def test_minibatch_sensible_reassign_fit():
# check if identical initial clusters are reassigned
# also a regression test for when there are more desired reassignments than
# samples.
zeroed_X, true_labels = make_blobs(n_samples=100,
centers=5,
cluster_std=1.,
random_state=42)
zeroed_X[::2, :] = 0
mb_k_means = MiniBatchKMeans(n_clusters=20,
batch_size=10,
random_state=42,
init="random")
mb_k_means.fit(zeroed_X)
# there should not be too many exact zero cluster centers
assert mb_k_means.cluster_centers_.any(axis=1).sum() > 10
# do the same with batch-size > X.shape[0] (regression test)
mb_k_means = MiniBatchKMeans(n_clusters=20,
batch_size=201,
random_state=42,
init="random")
mb_k_means.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_k_means_init(data, init):
mb_k_means = MiniBatchKMeans(init=init,
n_clusters=n_clusters,
random_state=42,
n_init=10)
mb_k_means.fit(data)
_check_fitted_model(mb_k_means)
def test_mb_kmeans_verbose():
mb_k_means = MiniBatchKMeans(init="k-means++",
n_clusters=n_clusters,
random_state=42,
verbose=1)
old_stdout = sys.stdout
sys.stdout = StringIO()
try:
mb_k_means.fit(X)
finally:
sys.stdout = old_stdout
def test_minibatch_reassign():
# Give a perfect initialization, but a large reassignment_ratio,
# as a result all the centers should be reassigned and the model
# should no longer be good
sample_weight = np.ones(X.shape[0], dtype=X.dtype)
for this_X in (X, X_csr):
mb_k_means = MiniBatchKMeans(n_clusters=n_clusters,
batch_size=100,
random_state=42)
mb_k_means.fit(this_X)
score_before = mb_k_means.score(this_X)
try:
old_stdout = sys.stdout
sys.stdout = StringIO()
# Turn on verbosity to smoke test the display code
_mini_batch_step(this_X,
sample_weight, (X**2).sum(axis=1),
mb_k_means.cluster_centers_,
mb_k_means.counts_,
np.zeros(X.shape[1], np.double),
False,
distances=np.zeros(X.shape[0]),
random_reassign=True,
random_state=42,
reassignment_ratio=1,
verbose=True)
finally:
sys.stdout = old_stdout
assert score_before > mb_k_means.score(this_X)
# Give a perfect initialization, with a small reassignment_ratio,
# no center should be reassigned
for this_X in (X, X_csr):
mb_k_means = MiniBatchKMeans(n_clusters=n_clusters,
batch_size=100,
init=centers.copy(),
random_state=42,
n_init=1)
mb_k_means.fit(this_X)
clusters_before = mb_k_means.cluster_centers_
# Turn on verbosity to smoke test the display code
_mini_batch_step(this_X,
sample_weight, (X**2).sum(axis=1),
mb_k_means.cluster_centers_,
mb_k_means.counts_,
np.zeros(X.shape[1], np.double),
False,
distances=np.zeros(X.shape[0]),
random_reassign=True,
random_state=42,
reassignment_ratio=1e-15)
assert_array_almost_equal(clusters_before, mb_k_means.cluster_centers_)
ax.scatter(X[mask, 0], X[mask, 1],
c='w', edgecolor=col, marker='.', alpha=0.5)
if birch_model.n_clusters is None:
ax.scatter(this_centroid[0], this_centroid[1], marker='+',
c='k', s=25)
ax.set_ylim([-25, 25])
ax.set_xlim([-25, 25])
ax.set_autoscaley_on(False)
ax.set_title('Birch %s' % info)
# Compute clustering with MiniBatchKMeans.
mbk = MiniBatchKMeans(init='k-means++', n_clusters=100, batch_size=100,
n_init=10, max_no_improvement=10, verbose=0,
random_state=0)
t0 = time()
mbk.fit(X)
t_mini_batch = time() - t0
print("Time taken to run MiniBatchKMeans %0.2f seconds" % t_mini_batch)
mbk_means_labels_unique = np.unique(mbk.labels_)
ax = fig.add_subplot(1, 3, 3)
for this_centroid, k, col in zip(mbk.cluster_centers_,
range(n_clusters), colors_):
mask = mbk.labels_ == k
ax.scatter(X[mask, 0], X[mask, 1], marker='.',
c='w', edgecolor=col, alpha=0.5)
ax.scatter(this_centroid[0], this_centroid[1], marker='+',
c='k', s=25)
ax.set_xlim([-25, 25])
ax.set_ylim([-25, 25])
ax.set_title("MiniBatchKMeans")
km = MiniBatchKMeans(n_clusters=true_k,
init='k-means++',
n_init=1,
init_size=1000,
batch_size=1000,
verbose=opts.verbose)
else:
km = KMeans(n_clusters=true_k,
init='k-means++',
max_iter=100,
n_init=1,
verbose=opts.verbose)
print("Clustering sparse data with %s" % km)
t0 = time()
km.fit(X)
print("done in %0.3fs" % (time() - t0))
print()
print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels, km.labels_))
print("Completeness: %0.3f" % metrics.completeness_score(labels, km.labels_))
print("V-measure: %0.3f" % metrics.v_measure_score(labels, km.labels_))
print("Adjusted Rand-Index: %.3f" %
metrics.adjusted_rand_score(labels, km.labels_))
print("Silhouette Coefficient: %0.3f" %
metrics.silhouette_score(X, km.labels_, sample_size=1000))
print()
if not opts.use_hashing:
print("Top terms per cluster:")