def test_can_specify_a_gaussian_proposal_distribution(net: BayesNet) -> None:
algo = MetropolisHastingsSampler(proposal_distribution="gaussian",
latents=net.iter_latent_vertices(),
proposal_distribution_sigma=np.array(1.))
generate_samples(net=net,
sample_from=net.iter_latent_vertices(),
sampling_algorithm=algo)
def test_sample_throws_if_vertices_in_sample_from_are_missing_labels() -> None:
sigma = Gamma(1., 1)
vertex = Gaussian(0., sigma, label="gaussian")
assert sigma.get_label() is None
net = BayesNet([sigma, vertex])
with pytest.raises(ValueError,
match=r"Vertices in sample_from must be labelled."):
samples = sample(net=net, sample_from=net.iter_latent_vertices())
def test_probe_for_non_zero_probability_from_bayes_net() -> None:
gamma = Gamma(1., 1.)
poisson = Poisson(gamma)
net = BayesNet([poisson, gamma])
assert not gamma.has_value()
assert not poisson.has_value()
net.probe_for_non_zero_probability(100, KeanuRandom())
assert gamma.has_value()
assert poisson.has_value()
def test_iter_returns_same_result_as_sample(algo: str) -> None:
draws = 100
model = thermometers.model()
net = BayesNet(model.temperature.get_connected_graph())
set_starting_state(model)
samples = sample(net=net, sample_from=net.get_latent_vertices(), algo=algo, draws=draws)
set_starting_state(model)
iter_samples = generate_samples(net=net, sample_from=net.get_latent_vertices(), algo=algo)
samples_dataframe = pd.DataFrame()
[samples_dataframe.append(pd.DataFrame(list(next_sample.items()))) for next_sample in islice(iter_samples, draws)]
for vertex_id in samples_dataframe:
np.testing.assert_almost_equal(samples_dataframe[vertex_id].mean(), np.average(samples[vertex_id]))
def test_construct_bayes_net() -> None:
uniform = UniformInt(0, 1)
graph = set(uniform.get_connected_graph())
vertex_ids = [vertex.get_id() for vertex in graph]
assert len(vertex_ids) == 3
assert uniform.get_id() in vertex_ids
net = BayesNet(graph)
latent_vertex_ids = [
vertex.get_id() for vertex in net.get_latent_vertices()
]
assert len(latent_vertex_ids) == 1
assert uniform.get_id() in latent_vertex_ids
def test_coalmining() -> None:
coal_mining = CoalMining()
model = coal_mining.model()
model.disasters.observe(coal_mining.training_data())
net = BayesNet(model.switchpoint.iter_connected_graph())
samples = sample(net=net, sample_from=net.iter_latent_vertices(), draws=2000, drop=100, down_sample_interval=5)
vertex_samples: List[primitive_types] = samples["switchpoint"]
vertex_samples_concatentated: np.ndarray = np.array(vertex_samples)
switch_year = np.argmax(np.bincount(vertex_samples_concatentated))
assert switch_year == 1890
def test_sampling_returns_multi_indexed_dict_of_list_of_scalars_for_mixed_net(
algo: Callable[[BayesNet], PosteriorSamplingAlgorithm]) -> None:
exp = Exponential(1.)
add_rank_2 = exp + np.array([1., 2., 3., 4.]).reshape((2, 2))
add_rank_3 = exp + np.array([1., 2., 3., 4., 1., 2., 3., 4.]).reshape(
(2, 2, 2))
gaussian_rank_2 = Gaussian(add_rank_2, 2.)
gaussian_rank_3 = Gaussian(add_rank_3, 1.)
exp.set_label("exp")
gaussian_rank_2.set_label("gaussian")
gaussian_rank_3.set_label("gaussian2")
mixed_net = BayesNet(exp.iter_connected_graph())
draws = 5
sample_from = list(mixed_net.iter_latent_vertices())
vertex_labels = [vertex.get_label() for vertex in sample_from]
samples = sample(net=mixed_net,
sample_from=sample_from,
sampling_algorithm=algo(mixed_net),
draws=draws)
assert type(samples) == dict
__assert_valid_samples(draws, samples)
assert ('exp', (0, )) in samples
for i in (0, 1):
for j in (0, 1):
assert (('gaussian', (i, j)) in samples)
df = pd.DataFrame(samples)
expected_num_columns = {"exp": 1, "gaussian": 4, "gaussian2": 8}
expected_tuple_size = {"exp": 1, "gaussian": 2, "gaussian2": 3}
assert len(df.columns.levels[0]) == 3
for parent_column in df.columns.levels[0]:
assert parent_column in vertex_labels
assert len(
df[parent_column].columns) == expected_num_columns[parent_column]
for child_column in df[parent_column].columns:
assert type(child_column) == tuple
assert len(child_column) == expected_tuple_size[parent_column]
assert len(df[parent_column][child_column]) == 5
assert type(df[parent_column][child_column][0]) == np.float64
def test_iter_with_live_plot(net: BayesNet) -> None:
KeanuRandom.set_default_random_seed(1)
_, ax = plt.subplots(3, 1, squeeze=False)
samples = generate_samples(net=net,
sample_from=net.get_latent_vertices(),
live_plot=True,
refresh_every=5,
ax=ax)
for sample in islice(samples, 5):
pass
reorder_subplots(ax)
assert len(ax) == 3
assert all(len(ax[i][0].get_lines()) == 1 for i in range(3))
assert np.allclose(
ax[0][0].get_lines()[0].get_ydata(),
[0.49147822, 0.49147822, 0.49147822, 0.20033212, 0.20033212])
assert np.allclose(
ax[1][0].get_lines()[0].get_ydata(),
[0.87268333, 1.10409369, 1.10409369, 1.10409369, 0.69098161])
assert np.allclose(
ax[2][0].get_lines()[0].get_ydata(),
[-14.46166855, -14.46166855, 0.32305686, 0.32305686, 0.32305686])
def test_can_save_and_load(tmpdir) -> None:
PROTO_FILE_NAME = str(tmpdir.join("test.proto"))
JSON_FILE_NAME = str(tmpdir.join("test.json"))
DOT_FILE_NAME = str(tmpdir.join("test.dot"))
gamma = Gamma(1.0, 1.0)
gamma.set_value(2.5)
# %%SNIPPET_START%% PythonSaveSnippet
net = BayesNet(gamma.iter_connected_graph())
metadata = {"Author": "Documentation Team"}
protobuf_saver = ProtobufSaver(net)
protobuf_saver.save(PROTO_FILE_NAME, True, metadata)
json_saver = JsonSaver(net)
json_saver.save(JSON_FILE_NAME, True, metadata)
dot_saver = DotSaver(net)
dot_saver.save(DOT_FILE_NAME, True, metadata)
# %%SNIPPET_END%% PythonSaveSnippet
# %%SNIPPET_START%% PythonLoadSnippet
protobuf_loader = ProtobufLoader()
new_net_from_proto = protobuf_loader.load(PROTO_FILE_NAME)
json_loader = JsonLoader()
new_net_from_json = json_loader.load(JSON_FILE_NAME)
def test_can_get_vertices_from_bayes_net(get_method: str, latent: bool,
observed: bool, continuous: bool,
discrete: bool) -> None:
gamma = Gamma(1., 1.)
gamma.observe(0.5)
poisson = Poisson(gamma)
cauchy = Cauchy(gamma, 1.)
assert gamma.is_observed()
assert not poisson.is_observed()
assert not cauchy.is_observed()
net = BayesNet([gamma, poisson, cauchy])
vertex_ids = [vertex.get_id() for vertex in getattr(net, get_method)()]
if observed and continuous:
assert gamma.get_id() in vertex_ids
if latent and discrete:
assert poisson.get_id() in vertex_ids
if latent and continuous:
assert cauchy.get_id() in vertex_ids
assert len(vertex_ids) == (observed and continuous) + (
latent and discrete) + (latent and continuous)
def test_can_iter_through_samples(algo: str, net: BayesNet) -> None:
draws = 10
samples = generate_samples(net=net, sample_from=net.get_latent_vertices(), algo=algo, down_sample_interval=1)
count = 0
for sample in islice(samples, draws):
count += 1
assert count == draws
def test_can_get_acceptance_rates(net: BayesNet) -> None:
acceptance_rate_tracker = AcceptanceRateTracker()
latents = list(net.iter_latent_vertices())
algo = MetropolisHastingsSampler(
proposal_distribution='prior',
latents=net.iter_latent_vertices(),
proposal_listeners=[acceptance_rate_tracker])
samples = sample(net=net,
sample_from=latents,
sampling_algorithm=algo,
drop=3)
for latent in latents:
rate = acceptance_rate_tracker.get_acceptance_rate(latent)
assert 0 <= rate <= 1
def test_dropping_samples(net: BayesNet) -> None:
draws = 10
drop = 3
samples = sample(net=net, sample_from=net.get_latent_vertices(), draws=draws, drop=drop)
expected_num_samples = draws - drop
assert all(len(vertex_samples) == expected_num_samples for vertex_id, vertex_samples in samples.items())
def test_thermometers_max_likelihood_gradient(model: Model) -> None:
net = BayesNet(model.temperature.get_connected_graph())
gradient_optimizer = GradientOptimizer(net)
logProb = gradient_optimizer.max_likelihood()
assert logProb < 0.
temperature = model.temperature.get_value()
assert 20.995 < temperature < 21.005
def thermometers_max_likelihood_gradient(model: Model, algorithm) -> None:
net = BayesNet(model.temperature.iter_connected_graph())
gradient_optimizer = GradientOptimizer(net, algorithm)
result = gradient_optimizer.max_likelihood()
assert result.fitness() < 0.
temperature = result.value_for(model.temperature)
assert 20.99 < temperature < 21.01
def test_iter_returns_same_result_as_sample(algo: Callable) -> None:
draws = 100
model = thermometers.model()
net = BayesNet(model.temperature.get_connected_graph())
set_starting_state(model)
sampler = algo()
samples = sample(net=net, sample_from=net.get_latent_vertices(), sampling_algorithm=sampler, draws=draws)
set_starting_state(model)
sampler = algo()
iter_samples = generate_samples(net=net, sample_from=net.get_latent_vertices(), sampling_algorithm=sampler)
samples_dataframe = pd.DataFrame()
for iter_sample in islice(iter_samples, draws):
samples_dataframe = samples_dataframe.append(iter_sample, ignore_index=True)
for vertex_label in samples_dataframe:
np.testing.assert_almost_equal(samples_dataframe[vertex_label].mean(), np.average(samples[vertex_label]))
def test_down_sample_interval(net: BayesNet) -> None:
draws = 10
down_sample_interval = 2
samples = sample(
net=net, sample_from=net.get_latent_vertices(), draws=draws, down_sample_interval=down_sample_interval)
expected_num_samples = draws / down_sample_interval
assert all(len(vertex_samples) == expected_num_samples for vertex_id, vertex_samples in samples.items())
def test_coalmining() -> None:
KeanuRandom.set_default_random_seed(1)
coal_mining = CoalMining()
model = coal_mining.model()
model.disasters.observe(coal_mining.training_data())
net = BayesNet(model.switchpoint.get_connected_graph())
samples = sample(net=net, sample_from=net.get_latent_vertices(), draws=50000, drop=10000, down_sample_interval=5)
vertex_samples: List[numpy_types] = samples["switchpoint"]
vertex_samples_primitive: List[List[primitive_types]] = list(map(
lambda a: a.tolist(), vertex_samples)) # because you can't concatenate 0-d arrays
vertex_samples_concatentated: np.ndarray = np.array(vertex_samples_primitive)
switch_year = np.argmax(np.bincount(vertex_samples_concatentated))
assert switch_year == 1890
def test_sample_with_plot(net: BayesNet) -> None:
KeanuRandom.set_default_random_seed(1)
_, ax = plt.subplots(3, 1, squeeze=False)
sample(net=net, sample_from=net.get_latent_vertices(), draws=5, plot=True, ax=ax)
reorder_subplots(ax)
assert len(ax) == 3
assert all(len(ax[i][0].get_lines()) == 1 for i in range(3))
assert all(len(ax[i][0].get_lines()[0].get_ydata()) == 5 for i in range(3))
def test_it_throws_if_you_pass_in_a_proposal_listener_but_you_didnt_specify_the_proposal_type(
net: BayesNet) -> None:
with pytest.raises(TypeError) as excinfo:
sample(net=net,
sample_from=net.get_latent_vertices(),
proposal_listeners=[AcceptanceRateTracker()],
drop=3)
assert str(
excinfo.value
) == "If you pass in proposal_listeners you must also specify proposal_distribution"
def test_it_throws_if_you_pass_in_a_proposal_listener_but_the_algo_isnt_metropolis(
net: BayesNet) -> None:
with pytest.raises(TypeError) as excinfo:
sample(net=net,
sample_from=net.get_latent_vertices(),
algo="hamiltonian",
proposal_listeners=[AcceptanceRateTracker()],
drop=3)
assert str(
excinfo.value
) == "Only Metropolis Hastings supports the proposal_listeners parameter"
def test_sampling_returns_multi_indexed_dict_of_list_of_scalars_for_tensor_in_sample_from(
algo: Callable[[BayesNet], PosteriorSamplingAlgorithm],
tensor_net: BayesNet) -> None:
draws = 5
sample_from = list(tensor_net.iter_latent_vertices())
samples = sample(net=tensor_net,
sample_from=sample_from,
sampling_algorithm=algo(tensor_net),
draws=draws)
assert type(samples) == dict
__assert_valid_samples(draws, samples)
def test_it_throws_if_you_pass_in_a_proposal_distribution_but_the_algo_isnt_metropolis(
net: BayesNet) -> None:
with pytest.raises(TypeError) as excinfo:
sample(net=net,
sample_from=net.get_latent_vertices(),
algo="hamiltonian",
proposal_distribution="prior",
drop=3)
assert str(
excinfo.value
) == "Only Metropolis Hastings supports the proposal_distribution parameter"
def test_can_track_acceptance_rate_when_iterating(net: BayesNet) -> None:
acceptance_rate_tracker = AcceptanceRateTracker()
latents = list(net.get_latent_vertices())
algo = MetropolisHastingsSampler(proposal_distribution='prior', proposal_listeners=[acceptance_rate_tracker])
samples = generate_samples(net=net, sample_from=latents, sampling_algorithm=algo, drop=3)
draws = 100
for _ in islice(samples, draws):
for latent in latents:
rate = acceptance_rate_tracker.get_acceptance_rate(latent)
assert 0 <= rate <= 1
def test_sampling_returns_dict_of_list_of_ndarrays_for_vertices_in_sample_from(
algo: Callable[[BayesNet], PosteriorSamplingAlgorithm],
net: BayesNet) -> None:
draws = 5
sample_from = list(net.iter_latent_vertices())
samples = sample(net=net,
sample_from=sample_from,
sampling_algorithm=algo(net),
draws=draws)
assert len(samples) == len(sample_from)
assert type(samples) == dict
__assert_valid_samples(draws, samples)
def test_sample_dict_can_be_loaded_in_to_dataframe(net: BayesNet) -> None:
sample_from = list(net.iter_latent_vertices())
vertex_labels = [vertex.get_label() for vertex in sample_from]
samples = sample(net=net, sample_from=sample_from, draws=5)
df = pd.DataFrame(samples)
for column in df:
header = df[column].name
vertex_label = header
assert vertex_label in vertex_labels
assert len(df[column]) == 5
assert type(df[column][0]) == np.float64
def test_can_iter_through_samples(algo: Callable[[BayesNet],
PosteriorSamplingAlgorithm],
net: BayesNet) -> None:
draws = 10
samples = generate_samples(net=net,
sample_from=net.iter_latent_vertices(),
sampling_algorithm=algo(net),
down_sample_interval=1)
count = 0
for sample in islice(samples, draws):
count += 1
assert count == draws
def test_can_get_acceptance_rates(net: BayesNet) -> None:
acceptance_rate_tracker = AcceptanceRateTracker()
latents = list(net.get_latent_vertices())
samples = sample(net=net,
sample_from=latents,
proposal_distribution='prior',
proposal_listeners=[acceptance_rate_tracker],
drop=3)
for latent in latents:
rate = acceptance_rate_tracker.get_acceptance_rate(latent)
assert 0 <= rate <= 1
def test_can_specify_nuts_params(net: BayesNet) -> None:
algo = NUTSSampler(adapt_count=1000,
target_acceptance_prob=0.65,
adapt_step_size_enabled=True,
adapt_potential_enabled=True,
initial_step_size=0.1,
max_tree_height=10)
samples = sample(net,
list(net.iter_latent_vertices()),
algo,
draws=500,
drop=100)
def test_iter_with_live_plot(net: BayesNet) -> None:
KeanuRandom.set_default_random_seed(1)
_, ax = plt.subplots(3, 1, squeeze=False)
samples = generate_samples(net=net, sample_from=net.get_latent_vertices(), live_plot=True, refresh_every=5, ax=ax)
for sample in islice(samples, 5):
pass
reorder_subplots(ax)
assert len(ax) == 3
assert all(len(ax[i][0].get_lines()) == 1 for i in range(3))
assert all(len(ax[i][0].get_lines()[0].get_ydata() == 5) for i in range(3))
