Apply new validation to cuml.explainer

conda/environments/all_cuda-129_arch-aarch64.yaml

@@ -40,6 +40,7 @@ dependencies:
 - libopenblas<=0.3.30
 - libraft==26.6.*,>=0.0.0a0
 - librmm==26.6.*,>=0.0.0a0
+- lightgbm
 - matplotlib-base
 - nbsphinx
 - ninja
@@ -75,6 +76,7 @@ dependencies:
 - scikit-learn>=1.5
 - scipy>=1.14.0
 - seaborn
+- shap
 - skl2onnx
 - sphinx
 - sphinx-copybutton

conda/environments/all_cuda-129_arch-x86_64.yaml

@@ -39,6 +39,7 @@ dependencies:
 - libcuvs==26.6.*,>=0.0.0a0
 - libraft==26.6.*,>=0.0.0a0
 - librmm==26.6.*,>=0.0.0a0
+- lightgbm
 - matplotlib-base
 - nbsphinx
 - ninja
@@ -74,6 +75,7 @@ dependencies:
 - scikit-learn>=1.5
 - scipy>=1.14.0
 - seaborn
+- shap
 - skl2onnx
 - sphinx
 - sphinx-copybutton

conda/environments/all_cuda-131_arch-aarch64.yaml

@@ -40,6 +40,7 @@ dependencies:
 - libopenblas<=0.3.30
 - libraft==26.6.*,>=0.0.0a0
 - librmm==26.6.*,>=0.0.0a0
+- lightgbm
 - matplotlib-base
 - nbsphinx
 - ninja
@@ -75,6 +76,7 @@ dependencies:
 - scikit-learn>=1.5
 - scipy>=1.14.0
 - seaborn
+- shap
 - skl2onnx
 - sphinx
 - sphinx-copybutton

conda/environments/all_cuda-131_arch-x86_64.yaml

@@ -39,6 +39,7 @@ dependencies:
 - libcuvs==26.6.*,>=0.0.0a0
 - libraft==26.6.*,>=0.0.0a0
 - librmm==26.6.*,>=0.0.0a0
+- lightgbm
 - matplotlib-base
 - nbsphinx
 - ninja
@@ -74,6 +75,7 @@ dependencies:
 - scikit-learn>=1.5
 - scipy>=1.14.0
 - seaborn
+- shap
 - skl2onnx
 - sphinx
 - sphinx-copybutton

dependencies.yaml

@@ -604,6 +604,8 @@ dependencies:
           - statsmodels
           - umap-learn>=0.5.7,<0.5.12
           - pynndescent
+          - lightgbm
+          - shap
       - output_types: conda
         packages:
           - cuvs==26.6.*,>=0.0.0a0

python/cuml/cuml/explainer/base.pyx

@@ -16,7 +16,7 @@ from cuml.explainer.common import (
     output_list_shap_values,
 )
 from cuml.internals.base import get_handle
-from cuml.internals.input_utils import input_to_cupy_array, input_to_host_array
+from cuml.internals.validation import check_array
 
 from libc.stdint cimport uintptr_t
 from libcpp cimport bool
@@ -129,9 +129,10 @@ class SHAPBase():
             raise ValueError("dtype must be either np.float32 or np.float64.")
         self.dtype = dtype
 
-        self.background, self.nrows, self.ncols, _ = \
-            input_to_cupy_array(background, order=self.order,
-                                convert_to_dtype=self.dtype)
+        self.background = check_array(
+            background, order=self.order, dtype=self.dtype, ensure_all_finite=False
+        )
+        self.nrows, self.ncols = self.background.shape
 
         self.random_state = random_state
 
@@ -204,9 +205,13 @@ class SHAPBase():
         """
         self._reset_timers()
 
-        X = input_to_cupy_array(X,
-                                order=self.order,
-                                convert_to_dtype=self.dtype)[0]
+        X = check_array(
+            X,
+            order=self.order,
+            dtype=self.dtype,
+            ensure_2d=False,
+            ensure_all_finite=False,
+        )
 
         if X.ndim == 1:
             X = X.reshape((1, self.ncols))
@@ -294,7 +299,9 @@ class SHAPBase():
         out = Explanation(
             values=shap_values,
             base_values=base_values,
-            data=input_to_host_array(X).array,
+            data=check_array(
+                X, mem_type="host", ensure_2d=False, ensure_all_finite=False
+            ),
             feature_names=self.feature_names,
             main_effects=main_effect_values
         )

python/cuml/cuml/explainer/common.py

@@ -1,10 +1,10 @@
 #
-# SPDX-FileCopyrightText: Copyright (c) 2020-2025, NVIDIA CORPORATION.
+# SPDX-FileCopyrightText: Copyright (c) 2020-2026, NVIDIA CORPORATION.
 # SPDX-License-Identifier: Apache-2.0
 #
 import cupy as cp
 
-from cuml.internals.input_utils import input_to_cupy_array
+from cuml.internals.validation import check_array
 
 
 def get_tag_from_model_func(func, tag, default=None):
@@ -39,17 +39,17 @@ def model_func_call(X, model_func, gpu_model=False):
     Returns the results as CuPy arrays.
     """
     if gpu_model:
-        y = input_to_cupy_array(X=model_func(X), order="K").array
+        y = model_func(X)
     else:
         try:
-            y = input_to_cupy_array(model_func(cp.asnumpy(X))).array
+            y = model_func(cp.asnumpy(X))
         except TypeError:
             raise TypeError(
                 "Explainer can only explain models that can "
                 "take GPU data or NumPy arrays as input."
             )
 
-    return y
+    return check_array(y, ensure_2d=False, ensure_all_finite=False)
 
 
 def get_cai_ptr(X):

python/cuml/cuml/explainer/kernel_shap.pyx

@@ -13,7 +13,7 @@ import numpy as np
 from cuml.explainer.base import SHAPBase
 from cuml.explainer.common import get_cai_ptr, model_func_call
 from cuml.internals import get_handle
-from cuml.internals.input_utils import input_to_cupy_array
+from cuml.internals.validation import check_array
 from cuml.linear_model import Lasso, LinearRegression
 
 from libc.stdint cimport uint64_t, uintptr_t
@@ -279,8 +279,9 @@ class KernelExplainer(SHAPBase):
                                            self.randind,
                                            self.dtype)
 
-        row, _, _, _ = \
-            input_to_cupy_array(row, order=self.order)
+        row = check_array(
+            row, order=self.order, ensure_2d=False, ensure_all_finite=False
+        )
 
         handle = get_handle()
         cdef handle_t* handle_ = <handle_t*><size_t>handle.getHandle()

python/cuml/cuml/explainer/sampling.py

@@ -1,15 +1,14 @@
-# SPDX-FileCopyrightText: Copyright (c) 2021-2025, NVIDIA CORPORATION.
+# SPDX-FileCopyrightText: Copyright (c) 2021-2026, NVIDIA CORPORATION.
 # SPDX-License-Identifier: Apache-2.0
 #
+import cudf
 import cupy as cp
-from scipy.sparse import issparse
+import pandas as pd
 
 import cuml
 from cuml import KMeans
-from cuml.internals.input_utils import (
-    determine_array_type,
-    get_supported_input_type,
-)
+from cuml.internals.array import CumlArray
+from cuml.internals.validation import check_array
 from cuml.preprocessing import SimpleImputer
 
 
@@ -43,58 +42,48 @@ def kmeans_sampling(X, k, round_values=True, detailed=False, random_state=0):
     labels : Cluster labels of the data points in the original dataset,
              shape (n_samples, 1)
     """
-    output_dtype = get_supported_input_type(X)
-    _output_dtype_str = determine_array_type(X)
-
-    if output_dtype is None:
-        raise TypeError(
-            f"Type of input {type(X)} is not supported. Supported \
-                        dtypes: cuDF DataFrame, cuDF Series, cupy, numba,\
-                        numpy, pandas DataFrame, pandas Series"
-        )
-
-    if "DataFrame" in str(output_dtype):
-        group_names = X.columns
-        X = cp.array(X.values, copy=False)
-    if "Series" in str(output_dtype):
-        group_names = X.name
-        X = cp.array(X.values.reshape(-1, 1), copy=False)
+    if isinstance(X, (cudf.DataFrame, pd.DataFrame)):
+        group_names = [str(c) for c in X.columns]
+    elif isinstance(X, (cudf.Series, pd.Series)):
+        group_names = [str(X.name)]
+    elif len(X.shape) == 2:
+        group_names = [str(i) for i in range(X.shape[1])]
     else:
-        # it's either numpy, cupy or numba
-        X = cp.array(X, copy=False)
-        try:
-            # more than one column
-            group_names = [str(i) for i in range(X.shape[1])]
-        except IndexError:
-            # one column
-            X = X.reshape(-1, 1)
-            group_names = ["0"]
+        group_names = ["0"]
+
+    X, index = check_array(
+        X, ensure_2d=False, ensure_all_finite=False, return_index=True
+    )
+    if X.ndim == 1:
+        X = X.reshape(-1, 1)
 
     # in case there are any missing values in data impute them
     imp = SimpleImputer(
-        missing_values=cp.nan, strategy="mean", output_type=_output_dtype_str
+        missing_values=cp.nan, strategy="mean", output_type="cupy"
     )
     X = imp.fit_transform(X)
 
     kmeans = KMeans(
         n_clusters=k,
         random_state=random_state,
-        output_type=_output_dtype_str,
+        output_type="cupy",
         n_init="auto",
     ).fit(X)
 
     if round_values:
         for i in range(k):
             for j in range(X.shape[1]):
-                xj = (
-                    X[:, j].toarray().flatten() if issparse(X) else X[:, j]
-                )  # sparse support courtesy of @PrimozGodec
+                xj = X[:, j]
                 ind = cp.argmin(cp.abs(xj - kmeans.cluster_centers_[i, j]))
                 kmeans.cluster_centers_[i, j] = X[ind, j]
     summary = kmeans.cluster_centers_
     labels = kmeans.labels_
 
     if detailed:
-        return summary, group_names, labels
+        return (
+            CumlArray(data=summary),
+            group_names,
+            CumlArray(labels, index=index),
+        )
     else:
-        return summary
+        return CumlArray(data=summary)