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
def test_minibatch_sensible_reassign_partial_fit():
zeroed_X, true_labels = make_blobs(n_samples=n_samples,
centers=5,
cluster_std=1.,
random_state=42)
zeroed_X[::2, :] = 0
mb_k_means = MiniBatchKMeans(n_clusters=20, random_state=42, init="random")
for i in range(100):
mb_k_means.partial_fit(zeroed_X)
# there should not be too many exact zero cluster centers
assert mb_k_means.cluster_centers_.any(axis=1).sum() > 10
def test_minibatch_kmeans_partial_fit_int_data():
# Issue GH #14314
X = np.array([[-1], [1]], dtype=np.int)
km = MiniBatchKMeans(n_clusters=2)
km.partial_fit(X)
assert km.cluster_centers_.dtype.kind == "f"
# The online learning part: cycle over the whole dataset 6 times
index = 0
for _ in range(6):
for img in faces.images:
data = extract_patches_2d(img,
patch_size,
max_patches=50,
random_state=rng)
data = np.reshape(data, (len(data), -1))
buffer.append(data)
index += 1
if index % 10 == 0:
data = np.concatenate(buffer, axis=0)
data -= np.mean(data, axis=0)
data /= np.std(data, axis=0)
kmeans.partial_fit(data)
buffer = []
if index % 100 == 0:
print('Partial fit of %4i out of %i' %
(index, 6 * len(faces.images)))
dt = time.time() - t0
print('done in %.2fs.' % dt)
# #############################################################################
# Plot the results
plt.figure(figsize=(4.2, 4))
for i, patch in enumerate(kmeans.cluster_centers_):
plt.subplot(9, 9, i + 1)
plt.imshow(patch.reshape(patch_size),
cmap=plt.cm.gray,