def test_shuffle_with_random_state():
gm_1 = GaussianMixture(
20,
centers,
covariances,
class_probs,
random_state=42,
shuffle=True,
shuffle_random_state=42,
)
gm_1.sample_views("poly")
Xs_1, y_1 = gm_1.get_Xy()
gm_2 = GaussianMixture(
20,
centers,
covariances,
class_probs,
random_state=42,
shuffle=True,
shuffle_random_state=42,
)
gm_2.sample_views("poly")
Xs_2, y_2 = gm_2.get_Xy()
for view1, view2 in zip(Xs_1, Xs_2):
assert np.allclose(view1, view2)
assert np.allclose(y_1, y_2)
def test_random_state():
gm_1 = GaussianMixture(mu, sigma, 10, class_probs, random_state=42)
gm_1.sample_views('poly')
Xs_1, y_1 = gm_1.get_Xy()
gm_2 = GaussianMixture(mu, sigma, 10, class_probs, random_state=42)
gm_2.sample_views('poly')
Xs_2, y_2 = gm_2.get_Xy()
for view1, view2 in zip(Xs_1, Xs_2):
assert np.allclose(view1, view2)
assert np.allclose(y_1, y_2)
def test_noise_dims_not_same_but_reproducible():
gm_1 = GaussianMixture(mu, sigma, 20, class_probs, random_state=42)
gm_1.sample_views('poly', n_noise=2)
Xs_2, y_2 = gm_1.get_Xy()
view1_noise, view2_noise = Xs_2[0][:, -2:], Xs_2[1][:, -2:]
assert not np.allclose(view1_noise, view2_noise)
gm_2 = GaussianMixture(mu, sigma, 20, class_probs, random_state=42)
gm_2.sample_views('poly', n_noise=2)
Xs_2, y_2 = gm_1.get_Xy()
view1_noise2, view2_noise2 = Xs_2[0][:, -2:], Xs_2[1][:, -2:]
assert np.allclose(view1_noise, view1_noise2)
assert np.allclose(view2_noise, view2_noise2)
def test_noise_dims_not_same_but_reproducible():
gm_1 = GaussianMixture(20,
centers,
covariances,
class_probs,
random_state=42)
gm_1.sample_views("poly", n_noise=2)
Xs_2, _ = gm_1.get_Xy()
view1_noise, view2_noise = Xs_2[0][:, -2:], Xs_2[1][:, -2:]
assert not np.allclose(view1_noise, view2_noise)
gm_2 = GaussianMixture(20,
centers,
covariances,
class_probs,
random_state=42)
gm_2.sample_views("poly", n_noise=2)
Xs_2, _ = gm_1.get_Xy()
view1_noise2, view2_noise2 = Xs_2[0][:, -2:], Xs_2[1][:, -2:]
assert np.allclose(view1_noise, view1_noise2)
assert np.allclose(view2_noise, view2_noise2)
def test_shuffle():
np.random.seed(42)
gm_1 = GaussianMixture(mu,
sigma,
20,
class_probs,
random_state=42,
shuffle=True,
shuffle_random_state=42)
gm_1.sample_views('poly')
Xs_1, y_1 = gm_1.get_Xy()
np.random.seed(30)
gm_2 = GaussianMixture(mu,
sigma,
20,
class_probs,
random_state=42,
shuffle=True,
shuffle_random_state=10)
gm_2.sample_views('poly')
Xs_2, y_2 = gm_2.get_Xy()
for view1, view2 in zip(Xs_1, Xs_2):
assert not np.allclose(view1, view2)
assert not np.allclose(y_1, y_2)
def test_no_sample():
gaussm = GaussianMixture(mu, sigma, n, class_probs)
with pytest.raises(NameError):
gaussm.get_Xy()
# Latent variables are sampled from two multivariate Gaussians with equal
# prior probability. Then a polynomial transformation is applied and noise is
# added independently to both the transformed and untransformed latents.
n_samples = 100
centers = [[0, 1], [0, -1]]
covariances = [np.eye(2), np.eye(2)]
gm = GaussianMixture(n_samples,
centers,
covariances,
random_state=42,
shuffle=True,
shuffle_random_state=42)
gm = gm.sample_views(transform='poly', n_noise=2)
latent, y = gm.get_Xy(latents=True)
Xs, _ = gm.get_Xy(latents=False)
# The latent data is plotted against itself to reveal the underlying
# distribtution.
crossviews_plot([latent, latent],
labels=y,
title='Latent Variable',
equal_axes=True)
# The noisy latent variable (view 1) is plotted against the transformed latent
# variable (view 2), an example of a dataset with two views.
crossviews_plot(Xs,
labels=y,
def test_no_sample():
gaussm = GaussianMixture(n_samples, centers, covariances, class_probs)
with pytest.raises(NameError):
gaussm.get_Xy()
gm_train = GaussianMixture(n_samples, centers, covariances)
# Test
gm_test = GaussianMixture(n_samples, centers, covariances)
# Make 2 views
n_noise = 2
transforms = ['linear', 'poly', 'sin']
Xs_train = []
Xs_test = []
for transform in transforms:
gm_train.sample_views(transform=transform, n_noise=n_noise)
gm_test.sample_views(transform=transform, n_noise=n_noise)
Xs_train.append(gm_train.get_Xy()[0])
Xs_test.append(gm_test.get_Xy()[0])
# Plotting parameters
labels = gm_test.latent_[:, 0]
cmap = matplotlib.colors.ListedColormap(
sns.diverging_palette(240, 10, n=len(labels), center='light').as_hex())
cmap = 'coolwarm'
method_labels = \
['Raw Views', 'Linear KCCA', 'Polynomial KCCA', 'Gaussian KCCA', 'DCCA']
transform_labels = \
['Linear Transform', 'Polynomial Transform', 'Sinusoidal Transform']
input_size1, input_size2 = Xs_train[0][0].shape[1], Xs_train[0][1].shape[1]
outdim_size = min(Xs_train[0][0].shape[1], 2)
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
#
# Latent variables are sampled from two multivariate Gaussians with equal
# prior probability. Then a polynomial transformation is applied and noise is
# added independently to both the transformed and untransformed latents.
n_samples = 2000
means = [[0, 1], [0, -1]]
covariances = [np.eye(2), np.eye(2)]
gm = GaussianMixture(n_samples,
means,
covariances,
random_state=42,
shuffle=True,
shuffle_random_state=42)
latent, y = gm.get_Xy(latents=True)
# Plot latent data against itself to reveal the underlying distribtution.
crossviews_plot([latent, latent],
labels=y,
title='Latent Variable',
equal_axes=True)
# Split data into train and test sets
Xs, y = gm.sample_views(transform='poly', n_noise=2).get_Xy()
Xs_train, Xs_test, y_train, y_test = train_test_split(Xs,
y,
test_size=0.3,
random_state=42)
# Plot the testing data after polynomial transformation