def test_query_same_result_with_fixed_random_state(self):
knn_index1 = nearest_neighbors.NNDescent("euclidean", random_state=1)
indices1, distances1 = knn_index1.build(self.x1, k=30)
knn_index2 = nearest_neighbors.NNDescent("euclidean", random_state=1)
indices2, distances2 = knn_index2.build(self.x1, k=30)
np.testing.assert_equal(indices1, indices2)
np.testing.assert_equal(distances1, distances2)
def test_random_cluster_when_invalid_indices(self):
class MockIndex:
def __init__(self, data, n_neighbors, **_):
n_samples = data.shape[0]
rs = check_random_state(0)
indices = rs.randint(0, n_samples, size=(n_samples, n_neighbors))
distances = rs.exponential(5, (n_samples, n_neighbors))
# Set some of the points to have invalid indices
indices[:10] = -1
distances[:10] = -1
self.neighbor_graph = indices, distances
with patch("pynndescent.NNDescent", wraps=MockIndex):
knn_index = nearest_neighbors.NNDescent(self.x1, 5, "euclidean", n_jobs=2)
indices, distances = knn_index.build()
# Check that indices were replaced by something
self.assertTrue(np.all(indices[:10] != -1))
# Check that that "something" are all indices of failed points
self.assertTrue(np.all(indices[:10] < 10))
# And check that the distances were set to something positive
self.assertTrue(np.all(distances[:10] > 0))
def test_runs_with_correct_njobs_if_sparse_input(self):
with patch("pynndescent.NNDescent",
wraps=pynndescent.NNDescent) as nndescent:
x_sparse = sp.csr_matrix(self.x1)
knn_index = nearest_neighbors.NNDescent("euclidean", n_jobs=2)
knn_index.build(x_sparse, k=5)
check_mock_called_with_kwargs(nndescent, dict(n_jobs=2))
def test_random_state_being_passed_through(self, nndescent):
random_state = 1
knn_index = nearest_neighbors.NNDescent("euclidean", random_state=random_state)
knn_index.build(self.x1, k=30)
nndescent.assert_called_once()
check_mock_called_with_kwargs(nndescent, {"random_state": random_state})
def test_runs_with_correct_njobs_if_dense_input(self):
with patch("pynndescent.NNDescent",
wraps=pynndescent.NNDescent) as nndescent:
knn_index = nearest_neighbors.NNDescent(self.x1,
5,
"euclidean",
n_jobs=2)
knn_index.build()
check_mock_called_with_kwargs(nndescent, dict(n_jobs=2))
def test_random_state_being_passed_through(self):
random_state = 1
with patch("pynndescent.NNDescent", wraps=pynndescent.NNDescent) as nndescent:
knn_index = nearest_neighbors.NNDescent(
self.x1, 30, "euclidean", random_state=random_state
)
knn_index.build()
nndescent.assert_called_once()
check_mock_called_with_kwargs(nndescent, {"random_state": random_state})
def test_building_with_lt15_builds_proper_graph(self, nndescent):
knn_index = nearest_neighbors.NNDescent("euclidean")
indices, distances = knn_index.build(self.x1, k=10)
self.assertEqual(indices.shape, (self.x1.shape[0], 10))
self.assertEqual(distances.shape, (self.x1.shape[0], 10))
self.assertFalse(np.all(indices[:, 0] == np.arange(self.x1.shape[0])))
# Should be called with 11 because nearest neighbor in pynndescent is itself
check_mock_called_with_kwargs(nndescent, dict(n_neighbors=11))
def test_uncompiled_callable_is_compiled(self):
knn_index = nearest_neighbors.NNDescent("manhattan")
def manhattan(x, y):
result = 0.0
for i in range(x.shape[0]):
result += np.abs(x[i] - y[i])
return result
compiled_metric = knn_index.check_metric(manhattan)
self.assertTrue(isinstance(compiled_metric, CPUDispatcher))
def test_building_with_gt15_calls_query(self, nndescent):
nndescent.query = MagicMock(wraps=nndescent.query)
knn_index = nearest_neighbors.NNDescent("euclidean")
indices, distances = knn_index.build(self.x1, k=30)
self.assertEqual(indices.shape, (self.x1.shape[0], 30))
self.assertEqual(distances.shape, (self.x1.shape[0], 30))
self.assertFalse(np.all(indices[:, 0] == np.arange(self.x1.shape[0])))
# The index should be built with 15 neighbors
check_mock_called_with_kwargs(nndescent, dict(n_neighbors=15))
# And subsequently queried with the correct number of neighbors. Check
# for 31 neighbors because query will return the original point as well,
# which we don't consider.
check_mock_called_with_kwargs(nndescent.query, dict(k=31))
def test_runs_with_njobs1_if_sparse_input(self, nndescent):
x_sparse = sp.csr_matrix(self.x1)
knn_index = nearest_neighbors.NNDescent("euclidean", n_jobs=4)
knn_index.build(x_sparse, k=5)
check_mock_called_with_kwargs(nndescent, dict(n_jobs=1))
def test_runs_with_correct_njobs_if_dense_input(self, nndescent):
knn_index = nearest_neighbors.NNDescent("euclidean", n_jobs=4)
knn_index.build(self.x1, k=5)
check_mock_called_with_kwargs(nndescent, dict(n_jobs=4))