Backport PR #52577 on branch 2.0.x (BUG: describe not respecting ArrowDtype in include/exclude)

doc/source/whatsnew/v2.0.1.rst

@@ -38,6 +38,7 @@ Bug fixes
 - Bug in :func:`to_datetime` and :func:`to_timedelta` when trying to convert numeric data with a :class:`ArrowDtype` (:issue:`52425`)
 - Bug in :func:`to_numeric` with ``errors='coerce'`` and ``dtype_backend='pyarrow'`` with :class:`ArrowDtype` data (:issue:`52588`)
 - Bug in :meth:`ArrowDtype.__from_arrow__` not respecting if dtype is explicitly given (:issue:`52533`)
+- Bug in :meth:`DataFrame.describe` not respecting ``ArrowDtype`` in ``include`` and ``exclude`` (:issue:`52570`)
 - Bug in :meth:`DataFrame.max` and related casting different :class:`Timestamp` resolutions always to nanoseconds (:issue:`52524`)
 - Bug in :meth:`Series.describe` not returning :class:`ArrowDtype` with ``pyarrow.float64`` type with numeric data (:issue:`52427`)
 - Bug in :meth:`Series.dt.tz_localize` incorrectly localizing timestamps with :class:`ArrowDtype` (:issue:`52677`)

pandas/core/dtypes/common.py

@@ -1565,6 +1565,10 @@ def infer_dtype_from_object(dtype) -> type:
         except TypeError:
             # Should still pass if we don't have a date-like
             pass
+        if hasattr(dtype, "numpy_dtype"):
+            # TODO: Implement this properly
+            # https://github.com/pandas-dev/pandas/issues/52576
+            return dtype.numpy_dtype.type
         return dtype.type
 
     try:

pandas/core/frame.py

@@ -171,6 +171,7 @@
     PeriodArray,
     TimedeltaArray,
 )
+from pandas.core.arrays.arrow import ArrowDtype
 from pandas.core.arrays.sparse import SparseFrameAccessor
 from pandas.core.construction import (
     ensure_wrapped_if_datetimelike,
@@ -4695,6 +4696,7 @@ def check_int_infer_dtype(dtypes):
 
         def dtype_predicate(dtype: DtypeObj, dtypes_set) -> bool:
             # GH 46870: BooleanDtype._is_numeric == True but should be excluded
+            dtype = dtype if not isinstance(dtype, ArrowDtype) else dtype.numpy_dtype
             return issubclass(dtype.type, tuple(dtypes_set)) or (
                 np.number in dtypes_set
                 and getattr(dtype, "_is_numeric", False)

pandas/tests/frame/methods/test_describe.py

@@ -395,3 +395,23 @@ def test_ea_with_na(self, any_numeric_ea_dtype):
             dtype="Float64",
         )
         tm.assert_frame_equal(result, expected)
+
+    def test_describe_exclude_pa_dtype(self):
+        # GH#52570
+        pa = pytest.importorskip("pyarrow")
+        df = DataFrame(
+            {
+                "a": Series([1, 2, 3], dtype=pd.ArrowDtype(pa.int8())),
+                "b": Series([1, 2, 3], dtype=pd.ArrowDtype(pa.int16())),
+                "c": Series([1, 2, 3], dtype=pd.ArrowDtype(pa.int32())),
+            }
+        )
+        result = df.describe(
+            include=pd.ArrowDtype(pa.int8()), exclude=pd.ArrowDtype(pa.int32())
+        )
+        expected = DataFrame(
+            {"a": [3, 2, 1, 1, 1.5, 2, 2.5, 3]},
+            index=["count", "mean", "std", "min", "25%", "50%", "75%", "max"],
+            dtype=pd.ArrowDtype(pa.float64()),
+        )
+        tm.assert_frame_equal(result, expected)