REF: use _cast_pointwise_result in map

.gitignore

@@ -141,3 +141,5 @@ doc/source/savefig/
 # Pyodide/WASM related files #
 ##############################
 /.pyodide-xbuildenv-*
+
+.venv/

pandas/core/arrays/arrow/array.py

@@ -1612,15 +1612,23 @@ def to_numpy(
             result[~mask] = data[~mask]._pa_array.to_numpy()
         return result
 
-    def map(self, mapper, na_action: Literal["ignore"] | None = None):
+    def map(
+        self,
+        mapper,
+        na_action: Literal["ignore"] | None = None,
+        preserve_dtype: bool = False,
+    ):
         if is_numeric_dtype(self.dtype):
-            return map_array(self.to_numpy(), mapper, na_action=na_action)
+            result = map_array(self.to_numpy(), mapper, na_action=na_action)
+            if preserve_dtype:
+                result = self._cast_pointwise_result(result)
+            return result
         else:
             # For "mM" cases, the super() method passes `self` without the
             #  to_numpy call, which inside map_array casts to ndarray[object].
             #  Without the to_numpy() call, NA is preserved instead of changed
             #  to None.
-            return super().map(mapper, na_action)
+            return super().map(mapper, na_action, preserve_dtype=preserve_dtype)
 
     @doc(ExtensionArray.duplicated)
     def duplicated(

pandas/core/arrays/base.py

@@ -2538,7 +2538,12 @@ def __array_ufunc__(self, ufunc: np.ufunc, method: str, *inputs, **kwargs):
 
         return arraylike.default_array_ufunc(self, ufunc, method, *inputs, **kwargs)
 
-    def map(self, mapper, na_action: Literal["ignore"] | None = None):
+    def map(
+        self,
+        mapper,
+        na_action: Literal["ignore"] | None = None,
+        preserve_dtype: bool = False,
+    ):
         """
         Map values using an input mapping or function.
 
@@ -2550,6 +2555,12 @@ def map(self, mapper, na_action: Literal["ignore"] | None = None):
             If 'ignore', propagate NA values, without passing them to the
             mapping correspondence. If 'ignore' is not supported, a
             ``NotImplementedError`` should be raised.
+        preserve_dtype : bool, default False
+            If True, attempt to cast the elementwise result back to the
+            original ExtensionArray type (and dtype) when possible. This is
+            primarily intended for identity or dtype-preserving mappings.
+            If False, the result of the mapping is returned as produced by
+            the underlying implementation (typically a NumPy ndarray).
 
         Returns
         -------
@@ -2558,7 +2569,10 @@ def map(self, mapper, na_action: Literal["ignore"] | None = None):
             If the function returns a tuple with more than one element
             a MultiIndex will be returned.
         """
-        return map_array(self, mapper, na_action=na_action)
+        results = map_array(self, mapper, na_action=na_action)
+        if preserve_dtype:
+            results = self._cast_pointwise_result(results)
+        return results
 
     # ------------------------------------------------------------------------
     # GroupBy Methods

pandas/core/arrays/categorical.py

@@ -1514,6 +1514,7 @@ def map(
         self,
         mapper,
         na_action: Literal["ignore"] | None = None,
+        preserve_dtype: bool = True,
     ):
         """
         Map categories using an input mapping or function.
@@ -1535,6 +1536,9 @@ def map(
             If 'ignore', propagate NaN values, without passing them to the
             mapping correspondence.
 
+        preserve_dtype : bool, default True
+            Please safely ignore this parameter.
+
         Returns
         -------
         pandas.Categorical or pandas.Index

pandas/core/arrays/datetimelike.py

@@ -742,7 +742,13 @@ def _unbox(self, other) -> np.int64 | np.datetime64 | np.timedelta64 | np.ndarra
     #  pandas assumes they're there.
 
     @ravel_compat
-    def map(self, mapper, na_action: Literal["ignore"] | None = None):
+    def map(
+        self,
+        mapper,
+        na_action: Literal["ignore"] | None = None,
+        preserve_type: bool = True,
+    ):
+        """Safely ignore the `preserve_type` parameter"""
         from pandas import Index
 
         result = map_array(self, mapper, na_action=na_action)

pandas/core/arrays/masked.py

@@ -1397,8 +1397,17 @@ def max(self, *, skipna: bool = True, axis: AxisInt | None = 0, **kwargs):
         )
         return self._wrap_reduction_result("max", result, skipna=skipna, axis=axis)
 
-    def map(self, mapper, na_action: Literal["ignore"] | None = None):
-        return map_array(self.to_numpy(), mapper, na_action=na_action)
+    def map(
+        self,
+        mapper,
+        na_action: Literal["ignore"] | None = None,
+        preserve_dtype: bool = False,
+    ):
+        """See ExtensionArray.map."""
+        result = map_array(self.to_numpy(), mapper, na_action=na_action)
+        if preserve_dtype:
+            result = self._cast_pointwise_result(result)
+        return result
 
     @overload
     def any(

pandas/core/arrays/sparse/array.py

@@ -1337,7 +1337,12 @@ def astype(self, dtype: AstypeArg | None = None, copy: bool = True):
 
         return self._simple_new(sp_values, self.sp_index, dtype)
 
-    def map(self, mapper, na_action: Literal["ignore"] | None = None) -> Self:
+    def map(
+        self,
+        mapper,
+        na_action: Literal["ignore"] | None = None,
+        preserve_dtype: bool = True,
+    ) -> Self:
         """
         Map categories using an input mapping or function.
 
@@ -1348,6 +1353,8 @@ def map(self, mapper, na_action: Literal["ignore"] | None = None) -> Self:
         na_action : {None, 'ignore'}, default None
             If 'ignore', propagate NA values, without passing them to the
             mapping correspondence.
+        preserve_dtype : bool, default True
+            Please safely ignore this parameter.
 
         Returns
         -------

pandas/core/groupby/groupby.py

@@ -4321,7 +4321,7 @@ def nth(self) -> GroupByNthSelector:
     def _nth(
         self,
         n: PositionalIndexer | tuple,
-        dropna: Literal["any", "all", None] = None,
+        dropna: Literal["any", "all"] | None = None,
     ) -> NDFrameT:
         if not dropna:
             mask = self._make_mask_from_positional_indexer(n)

pandas/core/groupby/indexing.py

@@ -296,7 +296,7 @@ def __init__(self, groupby_object: groupby.GroupBy) -> None:
     def __call__(
         self,
         n: PositionalIndexer | tuple,
-        dropna: Literal["any", "all", None] = None,
+        dropna: Literal["any", "all"] | None = None,
     ) -> DataFrame | Series:
         return self.groupby_object._nth(n, dropna)
 

pandas/io/html.py

@@ -220,7 +220,7 @@ def __init__(
         attrs: dict[str, str] | None,
         encoding: str,
         displayed_only: bool,
-        extract_links: Literal[None, "header", "footer", "body", "all"],
+        extract_links: Literal["header", "footer", "body", "all"] | None,
         storage_options: StorageOptions = None,
     ) -> None:
         self.io = io
@@ -1042,7 +1042,7 @@ def read_html(
     na_values: Iterable[object] | None = None,
     keep_default_na: bool = True,
     displayed_only: bool = True,
-    extract_links: Literal[None, "header", "footer", "body", "all"] = None,
+    extract_links: Literal["header", "footer", "body", "all"] | None = None,
     dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
     storage_options: StorageOptions = None,
 ) -> list[DataFrame]:

pandas/tests/frame/test_query_eval.py

@@ -160,21 +160,13 @@ def test_query_empty_string(self):
             df.query("")
 
     def test_query_duplicate_column_name(self, engine, parser):
-        df = DataFrame(
-            {
-                "A": range(3),
-                "B": range(3),
-                "C": range(3)
-            }
-        ).rename(columns={"B": "A"})
+        df = DataFrame({"A": range(3), "B": range(3), "C": range(3)}).rename(
+            columns={"B": "A"}
+        )
 
         res = df.query("C == 1", engine=engine, parser=parser)
 
-        expect = DataFrame(
-            [[1, 1, 1]],
-            columns=["A", "A", "C"],
-            index=[1]
-        )
+        expect = DataFrame([[1, 1, 1]], columns=["A", "A", "C"], index=[1])
 
         tm.assert_frame_equal(res, expect)
 
@@ -1140,9 +1132,7 @@ def test_query_with_nested_special_character(self, parser, engine):
             [">=", operator.ge],
         ],
     )
-    def test_query_lex_compare_strings(
-        self, parser, engine, op, func
-    ):
+    def test_query_lex_compare_strings(self, parser, engine, op, func):
         a = Series(np.random.default_rng(2).choice(list("abcde"), 20))
         b = Series(np.arange(a.size))
         df = DataFrame({"X": a, "Y": b})