def test_predict_diff_dimention_data():
bkmeans = BisectingKMeans(max_n_clusters=3)
X = np.array([[1], [2], [3],
[4], [5], [6],
[7], [8], [10]])
bkmeans.fit(X)
with pytest.raises(ValueError):
bkmeans.predict(np.array([[1,2]]))
def test_predict(max_n_clusters):
X, _ = make_blobs(n_samples=500, n_features=10, centers=max_n_clusters, random_state=0)
clf = BisectingKMeans(max_n_clusters)
clf.fit(X)
labels = clf.labels_
# re-predict labels for training set using predict
pred = clf.predict(X)
assert_array_equal(pred, labels)
# predict centroid labels (this should pass once fit is implemented)
pred = clf.predict(clf.centroids)
assert_array_equal(pred, np.arange(clf.max_n_clusters))
def test_three_clusters(bisecting_strategy):
"""Tries to perform bisect k-means for three clusters to check
if splitting data is performed correctly.
"""
# X = np.array([[1, 2], [1, 4], [1, 0],
# [10, 2], [10, 4], [10, 0],
# [10, 6], [10, 8], [10, 10]])
# X[0][1] swapped with X[1][1] intentionally for checking labeling
X = np.array([[1, 2], [10, 4], [1, 0], [10, 2], [1, 4], [10, 0], [10, 6],
[10, 8], [10, 10]])
bisect_means = BisectingKMeans(n_clusters=3,
random_state=0,
bisecting_strategy=bisecting_strategy)
bisect_means.fit(X)
expected_centers = [[10, 2], [10, 8], [1, 2]]
expected_predict = [2, 0]
expected_labels = [2, 0, 2, 0, 2, 0, 1, 1, 1]
assert_allclose(expected_centers, bisect_means.cluster_centers_)
assert_array_equal(expected_predict, bisect_means.predict([[0, 0], [12,
3]]))
assert_array_equal(expected_labels, bisect_means.labels_)
def test_one_cluster():
"""Test single cluster."""
X = np.array([[1, 2], [10, 2], [10, 8]])
bisect_means = BisectingKMeans(n_clusters=1, random_state=0).fit(X)
# All labels from fit or predict should be equal 0
assert all(bisect_means.labels_ == 0)
assert all(bisect_means.predict(X) == 0)
assert_allclose(bisect_means.cluster_centers_,
X.mean(axis=0).reshape(1, -1))
def test_fit_predict(is_sparse):
"""Check if labels from fit(X) method are same as from fit(X).predict(X)."""
rng = np.random.RandomState(0)
X = rng.rand(10, 2)
if is_sparse:
X[X < 0.8] = 0
X = sp.csr_matrix(X)
bisect_means = BisectingKMeans(n_clusters=3, random_state=0)
bisect_means.fit(X)
assert_array_equal(bisect_means.labels_, bisect_means.predict(X))
def test_predict_not_fitted():
bkmeans = BisectingKMeans(max_n_clusters=2)
X = np.zeros([3])
with pytest.raises(NotFittedError):
bkmeans.predict(X)