def test_predict(self):
"""Tests GaussianMixture.predict()"""
x_train = np.array([[1, 2], [-1, -2], [2, 1], [-2, -1]])
ds_x_train = ds.array(x_train, block_size=(2, 2))
gm = GaussianMixture(n_components=2, random_state=666)
gm.fit(ds_x_train)
x_test = np.concatenate((x_train, [[2, 2], [-1, -3]]))
ds_x_test = ds.array(x_test, block_size=(2, 2))
pred = gm.predict(ds_x_test).collect()
self.assertTrue(pred[0] != pred[1])
self.assertTrue(pred[0] == pred[2] == pred[4])
self.assertTrue(pred[1] == pred[3] == pred[5])
def test_fit_predict_vs_fit_and_predict(self):
"""Tests GaussianMixture fit_predict() eq. fit() and predict() for both
converged and not converged runs (and a fixed random_state)."""
x0 = np.random.normal(size=(1000, 2))
x1 = np.random.normal(size=(2000, 2))
x0 = np.dot(x0, [[1.2, 1], [0, 0.5]]) + [0, 3]
x1 = np.dot(x1, [[0.4, 0], [1, 2.5]]) + [1, 0]
x = np.concatenate((x0, x1))
x_ds = ds.array(x, (1500, 2))
# We check the cases with and without convergence
with warnings.catch_warnings():
warnings.simplefilter("ignore", ConvergenceWarning)
for max_iter, converges in ((5, False), (100, True)):
gm1 = GaussianMixture(n_components=2,
max_iter=max_iter,
random_state=0)
gm1.fit(x_ds)
labels1 = gm1.predict(x_ds)
gm2 = GaussianMixture(n_components=2,
max_iter=max_iter,
random_state=0)
labels2 = gm2.fit_predict(x_ds)
self.assertTrue(np.all(labels1.collect() == labels2.collect()))
self.assertEqual(gm1.n_iter, gm2.n_iter)
self.assertEqual(converges, gm1.converged_)
self.assertEqual(gm1.converged_, gm2.converged_)
self.assertEqual(gm1.lower_bound_, gm2.lower_bound_)
gm1.weights_ = compss_wait_on(gm1.weights_)
gm1.means_ = compss_wait_on(gm1.means_)
gm1.covariances_ = compss_wait_on(gm1.covariances_)
gm2.weights_ = compss_wait_on(gm2.weights_)
gm2.means_ = compss_wait_on(gm2.means_)
gm2.covariances_ = compss_wait_on(gm2.covariances_)
self.assertTrue(np.all(gm1.weights_ == gm2.weights_))
self.assertTrue(np.all(gm1.means_ == gm2.means_))
self.assertTrue(np.all(gm1.covariances_ == gm2.covariances_))