def test_bayesian_mixture_predict_predict_proba():
# this is the same test as test_gaussian_mixture_predict_predict_proba()
rng = np.random.RandomState(0)
rand_data = RandomData(rng)
for prior_type in PRIOR_TYPE:
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
Y = rand_data.Y
bgmm = BayesianGaussianMixture(
n_components=rand_data.n_components,
random_state=rng,
weight_concentration_prior_type=prior_type,
covariance_type=covar_type)
# Check a warning message arrive if we don't do fit
assert_raise_message(
NotFittedError, "This BayesianGaussianMixture instance"
" is not fitted yet. Call 'fit' with "
"appropriate arguments before using "
"this estimator.", bgmm.predict, X)
bgmm.fit(X)
Y_pred = bgmm.predict(X)
Y_pred_proba = bgmm.predict_proba(X).argmax(axis=1)
assert_array_equal(Y_pred, Y_pred_proba)
assert adjusted_rand_score(Y, Y_pred) >= .95
def test_invariant_translation():
# We check here that adding a constant in the data change correctly the
# parameters of the mixture
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=100)
n_components = 2 * rand_data.n_components
for prior_type in PRIOR_TYPE:
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
bgmm1 = BayesianGaussianMixture(
weight_concentration_prior_type=prior_type,
n_components=n_components,
max_iter=100,
random_state=0,
tol=1e-3,
reg_covar=0).fit(X)
bgmm2 = BayesianGaussianMixture(
weight_concentration_prior_type=prior_type,
n_components=n_components,
max_iter=100,
random_state=0,
tol=1e-3,
reg_covar=0).fit(X + 100)
assert_almost_equal(bgmm1.means_, bgmm2.means_ - 100)
assert_almost_equal(bgmm1.weights_, bgmm2.weights_)
assert_almost_equal(bgmm1.covariances_, bgmm2.covariances_)
def test_check_covariance_precision():
# We check that the dot product of the covariance and the precision
# matrices is identity.
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=7)
n_components, n_features = 2 * rand_data.n_components, 2
# Computation of the full_covariance
bgmm = BayesianGaussianMixture(n_components=n_components,
max_iter=100,
random_state=rng,
tol=1e-3,
reg_covar=0)
for covar_type in COVARIANCE_TYPE:
bgmm.covariance_type = covar_type
bgmm.fit(rand_data.X[covar_type])
if covar_type == 'full':
for covar, precision in zip(bgmm.covariances_, bgmm.precisions_):
assert_almost_equal(np.dot(covar, precision),
np.eye(n_features))
elif covar_type == 'tied':
assert_almost_equal(np.dot(bgmm.covariances_, bgmm.precisions_),
np.eye(n_features))
elif covar_type == 'diag':
assert_almost_equal(bgmm.covariances_ * bgmm.precisions_,
np.ones((n_components, n_features)))
else:
assert_almost_equal(bgmm.covariances_ * bgmm.precisions_,
np.ones(n_components))
def test_monotonic_likelihood():
# We check that each step of the each step of variational inference without
# regularization improve monotonically the training set of the bound
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=20)
n_components = rand_data.n_components
for prior_type in PRIOR_TYPE:
for covar_type in COVARIANCE_TYPE:
X = rand_data.X[covar_type]
bgmm = BayesianGaussianMixture(
weight_concentration_prior_type=prior_type,
n_components=2 * n_components,
covariance_type=covar_type,
warm_start=True,
max_iter=1,
random_state=rng,
tol=1e-3)
current_lower_bound = -np.infty
# Do one training iteration at a time so we can make sure that the
# training log likelihood increases after each iteration.
for _ in range(600):
prev_lower_bound = current_lower_bound
current_lower_bound = bgmm.fit(X).lower_bound_
assert current_lower_bound >= prev_lower_bound
if bgmm.converged_:
break
assert (bgmm.converged_)
def test_compare_covar_type():
# We can compare the 'full' precision with the other cov_type if we apply
# 1 iter of the M-step (done during _initialize_parameters).
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=7)
X = rand_data.X['full']
n_components = rand_data.n_components
for prior_type in PRIOR_TYPE:
# Computation of the full_covariance
bgmm = BayesianGaussianMixture(
weight_concentration_prior_type=prior_type,
n_components=2 * n_components, covariance_type='full',
max_iter=1, random_state=0, tol=1e-7)
bgmm._check_initial_parameters(X)
bgmm._initialize_parameters(X, np.random.RandomState(0))
full_covariances = (
bgmm.covariances_ *
bgmm.degrees_of_freedom_[:, np.newaxis, np.newaxis])
# Check tied_covariance = mean(full_covariances, 0)
bgmm = BayesianGaussianMixture(
weight_concentration_prior_type=prior_type,
n_components=2 * n_components, covariance_type='tied',
max_iter=1, random_state=0, tol=1e-7)
bgmm._check_initial_parameters(X)
bgmm._initialize_parameters(X, np.random.RandomState(0))
tied_covariance = bgmm.covariances_ * bgmm.degrees_of_freedom_
assert_almost_equal(tied_covariance, np.mean(full_covariances, 0))
# Check diag_covariance = diag(full_covariances)
bgmm = BayesianGaussianMixture(
weight_concentration_prior_type=prior_type,
n_components=2 * n_components, covariance_type='diag',
max_iter=1, random_state=0, tol=1e-7)
bgmm._check_initial_parameters(X)
bgmm._initialize_parameters(X, np.random.RandomState(0))
diag_covariances = (bgmm.covariances_ *
bgmm.degrees_of_freedom_[:, np.newaxis])
assert_almost_equal(diag_covariances,
np.array([np.diag(cov)
for cov in full_covariances]))
# Check spherical_covariance = np.mean(diag_covariances, 0)
bgmm = BayesianGaussianMixture(
weight_concentration_prior_type=prior_type,
n_components=2 * n_components, covariance_type='spherical',
max_iter=1, random_state=0, tol=1e-7)
bgmm._check_initial_parameters(X)
bgmm._initialize_parameters(X, np.random.RandomState(0))
spherical_covariances = bgmm.covariances_ * bgmm.degrees_of_freedom_
assert_almost_equal(
spherical_covariances, np.mean(diag_covariances, 1))
def test_bayesian_mixture_fit_predict(seed, max_iter, tol):
rng = np.random.RandomState(seed)
rand_data = RandomData(rng, n_samples=50, scale=7)
n_components = 2 * rand_data.n_components
for covar_type in COVARIANCE_TYPE:
bgmm1 = BayesianGaussianMixture(n_components=n_components,
max_iter=max_iter, random_state=rng,
tol=tol, reg_covar=0)
bgmm1.covariance_type = covar_type
bgmm2 = copy.deepcopy(bgmm1)
X = rand_data.X[covar_type]
Y_pred1 = bgmm1.fit(X).predict(X)
Y_pred2 = bgmm2.fit_predict(X)
assert_array_equal(Y_pred1, Y_pred2)