REF: rename PandasArray->NumpyExtensionArray (#54101)

* REF: rename PandasArray->NumpyExtensionArray

* document PandasDtype->NumpyEADtype

Author: jbrockmendel

ci/code_checks.sh

@@ -105,7 +105,7 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.api.indexers.VariableOffsetWindowIndexer \
         pandas.api.extensions.ExtensionDtype \
         pandas.api.extensions.ExtensionArray \
-        pandas.arrays.PandasArray \
+        pandas.arrays.NumpyExtensionArray \
         pandas.api.extensions.ExtensionArray._accumulate \
         pandas.api.extensions.ExtensionArray._concat_same_type \
         pandas.api.extensions.ExtensionArray._formatter \

doc/source/development/contributing_codebase.rst

@@ -475,7 +475,7 @@ be located.
 
 8) Is your test for one of the pandas-provided ExtensionArrays (``Categorical``,
    ``DatetimeArray``, ``TimedeltaArray``, ``PeriodArray``, ``IntervalArray``,
-   ``PandasArray``, ``FloatArray``, ``BoolArray``, ``StringArray``)?
+   ``NumpyExtensionArray``, ``FloatArray``, ``BoolArray``, ``StringArray``)?
    This test likely belongs in one of:
 
    - tests.arrays

doc/source/reference/extensions.rst

@@ -24,7 +24,7 @@ objects.
    :template: autosummary/class_without_autosummary.rst
 
    api.extensions.ExtensionArray
-   arrays.PandasArray
+   arrays.NumpyExtensionArray
 
 .. We need this autosummary so that methods and attributes are generated.
 .. Separate block, since they aren't classes.

doc/source/whatsnew/v2.1.0.rst

@@ -286,6 +286,7 @@ See :ref:`install.dependencies` and :ref:`install.optional_dependencies` for mor
 
 Other API changes
 ^^^^^^^^^^^^^^^^^
+- :class:`arrays.PandasArray` has been renamed ``NumpyExtensionArray`` and the attached dtype name changed from ``PandasDtype`` to ``NumpyEADtype``; importing ``PandasArray`` still works until the next major version (:issue:`53694`)
 -
 
 .. ---------------------------------------------------------------------------

pandas/_testing/__init__.py

@@ -102,7 +102,7 @@
 from pandas.core.arrays import (
     BaseMaskedArray,
     ExtensionArray,
-    PandasArray,
+    NumpyExtensionArray,
 )
 from pandas.core.arrays._mixins import NDArrayBackedExtensionArray
 from pandas.core.construction import extract_array
@@ -307,7 +307,7 @@ def box_expected(expected, box_cls, transpose: bool = True):
     if box_cls is pd.array:
         if isinstance(expected, RangeIndex):
             # pd.array would return an IntegerArray
-            expected = PandasArray(np.asarray(expected._values))
+            expected = NumpyExtensionArray(np.asarray(expected._values))
         else:
             expected = pd.array(expected, copy=False)
     elif box_cls is Index:

pandas/_testing/asserters.py

@@ -25,7 +25,7 @@
     CategoricalDtype,
     DatetimeTZDtype,
     ExtensionDtype,
-    PandasDtype,
+    NumpyEADtype,
 )
 from pandas.core.dtypes.missing import array_equivalent
 
@@ -577,12 +577,12 @@ def raise_assert_detail(
 
     if isinstance(left, np.ndarray):
         left = pprint_thing(left)
-    elif isinstance(left, (CategoricalDtype, PandasDtype, StringDtype)):
+    elif isinstance(left, (CategoricalDtype, NumpyEADtype, StringDtype)):
         left = repr(left)
 
     if isinstance(right, np.ndarray):
         right = pprint_thing(right)
-    elif isinstance(right, (CategoricalDtype, PandasDtype, StringDtype)):
+    elif isinstance(right, (CategoricalDtype, NumpyEADtype, StringDtype)):
         right = repr(right)
 
     msg += f"""

pandas/arrays/__init__.py

@@ -12,7 +12,7 @@
     FloatingArray,
     IntegerArray,
     IntervalArray,
-    PandasArray,
+    NumpyExtensionArray,
     PeriodArray,
     SparseArray,
     StringArray,
@@ -28,9 +28,26 @@
     "FloatingArray",
     "IntegerArray",
     "IntervalArray",
-    "PandasArray",
+    "NumpyExtensionArray",
     "PeriodArray",
     "SparseArray",
     "StringArray",
     "TimedeltaArray",
 ]
+
+
+def __getattr__(name: str):
+    if name == "PandasArray":
+        # GH#53694
+        import warnings
+
+        from pandas.util._exceptions import find_stack_level
+
+        warnings.warn(
+            "PandasArray has been renamed NumpyExtensionArray. Use that "
+            "instead. This alias will be removed in a future version.",
+            FutureWarning,
+            stacklevel=find_stack_level(),
+        )
+        return NumpyExtensionArray
+    raise AttributeError(f"module 'pandas.arrays' has no attribute '{name}'")

pandas/core/algorithms.py

@@ -58,7 +58,7 @@
     BaseMaskedDtype,
     CategoricalDtype,
     ExtensionDtype,
-    PandasDtype,
+    NumpyEADtype,
 )
 from pandas.core.dtypes.generic import (
     ABCDatetimeArray,
@@ -1439,8 +1439,8 @@ def diff(arr, n: int, axis: AxisInt = 0):
     else:
         op = operator.sub
 
-    if isinstance(dtype, PandasDtype):
-        # PandasArray cannot necessarily hold shifted versions of itself.
+    if isinstance(dtype, NumpyEADtype):
+        # NumpyExtensionArray cannot necessarily hold shifted versions of itself.
         arr = arr.to_numpy()
         dtype = arr.dtype
 

pandas/core/arrays/__init__.py

@@ -11,7 +11,7 @@
 from pandas.core.arrays.integer import IntegerArray
 from pandas.core.arrays.interval import IntervalArray
 from pandas.core.arrays.masked import BaseMaskedArray
-from pandas.core.arrays.numpy_ import PandasArray
+from pandas.core.arrays.numpy_ import NumpyExtensionArray
 from pandas.core.arrays.period import (
     PeriodArray,
     period_array,
@@ -34,7 +34,7 @@
     "FloatingArray",
     "IntegerArray",
     "IntervalArray",
-    "PandasArray",
+    "NumpyExtensionArray",
     "PeriodArray",
     "period_array",
     "SparseArray",

pandas/core/arrays/_mixins.py

@@ -317,7 +317,8 @@ def fillna(self, value=None, method=None, limit: int | None = None) -> Self:
                 func(npvalues, limit=limit, mask=mask.T)
                 npvalues = npvalues.T
 
-                # TODO: PandasArray didn't used to copy, need tests for this
+                # TODO: NumpyExtensionArray didn't used to copy, need tests
+                #  for this
                 new_values = self._from_backing_data(npvalues)
             else:
                 # fill with value

pandas/core/arrays/categorical.py

@@ -2645,18 +2645,18 @@ def _str_map(
         # Optimization to apply the callable `f` to the categories once
         # and rebuild the result by `take`ing from the result with the codes.
         # Returns the same type as the object-dtype implementation though.
-        from pandas.core.arrays import PandasArray
+        from pandas.core.arrays import NumpyExtensionArray
 
         categories = self.categories
         codes = self.codes
-        result = PandasArray(categories.to_numpy())._str_map(f, na_value, dtype)
+        result = NumpyExtensionArray(categories.to_numpy())._str_map(f, na_value, dtype)
         return take_nd(result, codes, fill_value=na_value)
 
     def _str_get_dummies(self, sep: str = "|"):
         # sep may not be in categories. Just bail on this.
-        from pandas.core.arrays import PandasArray
+        from pandas.core.arrays import NumpyExtensionArray
 
-        return PandasArray(self.astype(str))._str_get_dummies(sep)
+        return NumpyExtensionArray(self.astype(str))._str_get_dummies(sep)
 
     # ------------------------------------------------------------------------
     # GroupBy Methods

pandas/core/arrays/datetimelike.py

@@ -652,7 +652,8 @@ def _validate_listlike(self, value, allow_object: bool = False):
                     msg = self._validation_error_message(value, True)
                     raise TypeError(msg)
 
-        # Do type inference if necessary up front (after unpacking PandasArray)
+        # Do type inference if necessary up front (after unpacking
+        # NumpyExtensionArray)
         # e.g. we passed PeriodIndex.values and got an ndarray of Periods
         value = extract_array(value, extract_numpy=True)
         value = pd_array(value)

pandas/core/arrays/numpy_.py

@@ -17,7 +17,7 @@
 from pandas.core.dtypes.astype import astype_array
 from pandas.core.dtypes.cast import construct_1d_object_array_from_listlike
 from pandas.core.dtypes.common import pandas_dtype
-from pandas.core.dtypes.dtypes import PandasDtype
+from pandas.core.dtypes.dtypes import NumpyEADtype
 from pandas.core.dtypes.missing import isna
 
 from pandas.core import (
@@ -48,7 +48,7 @@
 
 # error: Definition of "_concat_same_type" in base class "NDArrayBacked" is
 # incompatible with definition in base class "ExtensionArray"
-class PandasArray(  # type: ignore[misc]
+class NumpyExtensionArray(  # type: ignore[misc]
     OpsMixin,
     NDArrayBackedExtensionArray,
     ObjectStringArrayMixin,
@@ -76,19 +76,21 @@ class PandasArray(  # type: ignore[misc]
     """
 
     # If you're wondering why pd.Series(cls) doesn't put the array in an
-    # ExtensionBlock, search for `ABCPandasArray`. We check for
+    # ExtensionBlock, search for `ABCNumpyExtensionArray`. We check for
     # that _typ to ensure that users don't unnecessarily use EAs inside
     # pandas internals, which turns off things like block consolidation.
     _typ = "npy_extension"
     __array_priority__ = 1000
     _ndarray: np.ndarray
-    _dtype: PandasDtype
+    _dtype: NumpyEADtype
     _internal_fill_value = np.nan
 
     # ------------------------------------------------------------------------
     # Constructors
 
-    def __init__(self, values: np.ndarray | PandasArray, copy: bool = False) -> None:
+    def __init__(
+        self, values: np.ndarray | NumpyExtensionArray, copy: bool = False
+    ) -> None:
         if isinstance(values, type(self)):
             values = values._ndarray
         if not isinstance(values, np.ndarray):
@@ -98,19 +100,19 @@ def __init__(self, values: np.ndarray | PandasArray, copy: bool = False) -> None
 
         if values.ndim == 0:
             # Technically we support 2, but do not advertise that fact.
-            raise ValueError("PandasArray must be 1-dimensional.")
+            raise ValueError("NumpyExtensionArray must be 1-dimensional.")
 
         if copy:
             values = values.copy()
 
-        dtype = PandasDtype(values.dtype)
+        dtype = NumpyEADtype(values.dtype)
         super().__init__(values, dtype)
 
     @classmethod
     def _from_sequence(
         cls, scalars, *, dtype: Dtype | None = None, copy: bool = False
-    ) -> PandasArray:
-        if isinstance(dtype, PandasDtype):
+    ) -> NumpyExtensionArray:
+        if isinstance(dtype, NumpyEADtype):
             dtype = dtype._dtype
 
         # error: Argument "dtype" to "asarray" has incompatible type
@@ -131,14 +133,14 @@ def _from_sequence(
             result = result.copy()
         return cls(result)
 
-    def _from_backing_data(self, arr: np.ndarray) -> PandasArray:
+    def _from_backing_data(self, arr: np.ndarray) -> NumpyExtensionArray:
         return type(self)(arr)
 
     # ------------------------------------------------------------------------
     # Data
 
     @property
-    def dtype(self) -> PandasDtype:
+    def dtype(self) -> NumpyEADtype:
         return self._dtype
 
     # ------------------------------------------------------------------------
@@ -151,7 +153,7 @@ def __array_ufunc__(self, ufunc: np.ufunc, method: str, *inputs, **kwargs):
         # Lightly modified version of
         # https://numpy.org/doc/stable/reference/generated/numpy.lib.mixins.NDArrayOperatorsMixin.html
         # The primary modification is not boxing scalar return values
-        # in PandasArray, since pandas' ExtensionArrays are 1-d.
+        # in NumpyExtensionArray, since pandas' ExtensionArrays are 1-d.
         out = kwargs.get("out", ())
 
         result = arraylike.maybe_dispatch_ufunc_to_dunder_op(
@@ -175,10 +177,12 @@ def __array_ufunc__(self, ufunc: np.ufunc, method: str, *inputs, **kwargs):
                 return result
 
         # Defer to the implementation of the ufunc on unwrapped values.
-        inputs = tuple(x._ndarray if isinstance(x, PandasArray) else x for x in inputs)
+        inputs = tuple(
+            x._ndarray if isinstance(x, NumpyExtensionArray) else x for x in inputs
+        )
         if out:
             kwargs["out"] = tuple(
-                x._ndarray if isinstance(x, PandasArray) else x for x in out
+                x._ndarray if isinstance(x, NumpyExtensionArray) else x for x in out
             )
         result = getattr(ufunc, method)(*inputs, **kwargs)
 
@@ -499,20 +503,20 @@ def to_numpy(
     # ------------------------------------------------------------------------
     # Ops
 
-    def __invert__(self) -> PandasArray:
+    def __invert__(self) -> NumpyExtensionArray:
         return type(self)(~self._ndarray)
 
-    def __neg__(self) -> PandasArray:
+    def __neg__(self) -> NumpyExtensionArray:
         return type(self)(-self._ndarray)
 
-    def __pos__(self) -> PandasArray:
+    def __pos__(self) -> NumpyExtensionArray:
         return type(self)(+self._ndarray)
 
-    def __abs__(self) -> PandasArray:
+    def __abs__(self) -> NumpyExtensionArray:
         return type(self)(abs(self._ndarray))
 
     def _cmp_method(self, other, op):
-        if isinstance(other, PandasArray):
+        if isinstance(other, NumpyExtensionArray):
             other = other._ndarray
 
         other = ops.maybe_prepare_scalar_for_op(other, (len(self),))
@@ -538,7 +542,7 @@ def _cmp_method(self, other, op):
 
     def _wrap_ndarray_result(self, result: np.ndarray):
         # If we have timedelta64[ns] result, return a TimedeltaArray instead
-        #  of a PandasArray
+        #  of a NumpyExtensionArray
         if result.dtype.kind == "m" and is_supported_unit(
             get_unit_from_dtype(result.dtype)
         ):