def test_fit_iris_unsplit(self):
split = 0
# get some test data
iris = ht.load("heat/datasets/iris.csv", sep=";", split=split)
ht.random.seed(1)
# fit the clusters
k = 3
kmedoid = ht.cluster.KMedoids(n_clusters=k, random_state=1)
kmedoid.fit(iris)
# check whether the results are correct
self.assertIsInstance(kmedoid.cluster_centers_, ht.DNDarray)
self.assertEqual(kmedoid.cluster_centers_.shape, (k, iris.shape[1]))
# same test with init=kmedoids++
kmedoid = ht.cluster.KMedoids(n_clusters=k, init="kmedoids++")
kmedoid.fit(iris)
# check whether the results are correct
self.assertIsInstance(kmedoid.cluster_centers_, ht.DNDarray)
self.assertEqual(kmedoid.cluster_centers_.shape, (k, iris.shape[1]))
# check whether result is actually a datapoint
for i in range(kmedoid.cluster_centers_.shape[0]):
self.assertTrue(
ht.any(
ht.sum(ht.abs(kmedoid.cluster_centers_[i, :] - iris),
axis=1) == 0))
def test_any(self):
# float values, minor axis
x = ht.float32([[2.7, 0, 0], [0, 0, 0], [0, 0.3, 0]], device=ht_device)
any_tensor = x.any(axis=1)
res = ht.uint8([1, 0, 1], device=ht_device)
self.assertIsInstance(any_tensor, ht.DNDarray)
self.assertEqual(any_tensor.shape, (3, ))
self.assertEqual(any_tensor.dtype, ht.bool)
self.assertTrue(ht.equal(any_tensor, res))
# integer values, major axis, output tensor
any_tensor = ht.zeros((2, ), device=ht_device)
x = ht.int32([[0, 0], [0, 0], [0, 1]], device=ht_device)
ht.any(x, axis=0, out=any_tensor)
res = ht.uint8([0, 1], device=ht_device)
self.assertIsInstance(any_tensor, ht.DNDarray)
self.assertEqual(any_tensor.shape, (2, ))
self.assertEqual(any_tensor.dtype, ht.bool)
self.assertTrue(ht.equal(any_tensor, res))
# float values, no axis
x = ht.float64([[0, 0, 0], [0, 0, 0]], device=ht_device)
res = ht.zeros(1, dtype=ht.uint8, device=ht_device)
any_tensor = ht.any(x)
self.assertIsInstance(any_tensor, ht.DNDarray)
self.assertEqual(any_tensor.shape, (1, ))
self.assertEqual(any_tensor.dtype, ht.bool)
self.assertTrue(ht.equal(any_tensor, res))
# split tensor, along axis
x = ht.arange(10, split=0, device=ht_device)
any_tensor = ht.any(x, axis=0)
res = ht.uint8([1], device=ht_device)
self.assertIsInstance(any_tensor, ht.DNDarray)
self.assertEqual(any_tensor.shape, (1, ))
self.assertEqual(any_tensor.dtype, ht.bool)
self.assertTrue(ht.equal(any_tensor, res))
def test_spherical_clusters(self):
seed = 1
n = 20 * ht.MPI_WORLD.size
data = self.create_spherical_dataset(num_samples_cluster=n,
radius=1.0,
offset=4.0,
dtype=ht.float32,
random_state=seed)
kmedoid = ht.cluster.KMedoids(n_clusters=4, init="kmedoids++")
kmedoid.fit(data)
self.assertIsInstance(kmedoid.cluster_centers_, ht.DNDarray)
self.assertEqual(kmedoid.cluster_centers_.shape, (4, 3))
for i in range(kmedoid.cluster_centers_.shape[0]):
self.assertTrue(
ht.any(
ht.sum(ht.abs(kmedoid.cluster_centers_[i, :] - data),
axis=1) == 0))
# More Samples
n = 100 * ht.MPI_WORLD.size
data = self.create_spherical_dataset(num_samples_cluster=n,
radius=1.0,
offset=4.0,
dtype=ht.float32,
random_state=seed)
kmedoid = ht.cluster.KMedoids(n_clusters=4, init="kmedoids++")
kmedoid.fit(data)
self.assertIsInstance(kmedoid.cluster_centers_, ht.DNDarray)
self.assertEqual(kmedoid.cluster_centers_.shape, (4, 3))
# check whether result is actually a datapoint
for i in range(kmedoid.cluster_centers_.shape[0]):
self.assertTrue(
ht.any(
ht.sum(ht.abs(kmedoid.cluster_centers_[i, :] - data),
axis=1) == 0))
# different datatype
n = 20 * ht.MPI_WORLD.size
data = self.create_spherical_dataset(num_samples_cluster=n,
radius=1.0,
offset=4.0,
dtype=ht.float64,
random_state=seed)
kmedoid = ht.cluster.KMedoids(n_clusters=4, init="kmedoids++")
kmedoid.fit(data)
self.assertIsInstance(kmedoid.cluster_centers_, ht.DNDarray)
self.assertEqual(kmedoid.cluster_centers_.shape, (4, 3))
for i in range(kmedoid.cluster_centers_.shape[0]):
self.assertTrue(
ht.any(
ht.sum(ht.abs(kmedoid.cluster_centers_[i, :] -
data.astype(ht.float32)),
axis=1) == 0))
# on Ints (different radius, offset and datatype
data = self.create_spherical_dataset(num_samples_cluster=n,
radius=10.0,
offset=40.0,
dtype=ht.int32,
random_state=seed)
kmedoid = ht.cluster.KMedoids(n_clusters=4, init="kmedoids++")
kmedoid.fit(data)
self.assertIsInstance(kmedoid.cluster_centers_, ht.DNDarray)
self.assertEqual(kmedoid.cluster_centers_.shape, (4, 3))
for i in range(kmedoid.cluster_centers_.shape[0]):
self.assertTrue(
ht.any(
ht.sum(ht.abs(kmedoid.cluster_centers_[i, :] - data),
axis=1) == 0))
