BUG: Fix GroupBy aggregate coersion of outputs inconsistency for pyarrow dtypes (#61636)

Author: heoh

pandas/core/arrays/arrow/array.py

@@ -185,6 +185,7 @@ def floordiv_compat(
  ArrayLike,
  AxisInt,
  Dtype,
+ DtypeObj,
  FillnaOptions,
  InterpolateOptions,
  Iterator,
@@ -313,6 +314,18 @@ def __init__(self, values: pa.Array | pa.ChunkedArray) -> None:
  )
  self._dtype = ArrowDtype(self._pa_array.type)
 
+ @classmethod
+ def _from_scalars(cls, scalars, dtype: DtypeObj) -> Self:
+ try:
+ pa_array = cls._from_sequence(scalars, dtype=dtype)
+ except pa.ArrowNotImplementedError:
+ # _from_scalars should only raise ValueError or TypeError.
+ raise ValueError
+
+ if lib.infer_dtype(scalars, skipna=True) != lib.infer_dtype(pa_array, skipna=True):
+ raise ValueError
+ return pa_array
+
  @classmethod
  def _from_sequence(
  cls, scalars, *, dtype: Dtype | None = None, copy: bool = False

pandas/core/arrays/string_arrow.py

@@ -53,6 +53,7 @@
  from pandas._typing import (
  ArrayLike,
  Dtype,
+ DtypeObj,
  NpDtype,
  Self,
  npt,
@@ -180,6 +181,12 @@ def __len__(self) -> int:
  """
  return len(self._pa_array)
 
+ @classmethod
+ def _from_scalars(cls, scalars, dtype: DtypeObj) -> Self:
+ if lib.infer_dtype(scalars, skipna=True) not in ["string", "empty"]:
+ raise ValueError
+ return cls._from_sequence(scalars, dtype=dtype)
+
  @classmethod
  def _from_sequence(
  cls, scalars, *, dtype: Dtype | None = None, copy: bool = False