Skip to content

Do not set n_features_in_ attribute before fit #6624

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 7 commits into from
May 8, 2025
Merged

Do not set n_features_in_ attribute before fit #6624

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
b1312d8
Do not set n_features_in_ attribute before `fit`
betatim May 6, 2025
e1a7d9f
Fix up descriptor testing
betatim May 6, 2025
bdd8d7c
Update xfail list
betatim May 6, 2025
5f14dfe
Update xfail list
betatim May 7, 2025
7007e95
Merge remote-tracking branch 'origin/branch-25.06' into fix-n-feature…
csadorf May 7, 2025
11d578e
meh
betatim May 8, 2025
797baad
Flake
betatim May 8, 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
21 changes: 1 addition & 20 deletions python/cuml/cuml/accel/tests/scikit-learn/xfail-list.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -412,7 +412,6 @@
- "sklearn.inspection.tests.test_partial_dependence::test_multiclass_multioutput[RandomForestClassifier]"
- "sklearn.inspection.tests.test_partial_dependence::test_partial_dependence_sample_weight_with_recursion"
- "sklearn.inspection.tests.test_partial_dependence::test_partial_dependence_unfitted[estimator0]"
- "sklearn.inspection.tests.test_partial_dependence::test_partial_dependence_unfitted[estimator1]"
- "sklearn.inspection.tests.test_partial_dependence::test_recursion_decision_tree_vs_forest_and_gbdt[0]"
- "sklearn.inspection.tests.test_permutation_importance::test_permutation_importance_correlated_feature_regression[ones-0.5-1]"
- "sklearn.inspection.tests.test_permutation_importance::test_permutation_importance_correlated_feature_regression[ones-0.5-2]"
Expand Down Expand Up @@ -702,22 +701,8 @@
- "sklearn.manifold.tests.test_t_sne::test_uniform_grid[barnes_hut]"
- "sklearn.manifold.tests.test_t_sne::test_uniform_grid[exact]"
- "sklearn.manifold.tests.test_t_sne::test_verbose"
- "sklearn.metrics._plot.tests.test_common_curve_display::test_display_curve_not_fitted_errors[DetCurveDisplay-clf0]"
- "sklearn.metrics._plot.tests.test_common_curve_display::test_display_curve_not_fitted_errors[DetCurveDisplay-clf1]"
- "sklearn.metrics._plot.tests.test_common_curve_display::test_display_curve_not_fitted_errors[DetCurveDisplay-clf2]"
- "sklearn.metrics._plot.tests.test_common_curve_display::test_display_curve_not_fitted_errors[PrecisionRecallDisplay-clf0]"
- "sklearn.metrics._plot.tests.test_common_curve_display::test_display_curve_not_fitted_errors[PrecisionRecallDisplay-clf1]"
- "sklearn.metrics._plot.tests.test_common_curve_display::test_display_curve_not_fitted_errors[PrecisionRecallDisplay-clf2]"
- "sklearn.metrics._plot.tests.test_common_curve_display::test_display_curve_not_fitted_errors[RocCurveDisplay-clf0]"
- "sklearn.metrics._plot.tests.test_common_curve_display::test_display_curve_not_fitted_errors[RocCurveDisplay-clf1]"
- "sklearn.metrics._plot.tests.test_common_curve_display::test_display_curve_not_fitted_errors[RocCurveDisplay-clf2]"
- "sklearn.metrics._plot.tests.test_confusion_matrix_display::test_confusion_matrix_pipeline[clf]"
- "sklearn.metrics._plot.tests.test_precision_recall_display::test_precision_recall_display_pipeline[clf0]"
- "sklearn.metrics._plot.tests.test_precision_recall_display::test_precision_recall_display_pipeline[clf1]"
- "sklearn.metrics._plot.tests.test_predict_error_display::test_from_estimator_not_fitted"
- "sklearn.metrics._plot.tests.test_roc_curve_display::test_roc_curve_display_complex_pipeline[from_estimator-clf0]"
- "sklearn.metrics._plot.tests.test_roc_curve_display::test_roc_curve_display_complex_pipeline[from_estimator-clf1]"
- "sklearn.metrics._plot.tests.test_roc_curve_display::test_roc_curve_display_complex_pipeline[from_estimator-clf2]"
- "sklearn.metrics.tests.test_pairwise::test_euclidean_distances_extreme_values[1-float64-1e-08-0.99]"
- "sklearn.metrics.tests.test_pairwise::test_euclidean_distances_extreme_values[1000000-float64-1e-08-0.99]"
- "sklearn.metrics.tests.test_score_objects::test_get_scorer_multilabel_indicator"
Expand Down Expand Up @@ -962,7 +947,6 @@
- "sklearn.tests.test_common::test_estimators[Pipeline(steps=[('scaler',StandardScaler()),('final_estimator',LogisticRegression())])-check_estimators_nan_inf]"
- "sklearn.tests.test_common::test_estimators[Pipeline(steps=[('scaler',StandardScaler()),('final_estimator',LogisticRegression())])-check_estimators_overwrite_params]"
- "sklearn.tests.test_common::test_estimators[Pipeline(steps=[('scaler',StandardScaler()),('final_estimator',LogisticRegression())])-check_fit2d_1sample]"
- "sklearn.tests.test_common::test_estimators[Pipeline(steps=[('scaler',StandardScaler()),('final_estimator',LogisticRegression())])-check_fit_check_is_fitted]"
- "sklearn.tests.test_common::test_estimators[Pipeline(steps=[('scaler',StandardScaler()),('final_estimator',LogisticRegression())])-check_supervised_y_2d]"
- "sklearn.tests.test_common::test_estimators[Pipeline(steps=[('scaler',StandardScaler()),('final_estimator',LogisticRegression())])-check_supervised_y_no_nan]"
- "sklearn.tests.test_common::test_estimators[Pipeline(steps=[('scaler',StandardScaler()),('final_estimator',Ridge())])-check_dont_overwrite_parameters]"
Expand Down Expand Up @@ -1212,15 +1196,12 @@
- "sklearn.utils.tests.test_estimator_checks::test_check_estimator"
- "sklearn.utils.tests.test_estimator_checks::test_check_estimator_clones"
- "sklearn.utils.tests.test_estimator_checks::test_check_estimator_pairwise"
- "sklearn.utils.tests.test_estimator_html_repr::test_estimator_html_repr_fitted_icon[estimator0]"
- "sklearn.utils.tests.test_estimator_html_repr::test_estimator_html_repr_fitted_icon[estimator1]"
- "sklearn.utils.tests.test_estimator_html_repr::test_estimator_html_repr_fitted_icon[estimator2]"
- "sklearn.utils.tests.test_estimator_html_repr::test_show_arrow_pipeline"
- "sklearn.utils.tests.test_validation::test_has_fit_parameter"
- reason: Test is flaky with cuml.accel
strict: false
marker: cuml_accel_flaky
tests:
- "sklearn.utils.tests.test_estimator_html_repr::test_show_arrow_pipeline"
- "sklearn.cluster.tests.test_k_means::test_score_max_iter[42-KMeans]"
- "sklearn.decomposition.tests.test_truncated_svd::test_explained_variance_components_10_20[arpack-sparse]"
- "sklearn.decomposition.tests.test_truncated_svd::test_explained_variance_components_10_20[randomized-sparse]"
Expand Down
8 changes: 6 additions & 2 deletions python/cuml/cuml/internals/base.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -268,7 +268,6 @@ class Base(TagsMixin,
self._input_type = None
self._input_mem_type = None
self.target_dtype = None
self.n_features_in_ = None

nvtx_benchmark = os.getenv('NVTX_BENCHMARK')
if nvtx_benchmark and nvtx_benchmark.lower() == 'true':
Expand Down Expand Up @@ -479,7 +478,12 @@ class Base(TagsMixin,
if isinstance(X, int):
self.n_features_in_ = X
else:
self.n_features_in_ = X.shape[1]
shape = X.shape
# dataframes can have only one dimension
if len(shape) == 1:
self.n_features_in_ = 1
else:
self.n_features_in_ = shape[1]

def _more_tags(self):
# 'preserves_dtype' tag's Scikit definition currently only applies to
Expand Down
6 changes: 3 additions & 3 deletions python/cuml/cuml/tests/test_cuml_descr_decor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,7 @@ def get_input(self):

# === Standard Functions ===
def fit(self, X, convert_dtype=True) -> "DummyTestEstimator":

self._set_base_attributes(output_type=X, n_features=X)
return self

def predict(self, X, convert_dtype=True) -> CumlArray:
Expand Down Expand Up @@ -228,11 +228,11 @@ def calc_n_features(shape):
# When cudf and shape[1] is used, a series is created which will
# remove the last shape
if input_type == "cudf" and shape[1] == 1:
return None
return 1

return shape[1]

return None
return 1

assert est._input_type == input_type
assert est.target_dtype is None
Expand Down
Loading