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)
def test_GMMStats():
# Test a GMMStats
# Initializes a GMMStats
n_gaussians = 2
n_features = 3
gs = GMMStats(n_gaussians, n_features)
log_likelihood = -3.0
T = 57
n = np.array([4.37, 5.31], "float64")
sumpx = np.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]], "float64")
sumpxx = np.array([[10.0, 20.0, 30.0], [40.0, 50.0, 60.0]], "float64")
gs.log_likelihood = log_likelihood
gs.t = T
gs.n = n
gs.sum_px = sumpx
gs.sum_pxx = sumpxx
np.testing.assert_equal(gs.log_likelihood, log_likelihood)
np.testing.assert_equal(gs.t, T)
np.testing.assert_equal(gs.n, n)
np.testing.assert_equal(gs.sum_px, sumpx)
np.testing.assert_equal(gs.sum_pxx, sumpxx)
np.testing.assert_equal(gs.shape, (n_gaussians, n_features))
# Saves and reads from file using `from_hdf5`
filename = str(tempfile.mkstemp(".hdf5")[1])
gs.save(HDF5File(filename, "w"))
gs_loaded = GMMStats.from_hdf5(HDF5File(filename, "r"))
assert gs == gs_loaded
assert (gs != gs_loaded) is False
assert gs.is_similar_to(gs_loaded)
assert type(gs_loaded.n_gaussians) is np.int64
assert type(gs_loaded.n_features) is np.int64
assert type(gs_loaded.log_likelihood) is np.float64
# Saves and load from file using `load`
filename = str(tempfile.mkstemp(".hdf5")[1])
gs.save(hdf5=HDF5File(filename, "w"))
gs_loaded = GMMStats(n_gaussians, n_features)
gs_loaded.load(HDF5File(filename, "r"))
assert gs == gs_loaded
assert (gs != gs_loaded) is False
assert gs.is_similar_to(gs_loaded)
# Makes them different
gs_loaded.t = 58
assert (gs == gs_loaded) is False
assert gs != gs_loaded
assert not (gs.is_similar_to(gs_loaded))
# Accumulates from another GMMStats
gs2 = GMMStats(n_gaussians, n_features)
gs2.log_likelihood = log_likelihood
gs2.t = T
gs2.n = n.copy()
gs2.sum_px = sumpx.copy()
gs2.sum_pxx = sumpxx.copy()
gs2 += gs
np.testing.assert_equal(gs2.log_likelihood, 2 * log_likelihood)
np.testing.assert_equal(gs2.t, 2 * T)
np.testing.assert_almost_equal(gs2.n, 2 * n, decimal=8)
np.testing.assert_almost_equal(gs2.sum_px, 2 * sumpx, decimal=8)
np.testing.assert_almost_equal(gs2.sum_pxx, 2 * sumpxx, decimal=8)
# Re-init and checks for zeros
gs_loaded.init_fields()
np.testing.assert_equal(gs_loaded.log_likelihood, 0)
np.testing.assert_equal(gs_loaded.t, 0)
np.testing.assert_equal(gs_loaded.n, np.zeros((n_gaussians, )))
np.testing.assert_equal(gs_loaded.sum_px,
np.zeros((n_gaussians, n_features)))
np.testing.assert_equal(gs_loaded.sum_pxx,
np.zeros((n_gaussians, n_features)))
# Resize and checks size
assert gs_loaded.shape == (n_gaussians, n_features)
gs_loaded.resize(4, 5)
assert gs_loaded.shape == (4, 5)
assert gs_loaded.sum_px.shape[0] == 4
assert gs_loaded.sum_px.shape[1] == 5
# Clean-up
os.unlink(filename)