Merge remote-tracking branch 'upstream/main' into settingwithcopywarning

# Conflicts: #	ci/code_checks.sh #	pandas/core/generic.py #	pandas/core/groupby/groupby.py #	pandas/errors/__init__.py #	pandas/tests/copy_view/test_chained_assignment_deprecation.py #	pandas/tests/copy_view/test_indexing.py #	pandas/tests/indexing/test_chaining_and_caching.py #	pandas/tests/series/test_ufunc.py

ci/code_checks.sh

@@ -69,104 +69,118 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
  $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX01,EX03,EX04,GL01,GL02,GL03,GL04,GL05,GL06,GL07,GL09,GL10,PR03,PR04,PR05,PR06,PR08,PR09,PR10,RT01,RT02,RT04,RT05,SA02,SA03,SA04,SS01,SS02,SS03,SS04,SS05,SS06
  RET=$(($RET + $?)) ; echo $MSG "DONE"
 
- MSG='Partially validate docstrings (EX03)' ; echo $MSG
- $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX03 --ignore_functions \
- pandas.Series.dt.day_name \
- pandas.Series.str.len \
- pandas.Series.cat.set_categories \
- pandas.Series.plot.bar \
- pandas.Series.plot.hist \
- pandas.Series.plot.line \
- pandas.Series.to_sql \
- pandas.Series.to_latex \
- pandas.errors.CategoricalConversionWarning \
- pandas.errors.ChainedAssignmentError \
- pandas.errors.ClosedFileError \
- pandas.errors.DatabaseError \
- pandas.errors.IndexingError \
- pandas.errors.InvalidColumnName \
- pandas.errors.NumExprClobberingError \
- pandas.errors.PossibleDataLossError \
- pandas.errors.PossiblePrecisionLoss \
- pandas.errors.SpecificationError \
- pandas.errors.UndefinedVariableError \
- pandas.errors.ValueLabelTypeMismatch \
- pandas.Timestamp.ceil \
- pandas.Timestamp.floor \
- pandas.Timestamp.round \
- pandas.read_pickle \
- pandas.ExcelWriter \
- pandas.read_json \
- pandas.io.json.build_table_schema \
- pandas.DataFrame.to_latex \
- pandas.io.formats.style.Styler.to_latex \
- pandas.read_parquet \
- pandas.DataFrame.to_sql \
- pandas.read_stata \
- pandas.core.resample.Resampler.pipe \
- pandas.core.resample.Resampler.fillna \
- pandas.core.resample.Resampler.interpolate \
- pandas.plotting.scatter_matrix \
- pandas.pivot \
- pandas.merge_asof \
- pandas.wide_to_long \
- pandas.Index.rename \
- pandas.Index.droplevel \
- pandas.Index.isin \
- pandas.CategoricalIndex.set_categories \
- pandas.MultiIndex.names \
- pandas.MultiIndex.droplevel \
- pandas.IndexSlice \
- pandas.DatetimeIndex.month_name \
- pandas.DatetimeIndex.day_name \
- pandas.core.window.rolling.Rolling.corr \
- pandas.Grouper \
- pandas.core.groupby.SeriesGroupBy.apply \
- pandas.core.groupby.DataFrameGroupBy.apply \
- pandas.core.groupby.SeriesGroupBy.transform \
- pandas.core.groupby.SeriesGroupBy.pipe \
- pandas.core.groupby.DataFrameGroupBy.pipe \
- pandas.core.groupby.DataFrameGroupBy.describe \
- pandas.core.groupby.DataFrameGroupBy.idxmax \
- pandas.core.groupby.DataFrameGroupBy.idxmin \
- pandas.core.groupby.DataFrameGroupBy.value_counts \
- pandas.core.groupby.SeriesGroupBy.describe \
- pandas.core.groupby.DataFrameGroupBy.boxplot \
- pandas.core.groupby.DataFrameGroupBy.hist \
- pandas.io.formats.style.Styler.map \
- pandas.io.formats.style.Styler.apply_index \
- pandas.io.formats.style.Styler.map_index \
- pandas.io.formats.style.Styler.format \
- pandas.io.formats.style.Styler.format_index \
- pandas.io.formats.style.Styler.relabel_index \
- pandas.io.formats.style.Styler.hide \
- pandas.io.formats.style.Styler.set_td_classes \
- pandas.io.formats.style.Styler.set_tooltips \
- pandas.io.formats.style.Styler.set_uuid \
- pandas.io.formats.style.Styler.pipe \
- pandas.io.formats.style.Styler.highlight_between \
- pandas.io.formats.style.Styler.highlight_quantile \
- pandas.io.formats.style.Styler.background_gradient \
- pandas.io.formats.style.Styler.text_gradient \
- pandas.DataFrame.values \
- pandas.DataFrame.loc \
- pandas.DataFrame.iloc \
- pandas.DataFrame.groupby \
- pandas.DataFrame.describe \
- pandas.DataFrame.skew \
- pandas.DataFrame.var \
- pandas.DataFrame.idxmax \
- pandas.DataFrame.idxmin \
- pandas.DataFrame.last \
- pandas.DataFrame.pivot \
- pandas.DataFrame.sort_values \
- pandas.DataFrame.tz_convert \
- pandas.DataFrame.tz_localize \
- pandas.DataFrame.plot.bar \
- pandas.DataFrame.plot.hexbin \
- pandas.DataFrame.plot.hist \
- pandas.DataFrame.plot.line \
- pandas.DataFrame.hist \
+ MSG='Partially validate docstrings (PR02)' ; echo $MSG
+ $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=PR02 --ignore_functions \
+ pandas.io.formats.style.Styler.to_excel\
+ pandas.CategoricalIndex.rename_categories\
+ pandas.CategoricalIndex.reorder_categories\
+ pandas.CategoricalIndex.add_categories\
+ pandas.CategoricalIndex.remove_categories\
+ pandas.CategoricalIndex.set_categories\
+ pandas.IntervalIndex.set_closed\
+ pandas.IntervalIndex.contains\
+ pandas.IntervalIndex.overlaps\
+ pandas.IntervalIndex.to_tuples\
+ pandas.DatetimeIndex.round\
+ pandas.DatetimeIndex.floor\
+ pandas.DatetimeIndex.ceil\
+ pandas.DatetimeIndex.month_name\
+ pandas.DatetimeIndex.day_name\
+ pandas.DatetimeIndex.to_period\
+ pandas.DatetimeIndex.std\
+ pandas.TimedeltaIndex.round\
+ pandas.TimedeltaIndex.floor\
+ pandas.TimedeltaIndex.ceil\
+ pandas.PeriodIndex\
+ pandas.PeriodIndex.strftime\
+ pandas.Series.rename_axis\
+ pandas.Series.dt.to_period\
+ pandas.Series.dt.tz_localize\
+ pandas.Series.dt.tz_convert\
+ pandas.Series.dt.strftime\
+ pandas.Series.dt.round\
+ pandas.Series.dt.floor\
+ pandas.Series.dt.ceil\
+ pandas.Series.dt.month_name\
+ pandas.Series.dt.day_name\
+ pandas.Series.str.wrap\
+ pandas.Series.cat.rename_categories\
+ pandas.Series.cat.reorder_categories\
+ pandas.Series.cat.add_categories\
+ pandas.Series.cat.remove_categories\
+ pandas.Series.cat.set_categories\
+ pandas.Series.plot\
+ pandas.Series.plot.bar\
+ pandas.Series.plot.barh\
+ pandas.Series.plot.line\
+ pandas.Series.plot.pie\
+ pandas.DataFrame.plot\
+ pandas.DataFrame.plot.bar\
+ pandas.DataFrame.plot.barh\
+ pandas.DataFrame.plot.line\
+ pandas.DataFrame.plot.pie\
+ pandas.tseries.offsets.DateOffset\
+ pandas.tseries.offsets.BusinessDay\
+ pandas.tseries.offsets.BDay\
+ pandas.tseries.offsets.BusinessHour\
+ pandas.tseries.offsets.CustomBusinessDay\
+ pandas.tseries.offsets.CDay\
+ pandas.tseries.offsets.CustomBusinessHour\
+ pandas.tseries.offsets.MonthEnd\
+ pandas.tseries.offsets.MonthBegin\
+ pandas.tseries.offsets.BusinessMonthEnd\
+ pandas.tseries.offsets.BMonthEnd\
+ pandas.tseries.offsets.BusinessMonthBegin\
+ pandas.tseries.offsets.BMonthBegin\
+ pandas.tseries.offsets.CustomBusinessMonthEnd\
+ pandas.tseries.offsets.CBMonthEnd\
+ pandas.tseries.offsets.CustomBusinessMonthBegin\
+ pandas.tseries.offsets.CBMonthBegin\
+ pandas.tseries.offsets.SemiMonthEnd\
+ pandas.tseries.offsets.SemiMonthBegin\
+ pandas.tseries.offsets.Week\
+ pandas.tseries.offsets.WeekOfMonth\
+ pandas.tseries.offsets.LastWeekOfMonth\
+ pandas.tseries.offsets.BQuarterEnd\
+ pandas.tseries.offsets.BQuarterBegin\
+ pandas.tseries.offsets.QuarterEnd\
+ pandas.tseries.offsets.QuarterBegin\
+ pandas.tseries.offsets.BYearEnd\
+ pandas.tseries.offsets.BYearBegin\
+ pandas.tseries.offsets.YearEnd\
+ pandas.tseries.offsets.YearBegin\
+ pandas.tseries.offsets.FY5253\
+ pandas.tseries.offsets.FY5253Quarter\
+ pandas.tseries.offsets.Easter\
+ pandas.tseries.offsets.Day\
+ pandas.tseries.offsets.Hour\
+ pandas.tseries.offsets.Minute\
+ pandas.tseries.offsets.Second\
+ pandas.tseries.offsets.Milli\
+ pandas.tseries.offsets.Micro\
+ pandas.tseries.offsets.Nano\
+ pandas.set_option\
+ pandas.Timestamp.max\
+ pandas.Timestamp.min\
+ pandas.Timestamp.resolution\
+ pandas.Timedelta.max\
+ pandas.Timedelta.min\
+ pandas.Timedelta.resolution\
+ pandas.Interval\
+ pandas.Grouper\
+ pandas.core.groupby.SeriesGroupBy.apply\
+ pandas.core.groupby.SeriesGroupBy.transform\
+ pandas.core.groupby.DataFrameGroupBy.transform\
+ pandas.core.groupby.DataFrameGroupBy.nth\
+ pandas.core.groupby.DataFrameGroupBy.rolling\
+ pandas.core.groupby.SeriesGroupBy.nth\
+ pandas.core.groupby.SeriesGroupBy.rolling\
+ pandas.core.groupby.DataFrameGroupBy.hist\
+ pandas.core.groupby.DataFrameGroupBy.plot\
+ pandas.core.groupby.DataFrameGroupBy.corrwith\
+ pandas.core.groupby.SeriesGroupBy.plot\
+ pandas.core.window.rolling.Rolling.quantile\
+ pandas.core.window.expanding.Expanding.quantile # There should be no backslash in the final line, please keep this comment in the last ignored function
  RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

pandas/core/generic.py

@@ -97,6 +97,8 @@
  AbstractMethodError,
  ChainedAssignmentError,
  InvalidIndexError,
+)
+from pandas.errors.cow import (
  _chained_assignment_method_msg,
  _chained_assignment_warning_method_msg,
  _check_cacher,
@@ -171,10 +173,7 @@
  ensure_index,
 )
 from pandas.core.internals import BlockManager
-from pandas.core.internals.construction import (
- mgr_to_mgr,
- ndarray_to_mgr,
-)
+from pandas.core.internals.construction import ndarray_to_mgr
 from pandas.core.methods.describe import describe_ndframe
 from pandas.core.missing import (
  clean_fill_method,

pandas/core/groupby/groupby.py

@@ -1122,19 +1122,7 @@ def get_group(self, name) -> DataFrame | Series:
  inds = self._get_index(name)
  if not len(inds):
  raise KeyError(name)
-
- if obj is None:
- indexer = inds if self.axis == 0 else (slice(None), inds)
- return self._selected_obj.iloc[indexer]
- else:
- warnings.warn(
- "obj is deprecated and will be removed in a future version. "
- "Do ``df.iloc[gb.indices.get(name)]`` "
- "instead of ``gb.get_group(name, obj=df)``.",
- FutureWarning,
- stacklevel=find_stack_level(),
- )
- return obj.take(inds, axis=self.axis)
+ return self._selected_obj.iloc[inds]
 
  @final
  def __iter__(self) -> Iterator[tuple[Hashable, NDFrameT]]:
@@ -1772,7 +1760,7 @@ def f(g):
  ):
  warnings.warn(
  message=_apply_groupings_depr.format(type(self).__name__, "apply"),
- category=FutureWarning,
+ category=DeprecationWarning,
  stacklevel=find_stack_level(),
  )
  except TypeError:

pandas/tests/copy_view/test_chained_assignment_deprecation.py

@@ -1,6 +1,7 @@
 import numpy as np
 import pytest
 
+from pandas.compat import PY311
 from pandas.errors import ChainedAssignmentError
 
 from pandas import DataFrame

pandas/tests/copy_view/test_indexing.py

@@ -1029,6 +1029,7 @@ def test_series_midx_tuples_slice(using_copy_on_write, warn_copy_on_write):
 
 
 def test_midx_read_only_bool_indexer():
+ # GH#56635
  def mklbl(prefix, n):
  return [f"{prefix}{i}" for i in range(n)]
 
@@ -1041,9 +1042,11 @@ def mklbl(prefix, n):
  df = DataFrame(1, index=idx, columns=cols).sort_index().sort_index(axis=1)
 
  mask = df[("a", "foo")] == 1
+ expected_mask = mask.copy()
  result = df.loc[pd.IndexSlice[mask, :, ["C1", "C3"]], :]
  expected = df.loc[pd.IndexSlice[:, :, ["C1", "C3"]], :]
  tm.assert_frame_equal(result, expected)
+ tm.assert_series_equal(mask, expected_mask)
 
 
 def test_loc_enlarging_with_dataframe(using_copy_on_write):

pandas/tests/series/test_ufunc.py

@@ -454,8 +454,7 @@ def add3(x, y, z):
  ufunc(ser, ser, df)
 
 
-# TODO(CoW) see https://github.com/pandas-dev/pandas/pull/51082
-@pytest.mark.skip(reason="not implemented with CoW")
+@pytest.mark.xfail(reason="see https://github.com/pandas-dev/pandas/pull/51082")
 def test_np_fix():
  # np.fix is not a ufunc but is composed of several ufunc calls under the hood
  # with `out` and `where` keywords