = {
0: get_cgpms_by_output_index(infinite_mixture, 0),
1: get_cgpms_by_output_index(infinite_mixture, 1),
}
grids = {
0: transition_hyper_grids(cgpms[0], 30),
1: transition_hyper_grids(cgpms[1], 30),
}
for _step in xrange(50):
rowids = prng.permutation(range(len(data)))
for rowid in rowids:
transition_rows(infinite_mixture, rowid, prng)
for output in infinite_mixture.outputs:
transition_hypers(cgpms[output], grids[output], prng)
rowids = range(60)
assignments0 = [
infinite_mixture.simulate(r, [1])[1] for r in rowids[00:20]
]
assignments1 = [
infinite_mixture.simulate(r, [1])[1] for r in rowids[20:40]
]
assignments2 = [
infinite_mixture.simulate(r, [1])[1] for r in rowids[40:60]
]
mode0 = Counter(assignments0).most_common(1)[0][0]
mode1 = Counter(assignments1).most_common(1)[0][0]
mode2 = Counter(assignments2).most_common(1)[0][0]
assert sum(a == mode0
for a in assignments0) > int(0.95 * len(assignments0))
assert sum(a == mode1
for a in assignments1) > int(0.95 * len(assignments1))
assert sum(a == mode2
for a in assignments2) > int(0.95 * len(assignments2))
def test_simple_product_as_chain():
prng = get_prng(2)
component0 = Chain([
Poisson([0], [], hypers={'a': 10, 'b': 1}, rng=prng),
Normal([1], [], hypers={'m':100}, rng=prng)
],
rng=prng)
cgpm_row_divide = CRP([2], [], rng=prng)
infinite_mixture = FlexibleRowMixture(
cgpm_row_divide=cgpm_row_divide,
cgpm_components_base=component0,
rng=prng)
assert infinite_mixture.cgpm_row_divide.support() == [0]
# Test logpdf identities.
lp0 = infinite_mixture.logpdf(None, {0:1})
assert lp0 < 0
lp1 = infinite_mixture.logpdf(None, {0:1, 2:0})
assert np.allclose(lp0, lp1)
lp2 = infinite_mixture.logpdf(None, {0:1, 2:1})
assert lp2 == -float('inf')
# Add an observation.
infinite_mixture.observe(0, {1:100})
lp0 = infinite_mixture.logpdf(None, {1:100, 2:0}, constraints={0:1})
lp1 = infinite_mixture.logpdf(None, {1:100, 2:1}, constraints={0:1})
lp2 = infinite_mixture.logpdf(None, {1:100, 2:2}, constraints={0:1})
assert lp1 < lp0
assert lp2 == float('-inf')
# Remove observation.
observation = infinite_mixture.unobserve(0)
assert observation == ({1:100, 2:0}, {})
# Remove observation again.
with pytest.raises(Exception):
infinite_mixture.unobserve(0)
# Add more observations.
infinite_mixture.observe(0, {1:100})
infinite_mixture.observe(1, {1:300})
infinite_mixture.observe(2, {0:2})
# Constrained cluster has zero density.
with pytest.raises(ValueError):
infinite_mixture.logpdf(None, {0:1}, constraints={2:10})
with pytest.raises(ValueError):
infinite_mixture.logpdf(None, {0:1}, constraints={2:10})
# Convert to/from metadata and assert unobserves return correct data.
metadata = infinite_mixture.to_metadata()
infinite_mixture2 = FlexibleRowMixture.from_metadata(metadata, prng)
assert infinite_mixture2.unobserve(0) == \
({1:100, 2: infinite_mixture.cgpm_row_divide.data[0]}, {})
assert infinite_mixture2.unobserve(1) == \
({1:300, 2: infinite_mixture.cgpm_row_divide.data[1]}, {})
assert infinite_mixture2.unobserve(2) == \
({0:2, 2: infinite_mixture.cgpm_row_divide.data[2]}, {})