Skip to content

Enable dice metric for UMAP and pairwise_distances #6842

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 21 commits into
base: branch-25.08
Choose a base branch
from
Open

Enable dice metric for UMAP and pairwise_distances #6842

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
21 commits
Select commit Hold shift + click to select a range
612b2e3
init umap-dice-coefficient-update
aamijar Jun 3, 2025
73bfd05
Merge branch 'branch-25.08' into umap-dice-coefficient-update
aamijar Jun 3, 2025
3218954
add dice to pairwise_distances
aamijar Jun 4, 2025
2e67aaf
Merge branch 'branch-25.08' into umap-dice-coefficient-update
aamijar Jun 4, 2025
617760a
test ci with local cuvs
aamijar Jun 4, 2025
ffb5ff2
merge
aamijar Jun 4, 2025
4ccc848
Merge branch 'branch-25.08' into umap-dice-coefficient-update
aamijar Jun 4, 2025
d182930
test ci
aamijar Jun 4, 2025
3321fbf
test ci
aamijar Jun 4, 2025
f54ff1b
test ci
aamijar Jun 4, 2025
dc63226
Merge branch 'branch-25.08' into umap-dice-coefficient-update
aamijar Jun 4, 2025
e44e9c4
test ci
aamijar Jun 4, 2025
4f0191b
test ci
aamijar Jun 4, 2025
8551d19
test ci
aamijar Jun 6, 2025
c313bd4
Merge branch 'branch-25.08' into umap-dice-coefficient-update
aamijar Jun 6, 2025
99d3659
fix ci
aamijar Jun 12, 2025
c10d8f1
pin cuvs
aamijar Jun 12, 2025
f0c70ae
Merge branch 'branch-25.08' into umap-dice-coefficient-update
aamijar Jun 12, 2025
18d8640
rerun CI
aamijar Jun 12, 2025
ab4c7a4
Merge branch 'branch-25.08' into umap-dice-coefficient-update
aamijar Jun 13, 2025
f6c5707
Merge branch 'branch-25.08' into umap-dice-coefficient-update
aamijar Jun 27, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions cpp/cmake/thirdparty/get_cuvs.cmake
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,8 +73,8 @@ endfunction()
# To use a different CUVS locally, set the CMake variable
# CPM_cuvs_SOURCE=/path/to/local/cuvs
find_and_configure_cuvs(VERSION ${CUML_MIN_VERSION_cuvs}
FORK rapidsai
PINNED_TAG branch-${CUML_BRANCH_VERSION_cuvs}
FORK aamijar
PINNED_TAG umap-dice-coefficient
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Remove later

EXCLUDE_FROM_ALL ${CUML_EXCLUDE_CUVS_FROM_ALL}
# When PINNED_TAG above doesn't match cuml,
# force local cuvs clone in build directory
Expand Down
5 changes: 4 additions & 1 deletion python/cuml/cuml/manifold/umap_utils.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -147,7 +147,8 @@ _METRICS = {
"hellinger": DistanceType.HellingerExpanded,
"hamming": DistanceType.HammingUnexpanded,
"jaccard": DistanceType.JaccardExpanded,
"canberra": DistanceType.Canberra
"canberra": DistanceType.Canberra,
"dice": DistanceType.DiceExpanded,
}

_SUPPORTED_METRICS = {
Expand All @@ -168,6 +169,7 @@ _SUPPORTED_METRICS = {
DistanceType.L2Expanded,
DistanceType.Linf,
DistanceType.LpUnexpanded,
DistanceType.DiceExpanded,
)),
"dense": frozenset((
DistanceType.Canberra,
Expand All @@ -181,6 +183,7 @@ _SUPPORTED_METRICS = {
DistanceType.L2Expanded,
DistanceType.Linf,
DistanceType.LpUnexpanded,
DistanceType.DiceExpanded,
))
}
}
Expand Down
7 changes: 4 additions & 3 deletions python/cuml/cuml/metrics/pairwise_distances.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,7 +82,8 @@ PAIRWISE_DISTANCE_METRICS = {
"hamming": DistanceType.HammingUnexpanded,
"kldivergence": DistanceType.KLDivergence,
"russellrao": DistanceType.RusselRaoExpanded,
"nan_euclidean": DistanceType.L2Expanded
"nan_euclidean": DistanceType.L2Expanded,
"dice": DistanceType.DiceExpanded
}

PAIRWISE_DISTANCE_SPARSE_METRICS = {
Expand Down Expand Up @@ -350,7 +351,7 @@ def pairwise_distances(X, Y=None, metric="euclidean", handle=None,
if metric in ['nan_euclidean']:
return nan_euclidean_distances(X, Y, **kwds)

if metric in ['russellrao'] and not np.all(X.data == 1.):
if metric in ['russellrao', 'dice'] and not np.all(X.data == 1.):
warnings.warn("X was converted to boolean for metric {}"
.format(metric))
X = np.where(X != 0., 1.0, 0.0)
Expand All @@ -377,7 +378,7 @@ def pairwise_distances(X, Y=None, metric="euclidean", handle=None,
if (n_samples_x == 1 or n_features_x == 1):
input_order = "K"

if metric in ['russellrao'] and not np.all(Y.data == 1.):
if metric in ['russellrao', 'dice'] and not np.all(Y.data == 1.):
warnings.warn("Y was converted to boolean for metric {}"
.format(metric))
Y = np.where(Y != 0., 1.0, 0.0)
Expand Down
2 changes: 2 additions & 0 deletions python/cuml/cuml/tests/test_umap.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -699,6 +699,7 @@ def test_fuzzy_simplicial_set(n_rows, n_features, n_neighbors):
@pytest.mark.parametrize(
"metric,build_algo,supported",
[
("dice", "brute_force_knn", True),
("l2", "brute_force_knn", True),
("euclidean", "brute_force_knn", True),
("sqeuclidean", "brute_force_knn", True),
Expand Down Expand Up @@ -767,6 +768,7 @@ def test_umap_distance_metrics_fit_transform_trust(
@pytest.mark.parametrize(
"metric,supported,umap_learn_supported",
[
("dice", True, False),
("l2", True, False),
("euclidean", True, True),
("sqeuclidean", True, False),
Expand Down
Loading