def neighbors(self, k=10, queue_size=5, random_state=0):
"""\
Calculate neighbors of `adata_new` observations in `adata`.
This function calculates `k` neighbors in `adata` for
each observation of `adata_new`.
"""
from umap.nndescent import initialise_search
from umap.utils import deheap_sort
from umap.umap_ import INT32_MAX, INT32_MIN
random_state = check_random_state(random_state)
rng_state = random_state.randint(INT32_MIN, INT32_MAX, 3).astype(np.int64)
train = self._rep
test = self._obsm['rep']
init = initialise_search(
self._rp_forest,
train,
test,
int(k * queue_size),
self._random_init,
self._tree_init,
rng_state,
)
result = self._search(
train, self._search_graph.indptr, self._search_graph.indices, init, test,
)
indices, dists = deheap_sort(result)
self._indices, self._distances = indices[:, :k], dists[:, :k]
def test_nn_search(nn_data):
train = nn_data[100:]
test = nn_data[:100]
(knn_indices, knn_dists, rp_forest) = nearest_neighbors(
train,
10,
"euclidean",
{},
False,
np.random,
use_pynndescent=False,
)
# Commented - NOT REALLY USED IN THE TEST
# graph = fuzzy_simplicial_set(
# nn_data,
# 10,
# np.random,
# "euclidean",
# {},
# knn_indices,
# knn_dists,
# False,
# 1.0,
# 1.0,
# False,
# )
search_graph = setup_search_graph(knn_dists, knn_indices, train)
rng_state = np.random.randint(INT32_MIN, INT32_MAX, 3).astype(np.int64)
init = initialise_search(rp_forest, train, test, int(10 * 3), rng_state,
dist.euclidean)
result = initialized_nnd_search(train, search_graph.indptr,
search_graph.indices, init, test,
dist.euclidean)
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_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 _nhood_search(umap_object, nhood_size):
if umap_object._small_data:
dmat = sklearn.metrics.pairwise_distances(umap_object._raw_data)
indices = np.argpartition(dmat, nhood_size)[:, :nhood_size]
dmat_shortened = submatrix(dmat, indices, nhood_size)
indices_sorted = np.argsort(dmat_shortened)
indices = submatrix(indices, indices_sorted, nhood_size)
dists = submatrix(dmat_shortened, indices_sorted, nhood_size)
else:
rng_state = np.empty(3, dtype=np.int64)
if len(umap_object._metric_kwds) >= 1:
_dist = umap_object._input_distance_func
_args = tuple(umap_object._metric_kwds.values())
@numba.njit()
def _metric(x, y):
_dist(x, y, *_args)
else:
_metric = umap_object._input_distance_func
init = initialise_search(
umap_object._rp_forest,
umap_object._raw_data,
umap_object._raw_data,
int(nhood_size * umap_object.transform_queue_size),
rng_state,
_metric,
)
result = initialized_nnd_search(
umap_object._raw_data,
umap_object._search_graph.indptr,
umap_object._search_graph.indices,
init,
umap_object._raw_data,
_metric,
)
indices, dists = deheap_sort(result)
indices = indices[:, :nhood_size]
dists = dists[:, :nhood_size]
return indices, dists
def neighbors_update(adata, adata_new, k=10, queue_size=5, random_state=0):
# only with use_rep='X' for now
from umap.nndescent import make_initialisations, make_initialized_nnd_search, initialise_search
from umap.umap_ import INT32_MAX, INT32_MIN
from umap.utils import deheap_sort
import umap.distances as dist
if 'metric_kwds' in adata.uns['neighbors']['params']:
dist_args = tuple(
adata.uns['neighbors']['params']['metric_kwds'].values())
else:
dist_args = ()
dist_func = dist.named_distances[adata.uns['neighbors']['params']
['metric']]
random_init, tree_init = make_initialisations(dist_func, dist_args)
search = make_initialized_nnd_search(dist_func, dist_args)
search_graph = adata.uns['neighbors']['distances'].copy()
search_graph.data = (search_graph.data > 0).astype(np.int8)
search_graph = search_graph.maximum(search_graph.transpose())
# prune it?
random_state = check_random_state(random_state)
rng_state = random_state.randint(INT32_MIN, INT32_MAX, 3).astype(np.int64)
if 'rp_forest' in adata.uns['neighbors']:
rp_forest = _rp_forest_generate(adata.uns['neighbors']['rp_forest'])
else:
rp_forest = None
train = adata.X
test = adata_new.X
init = initialise_search(rp_forest, train, test, int(k * queue_size),
random_init, tree_init, rng_state)
result = search(train, search_graph.indptr, search_graph.indices, init,
test)
indices, dists = deheap_sort(result)
return indices[:, :k], dists[:, :k]
def _nhood_search(umap_object, nhood_size):
if umap_object._small_data:
dmat = sklearn.metrics.pairwise_distances(umap_object._raw_data)
indices = np.argpartition(dmat, nhood_size)[:, :nhood_size]
dmat_shortened = submatrix(dmat, indices, nhood_size)
indices_sorted = np.argsort(dmat_shortened)
indices = submatrix(indices, indices_sorted, nhood_size)
dists = submatrix(dmat_shortened, indices_sorted, nhood_size)
else:
rng_state = np.empty(3, dtype=np.int64)
init = initialise_search(
umap_object._rp_forest,
umap_object._raw_data,
umap_object._raw_data,
int(nhood_size * umap_object.transform_queue_size),
rng_state,
umap_object._distance_func,
umap_object._dist_args,
)
result = initialized_nnd_search(
umap_object._raw_data,
umap_object._search_graph.indptr,
umap_object._search_graph.indices,
init,
umap_object._raw_data,
umap_object._distance_func,
umap_object._dist_args,
)
indices, dists = deheap_sort(result)
indices = indices[:, :nhood_size]
dists = dists[:, :nhood_size]
return indices, dists
