def test_kmeans_constraint_weights_bigger(self):
n_samples = 100
data = make_blobs(n_samples=n_samples,
n_features=2,
centers=2,
cluster_std=1.0,
center_box=(-10.0, 0.0),
shuffle=True,
random_state=2)
X1 = data[0]
data = make_blobs(n_samples=n_samples // 2,
n_features=2,
centers=2,
cluster_std=1.0,
center_box=(0.0, 10.0),
shuffle=True,
random_state=2)
X2 = data[0]
X = numpy.vstack([X1, X2])
km = ConstraintKMeans(n_clusters=4, strategy='weights', history=True)
km.fit(X)
cl = km.predict(X)
self.assertEqual(cl.shape, (X.shape[0], ))
cls = km.cluster_centers_iter_
self.assertEqual(len(cls.shape), 3)
edges = km.cluster_edges()
self.assertIsInstance(edges, set)
self.assertEqual(len(edges), 5)
self.assertIsInstance(list(edges)[0], tuple)
def test_kmeans_constraint_weights(self):
mat = numpy.array([[0, 0], [0.2, 0.2], [-0.1, -0.1], [1, 1]])
km = ConstraintKMeans(n_clusters=2,
verbose=10,
kmeans0=False,
random_state=1,
strategy='weights')
buf = BufferedPrint()
km.fit(mat, fLOG=buf.fprint)
km = ConstraintKMeans(n_clusters=2,
verbose=5,
kmeans0=False,
random_state=1,
strategy='weights')
km.fit(mat, fLOG=buf.fprint)
self.assertEqual(km.cluster_centers_.shape, (2, 2))
self.assertLesser(km.inertia_, 4.55)
self.assertEqual(km.cluster_centers_,
numpy.array([[0.6, 0.6], [-0.05, -0.05]]))
self.assertEqual(km.labels_, numpy.array([1, 0, 1, 0]))
pred = km.predict(mat)
self.assertEqual(pred, numpy.array([1, 1, 1, 0]))
dist = km.transform(mat)
self.assertEqual(dist.shape, (4, 2))
score = km.score(mat)
self.assertEqual(score.shape, (4, ))
self.assertIn("CKMeans", str(buf))
def test_kmeans_constraint_blobs20(self):
data = make_blobs(n_samples=20,
n_features=2,
centers=2,
cluster_std=1.0,
center_box=(-10.0, 0.0),
shuffle=True,
random_state=0)
X1 = data[0]
data = make_blobs(n_samples=10,
n_features=2,
centers=2,
cluster_std=1.0,
center_box=(0.0, 10.0),
shuffle=True,
random_state=0)
X2 = data[0]
X = numpy.vstack([X1, X2])
km = ConstraintKMeans(n_clusters=4,
verbose=0,
kmeans0=False,
random_state=2,
strategy='gain',
balanced_predictions=True,
history=True)
km.fit(X)
pred = km.predict(X)
diff = numpy.abs(km.labels_ - pred).sum()
self.assertLesser(diff, 6)
cls = km.cluster_centers_iter_
self.assertEqual(len(cls.shape), 3)
def test_kmeans_constraint_gain(self):
mat = numpy.array([[0, 0], [0.2, 0.2], [-0.1, -0.1], [1, 1]])
km = ConstraintKMeans(n_clusters=2, verbose=0, kmeans0=False,
random_state=1, strategy='gain')
km.fit(mat)
self.assertEqual(km.cluster_centers_.shape, (2, 2))
self.assertEqualFloat(km.inertia_, 0.455)
self.assertEqual(km.cluster_centers_, numpy.array(
[[0.6, 0.6], [-0.05, -0.05]]))
self.assertEqual(km.labels_, numpy.array([1, 0, 1, 0]))
pred = km.predict(mat)
self.assertEqual(pred, numpy.array([1, 1, 1, 0]))
def test_kmeans_constraint_gain3(self):
mat = numpy.array([[0, 0], [0.2, 0.2], [-0.1, -0.1],
[1, 1], [1.1, 0.9], [-1.1, 1.]])
# Choose random_state=2 to get the labels [1 1 0 2 2 0].
# This configuration can only be modified with a permutation
# of 3 elements.
km = ConstraintKMeans(n_clusters=3, verbose=0, kmeans0=False,
random_state=1, strategy='gain',
balanced_predictions=True)
km.fit(mat)
self.assertEqual(km.cluster_centers_.shape, (3, 2))
lab = km.labels_
self.assertEqual(lab[1], lab[2])
self.assertEqual(lab[0], lab[5])
self.assertEqual(lab[3], lab[4])
pred = km.predict(mat)
self.assertEqualArray(pred, lab)
def test_kmeans_constraint_sparse(self):
mat = numpy.array([[0, 0], [0.2, 0.2], [-0.1, -0.1], [1, 1]])
mat = scipy.sparse.csr_matrix(mat)
km = ConstraintKMeans(n_clusters=2, verbose=0, strategy='distance')
km.fit(mat)
self.assertEqual(km.cluster_centers_.shape, (2, 2))
self.assertEqualFloat(km.inertia_, 0.455)
if km.labels_[0] == 0:
self.assertEqual(km.labels_, numpy.array([0, 1, 0, 1]))
self.assertEqual(km.cluster_centers_, numpy.array(
[[-0.05, -0.05], [0.6, 0.6]]))
else:
self.assertEqual(km.labels_, numpy.array([1, 0, 1, 0]))
self.assertEqual(km.cluster_centers_, numpy.array(
[[0.6, 0.6], [-0.05, -0.05]]))
pred = km.predict(mat)
if km.labels_[0] == 0:
self.assertEqual(pred, numpy.array([0, 0, 0, 1]))
else:
self.assertEqual(pred, numpy.array([1, 1, 1, 0]))
km1 = ConstraintKMeans(n_clusters=4,
strategy='gain',
balanced_predictions=True)
km1.fit(X)
km2 = ConstraintKMeans(n_clusters=4,
strategy='distance',
balanced_predictions=True)
km2.fit(X)
##########################
# This algorithm tries to exchange points
# between clusters.
cl1 = km1.predict(X)
hist1 = Counter(cl1)
cl2 = km2.predict(X)
hist2 = Counter(cl2)
fig, ax = plt.subplots(1, 2, figsize=(10, 4))
for i in range(0, max(cl1) + 1):
ax[0].plot(X[cl1 == i, 0],
X[cl1 == i, 1],
colors[i] + '.',
label='cl%d' % i)
ax[1].plot(X[cl2 == i, 0],
X[cl2 == i, 1],
colors[i] + '.',
label='cl%d' % i)
