def test_predict_minibatch_dense_sparse(init):
# check that models trained on sparse input also works for dense input at
# predict time
mb_k_means = MiniBatchKMeans(n_clusters=n_clusters,
init=init,
n_init=10,
random_state=0).fit(X_csr)
assert_array_equal(mb_k_means.predict(X), mb_k_means.labels_)
def test_mini_batch_k_means_random_init_partial_fit():
km = MiniBatchKMeans(n_clusters=n_clusters, init="random", random_state=42)
# use the partial_fit API for online learning
for X_minibatch in np.array_split(X, 10):
km.partial_fit(X_minibatch)
# compute the labeling on the complete dataset
labels = km.predict(X)
assert v_measure_score(true_labels, labels) == 1.0