def testPdistExecution(self):
from scipy.spatial.distance import pdist as sp_pdist
raw = np.random.rand(100, 10)
# test 1 chunk
x = tensor(raw, chunk_size=100)
dist = distance.pdist(x)
result = self._executor.execute_tensor(dist, concat=True)[0]
expected = sp_pdist(raw)
np.testing.assert_array_equal(result, expected)
dist = distance.pdist(x, metric='hamming')
result = self._executor.execute_tensor(dist, concat=True)[0]
expected = sp_pdist(raw, metric='hamming')
np.testing.assert_array_equal(result, expected)
f = lambda u, v: np.sqrt(((u - v)**2).sum())
dist = distance.pdist(x, metric=f)
result = self._executor.execute_tensor(dist, concat=True)[0]
expected = sp_pdist(raw, metric=f)
np.testing.assert_array_equal(result, expected)
# test more than 1 chunk
x = tensor(raw, chunk_size=12)
dist = distance.pdist(x)
tdist = dist.tiles()
self.assertEqual(len(tdist.chunks), 1)
result = self._executor.execute_tensor(dist, concat=True)[0]
expected = sp_pdist(raw)
np.testing.assert_array_equal(result, expected)
dist = distance.pdist(x, aggregate_size=3)
tdist = dist.tiles()
self.assertEqual(len(tdist.chunks), 3)
result = self._executor.execute_tensor(dist, concat=True)[0]
expected = sp_pdist(raw)
np.testing.assert_array_equal(result, expected)
dist = distance.pdist(x, metric='hamming', aggregate_size=2)
tdist = dist.tiles()
self.assertEqual(len(tdist.chunks), 2)
result = self._executor.execute_tensor(dist, concat=True)[0]
expected = sp_pdist(raw, metric='hamming')
np.testing.assert_array_equal(result, expected)
f = lambda u, v: np.sqrt(((u - v)**2).sum())
dist = distance.pdist(x, metric=f, aggregate_size=2)
result = self._executor.execute_tensor(dist, concat=True)[0]
expected = sp_pdist(raw, metric=f)
np.testing.assert_array_equal(result, expected)
for x in [tensor(raw), tensor(raw, chunk_size=12)]:
# test w
weight = np.random.rand(10)
w = tensor(weight, chunk_size=7)
dist = distance.pdist(x, metric='wminkowski', p=3, w=w)
result = self._executor.execute_tensor(dist, concat=True)[0]
expected = sp_pdist(raw, metric='wminkowski', p=3, w=weight)
np.testing.assert_array_equal(result, expected)
# test V
v = np.random.rand(10)
V = tensor(v, chunk_size=7)
dist = distance.pdist(x, metric='seuclidean', V=V)
result = self._executor.execute_tensor(dist, concat=True)[0]
expected = sp_pdist(raw, metric='seuclidean', V=v)
np.testing.assert_array_equal(result, expected)
# test VI
vi = np.random.rand(10, 10)
VI = tensor(vi, chunk_size=8)
dist = distance.pdist(x, metric='mahalanobis', VI=VI)
result = self._executor.execute_tensor(dist, concat=True)[0]
expected = sp_pdist(raw, metric='mahalanobis', VI=vi)
np.testing.assert_array_equal(result, expected)
def test_pdist():
raw = np.random.rand(100, 10)
# test 1 chunk
a = tensor(raw, chunk_size=100)
dist = distance.pdist(a)
assert dist.shape == (100 * 99 // 2,)
dist = tile(dist)
assert len(dist.chunks) == 1
for c in dist.chunks:
assert c.shape == (dist.shape[0],)
# test multiple chunks
a = tensor(raw, chunk_size=15)
dist = distance.pdist(a, aggregate_size=2)
assert dist.shape == (100 * 99 // 2,)
dist = tile(dist)
assert len(dist.chunks) == 2
for c in dist.chunks:
assert c.shape == (dist.shape[0] // 2,)
# X cannot be sparse
raw = sps.csr_matrix(np.zeros((4, 3)))
a = tensor(raw)
with pytest.raises(ValueError):
distance.pdist(a)
# X can only be 2-d
with pytest.raises(ValueError):
distance.pdist(np.random.rand(3, 3, 3))
# out type wrong
with pytest.raises(TypeError):
distance.pdist(np.random.rand(3, 3), out=2)
# out shape wrong
with pytest.raises(ValueError):
distance.pdist(np.random.rand(3, 3),
out=tensor(np.random.rand(2)))
# out dtype wrong
with pytest.raises(ValueError):
distance.pdist(np.random.rand(3, 3),
out=tensor(np.random.randint(2, size=(3,))))
# test extra param
with pytest.raises(TypeError):
distance.pdist(np.random.rand(3, 3), unknown_kw='unknown_kw')
def testPdist(self):
raw = np.random.rand(100, 10)
# test 1 chunk
a = tensor(raw, chunk_size=100)
dist = distance.pdist(a)
self.assertEqual(dist.shape, (100 * 99 // 2, ))
dist = dist.tiles()
self.assertEqual(len(dist.chunks), 1)
for c in dist.chunks:
self.assertEqual(c.shape, (dist.shape[0], ))
# test multiple chunks
a = tensor(raw, chunk_size=15)
dist = distance.pdist(a, aggregate_size=2)
self.assertEqual(dist.shape, (100 * 99 // 2, ))
dist = dist.tiles()
self.assertEqual(len(dist.chunks), 2)
for c in dist.chunks:
self.assertEqual(c.shape, (dist.shape[0] // 2, ))
# X cannot be sparse
raw = sps.csr_matrix(np.zeros((4, 3)))
a = tensor(raw)
with self.assertRaises(ValueError):
distance.pdist(a)
# X can only be 2-d
with self.assertRaises(ValueError):
distance.pdist(np.random.rand(3, 3, 3))
# out type wrong
with self.assertRaises(TypeError):
distance.pdist(np.random.rand(3, 3), out=2)
# out shape wrong
with self.assertRaises(ValueError):
distance.pdist(np.random.rand(3, 3), out=tensor(np.random.rand(2)))
# out dtype wrong
with self.assertRaises(ValueError):
distance.pdist(np.random.rand(3, 3),
out=tensor(np.random.randint(2, size=(3, ))))
# test extra param
with self.assertRaises(TypeError):
distance.pdist(np.random.rand(3, 3), unknown_kw='unknown_kw')