CLN: Enforce deprecation of DataFrame.idxmin/max with EAs and axis=1 (#62201)

Author: rhshadrach

pandas/core/frame.py

@@ -71,7 +71,6 @@
 )
 from pandas.util._exceptions import (
  find_stack_level,
- rewrite_warning,
 )
 from pandas.util._validators import (
  validate_ascending,
@@ -11926,25 +11925,13 @@ def _get_data() -> DataFrame:
  row_index = np.tile(np.arange(nrows), ncols)
  col_index = np.repeat(np.arange(ncols), nrows)
  ser = Series(arr, index=col_index, copy=False)
- # GroupBy will raise a warning with SeriesGroupBy as the object,
- # likely confusing users
- with rewrite_warning(
- target_message=(
- f"The behavior of SeriesGroupBy.{name} with all-NA values"
- ),
- target_category=FutureWarning,
- new_message=(
- f"The behavior of {type(self).__name__}.{name} with all-NA "
- "values, or any-NA and skipna=False, is deprecated. In "
- "a future version this will raise ValueError"
- ),
- ):
- result = ser.groupby(row_index).agg(name, **kwds)
+ if name == "all":
+ # Behavior here appears incorrect; preserving
+ # for backwards compatibility for now.
+ # See https://github.com/pandas-dev/pandas/issues/57171
+ skipna = True
+ result = ser.groupby(row_index).agg(name, **kwds, skipna=skipna)
  result.index = df.index
- if not skipna and name not in ("any", "all"):
- mask = df.isna().to_numpy(dtype=np.bool_).any(axis=1)
- other = -1 if name in ("idxmax", "idxmin") else lib.no_default
- result = result.mask(mask, other)
  return result
 
  df = df.T
@@ -13258,13 +13245,11 @@ def idxmin(
  # indices will always be np.ndarray since axis is not N
 
  if (indices == -1).any():
- warnings.warn(
- f"The behavior of {type(self).__name__}.idxmin with all-NA "
- "values, or any-NA and skipna=False, is deprecated. In a future "
- "version this will raise ValueError",
- FutureWarning,
- stacklevel=find_stack_level(),
- )
+ if skipna:
+ msg = "Encountered all NA values"
+ else:
+ msg = "Encountered an NA values with skipna=False"
+ raise ValueError(msg)
 
  index = data._get_axis(axis)
  result = algorithms.take(
@@ -13365,13 +13350,11 @@ def idxmax(
  # indices will always be 1d array since axis is not None
 
  if (indices == -1).any():
- warnings.warn(
- f"The behavior of {type(self).__name__}.idxmax with all-NA "
- "values, or any-NA and skipna=False, is deprecated. In a future "
- "version this will raise ValueError",
- FutureWarning,
- stacklevel=find_stack_level(),
- )
+ if skipna:
+ msg = "Encountered all NA values"
+ else:
+ msg = "Encountered an NA values with skipna=False"
+ raise ValueError(msg)
 
  index = data._get_axis(axis)
  result = algorithms.take(

pandas/core/groupby/groupby.py

@@ -5703,10 +5703,7 @@ def _idxmax_idxmin(
  "Specify observed=True in groupby instead."
  )
  elif not skipna and self._obj_with_exclusions.isna().any(axis=None):
- raise ValueError(
- f"{type(self).__name__}.{how} with skipna=False encountered an NA "
- f"value."
- )
+ raise ValueError(f"{how} with skipna=False encountered an NA value.")
 
  result = self._agg_general(
  numeric_only=numeric_only,
@@ -5724,8 +5721,7 @@ def _wrap_idxmax_idxmin(
  result = res.astype(index.dtype)
  elif skipna and res.lt(0).any(axis=None):
  raise ValueError(
- f"{type(self).__name__}.{how} with skipna=True encountered all NA "
- f"values in a group."
+ f"{how} with skipna=True encountered all NA values in a group."
  )
  else:
  if isinstance(index, MultiIndex):

pandas/tests/frame/test_reductions.py

@@ -2160,9 +2160,7 @@ def test_numeric_ea_axis_1(method, skipna, min_count, any_numeric_ea_dtype):
  kwargs["min_count"] = min_count
 
  if not skipna and method in ("idxmax", "idxmin"):
- # GH#57745 - EAs use groupby for axis=1 which still needs a proper deprecation.
- msg = f"The behavior of DataFrame.{method} with all-NA values"
- with tm.assert_produces_warning(FutureWarning, match=msg):
+ with pytest.raises(ValueError, match="encountered an NA value"):
  getattr(df, method)(axis=1, **kwargs)
  with pytest.raises(ValueError, match="Encountered an NA value"):
  getattr(expected_df, method)(axis=1, **kwargs)

pandas/tests/groupby/test_reductions.py

@@ -291,7 +291,7 @@ def test_idxmin_idxmax_extremes_skipna(skipna, how, float_numpy_dtype):
  gb = df.groupby("a")
 
  if not skipna:
- msg = f"DataFrameGroupBy.{how} with skipna=False"
+ msg = f"{how} with skipna=False"
  with pytest.raises(ValueError, match=msg):
  getattr(gb, how)(skipna=skipna)
  return

pandas/tests/groupby/transform/test_transform.py

@@ -1494,7 +1494,7 @@ def test_idxmin_idxmax_transform_args(how, skipna, numeric_only):
  expected = gb.transform(how, skipna=skipna, numeric_only=numeric_only)
  tm.assert_frame_equal(result, expected)
  else:
- msg = f"DataFrameGroupBy.{how} with skipna=False encountered an NA value"
+ msg = f"{how} with skipna=False encountered an NA value"
  with pytest.raises(ValueError, match=msg):
  gb.transform(how, skipna, numeric_only)