Merge remote-tracking branch 'upstream/main' into bugfix-slice-selection

Author: tehunter

doc/source/whatsnew/v3.0.0.rst

@@ -207,6 +207,7 @@ Removal of prior version deprecations/changes
 - All arguments except ``name`` in :meth:`Index.rename` are now keyword only (:issue:`56493`)
 - All arguments except the first ``path``-like argument in IO writers are now keyword only (:issue:`54229`)
 - Removed "freq" keyword from :class:`PeriodArray` constructor, use "dtype" instead (:issue:`52462`)
+- Removed deprecated "method" and "limit" keywords from :meth:`Series.replace` and :meth:`DataFrame.replace` (:issue:`53492`)
 - Removed the "closed" and "normalize" keywords in :meth:`DatetimeIndex.__new__` (:issue:`52628`)
 - Removed the "closed" and "unit" keywords in :meth:`TimedeltaIndex.__new__` (:issue:`52628`, :issue:`55499`)
 - All arguments in :meth:`Index.sort_values` are now keyword only (:issue:`56493`)
@@ -298,6 +299,7 @@ Performance improvements
 - Performance improvement in :meth:`DataFrameGroupBy.ffill`, :meth:`DataFrameGroupBy.bfill`, :meth:`SeriesGroupBy.ffill`, and :meth:`SeriesGroupBy.bfill` (:issue:`56902`)
 - Performance improvement in :meth:`Index.join` by propagating cached attributes in cases where the result matches one of the inputs (:issue:`57023`)
 - Performance improvement in :meth:`Index.take` when ``indices`` is a full range indexer from zero to length of index (:issue:`56806`)
+- Performance improvement in :meth:`Index.to_frame` returning a :class:`RangeIndex` columns of a :class:`Index` when possible. (:issue:`58018`)
 - Performance improvement in :meth:`MultiIndex.equals` for equal length indexes (:issue:`56990`)
 - Performance improvement in :meth:`RangeIndex.__getitem__` with a boolean mask or integers returning a :class:`RangeIndex` instead of a :class:`Index` when possible. (:issue:`57588`)
 - Performance improvement in :meth:`RangeIndex.append` when appending the same index (:issue:`57252`)
@@ -319,6 +321,7 @@ Bug fixes
 ~~~~~~~~~
 - Fixed bug in :class:`SparseDtype` for equal comparison with na fill value. (:issue:`54770`)
 - Fixed bug in :meth:`.DataFrameGroupBy.median` where nat values gave an incorrect result. (:issue:`57926`)
+- Fixed bug in :meth:`DataFrame.cumsum` which was raising ``IndexError`` if dtype is ``timedelta64[ns]`` (:issue:`57956`)
 - Fixed bug in :meth:`DataFrame.join` inconsistently setting result index name (:issue:`55815`)
 - Fixed bug in :meth:`DataFrame.to_string` that raised ``StopIteration`` with nested DataFrames. (:issue:`16098`)
 - Fixed bug in :meth:`DataFrame.update` bool dtype being converted to object (:issue:`55509`)

pandas/conftest.py

@@ -150,7 +150,6 @@ def pytest_collection_modifyitems(items, config) -> None:
         ("is_categorical_dtype", "is_categorical_dtype is deprecated"),
         ("is_sparse", "is_sparse is deprecated"),
         ("DataFrameGroupBy.fillna", "DataFrameGroupBy.fillna is deprecated"),
-        ("NDFrame.replace", "The 'method' keyword"),
         ("NDFrame.replace", "Series.replace without 'value'"),
         ("NDFrame.clip", "Downcasting behavior in Series and DataFrame methods"),
         ("Series.idxmin", "The behavior of Series.idxmin"),

pandas/core/array_algos/datetimelike_accumulations.py

@@ -49,7 +49,8 @@ def _cum_func(
     if not skipna:
         mask = np.maximum.accumulate(mask)
 
-    result = func(y)
+    # GH 57956
+    result = func(y, axis=0)
     result[mask] = iNaT
 
     if values.dtype.kind in "mM":

pandas/core/generic.py

@@ -6727,12 +6727,10 @@ def _pad_or_backfill(
         axis = self._get_axis_number(axis)
         method = clean_fill_method(method)
 
-        if not self._mgr.is_single_block and axis == 1:
-            # e.g. test_align_fill_method
-            # TODO(3.0): once downcast is removed, we can do the .T
-            #  in all axis=1 cases, and remove axis kward from mgr.pad_or_backfill.
-            if inplace:
+        if axis == 1:
+            if not self._mgr.is_single_block and inplace:
                 raise NotImplementedError()
+            # e.g. test_align_fill_method
             result = self.T._pad_or_backfill(
                 method=method, limit=limit, limit_area=limit_area
             ).T
@@ -6741,7 +6739,6 @@ def _pad_or_backfill(
 
         new_mgr = self._mgr.pad_or_backfill(
             method=method,
-            axis=self._get_block_manager_axis(axis),
             limit=limit,
             limit_area=limit_area,
             inplace=inplace,
@@ -7285,9 +7282,7 @@ def replace(
         value=...,
         *,
         inplace: Literal[False] = ...,
-        limit: int | None = ...,
         regex: bool = ...,
-        method: Literal["pad", "ffill", "bfill"] | lib.NoDefault = ...,
     ) -> Self: ...
 
     @overload
@@ -7297,9 +7292,7 @@ def replace(
         value=...,
         *,
         inplace: Literal[True],
-        limit: int | None = ...,
         regex: bool = ...,
-        method: Literal["pad", "ffill", "bfill"] | lib.NoDefault = ...,
     ) -> None: ...
 
     @overload
@@ -7309,9 +7302,7 @@ def replace(
         value=...,
         *,
         inplace: bool = ...,
-        limit: int | None = ...,
         regex: bool = ...,
-        method: Literal["pad", "ffill", "bfill"] | lib.NoDefault = ...,
     ) -> Self | None: ...
 
     @final
@@ -7326,32 +7317,9 @@ def replace(
         value=lib.no_default,
         *,
         inplace: bool = False,
-        limit: int | None = None,
         regex: bool = False,
-        method: Literal["pad", "ffill", "bfill"] | lib.NoDefault = lib.no_default,
     ) -> Self | None:
-        if method is not lib.no_default:
-            warnings.warn(
-                # GH#33302
-                f"The 'method' keyword in {type(self).__name__}.replace is "
-                "deprecated and will be removed in a future version.",
-                FutureWarning,
-                stacklevel=find_stack_level(),
-            )
-        elif limit is not None:
-            warnings.warn(
-                # GH#33302
-                f"The 'limit' keyword in {type(self).__name__}.replace is "
-                "deprecated and will be removed in a future version.",
-                FutureWarning,
-                stacklevel=find_stack_level(),
-            )
-        if (
-            value is lib.no_default
-            and method is lib.no_default
-            and not is_dict_like(to_replace)
-            and regex is False
-        ):
+        if value is lib.no_default and not is_dict_like(to_replace) and regex is False:
             # case that goes through _replace_single and defaults to method="pad"
             warnings.warn(
                 # GH#33302
@@ -7387,14 +7355,11 @@ def replace(
         if not is_bool(regex) and to_replace is not None:
             raise ValueError("'to_replace' must be 'None' if 'regex' is not a bool")
 
-        if value is lib.no_default or method is not lib.no_default:
+        if value is lib.no_default:
             # GH#36984 if the user explicitly passes value=None we want to
             #  respect that. We have the corner case where the user explicitly
             #  passes value=None *and* a method, which we interpret as meaning
             #  they want the (documented) default behavior.
-            if method is lib.no_default:
-                # TODO: get this to show up as the default in the docs?
-                method = "pad"
 
             # passing a single value that is scalar like
             # when value is None (GH5319), for compat
@@ -7408,12 +7373,12 @@ def replace(
 
                     result = self.apply(
                         Series._replace_single,
-                        args=(to_replace, method, inplace, limit),
+                        args=(to_replace, inplace),
                     )
                     if inplace:
                         return None
                     return result
-                return self._replace_single(to_replace, method, inplace, limit)
+                return self._replace_single(to_replace, inplace)
 
             if not is_dict_like(to_replace):
                 if not is_dict_like(regex):
@@ -7458,9 +7423,7 @@ def replace(
             else:
                 to_replace, value = keys, values
 
-            return self.replace(
-                to_replace, value, inplace=inplace, limit=limit, regex=regex
-            )
+            return self.replace(to_replace, value, inplace=inplace, regex=regex)
         else:
             # need a non-zero len on all axes
             if not self.size:
@@ -7524,9 +7487,7 @@ def replace(
                         f"or a list or dict of strings or regular expressions, "
                         f"you passed a {type(regex).__name__!r}"
                     )
-                return self.replace(
-                    regex, value, inplace=inplace, limit=limit, regex=True
-                )
+                return self.replace(regex, value, inplace=inplace, regex=True)
             else:
                 # dest iterable dict-like
                 if is_dict_like(value):  # NA -> {'A' : 0, 'B' : -1}

pandas/core/indexes/base.py

@@ -1374,16 +1374,19 @@ def _format_attrs(self) -> list[tuple[str_t, str_t | int | bool | None]]:
         return attrs
 
     @final
-    def _get_level_names(self) -> Hashable | Sequence[Hashable]:
+    def _get_level_names(self) -> range | Sequence[Hashable]:
         """
         Return a name or list of names with None replaced by the level number.
         """
         if self._is_multi:
-            return [
-                level if name is None else name for level, name in enumerate(self.names)
-            ]
+            return maybe_sequence_to_range(
+                [
+                    level if name is None else name
+                    for level, name in enumerate(self.names)
+                ]
+            )
         else:
-            return 0 if self.name is None else self.name
+            return range(1) if self.name is None else [self.name]
 
     @final
     def _mpl_repr(self) -> np.ndarray:
@@ -1630,8 +1633,11 @@ def to_frame(
         from pandas import DataFrame
 
         if name is lib.no_default:
-            name = self._get_level_names()
-        result = DataFrame({name: self}, copy=False)
+            result_name = self._get_level_names()
+        else:
+            result_name = Index([name])  # type: ignore[assignment]
+        result = DataFrame(self, copy=False)
+        result.columns = result_name
 
         if index:
             result.index = self

pandas/core/internals/blocks.py

@@ -1343,7 +1343,6 @@ def pad_or_backfill(
         self,
         *,
         method: FillnaOptions,
-        axis: AxisInt = 0,
         inplace: bool = False,
         limit: int | None = None,
         limit_area: Literal["inside", "outside"] | None = None,
@@ -1357,16 +1356,12 @@ def pad_or_backfill(
         # Dispatch to the NumpyExtensionArray method.
         # We know self.array_values is a NumpyExtensionArray bc EABlock overrides
         vals = cast(NumpyExtensionArray, self.array_values)
-        if axis == 1:
-            vals = vals.T
-        new_values = vals._pad_or_backfill(
+        new_values = vals.T._pad_or_backfill(
             method=method,
             limit=limit,
             limit_area=limit_area,
             copy=copy,
-        )
-        if axis == 1:
-            new_values = new_values.T
+        ).T
 
         data = extract_array(new_values, extract_numpy=True)
         return [self.make_block_same_class(data, refs=refs)]
@@ -1814,7 +1809,6 @@ def pad_or_backfill(
         self,
         *,
         method: FillnaOptions,
-        axis: AxisInt = 0,
         inplace: bool = False,
         limit: int | None = None,
         limit_area: Literal["inside", "outside"] | None = None,
@@ -1827,11 +1821,11 @@ def pad_or_backfill(
         elif limit_area is not None:
             raise NotImplementedError(
                 f"{type(values).__name__} does not implement limit_area "
-                "(added in pandas 2.2). 3rd-party ExtnsionArray authors "
+                "(added in pandas 2.2). 3rd-party ExtensionArray authors "
                 "need to add this argument to _pad_or_backfill."
             )
 
-        if values.ndim == 2 and axis == 1:
+        if values.ndim == 2:
             # NDArrayBackedExtensionArray.fillna assumes axis=0
             new_values = values.T._pad_or_backfill(**kwargs).T
         else:

pandas/core/series.py

@@ -5113,28 +5113,22 @@ def info(
         )
 
     @overload
-    def _replace_single(
-        self, to_replace, method: str, inplace: Literal[False], limit
-    ) -> Self: ...
+    def _replace_single(self, to_replace, inplace: Literal[False]) -> Self: ...
 
     @overload
-    def _replace_single(
-        self, to_replace, method: str, inplace: Literal[True], limit
-    ) -> None: ...
+    def _replace_single(self, to_replace, inplace: Literal[True]) -> None: ...
 
     @overload
-    def _replace_single(
-        self, to_replace, method: str, inplace: bool, limit
-    ) -> Self | None: ...
+    def _replace_single(self, to_replace, inplace: bool) -> Self | None: ...
 
     # TODO(3.0): this can be removed once GH#33302 deprecation is enforced
-    def _replace_single(
-        self, to_replace, method: str, inplace: bool, limit
-    ) -> Self | None:
+    def _replace_single(self, to_replace, inplace: bool) -> Self | None:
         """
         Replaces values in a Series using the fill method specified when no
         replacement value is given in the replace method
         """
+        limit = None
+        method = "pad"
 
         result = self if inplace else self.copy()
 

pandas/core/shared_docs.py

@@ -429,20 +429,11 @@
         filled). Regular expressions, strings and lists or dicts of such
         objects are also allowed.
     {inplace}
-    limit : int, default None
-        Maximum size gap to forward or backward fill.
-
-        .. deprecated:: 2.1.0
     regex : bool or same types as `to_replace`, default False
         Whether to interpret `to_replace` and/or `value` as regular
         expressions. Alternatively, this could be a regular expression or a
         list, dict, or array of regular expressions in which case
         `to_replace` must be ``None``.
-    method : {{'pad', 'ffill', 'bfill'}}
-        The method to use when for replacement, when `to_replace` is a
-        scalar, list or tuple and `value` is ``None``.
-
-        .. deprecated:: 2.1.0
 
     Returns
     -------
@@ -538,14 +529,6 @@
     3  1  8  d
     4  4  9  e
 
-    >>> s.replace([1, 2], method='bfill')
-    0    3
-    1    3
-    2    3
-    3    4
-    4    5
-    dtype: int64
-
     **dict-like `to_replace`**
 
     >>> df.replace({{0: 10, 1: 100}})
@@ -615,7 +598,7 @@
     When one uses a dict as the `to_replace` value, it is like the
     value(s) in the dict are equal to the `value` parameter.
     ``s.replace({{'a': None}})`` is equivalent to
-    ``s.replace(to_replace={{'a': None}}, value=None, method=None)``:
+    ``s.replace(to_replace={{'a': None}}, value=None)``:
 
     >>> s.replace({{'a': None}})
     0      10

pandas/tests/frame/methods/test_replace.py

@@ -1171,48 +1171,6 @@ def test_replace_with_empty_dictlike(self, mix_abc):
         tm.assert_frame_equal(df, df.replace({"b": {}}))
         tm.assert_frame_equal(df, df.replace(Series({"b": {}})))
 
-    @pytest.mark.parametrize(
-        "to_replace, method, expected",
-        [
-            (0, "bfill", {"A": [1, 1, 2], "B": [5, np.nan, 7], "C": ["a", "b", "c"]}),
-            (
-                np.nan,
-                "bfill",
-                {"A": [0, 1, 2], "B": [5.0, 7.0, 7.0], "C": ["a", "b", "c"]},
-            ),
-            ("d", "ffill", {"A": [0, 1, 2], "B": [5, np.nan, 7], "C": ["a", "b", "c"]}),
-            (
-                [0, 2],
-                "bfill",
-                {"A": [1, 1, 2], "B": [5, np.nan, 7], "C": ["a", "b", "c"]},
-            ),
-            (
-                [1, 2],
-                "pad",
-                {"A": [0, 0, 0], "B": [5, np.nan, 7], "C": ["a", "b", "c"]},
-            ),
-            (
-                (1, 2),
-                "bfill",
-                {"A": [0, 2, 2], "B": [5, np.nan, 7], "C": ["a", "b", "c"]},
-            ),
-            (
-                ["b", "c"],
-                "ffill",
-                {"A": [0, 1, 2], "B": [5, np.nan, 7], "C": ["a", "a", "a"]},
-            ),
-        ],
-    )
-    def test_replace_method(self, to_replace, method, expected):
-        # GH 19632
-        df = DataFrame({"A": [0, 1, 2], "B": [5, np.nan, 7], "C": ["a", "b", "c"]})
-
-        msg = "The 'method' keyword in DataFrame.replace is deprecated"
-        with tm.assert_produces_warning(FutureWarning, match=msg):
-            result = df.replace(to_replace=to_replace, value=None, method=method)
-        expected = DataFrame(expected)
-        tm.assert_frame_equal(result, expected)
-
     @pytest.mark.parametrize(
         "replace_dict, final_data",
         [({"a": 1, "b": 1}, [[3, 3], [2, 2]]), ({"a": 1, "b": 2}, [[3, 1], [2, 3]])],