def test_transform():
km = KMeans(n_clusters=n_clusters)
km.fit(X)
X_new = km.transform(km.cluster_centers_)
for c in range(n_clusters):
assert_equal(X_new[c, c], 0)
for c2 in range(n_clusters):
if c != c2:
assert_greater(X_new[c, c2], 0)
def test_n_init():
"""Check that increasing the number of init increases the quality"""
n_runs = 5
n_init_range = [1, 5, 10]
score = np.zeros((len(n_init_range), n_runs))
for i, n_init in enumerate(n_init_range):
for j in range(n_runs):
km = KMeans(n_clusters=n_clusters, n_init=n_init, random_state=j).fit(X)
score[i, j] = km.score_
score = score.mean(axis=1)
failure_msg = ("Score %r should be decreasing"
" when n_init is increasing.") % list(score)
for i in range(len(n_init_range) - 1):
assert_true(score[i] >= score[i + 1], failure_msg)
def test_predict():
km = KMeans(n_clusters=n_clusters, random_state=42)
km.fit(X)
# sanity check: predict centroid labels
pred = km.predict(km.cluster_centers_)
assert_array_equal(pred, np.arange(n_clusters))
# sanity check: re-predict labeling for training set samples
pred = km.predict(X)
assert_array_equal(pred, km.labels_)
# re-predict labels for training set using fit_predict
pred = km.fit_predict(X)
assert_array_equal(pred, km.labels_)
def test_k_means_random_init():
km = KMeans(n_clusters=n_clusters, random_state=42)
km.fit(X)
_check_fitted_model(km)
def test_score():
km1 = KMeans(n_clusters=n_clusters, n_init=1, max_iter=1, random_state=42)
s1 = km1.fit(X).score(X)
km2 = KMeans(n_clusters=n_clusters, max_iter=10, random_state=42)
s2 = km2.fit(X).score(X)
assert_greater(s2 + 1, s1)