Fix extension tests

Author: rhshadrach

pandas/tests/extension/base/accumulate.py

@@ -18,8 +18,9 @@ def _supports_accumulation(self, ser: pd.Series, op_name: str) -> bool:
     def check_accumulate(self, ser: pd.Series, op_name: str, skipna: bool):
         try:
             alt = ser.astype("float64")
-        except TypeError:
-            # e.g. Period can't be cast to float64
+        except (TypeError, ValueError):
+            # e.g. Period can't be cast to float64 (TypeError)
+            #      String can't be cast to float64 (ValueError)
             alt = ser.astype(object)
 
         result = getattr(ser, op_name)(skipna=skipna)

pandas/tests/extension/test_arrow.py

@@ -393,13 +393,12 @@ def _supports_accumulation(self, ser: pd.Series, op_name: str) -> bool:
         # attribute "pyarrow_dtype"
         pa_type = ser.dtype.pyarrow_dtype  # type: ignore[union-attr]
 
-        if (
-            pa.types.is_string(pa_type)
-            or pa.types.is_binary(pa_type)
-            or pa.types.is_decimal(pa_type)
-        ):
+        if pa.types.is_binary(pa_type) or pa.types.is_decimal(pa_type):
             if op_name in ["cumsum", "cumprod", "cummax", "cummin"]:
                 return False
+        elif pa.types.is_string(pa_type):
+            if op_name == "cumprod":
+                return False
         elif pa.types.is_boolean(pa_type):
             if op_name in ["cumprod", "cummax", "cummin"]:
                 return False
@@ -414,6 +413,12 @@ def _supports_accumulation(self, ser: pd.Series, op_name: str) -> bool:
     def test_accumulate_series(self, data, all_numeric_accumulations, skipna, request):
         pa_type = data.dtype.pyarrow_dtype
         op_name = all_numeric_accumulations
+
+        if pa.types.is_string(pa_type) and op_name in ["cumsum", "cummin", "cummax"]:
+            # https://github.com/pandas-dev/pandas/pull/60633
+            # Doesn't fit test structure, tested in series/test_cumulative.py instead.
+            return
+
         ser = pd.Series(data)
 
         if not self._supports_accumulation(ser, op_name):

pandas/tests/extension/test_string.py

@@ -192,6 +192,13 @@ def _supports_reduction(self, ser: pd.Series, op_name: str) -> bool:
             and op_name in ("any", "all")
         )
 
+    def _supports_accumulation(self, ser: pd.Series, op_name: str) -> bool:
+        return ser.dtype.storage == "pyarrow" and op_name in [
+            "cummin",
+            "cummax",
+            "cumsum",
+        ]
+
     def _cast_pointwise_result(self, op_name: str, obj, other, pointwise_result):
         dtype = cast(StringDtype, tm.get_dtype(obj))
         if op_name in ["__add__", "__radd__"]:

pandas/tests/series/test_cumulative.py

@@ -230,31 +230,19 @@ def test_cumprod_timedelta(self):
         with pytest.raises(TypeError, match="cumprod not supported for Timedelta"):
             ser.cumprod()
 
-    @pytest.mark.parametrize(
-        "data, skipna, expected_data",
-        [
-            ([], True, []),
-            ([], False, []),
-            (["x", "z", "y"], True, ["x", "xz", "xzy"]),
-            (["x", "z", "y"], False, ["x", "xz", "xzy"]),
-            (["x", pd.NA, "y"], True, ["x", "x", "xy"]),
-            (["x", pd.NA, "y"], False, ["x", pd.NA, pd.NA]),
-            ([pd.NA, pd.NA, pd.NA], True, ["", "", ""]),
-            ([pd.NA, pd.NA, pd.NA], False, [pd.NA, pd.NA, pd.NA]),
-        ],
-    )
-    def test_cumsum_pyarrow_strings(
-        self, pyarrow_string_dtype, data, skipna, expected_data
-    ):
-        # https://github.com/pandas-dev/pandas/pull/60633
-        ser = pd.Series(data, dtype=pyarrow_string_dtype)
-        expected = pd.Series(expected_data, dtype=pyarrow_string_dtype)
-        result = ser.cumsum(skipna=skipna)
-        tm.assert_series_equal(result, expected)
-
     @pytest.mark.parametrize(
         "data, op, skipna, expected_data",
         [
+            ([], "cumsum", True, []),
+            ([], "cumsum", False, []),
+            (["x", "z", "y"], "cumsum", True, ["x", "xz", "xzy"]),
+            (["x", "z", "y"], "cumsum", False, ["x", "xz", "xzy"]),
+            (["x", pd.NA, "y"], "cumsum", True, ["x", "x", "xy"]),
+            (["x", pd.NA, "y"], "cumsum", False, ["x", pd.NA, pd.NA]),
+            ([pd.NA, "x", "y"], "cumsum", True, ["", "x", "xy"]),
+            ([pd.NA, "x", "y"], "cumsum", False, [pd.NA, pd.NA, pd.NA]),
+            ([pd.NA, pd.NA, pd.NA], "cumsum", True, ["", "", ""]),
+            ([pd.NA, pd.NA, pd.NA], "cumsum", False, [pd.NA, pd.NA, pd.NA]),
             ([], "cummin", True, []),
             ([], "cummin", False, []),
             (["y", "z", "x"], "cummin", True, ["y", "y", "x"]),
@@ -277,13 +265,11 @@ def test_cumsum_pyarrow_strings(
             ([pd.NA, pd.NA, pd.NA], "cummax", False, [pd.NA, pd.NA, pd.NA]),
         ],
     )
-    def test_cummin_cummax_pyarrow_strings(
+    def test_cum_methods_pyarrow_strings(
         self, pyarrow_string_dtype, data, op, skipna, expected_data
     ):
         # https://github.com/pandas-dev/pandas/pull/60633
         ser = pd.Series(data, dtype=pyarrow_string_dtype)
-        if expected_data is None:
-            expected_data = ser.dtype.na_value
         method = getattr(ser, op)
         expected = pd.Series(expected_data, dtype=pyarrow_string_dtype)
         result = method(skipna=skipna)