Skip to content

FIX Raise TypeError when sparse input is not supported #7728

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

Merged
rapids-bot merged 10 commits into from
Feb 11, 2026
Merged

FIX Raise TypeError when sparse input is not supported #7728

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
b528e46
Raise TypeError when sparse input is not supported
betatim Jan 28, 2026
be82ce5
Merge branch 'main' into fix-sparse-exception
betatim Feb 4, 2026
34f847f
Improve xfail reason
betatim Feb 4, 2026
1bcab69
Merge branch 'main' into fix-sparse-exception
csadorf Feb 4, 2026
430d2b1
Merge branch 'main' into fix-sparse-exception
betatim Feb 5, 2026
ab277a2
Merge remote-tracking branch 'origin/fix-sparse-exception' into fix-s…
betatim Feb 5, 2026
ded1215
Merge branch 'main' into fix-sparse-exception
betatim Feb 6, 2026
890ecda
Merge branch 'main' into fix-sparse-exception
betatim Feb 10, 2026
a52f9e2
Cleanup xfails
betatim Feb 10, 2026
3b6320d
Merge branch 'main' into fix-sparse-exception
betatim Feb 11, 2026
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
12 changes: 6 additions & 6 deletions python/cuml/cuml/internals/array.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -983,12 +983,12 @@ def from_input(

if is_sparse(X):
# We don't support coercing sparse arrays to dense via this method.
# Raising a NotImplementedError here lets us nicely error
# for estimators that don't support sparse arrays without requiring
# an additional external check. Otherwise they'd get an opaque error
# for code below.
raise NotImplementedError(
"Sparse inputs are not currently supported for this method"
# Raising a TypeError here lets us nicely error for estimators that
# don't support sparse arrays without requiring an additional
# external check. Using TypeError with "sparse" in the message
# satisfies sklearn's check_estimator_sparse_tag check.
raise TypeError(
"A sparse matrix was passed, but dense data is required. "
)
if convert_to_mem_type is not False:
convert_to_mem_type = MemoryType.from_str(convert_to_mem_type)
Expand Down
6 changes: 3 additions & 3 deletions python/cuml/tests/test_exceptions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
#
# SPDX-FileCopyrightText: Copyright (c) 2024-2025, NVIDIA CORPORATION.
# SPDX-FileCopyrightText: Copyright (c) 2024-2026, NVIDIA CORPORATION.
# SPDX-License-Identifier: Apache-2.0
#

Expand All @@ -24,7 +24,7 @@
NearestNeighbors,
)

# Currently only certain estimators raise a NotImplementedError
# Estimators that raise TypeError when given sparse input (they don't support sparse)
estimators = {
"KMeans": lambda: KMeans(n_clusters=2, random_state=0),
"DBSCAN": lambda: DBSCAN(eps=1.0),
Expand All @@ -44,7 +44,7 @@ def test_sparse_not_implemented_exception(estimator_name):
y_reg = np.array([0.0, 1.0])
estimator = estimators[estimator_name]()
# Fit or fit_transform depending on the estimator type
with pytest.raises(NotImplementedError):
with pytest.raises(TypeError, match="sparse"):
if isinstance(
estimator, (KMeans, DBSCAN, TruncatedSVD, NearestNeighbors)
):
Expand Down
58 changes: 2 additions & 56 deletions python/cuml/tests/test_sklearn_compatibility.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,9 +56,6 @@
"check_complex_data": "KMeans does not handle complex data",
"check_dtype_object": "KMeans does not handle object dtype",
"check_estimators_nan_inf": "KMeans does not check for NaN and inf",
"check_estimator_sparse_tag": "KMeans does not support sparse data",
"check_estimator_sparse_array": "KMeans does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "KMeans does not handle sparse matrices gracefully",
"check_transformer_data_not_an_array": "KMeans does not handle non-array data",
"check_fit1d": "KMeans does not raise ValueError for 1D input",
"check_fit2d_predict1d": "KMeans does not handle 1D prediction input gracefully",
Expand All @@ -74,9 +71,6 @@
"check_dtype_object": "KernelRidge does not handle object dtype",
"check_estimators_empty_data_messages": "KernelRidge does not handle empty data",
"check_estimators_nan_inf": "KernelRidge does not check for NaN and inf",
"check_estimator_sparse_tag": "KernelRidge does not support sparse data",
"check_estimator_sparse_array": "KernelRidge does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "KernelRidge does not handle sparse matrices gracefully",
"check_regressors_train": "KernelRidge does not handle list inputs",
"check_regressors_train(readonly_memmap=True)": "KernelRidge does not handle readonly memmap",
"check_regressors_train(readonly_memmap=True,X_dtype=float32)": "KernelRidge does not handle readonly memmap with float32",
Expand Down Expand Up @@ -122,9 +116,6 @@
"check_dtype_object": "LinearRegression does not handle object dtype",
"check_estimators_empty_data_messages": "LinearRegression does not handle empty data",
"check_estimators_nan_inf": "LinearRegression does not check for NaN and inf",
"check_estimator_sparse_tag": "LinearRegression does not support sparse data",
"check_estimator_sparse_array": "LinearRegression does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "LinearRegression does not handle sparse matrices gracefully",
"check_regressors_train": "LinearRegression does not handle list inputs",
"check_regressors_train(readonly_memmap=True)": "LinearRegression does not handle readonly memmap",
"check_regressors_train(readonly_memmap=True,X_dtype=float32)": "LinearRegression does not handle readonly memmap with float32",
Expand All @@ -145,9 +136,6 @@
"check_complex_data": "Ridge does not handle complex data",
"check_dtype_object": "Ridge does not handle object dtype",
"check_estimators_nan_inf": "Ridge does not check for NaN and inf",
"check_estimator_sparse_tag": "Ridge does not support sparse data",
"check_estimator_sparse_array": "Ridge does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "Ridge does not handle sparse matrices gracefully",
"check_regressors_train": "Ridge does not handle list inputs",
"check_regressors_train(readonly_memmap=True)": "Ridge does not handle readonly memmap",
"check_regressors_train(readonly_memmap=True,X_dtype=float32)": "Ridge does not handle readonly memmap with float32",
Expand All @@ -167,9 +155,6 @@
"check_dtype_object": "RandomForestRegressor does not handle object dtype",
"check_estimators_empty_data_messages": "RandomForestRegressor does not handle empty data",
"check_estimators_nan_inf": "RandomForestRegressor does not check for NaN and inf",
"check_estimator_sparse_tag": "RandomForestRegressor does not support sparse data",
"check_estimator_sparse_array": "RandomForestRegressor does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "RandomForestRegressor does not handle sparse matrices gracefully",
"check_regressors_train": "RandomForestRegressor does not handle list inputs",
"check_regressors_train(readonly_memmap=True)": "RandomForestRegressor does not handle readonly memmap",
"check_regressors_train(readonly_memmap=True,X_dtype=float32)": "RandomForestRegressor does not handle readonly memmap with float32",
Expand Down Expand Up @@ -208,9 +193,6 @@
"check_dtype_object": "RandomForestClassifier does not handle object dtype",
"check_estimators_empty_data_messages": "RandomForestClassifier does not handle empty data",
"check_estimators_nan_inf": "RandomForestClassifier does not check for NaN and inf",
"check_estimator_sparse_tag": "RandomForestClassifier does not support sparse data",
"check_estimator_sparse_array": "RandomForestClassifier does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "RandomForestClassifier does not handle sparse matrices gracefully",
"check_classifier_data_not_an_array": "RandomForestClassifier does not handle non-array data",
"check_classifiers_train": "RandomForestClassifier does not handle list inputs",
"check_classifiers_train(readonly_memmap=True)": "RandomForestClassifier does not handle readonly memmap",
Expand Down Expand Up @@ -263,9 +245,6 @@
"check_complex_data": "LinearSVC does not handle complex data",
"check_dtype_object": "LinearSVC does not handle object dtype",
"check_estimators_nan_inf": "LinearSVC does not check for NaN and inf",
"check_estimator_sparse_tag": "LinearSVC does not support sparse data",
"check_estimator_sparse_array": "LinearSVC does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "LinearSVC does not handle sparse matrices gracefully",
"check_estimators_pickle": "LinearSVC does not support pickling",
"check_estimators_pickle(readonly_memmap=True)": "LinearSVC does not support pickling with readonly memmap",
"check_classifier_data_not_an_array": "LinearSVC does not handle non-array data",
Expand Down Expand Up @@ -293,9 +272,6 @@
"check_complex_data": "LinearSVR does not handle complex data",
"check_dtype_object": "LinearSVR does not handle object dtype",
"check_estimators_nan_inf": "LinearSVR does not check for NaN and inf",
"check_estimator_sparse_tag": "LinearSVR does not support sparse data",
"check_estimator_sparse_array": "LinearSVR does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "LinearSVR does not handle sparse matrices gracefully",
"check_regressors_train": "LinearSVR does not handle list inputs",
"check_regressors_train(readonly_memmap=True)": "LinearSVR does not handle readonly memmap",
"check_regressors_train(readonly_memmap=True,X_dtype=float32)": "LinearSVR does not handle readonly memmap with float32",
Expand Down Expand Up @@ -387,9 +363,6 @@
"check_dtype_object": "TruncatedSVD does not handle object dtype",
"check_estimators_empty_data_messages": "TruncatedSVD does not handle empty data",
"check_estimators_nan_inf": "TruncatedSVD does not check for NaN and inf",
"check_estimator_sparse_tag": "TruncatedSVD does not support sparse data",
"check_estimator_sparse_array": "TruncatedSVD does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "TruncatedSVD does not handle sparse matrices gracefully",
"check_transformer_data_not_an_array": "TruncatedSVD does not handle non-array data",
"check_fit2d_1sample": "TruncatedSVD does not handle single sample",
"check_fit2d_1feature": "TruncatedSVD does not handle single feature",
Expand Down Expand Up @@ -429,9 +402,6 @@
"check_complex_data": "Lasso does not handle complex data",
"check_dtype_object": "Lasso does not handle object dtype",
"check_estimators_nan_inf": "Lasso does not check for NaN and inf",
"check_estimator_sparse_tag": "Lasso does not support sparse data",
"check_estimator_sparse_array": "Lasso does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "Lasso does not handle sparse matrices gracefully",
"check_regressors_train": "Lasso does not handle list inputs",
"check_regressors_train(readonly_memmap=True)": "Lasso does not handle readonly memmap",
"check_regressors_train(readonly_memmap=True,X_dtype=float32)": "Lasso does not handle readonly memmap with float32",
Expand All @@ -452,9 +422,6 @@
"check_complex_data": "ElasticNet does not handle complex data",
"check_dtype_object": "ElasticNet does not handle object dtype",
"check_estimators_nan_inf": "ElasticNet does not check for NaN and inf",
"check_estimator_sparse_tag": "ElasticNet does not support sparse data",
"check_estimator_sparse_array": "ElasticNet does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "ElasticNet does not handle sparse matrices gracefully",
"check_regressors_train": "ElasticNet does not handle list inputs",
"check_regressors_train(readonly_memmap=True)": "ElasticNet does not handle readonly memmap",
"check_regressors_train(readonly_memmap=True,X_dtype=float32)": "ElasticNet does not handle readonly memmap with float32",
Expand All @@ -474,9 +441,6 @@
"check_complex_data": "KernelDensity does not handle complex data",
"check_dtype_object": "KernelDensity does not handle object dtype",
"check_estimators_nan_inf": "KernelDensity does not check for NaN and inf",
"check_estimator_sparse_tag": "KernelDensity does not support sparse data",
"check_estimator_sparse_array": "KernelDensity does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "KernelDensity does not handle sparse matrices gracefully",
"check_fit1d": "KernelDensity does not raise ValueError for 1D input",
},
LedoitWolf: {
Expand All @@ -486,9 +450,6 @@
"check_dtype_object": "LedoitWolf does not handle object dtype",
"check_estimators_empty_data_messages": "LedoitWolf does not handle empty data",
"check_estimators_nan_inf": "LedoitWolf does not check for NaN and inf",
"check_estimator_sparse_tag": "LedoitWolf does not support sparse data",
"check_estimator_sparse_array": "LedoitWolf does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "LedoitWolf does not handle sparse matrices gracefully",
},
DBSCAN: {
"check_estimator_tags_renamed": "No support for modern tags infrastructure",
Expand All @@ -499,9 +460,6 @@
"check_dtype_object": "DBSCAN does not handle object dtype",
"check_estimators_empty_data_messages": "DBSCAN does not handle empty data",
"check_estimators_nan_inf": "DBSCAN does not check for NaN and inf",
"check_estimator_sparse_tag": "DBSCAN does not support sparse data",
"check_estimator_sparse_array": "DBSCAN does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "DBSCAN does not handle sparse matrices gracefully",
"check_fit1d": "DBSCAN does not raise ValueError for 1D input",
},
HDBSCAN: {
Expand All @@ -512,7 +470,6 @@
"check_dtype_object": "HDBSCAN does not handle object dtype",
"check_estimators_empty_data_messages": "HDBSCAN does not handle empty data",
"check_estimators_nan_inf": "HDBSCAN does not check for NaN and inf",
"check_estimator_sparse_tag": "HDBSCAN does not support sparse data",
"check_estimator_sparse_array": "HDBSCAN does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "HDBSCAN does not handle sparse matrices gracefully",
"check_parameters_default_constructible": "HDBSCAN parameters are mutated on init",
Expand All @@ -537,7 +494,6 @@
"check_complex_data": "AgglomerativeClustering does not handle complex data",
"check_dtype_object": "AgglomerativeClustering does not handle object dtype",
"check_estimators_nan_inf": "AgglomerativeClustering does not check for NaN and inf",
"check_estimator_sparse_tag": "AgglomerativeClustering does not support sparse data",
"check_estimator_sparse_array": "AgglomerativeClustering does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "AgglomerativeClustering does not handle sparse matrices gracefully",
"check_parameters_default_constructible": "AgglomerativeClustering parameters are mutated on init",
Expand All @@ -556,8 +512,6 @@
"check_dtype_object": "GaussianNB does not handle object dtype",
"check_estimators_empty_data_messages": "GaussianNB does not handle empty data",
"check_estimators_nan_inf": "GaussianNB does not check for NaN and inf",
"check_estimator_sparse_tag": "GaussianNB does not support sparse data",
"check_estimator_sparse_array": "GaussianNB does not handle sparse arrays gracefully",
"check_classifier_data_not_an_array": "GaussianNB does not handle non-array data",
"check_classifiers_classes": "GaussianNB does not handle string data properly",
"check_estimators_partial_fit_n_features": "GaussianNB does not check n_features consistency in partial_fit",
Expand Down Expand Up @@ -586,7 +540,7 @@
"check_estimators_empty_data_messages": "GaussianRandomProjection does not handle empty data",
"check_pipeline_consistency": "GaussianRandomProjection raises ValueError with small datasets",
"check_estimators_nan_inf": "GaussianRandomProjection does not check for NaN and inf",
"check_estimator_sparse_tag": "GaussianRandomProjection does not support sparse data",
"check_estimator_sparse_tag": "GaussianRandomProjection raises ValueError with small datasets even though it supports sparse inputs",
"check_estimator_sparse_array": "GaussianRandomProjection does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "GaussianRandomProjection does not handle sparse matrices gracefully",
"check_estimators_pickle": "GaussianRandomProjection raises ValueError with small datasets",
Expand Down Expand Up @@ -615,7 +569,7 @@
"check_estimators_empty_data_messages": "SparseRandomProjection does not handle empty data",
"check_pipeline_consistency": "SparseRandomProjection raises ValueError with small datasets",
"check_estimators_nan_inf": "SparseRandomProjection does not check for NaN and inf",
"check_estimator_sparse_tag": "SparseRandomProjection does not support sparse data",
"check_estimator_sparse_tag": "SparseRandomProjection raises ValueError with small datasets",
"check_estimator_sparse_array": "SparseRandomProjection does not handle sparse arrays gracefully",
"check_estimator_sparse_matrix": "SparseRandomProjection does not handle sparse matrices gracefully",
"check_estimators_pickle": "SparseRandomProjection raises ValueError with small datasets",
Expand Down Expand Up @@ -644,8 +598,6 @@
"check_dtype_object": "BernoulliNB does not handle object dtype",
"check_estimators_empty_data_messages": "BernoulliNB does not provide proper error messages for empty data",
"check_estimators_nan_inf": "BernoulliNB does not check for NaN and inf",
"check_estimator_sparse_tag": "BernoulliNB sparse data handling does not follow sklearn conventions",
"check_estimator_sparse_array": "BernoulliNB does not handle sparse arrays gracefully",
"check_classifier_data_not_an_array": "BernoulliNB does not handle list inputs",
"check_classifiers_classes": "BernoulliNB does not handle string labels properly",
"check_estimators_partial_fit_n_features": "BernoulliNB does not check n_features consistency in partial_fit",
Expand Down Expand Up @@ -677,8 +629,6 @@
"check_estimators_empty_data_messages": "ComplementNB does not provide proper error messages for empty data",
"check_pipeline_consistency": "ComplementNB pipeline consistency issues",
"check_estimators_nan_inf": "ComplementNB does not check for NaN and inf",
"check_estimator_sparse_tag": "ComplementNB sparse data handling does not follow sklearn conventions",
"check_estimator_sparse_array": "ComplementNB does not handle sparse arrays gracefully",
"check_estimators_pickle": "ComplementNB pickling issues",
"check_estimators_pickle(readonly_memmap=True)": "ComplementNB pickling with readonly memmap issues",
"check_classifier_data_not_an_array": "ComplementNB does not handle list inputs",
Expand Down Expand Up @@ -711,8 +661,6 @@
"check_dtype_object": "CategoricalNB does not handle object dtype",
"check_estimators_empty_data_messages": "CategoricalNB does not provide proper error messages for empty data",
"check_estimators_nan_inf": "CategoricalNB does not check for NaN and inf",
"check_estimator_sparse_tag": "CategoricalNB sparse data handling does not follow sklearn conventions",
"check_estimator_sparse_array": "CategoricalNB does not handle sparse arrays gracefully",
"check_classifier_data_not_an_array": "CategoricalNB does not handle list inputs",
"check_classifiers_classes": "CategoricalNB does not handle string labels properly",
"check_estimators_partial_fit_n_features": "CategoricalNB does not check n_features consistency in partial_fit",
Expand All @@ -739,8 +687,6 @@
"check_dtype_object": "MultinomialNB does not handle object dtype",
"check_estimators_empty_data_messages": "MultinomialNB does not provide proper error messages for empty data",
"check_estimators_nan_inf": "MultinomialNB does not check for NaN and inf",
"check_estimator_sparse_tag": "MultinomialNB sparse data handling does not follow sklearn conventions",
"check_estimator_sparse_array": "MultinomialNB does not handle sparse arrays gracefully",
"check_classifier_data_not_an_array": "MultinomialNB does not handle non-array data",
"check_classifiers_classes": "MultinomialNB does not handle string labels properly",
"check_estimators_partial_fit_n_features": "MultinomialNB does not check n_features consistency in partial_fit",
Expand Down