def test_kcenters_8():
X = np.random.RandomState(1).randn(100, 2)
for dtype in [np.float64, np.float32]:
X = X.astype(dtype)
m1 = KCenters(n_clusters=10, random_state=0, opt=True).fit([X])
m2 = KCenters(n_clusters=10, random_state=0, opt=False).fit([X])
eq(m1.cluster_centers_, m2.cluster_centers_)
eq(m1.distances_[0], m2.distances_[0])
eq(m1.labels_[0], m2.labels_[0])
assert np.all(np.logical_not(np.isnan(m1.distances_[0])))
eq(m1.predict([X])[0], m2.predict([X])[0])
eq(m1.predict([X])[0], m1.labels_[0])
def test_kcenters_3():
# test for predict using euclidean distance
model = KCenters(n_clusters=10)
data = np.random.randn(100, 2)
labels1 = model.fit_predict([data])
labels2 = model.predict([data])
eq(labels1[0], labels2[0])
all_pairs = scipy.spatial.distance.cdist(data, model.cluster_centers_)
eq(labels2[0], np.argmin(all_pairs, axis=1))
def test_kcenters_4():
# test for predict() using non-euclidean distance. because of the
# way the code is structructured, this takes a different path
model = KCenters(n_clusters=10, metric='cityblock')
data = np.random.randn(100, 2)
labels1 = model.fit_predict([data])
labels2 = model.predict([data])
eq(labels1[0], labels2[0])
all_pairs = scipy.spatial.distance.cdist(data, model.cluster_centers_, metric='cityblock')
eq(labels2[0], np.argmin(all_pairs, axis=1))
