def test_nn_search():
train = nn_data[100:]
test = nn_data[:100]
(knn_indices, knn_dists,
rp_forest) = nearest_neighbors(train, 10, "euclidean", {}, False,
np.random)
graph = fuzzy_simplicial_set(
nn_data,
10,
np.random,
"euclidean",
{},
knn_indices,
knn_dists,
False,
1.0,
1.0,
False,
)
search_graph = sparse.lil_matrix((train.shape[0], train.shape[0]),
dtype=np.int8)
search_graph.rows = knn_indices
search_graph.data = (knn_dists != 0).astype(np.int8)
search_graph = search_graph.maximum(search_graph.transpose()).tocsr()
random_init, tree_init = make_initialisations(dist.euclidean, ())
search = make_initialized_nnd_search(dist.euclidean, ())
rng_state = np.random.randint(INT32_MIN, INT32_MAX, 3).astype(np.int64)
init = initialise_search(rp_forest, train, test, int(10 * 3), random_init,
tree_init, rng_state)
result = search(train, search_graph.indptr, search_graph.indices, init,
test)
indices, dists = deheap_sort(result)
indices = indices[:, :10]
tree = KDTree(train)
true_indices = tree.query(test, 10, return_distance=False)
num_correct = 0.0
for i in range(test.shape[0]):
num_correct += np.sum(np.in1d(true_indices[i], indices[i]))
percent_correct = num_correct / (test.shape[0] * 10)
assert_greater_equal(
percent_correct,
0.99,
"Sparse NN-descent did not get "
"99% accuracy on nearest "
"neighbors",
)
def test_smooth_knn_dist_l1norms_w_connectivity():
knn_indices, knn_dists, _ = nearest_neighbors(nn_data, 10, "euclidean", {},
False, np.random)
sigmas, rhos = smooth_knn_dist(knn_dists, 10, local_connectivity=1.75)
shifted_dists = knn_dists - rhos[:, np.newaxis]
shifted_dists[shifted_dists < 0.0] = 0.0
vals = np.exp(-(shifted_dists / sigmas[:, np.newaxis]))
norms = np.sum(vals, axis=1)
assert_array_almost_equal(
norms,
1.0 + np.log2(10) * np.ones(norms.shape[0]),
decimal=3,
err_msg="Smooth knn-dists does not give expected"
"norms for local_connectivity=1.75",
)
def test_nn_descent_neighbor_accuracy_callable_metric():
knn_indices, knn_dists, _ = nearest_neighbors(nn_data, 10, dist.euclidean,
{}, False, np.random)
tree = KDTree(nn_data)
true_indices = tree.query(nn_data, 10, return_distance=False)
num_correct = 0.0
for i in range(nn_data.shape[0]):
num_correct += np.sum(np.in1d(true_indices[i], knn_indices[i]))
percent_correct = num_correct / (spatial_data.shape[0] * 10)
assert_greater_equal(
percent_correct,
0.99,
"NN-descent did not get 99% "
"accuracy on nearest neighbors with callable metric",
)
def test_sparse_angular_nn_descent_neighbor_accuracy():
knn_indices, knn_dists, _ = nearest_neighbors(sparse_nn_data, 10, "cosine",
{}, True, np.random)
angular_data = normalize(sparse_nn_data, norm="l2").toarray()
tree = KDTree(angular_data)
true_indices = tree.query(angular_data, 10, return_distance=False)
num_correct = 0.0
for i in range(nn_data.shape[0]):
num_correct += np.sum(np.in1d(true_indices[i], knn_indices[i]))
percent_correct = num_correct / (spatial_data.shape[0] * 10)
assert_greater_equal(
percent_correct,
0.99,
"NN-descent did not get 99% "
"accuracy on nearest neighbors",
)
def test_sparse_nn_descent_neighbor_accuracy():
knn_indices, knn_dists, _ = nearest_neighbors(sparse_nn_data, 10,
"euclidean", {}, False,
np.random)
tree = KDTree(sparse_nn_data.todense())
true_indices = tree.query(sparse_nn_data.todense(),
10,
return_distance=False)
num_correct = 0.0
for i in range(nn_data.shape[0]):
num_correct += np.sum(np.in1d(true_indices[i], knn_indices[i]))
percent_correct = num_correct / (spatial_data.shape[0] * 10)
assert_greater_equal(
percent_correct,
0.99,
"Sparse NN-descent did not get "
"99% accuracy on nearest "
"neighbors",
)