def test_map_transformer():
post_data = np.array([[1, 2, 2], [2, 1, 2], [7, 8, 9], [7, 7, 8],
[7, 9, 7]])
test_data = np.array([[1, 1, 1], [1, 1, 2], [8, 9, 9], [8, 8, 8]])
n_gaussians = 2
n_features = 3
prior_machine = GMMMachine(n_gaussians)
prior_machine.means = np.array([[2, 2, 2], [8, 8, 8]])
prior_machine.variances = np.ones_like(prior_machine.means)
prior_machine.weights = np.array([0.5, 0.5])
machine = GMMMachine(
n_gaussians,
trainer="map",
ubm=prior_machine,
update_means=True,
update_variances=True,
update_weights=True,
)
for transform in (to_numpy, to_dask_array):
post_data = transform(post_data)
machine = machine.fit(post_data)
expected_means = np.array([[1.83333333, 1.83333333, 2.0],
[7.57142857, 8, 8]])
np.testing.assert_almost_equal(machine.means, expected_means)
eps = np.finfo(float).eps
expected_vars = np.array([[eps, eps, eps], [eps, eps, eps]])
np.testing.assert_almost_equal(machine.variances, expected_vars)
expected_weights = np.array([0.46226415, 0.53773585])
np.testing.assert_almost_equal(machine.weights, expected_weights)
stats = machine.acc_stats(test_data)
expected_stats = GMMStats(n_gaussians, n_features)
expected_stats.init_fields(
log_likelihood=-1.3837590691807108e16,
t=test_data.shape[0],
n=np.array([2, 2], dtype=float),
sum_px=np.array([[2, 2, 3], [16, 17, 17]], dtype=float),
sum_pxx=np.array([[2, 2, 5], [128, 145, 145]], dtype=float),
)
assert stats.is_similar_to(expected_stats)
def test_ml_transformer():
data = np.array([[1, 2, 2], [2, 1, 2], [7, 8, 9], [7, 7, 8], [7, 9, 7]])
test_data = np.array([[1, 1, 1], [1, 1, 2], [8, 9, 9], [8, 8, 8]])
n_gaussians = 2
n_features = 3
machine = GMMMachine(
n_gaussians,
update_means=True,
update_variances=True,
update_weights=True,
)
machine.means = np.array([[2, 2, 2], [8, 8, 8]])
machine.variances = np.ones_like(machine.means)
for transform in (to_numpy, to_dask_array):
data = transform(data)
machine = machine.fit(data)
expected_means = np.array([[1.5, 1.5, 2.0], [7.0, 8.0, 8.0]])
np.testing.assert_almost_equal(machine.means, expected_means)
expected_weights = np.array([2 / 5, 3 / 5])
np.testing.assert_almost_equal(machine.weights, expected_weights)
eps = np.finfo(float).eps
expected_variances = np.array([[1 / 4, 1 / 4, eps],
[eps, 2 / 3, 2 / 3]])
np.testing.assert_almost_equal(machine.variances, expected_variances)
stats = machine.acc_stats(test_data)
expected_stats = GMMStats(n_gaussians, n_features)
expected_stats.init_fields(
log_likelihood=-6755399441055685.0,
t=test_data.shape[0],
n=np.array([2, 2], dtype=float),
sum_px=np.array([[2, 2, 3], [16, 17, 17]], dtype=float),
sum_pxx=np.array([[2, 2, 5], [128, 145, 145]], dtype=float),
)
assert stats.is_similar_to(expected_stats)