Backport PR #60312 on branch 2.3.x (TST (string dtype): resolve xfails in pandas/tests/apply + raise TypeError for ArrowArray accumulate) (#60328)

* Backport PR #60312 on branch 2.3.x (TST (string dtype): resolve xfails in pandas/tests/apply + raise TypeError for ArrowArray accumulate)

(cherry picked from commit fba5f08)

* 2.3 test function compat

---------

Co-authored-by: Joris Van den Bossche <[email protected]>

Author: WillAyd

pandas/core/arrays/arrow/array.py

@@ -1633,7 +1633,11 @@ def _accumulate(
             else:
                 data_to_accum = data_to_accum.cast(pa.int64())
 
-        result = pyarrow_meth(data_to_accum, skip_nulls=skipna, **kwargs)
+        try:
+            result = pyarrow_meth(data_to_accum, skip_nulls=skipna, **kwargs)
+        except pa.ArrowNotImplementedError as err:
+            msg = f"operation '{name}' not supported for dtype '{self.dtype}'"
+            raise TypeError(msg) from err
 
         if convert_to_int:
             result = result.cast(pa_dtype)

pandas/tests/apply/test_invalid_arg.py

@@ -218,18 +218,12 @@ def transform(row):
 def test_agg_cython_table_raises_frame(df, func, expected, axis, using_infer_string):
     # GH 21224
     if using_infer_string:
-        if df.dtypes.iloc[0].storage == "pyarrow":
-            import pyarrow as pa
-
-            # TODO(infer_string)
-            # should raise a proper TypeError instead of propagating the pyarrow error
-
-            expected = (expected, pa.lib.ArrowNotImplementedError)
-        else:
-            expected = (expected, NotImplementedError)
+        expected = (expected, NotImplementedError)
 
     msg = (
-        "can't multiply sequence by non-int of type 'str'|has no kernel|cannot perform"
+        "can't multiply sequence by non-int of type 'str'"
+        "|cannot perform cumprod with type str"  # NotImplementedError python backend
+        "|operation 'cumprod' not supported for dtype 'str'"  # TypeError pyarrow
     )
     warn = None if isinstance(func, str) else FutureWarning
     with pytest.raises(expected, match=msg):
@@ -259,16 +253,12 @@ def test_agg_cython_table_raises_series(series, func, expected, using_infer_stri
     if func == "median" or func is np.nanmedian or func is np.median:
         msg = r"Cannot convert \['a' 'b' 'c'\] to numeric"
 
-    if using_infer_string:
-        if series.dtype.storage == "pyarrow":
-            import pyarrow as pa
-
-            # TODO(infer_string)
-            # should raise a proper TypeError instead of propagating the pyarrow error
-            expected = (expected, pa.lib.ArrowNotImplementedError)
-        else:
-            expected = (expected, NotImplementedError)
-    msg = msg + "|does not support|has no kernel|Cannot perform|cannot perform"
+    if using_infer_string and func in ("cumprod", np.cumprod, np.nancumprod):
+        expected = (expected, NotImplementedError)
+
+    msg = (
+        msg + "|does not support|has no kernel|Cannot perform|cannot perform|operation"
+    )
     warn = None if isinstance(func, str) else FutureWarning
 
     with pytest.raises(expected, match=msg):

pandas/tests/apply/test_str.py

@@ -4,8 +4,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas.core.dtypes.common import is_number
 
 from pandas import (
@@ -88,7 +86,6 @@ def test_apply_np_transformer(float_frame, op, how):
     tm.assert_frame_equal(result, expected)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize(
     "series, func, expected",
     chain(
@@ -147,7 +144,6 @@ def test_agg_cython_table_series(series, func, expected):
         assert result == expected
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize(
     "series, func, expected",
     chain(
@@ -170,10 +166,17 @@ def test_agg_cython_table_series(series, func, expected):
         ),
     ),
 )
-def test_agg_cython_table_transform_series(series, func, expected):
+def test_agg_cython_table_transform_series(request, series, func, expected):
     # GH21224
     # test transforming functions in
     # pandas.core.base.SelectionMixin._cython_table (cumprod, cumsum)
+    if series.dtype == "string" and func in ("cumsum", np.cumsum, np.nancumsum):
+        request.applymarker(
+            pytest.mark.xfail(
+                raises=(TypeError, NotImplementedError),
+                reason="TODO(infer_string) cumsum not yet implemented for string",
+            )
+        )
     warn = None if isinstance(func, str) else FutureWarning
     with tm.assert_produces_warning(warn, match="is currently using Series.*"):
         result = series.agg(func)

pandas/tests/extension/test_arrow.py

@@ -436,7 +436,7 @@ def test_accumulate_series(self, data, all_numeric_accumulations, skipna, reques
             request.applymarker(
                 pytest.mark.xfail(
                     reason=f"{all_numeric_accumulations} not implemented for {pa_type}",
-                    raises=NotImplementedError,
+                    raises=TypeError,
                 )
             )