def test_respawn(self):
m = 100
k = 5
X = np.random.randn(m, 2)
centroids = np.zeros((k, 2))
centroids = pvml.kmeans_train(X, k, init_centroids=centroids)
Z, _ = pvml.kmeans_inference(X, centroids)
self.assertListEqual(np.unique(Z).tolist(), list(range(k)))
def test_one_per_class(self):
for k in range(1, 12):
with self.subTest(k):
X = np.random.randn(k, 3)
centroids = pvml.kmeans_train(X, k)
Y, _ = pvml.kmeans_inference(X, centroids)
self.assertListEqual(
normalize_labels(Y).tolist(), list(range(k)))
def _linear(self, k, m):
Y = np.arange(m) % k
a = np.linspace(0, 2 * np.pi, m)
X = np.stack([np.cos(a) + 10 * Y, np.sin(a)], 1)
centroids = pvml.kmeans_train(X, k)
Z, _ = pvml.kmeans_inference(X, centroids)
self.assertListEqual(
normalize_labels(Y).tolist(),
normalize_labels(Z).tolist())
def test_init(self):
m = 100
k = 5
X = np.random.randn(m, 2)
init_centroids = np.arange(k * 2).reshape(k, 2)
centroids = pvml.kmeans_train(X,
k,
init_centroids=init_centroids,
steps=0)
self.assertListEqual(init_centroids.tolist(), centroids.tolist())
def train_step(self, X, Y, steps):
new_k = Y.max() + 1
if new_k > self.k:
# If the classes change centroids are reset
self.centroids = None
self.k = new_k
self.centroids = pvml.kmeans_train(X,
self.k,
steps=steps,
init_centroids=self.centroids)
self._sort_centroids(X, Y)
def test_errors4(self):
X = np.random.randn(10, 2)
with self.assertRaises(ValueError):
pvml.kmeans_train(X, 11)
def test_errors3(self):
X = np.random.randn(10, 2)
with self.assertRaises(ValueError):
pvml.kmeans_train(X, 3, init_centroids=np.zeros((3, 1)))