FIX avoid unecessary if copy branch for sparse array/matrix (scikit-learn#27336)

Co-authored-by: Olivier Grisel <olivier.grisel@ensta.org>

Author: glemaitre

doc/whats_new/v1.4.rst

@@ -300,6 +300,12 @@ Changelog
   which can be used to check whether a given set of parameters would be consumed.
   :pr:`26831` by `Adrin Jalali`_.
 
+- |Fix| :func:`sklearn.utils.check_array` should accept both matrix and array from
+  the sparse SciPy module. The previous implementation would fail if `copy=True` by
+  calling specific NumPy `np.may_share_memory` that does not work with SciPy sparse
+  array and does not return the correct result for SciPy sparse matrix.
+  :pr:`27336` by :user:`Guillaume Lemaitre <glemaitre>`.
+
 Code and Documentation Contributors
 -----------------------------------
 

sklearn/utils/tests/test_validation.py

@@ -49,7 +49,13 @@
     skip_if_array_api_compat_not_configured,
 )
 from sklearn.utils.estimator_checks import _NotAnArray
-from sklearn.utils.fixes import parse_version
+from sklearn.utils.fixes import (
+    COO_CONTAINERS,
+    CSC_CONTAINERS,
+    CSR_CONTAINERS,
+    DOK_CONTAINERS,
+    parse_version,
+)
 from sklearn.utils.validation import (
     FLOAT_DTYPES,
     _allclose_dense_sparse,
@@ -356,13 +362,20 @@ def test_check_array():
                 assert X is X_checked
 
     # allowed sparse != None
-    X_csc = sp.csc_matrix(X_C)
-    X_coo = X_csc.tocoo()
-    X_dok = X_csc.todok()
-    X_int = X_csc.astype(int)
-    X_float = X_csc.astype(float)
 
-    Xs = [X_csc, X_coo, X_dok, X_int, X_float]
+    # try different type of sparse format
+    Xs = []
+    Xs.extend(
+        [
+            sparse_container(X_C)
+            for sparse_container in CSR_CONTAINERS
+            + CSC_CONTAINERS
+            + COO_CONTAINERS
+            + DOK_CONTAINERS
+        ]
+    )
+    Xs.extend([Xs[0].astype(np.int64), Xs[0].astype(np.float64)])
+
     accept_sparses = [["csr", "coo"], ["coo", "dok"]]
     # scipy sparse matrices do not support the object dtype so
     # this dtype is skipped in this loop

sklearn/utils/validation.py

@@ -962,6 +962,19 @@ def is_sparse(dtype):
                 allow_nan=force_all_finite == "allow-nan",
             )
 
+        if copy:
+            if _is_numpy_namespace(xp):
+                # only make a copy if `array` and `array_orig` may share memory`
+                if np.may_share_memory(array, array_orig):
+                    array = _asarray_with_order(
+                        array, dtype=dtype, order=order, copy=True, xp=xp
+                    )
+            else:
+                # always make a copy for non-numpy arrays
+                array = _asarray_with_order(
+                    array, dtype=dtype, order=order, copy=True, xp=xp
+                )
+
     if ensure_min_samples > 0:
         n_samples = _num_samples(array)
         if n_samples < ensure_min_samples:
@@ -980,19 +993,6 @@ def is_sparse(dtype):
                 % (n_features, array.shape, ensure_min_features, context)
             )
 
-    if copy:
-        if _is_numpy_namespace(xp):
-            # only make a copy if `array` and `array_orig` may share memory`
-            if np.may_share_memory(array, array_orig):
-                array = _asarray_with_order(
-                    array, dtype=dtype, order=order, copy=True, xp=xp
-                )
-        else:
-            # always make a copy for non-numpy arrays
-            array = _asarray_with_order(
-                array, dtype=dtype, order=order, copy=True, xp=xp
-            )
-
     return array