Initial investigation into NumPy proxying in cudf.pandas (#16286)

Apart of #15397. Closes #14537. Creates `ProxyNDarray` which inherits from `np.ndarray`.

Authors:
  - Matthew Murray (https://github.com/Matt711)
  - GALI PREM SAGAR (https://github.com/galipremsagar)

Approvers:
  - GALI PREM SAGAR (https://github.com/galipremsagar)
  - Matthew Roeschke (https://github.com/mroeschke)

URL: #16286

python/cudf/cudf/pandas/_wrappers/numpy.py

@@ -14,6 +14,7 @@
     make_final_proxy_type,
     make_intermediate_proxy_type,
 )
+from ..proxy_base import ProxyNDarrayBase
 from .common import (
     array_interface,
     array_method,
@@ -111,12 +112,14 @@ def wrap_ndarray(cls, arr: cupy.ndarray | numpy.ndarray, constructor):
     numpy.ndarray,
     fast_to_slow=cupy.ndarray.get,
     slow_to_fast=cupy.asarray,
+    bases=(ProxyNDarrayBase,),
     additional_attributes={
         "__array__": array_method,
         # So that pa.array(wrapped-numpy-array) works
         "__arrow_array__": arrow_array_method,
         "__cuda_array_interface__": cuda_array_interface,
         "__array_interface__": array_interface,
+        "__array_ufunc__": _FastSlowAttribute("__array_ufunc__"),
         # ndarrays are unhashable
         "__hash__": None,
         # iter(cupy-array) produces an iterable of zero-dim device

python/cudf/cudf/pandas/fast_slow_proxy.py

@@ -19,6 +19,7 @@
 from ..options import _env_get_bool
 from ..testing import assert_eq
 from .annotation import nvtx
+from .proxy_base import ProxyNDarrayBase
 
 
 def call_operator(fn, args, kwargs):
@@ -564,7 +565,11 @@ def _fsproxy_wrap(cls, value, func):
         _FinalProxy subclasses can override this classmethod if they
         need particular behaviour when wrapped up.
         """
-        proxy = object.__new__(cls)
+        base_class = _get_proxy_base_class(cls)
+        if base_class is object:
+            proxy = base_class.__new__(cls)
+        else:
+            proxy = base_class.__new__(cls, value)
         proxy._fsproxy_wrapped = value
         return proxy
 
@@ -1193,6 +1198,19 @@ def is_proxy_object(obj: Any) -> bool:
     return False
 
 
+def _get_proxy_base_class(cls):
+    """Returns the proxy base class if one exists"""
+    for proxy_class in PROXY_BASE_CLASSES:
+        if proxy_class in cls.__mro__:
+            return proxy_class
+    return object
+
+
+PROXY_BASE_CLASSES: set[type] = {
+    ProxyNDarrayBase,
+}
+
+
 NUMPY_TYPES: set[str] = set(np.sctypeDict.values())
 
 

python/cudf/cudf/pandas/proxy_base.py

@@ -0,0 +1,23 @@
+# SPDX-FileCopyrightText: Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES.
+# All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+import cupy as cp
+import numpy as np
+
+
+class ProxyNDarrayBase(np.ndarray):
+    def __new__(cls, arr):
+        if isinstance(arr, cp.ndarray):
+            obj = np.asarray(arr.get()).view(cls)
+            return obj
+        elif isinstance(arr, np.ndarray):
+            obj = np.asarray(arr).view(cls)
+            return obj
+        else:
+            raise TypeError(
+                "Unsupported array type. Must be numpy.ndarray or cupy.ndarray"
+            )
+
+    def __array_finalize__(self, obj):
+        self._fsproxy_wrapped = getattr(obj, "_fsproxy_wrapped", None)

python/cudf/cudf_pandas_tests/test_cudf_pandas.py

@@ -1632,3 +1632,11 @@ def test_change_index_name(index):
 
         assert s.index.name == name
         assert df.index.name == name
+
+
+def test_numpy_ndarray_isinstancecheck(series):
+    s1, s2 = series
+    arr1 = s1.values
+    arr2 = s2.values
+    assert isinstance(arr1, np.ndarray)
+    assert isinstance(arr2, np.ndarray)