Backport PR #45523: DEPR: restore to_frame() name=None behaviour but deprecate it (#45529)

Co-authored-by: Joris Van den Bossche <[email protected]>

Author: meeseeksmachine

doc/source/whatsnew/v1.4.0.rst

@@ -696,6 +696,7 @@ Other Deprecations
 - Deprecated the behavior of :meth:`Timestamp.utcfromtimestamp`, in the future it will return a timezone-aware UTC :class:`Timestamp` (:issue:`22451`)
 - Deprecated :meth:`NaT.freq` (:issue:`45071`)
 - Deprecated behavior of :class:`Series` and :class:`DataFrame` construction when passed float-dtype data containing ``NaN`` and an integer dtype ignoring the dtype argument; in a future version this will raise (:issue:`40110`)
+- Deprecated the behaviour of :meth:`Series.to_frame` and :meth:`Index.to_frame` to ignore the ``name`` argument when ``name=None``. Currently, this means to preserve the existing name, but in the future explicitly passing ``name=None`` will set ``None`` as the name of the column in the resulting DataFrame (:issue:`44212`)
 
 .. ---------------------------------------------------------------------------
 
@@ -1041,7 +1042,6 @@ Other
 - Bug in :meth:`CustomBusinessMonthBegin.__add__` (:meth:`CustomBusinessMonthEnd.__add__`) not applying the extra ``offset`` parameter when beginning (end) of the target month is already a business day (:issue:`41356`)
 - Bug in :meth:`RangeIndex.union` with another ``RangeIndex`` with matching (even) ``step`` and starts differing by strictly less than ``step / 2`` (:issue:`44019`)
 - Bug in :meth:`RangeIndex.difference` with ``sort=None`` and ``step<0`` failing to sort (:issue:`44085`)
-- Bug in :meth:`Series.to_frame` and :meth:`Index.to_frame` ignoring the ``name`` argument when ``name=None`` is explicitly passed (:issue:`44212`)
 - Bug in :meth:`Series.replace` and :meth:`DataFrame.replace` with ``value=None`` and ExtensionDtypes (:issue:`44270`, :issue:`37899`)
 - Bug in :meth:`FloatingArray.equals` failing to consider two arrays equal if they contain ``np.nan`` values (:issue:`44382`)
 - Bug in :meth:`DataFrame.shift` with ``axis=1`` and ``ExtensionDtype`` columns incorrectly raising when an incompatible ``fill_value`` is passed (:issue:`44564`)

pandas/core/indexes/base.py

@@ -1625,6 +1625,17 @@ def to_frame(
         """
         from pandas import DataFrame
 
+        if name is None:
+            warnings.warn(
+                "Explicitly passing `name=None` currently preserves the Index's name "
+                "or uses a default name of 0. This behaviour is deprecated, and in "
+                "the future `None` will be used as the name of the resulting "
+                "DataFrame column.",
+                FutureWarning,
+                stacklevel=find_stack_level(),
+            )
+            name = lib.no_default
+
         if name is lib.no_default:
             name = self.name or 0
         result = DataFrame({name: self._values.copy()})

pandas/core/indexes/multi.py

@@ -1762,6 +1762,17 @@ def to_frame(self, index: bool = True, name=lib.no_default) -> DataFrame:
         """
         from pandas import DataFrame
 
+        if name is None:
+            warnings.warn(
+                "Explicitly passing `name=None` currently preserves the Index's name "
+                "or uses a default name of 0. This behaviour is deprecated, and in "
+                "the future `None` will be used as the name of the resulting "
+                "DataFrame column.",
+                FutureWarning,
+                stacklevel=find_stack_level(),
+            )
+            name = lib.no_default
+
         if name is not lib.no_default:
             if not is_list_like(name):
                 raise TypeError("'name' must be a list / sequence of column names.")

pandas/core/series.py

@@ -1752,7 +1752,7 @@ def to_frame(self, name: Hashable = lib.no_default) -> DataFrame:
 
         Parameters
         ----------
-        name : object, default None
+        name : object, optional
             The passed name should substitute for the series name (if it has
             one).
 
@@ -1771,6 +1771,17 @@ def to_frame(self, name: Hashable = lib.no_default) -> DataFrame:
         1    b
         2    c
         """
+        if name is None:
+            warnings.warn(
+                "Explicitly passing `name=None` currently preserves the Series' name "
+                "or uses a default name of 0. This behaviour is deprecated, and in "
+                "the future `None` will be used as the name of the resulting "
+                "DataFrame column.",
+                FutureWarning,
+                stacklevel=find_stack_level(),
+            )
+            name = lib.no_default
+
         columns: Index
         if name is lib.no_default:
             name = self.name

pandas/tests/indexes/datetimes/methods/test_to_frame.py

@@ -17,10 +17,15 @@ def test_to_frame_datetime_tz(self):
     def test_to_frame_respects_none_name(self):
         # GH#44212 if we explicitly pass name=None, then that should be respected,
         #  not changed to 0
+        # GH-45448 this is first deprecated to only change in the future
         idx = date_range(start="2019-01-01", end="2019-01-30", freq="D", tz="UTC")
-        result = idx.to_frame(name=None)
-        exp_idx = Index([None], dtype=object)
+        with tm.assert_produces_warning(FutureWarning):
+            result = idx.to_frame(name=None)
+        # exp_idx = Index([None], dtype=object)
+        exp_idx = Index([0])
         tm.assert_index_equal(exp_idx, result.columns)
 
-        result = idx.rename("foo").to_frame(name=None)
+        with tm.assert_produces_warning(FutureWarning):
+            result = idx.rename("foo").to_frame(name=None)
+        exp_idx = Index(["foo"], dtype=object)
         tm.assert_index_equal(exp_idx, result.columns)

pandas/tests/series/methods/test_to_frame.py

@@ -10,13 +10,18 @@ class TestToFrame:
     def test_to_frame_respects_name_none(self):
         # GH#44212 if we explicitly pass name=None, then that should be respected,
         #  not changed to 0
+        # GH-45448 this is first deprecated to only change in the future
         ser = Series(range(3))
-        result = ser.to_frame(None)
+        with tm.assert_produces_warning(FutureWarning):
+            result = ser.to_frame(None)
 
-        exp_index = Index([None], dtype=object)
+        # exp_index = Index([None], dtype=object)
+        exp_index = Index([0])
         tm.assert_index_equal(result.columns, exp_index)
 
-        result = ser.rename("foo").to_frame(None)
+        with tm.assert_produces_warning(FutureWarning):
+            result = ser.rename("foo").to_frame(None)
+        exp_index = Index(["foo"], dtype=object)
         tm.assert_index_equal(result.columns, exp_index)
 
     def test_to_frame(self, datetime_series):