DEPR: Deprecate remaining copy usages (#57870)

* DEPR: Deprecate remaining copy usages * Fixup * Fixup tests * Fixup tests --------- Co-authored-by: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>

Author: phofl

doc/source/whatsnew/v3.0.0.rst

@@ -173,6 +173,13 @@ will be removed in a future version:
 - :meth:`DataFrame.astype` / :meth:`Series.astype`
 - :meth:`DataFrame.reindex` / :meth:`Series.reindex`
 - :meth:`DataFrame.reindex_like` / :meth:`Series.reindex_like`
+- :meth:`DataFrame.set_axis` / :meth:`Series.set_axis`
+- :meth:`DataFrame.to_period` / :meth:`Series.to_period`
+- :meth:`DataFrame.to_timestamp` / :meth:`Series.to_timestamp`
+- :meth:`DataFrame.rename` / :meth:`Series.rename`
+- :meth:`DataFrame.transpose`
+- :meth:`DataFrame.swaplevel`
+- :meth:`DataFrame.merge` / :func:`pd.merge`
 
 Copy-on-Write utilizes a lazy copy mechanism that defers copying the data until
 necessary. Use ``.copy`` to trigger an eager copy. The copy keyword has no effect

pandas/core/frame.py

@@ -357,7 +357,7 @@
  of a string to indicate that the column name from `left` or
  `right` should be left as-is, with no suffix. At least one of the
  values must not be None.
-copy : bool, default True
+copy : bool, default False
  If False, avoid copy if possible.
 
  .. note::
@@ -371,6 +371,8 @@
 
  You can already get the future behavior and improvements through
  enabling copy on write ``pd.options.mode.copy_on_write = True``
+
+ .. deprecated:: 3.0.0
 indicator : bool or str, default False
  If True, adds a column to the output DataFrame called "_merge" with
  information on the source of each row. The column can be given a different
@@ -3576,7 +3578,11 @@ def memory_usage(self, index: bool = True, deep: bool = False) -> Series:
  result = index_memory_usage._append(result)
  return result
 
- def transpose(self, *args, copy: bool = False) -> DataFrame:
+ def transpose(
+ self,
+ *args,
+ copy: bool | lib.NoDefault = lib.no_default,
+ ) -> DataFrame:
  """
  Transpose index and columns.
 
@@ -3607,6 +3613,8 @@ def transpose(self, *args, copy: bool = False) -> DataFrame:
  You can already get the future behavior and improvements through
  enabling copy on write ``pd.options.mode.copy_on_write = True``
 
+ .. deprecated:: 3.0.0
+
  Returns
  -------
  DataFrame
@@ -3687,6 +3695,7 @@ def transpose(self, *args, copy: bool = False) -> DataFrame:
  1 object
  dtype: object
  """
+ self._check_copy_deprecation(copy)
  nv.validate_transpose(args, {})
  # construct the args
 
@@ -5062,9 +5071,9 @@ def set_axis(
  labels,
  *,
  axis: Axis = 0,
- copy: bool | None = None,
+ copy: bool | lib.NoDefault = lib.no_default,
  ) -> DataFrame:
- return super().set_axis(labels, axis=axis)
+ return super().set_axis(labels, axis=axis, copy=copy)
 
  @doc(
  NDFrame.reindex,
@@ -5313,7 +5322,7 @@ def rename(
  index: Renamer | None = ...,
  columns: Renamer | None = ...,
  axis: Axis | None = ...,
- copy: bool | None = ...,
+ copy: bool | lib.NoDefault = lib.no_default,
  inplace: Literal[True],
  level: Level = ...,
  errors: IgnoreRaise = ...,
@@ -5327,7 +5336,7 @@ def rename(
  index: Renamer | None = ...,
  columns: Renamer | None = ...,
  axis: Axis | None = ...,
- copy: bool | None = ...,
+ copy: bool | lib.NoDefault = lib.no_default,
  inplace: Literal[False] = ...,
  level: Level = ...,
  errors: IgnoreRaise = ...,
@@ -5341,7 +5350,7 @@ def rename(
  index: Renamer | None = ...,
  columns: Renamer | None = ...,
  axis: Axis | None = ...,
- copy: bool | None = ...,
+ copy: bool | lib.NoDefault = lib.no_default,
  inplace: bool = ...,
  level: Level = ...,
  errors: IgnoreRaise = ...,
@@ -5354,7 +5363,7 @@ def rename(
  index: Renamer | None = None,
  columns: Renamer | None = None,
  axis: Axis | None = None,
- copy: bool | None = None,
+ copy: bool | lib.NoDefault = lib.no_default,
  inplace: bool = False,
  level: Level | None = None,
  errors: IgnoreRaise = "ignore",
@@ -5384,7 +5393,7 @@ def rename(
  axis : {0 or 'index', 1 or 'columns'}, default 0
  Axis to target with ``mapper``. Can be either the axis name
  ('index', 'columns') or number (0, 1). The default is 'index'.
- copy : bool, default True
+ copy : bool, default False
  Also copy underlying data.
 
  .. note::
@@ -5398,6 +5407,8 @@ def rename(
 
  You can already get the future behavior and improvements through
  enabling copy on write ``pd.options.mode.copy_on_write = True``
+
+ .. deprecated:: 3.0.0
  inplace : bool, default False
  Whether to modify the DataFrame rather than creating a new one.
  If True then value of copy is ignored.
@@ -5478,6 +5489,7 @@ def rename(
  2 2 5
  4 3 6
  """
+ self._check_copy_deprecation(copy)
  return super()._rename(
  mapper=mapper,
  index=index,
@@ -10657,10 +10669,12 @@ def merge(
  right_index: bool = False,
  sort: bool = False,
  suffixes: Suffixes = ("_x", "_y"),
- copy: bool | None = None,
+ copy: bool | lib.NoDefault = lib.no_default,
  indicator: str | bool = False,
  validate: MergeValidate | None = None,
  ) -> DataFrame:
+ self._check_copy_deprecation(copy)
+
  from pandas.core.reshape.merge import merge
 
  return merge(
@@ -12462,7 +12476,7 @@ def to_timestamp(
  freq: Frequency | None = None,
  how: ToTimestampHow = "start",
  axis: Axis = 0,
- copy: bool | None = None,
+ copy: bool | lib.NoDefault = lib.no_default,
  ) -> DataFrame:
  """
  Cast to DatetimeIndex of timestamps, at *beginning* of period.
@@ -12476,7 +12490,7 @@ def to_timestamp(
  vs. end.
  axis : {0 or 'index', 1 or 'columns'}, default 0
  The axis to convert (the index by default).
- copy : bool, default True
+ copy : bool, default False
  If False then underlying input data is not copied.
 
  .. note::
@@ -12491,6 +12505,8 @@ def to_timestamp(
  You can already get the future behavior and improvements through
  enabling copy on write ``pd.options.mode.copy_on_write = True``
 
+ .. deprecated:: 3.0.0
+
  Returns
  -------
  DataFrame
@@ -12527,6 +12543,7 @@ def to_timestamp(
  >>> df2.index
  DatetimeIndex(['2023-01-31', '2024-01-31'], dtype='datetime64[ns]', freq=None)
  """
+ self._check_copy_deprecation(copy)
  new_obj = self.copy(deep=False)
 
  axis_name = self._get_axis_name(axis)
@@ -12540,7 +12557,10 @@ def to_timestamp(
  return new_obj
 
  def to_period(
- self, freq: Frequency | None = None, axis: Axis = 0, copy: bool | None = None
+ self,
+ freq: Frequency | None = None,
+ axis: Axis = 0,
+ copy: bool | lib.NoDefault = lib.no_default,
  ) -> DataFrame:
  """
  Convert DataFrame from DatetimeIndex to PeriodIndex.
@@ -12554,7 +12574,7 @@ def to_period(
  Frequency of the PeriodIndex.
  axis : {0 or 'index', 1 or 'columns'}, default 0
  The axis to convert (the index by default).
- copy : bool, default True
+ copy : bool, default False
  If False then underlying input data is not copied.
 
  .. note::
@@ -12569,6 +12589,8 @@ def to_period(
  You can already get the future behavior and improvements through
  enabling copy on write ``pd.options.mode.copy_on_write = True``
 
+ .. deprecated:: 3.0.0
+
  Returns
  -------
  DataFrame
@@ -12596,6 +12618,7 @@ def to_period(
  >>> idx.to_period("Y")
  PeriodIndex(['2001', '2002', '2003'], dtype='period[Y-DEC]')
  """
+ self._check_copy_deprecation(copy)
  new_obj = self.copy(deep=False)
 
  axis_name = self._get_axis_name(axis)

pandas/core/generic.py

@@ -398,7 +398,7 @@ def flags(self) -> Flags:
  def set_flags(
  self,
  *,
- copy: bool = False,
+ copy: bool | lib.NoDefault = lib.no_default,
  allows_duplicate_labels: bool | None = None,
  ) -> Self:
  """
@@ -420,6 +420,8 @@ def set_flags(
 
  You can already get the future behavior and improvements through
  enabling copy on write ``pd.options.mode.copy_on_write = True``
+
+ .. deprecated:: 3.0.0
  allows_duplicate_labels : bool, optional
  Whether the returned object allows duplicate labels.
 
@@ -454,6 +456,7 @@ def set_flags(
  >>> df2.flags.allows_duplicate_labels
  False
  """
+ self._check_copy_deprecation(copy)
  df = self.copy(deep=False)
  if allows_duplicate_labels is not None:
  df.flags["allows_duplicate_labels"] = allows_duplicate_labels
@@ -679,7 +682,7 @@ def set_axis(
  labels,
  *,
  axis: Axis = 0,
- copy: bool | None = None,
+ copy: bool | lib.NoDefault = lib.no_default,
  ) -> Self:
  """
  Assign desired index to given axis.
@@ -696,7 +699,7 @@ def set_axis(
  The axis to update. The value 0 identifies the rows. For `Series`
  this parameter is unused and defaults to 0.
 
- copy : bool, default True
+ copy : bool, default False
  Whether to make a copy of the underlying data.
 
  .. note::
@@ -711,6 +714,8 @@ def set_axis(
  You can already get the future behavior and improvements through
  enabling copy on write ``pd.options.mode.copy_on_write = True``
 
+ .. deprecated:: 3.0.0
+
  Returns
  -------
  %(klass)s
@@ -720,6 +725,7 @@ def set_axis(
  --------
  %(klass)s.rename_axis : Alter the name of the index%(see_also_sub)s.
  """
+ self._check_copy_deprecation(copy)
  return self._set_axis_nocheck(labels, axis, inplace=False)
 
  @overload
@@ -948,7 +954,6 @@ def _rename(
  index: Renamer | None = ...,
  columns: Renamer | None = ...,
  axis: Axis | None = ...,
- copy: bool | None = ...,
  inplace: Literal[False] = ...,
  level: Level | None = ...,
  errors: str = ...,
@@ -962,7 +967,6 @@ def _rename(
  index: Renamer | None = ...,
  columns: Renamer | None = ...,
  axis: Axis | None = ...,
- copy: bool | None = ...,
  inplace: Literal[True],
  level: Level | None = ...,
  errors: str = ...,
@@ -976,7 +980,6 @@ def _rename(
  index: Renamer | None = ...,
  columns: Renamer | None = ...,
  axis: Axis | None = ...,
- copy: bool | None = ...,
  inplace: bool,
  level: Level | None = ...,
  errors: str = ...,
@@ -990,7 +993,6 @@ def _rename(
  index: Renamer | None = None,
  columns: Renamer | None = None,
  axis: Axis | None = None,
- copy: bool | None = None,
  inplace: bool = False,
  level: Level | None = None,
  errors: str = "ignore",
@@ -1061,7 +1063,7 @@ def rename_axis(
  index=...,
  columns=...,
  axis: Axis = ...,
- copy: bool | None = ...,
+ copy: bool | lib.NoDefault = lib.no_default,
  inplace: Literal[False] = ...,
  ) -> Self: ...
 
@@ -1073,7 +1075,7 @@ def rename_axis(
  index=...,
  columns=...,
  axis: Axis = ...,
- copy: bool | None = ...,
+ copy: bool | lib.NoDefault = lib.no_default,
  inplace: Literal[True],
  ) -> None: ...
 
@@ -1085,7 +1087,7 @@ def rename_axis(
  index=...,
  columns=...,
  axis: Axis = ...,
- copy: bool | None = ...,
+ copy: bool | lib.NoDefault = lib.no_default,
  inplace: bool = ...,
  ) -> Self | None: ...
 
@@ -1096,7 +1098,7 @@ def rename_axis(
  index=lib.no_default,
  columns=lib.no_default,
  axis: Axis = 0,
- copy: bool | None = None,
+ copy: bool | lib.NoDefault = lib.no_default,
  inplace: bool = False,
  ) -> Self | None:
  """
@@ -1118,7 +1120,7 @@ def rename_axis(
  apply to that axis' values.
  axis : {0 or 'index', 1 or 'columns'}, default 0
  The axis to rename.
- copy : bool, default None
+ copy : bool, default False
  Also copy underlying data.
 
  .. note::
@@ -1132,6 +1134,8 @@ def rename_axis(
 
  You can already get the future behavior and improvements through
  enabling copy on write ``pd.options.mode.copy_on_write = True``
+
+ .. deprecated:: 3.0.0
  inplace : bool, default False
  Modifies the object directly, instead of creating a new Series
  or DataFrame.
@@ -1219,6 +1223,7 @@ class name
  cat 4 0
  monkey 2 2
  """
+ self._check_copy_deprecation(copy)
  axes = {"index": index, "columns": columns}
 
  if axis is not None:
@@ -6327,7 +6332,7 @@ def astype(
  return self.copy(deep=False)
 
  # GH 19920: retain column metadata after concat
- result = concat(results, axis=1, copy=False)
+ result = concat(results, axis=1)
  # GH#40810 retain subclass
  # error: Incompatible types in assignment
  # (expression has type "Self", variable has type "DataFrame")

pandas/core/interchange/dataframe.py

@@ -33,7 +33,7 @@ def __init__(self, df: DataFrame, allow_copy: bool = True) -> None:
  Constructor - an instance of this (private) class is returned from
  `pd.DataFrame.__dataframe__`.
  """
- self._df = df.rename(columns=str, copy=False)
+ self._df = df.rename(columns=str)
  self._allow_copy = allow_copy
  for i, _col in enumerate(self._df.columns):
  rechunked = maybe_rechunk(self._df.iloc[:, i], allow_copy=allow_copy)