cleanups

Author: rhshadrach

doc/source/whatsnew/v2.3.0.rst

@@ -37,7 +37,7 @@ Other enhancements
   updated to work correctly with NumPy >= 2 (:issue:`57739`)
 - :meth:`Series.str.decode` result now has ``StringDtype`` when ``future.infer_string`` is True (:issue:`60709`)
 - :meth:`~Series.to_hdf` and :meth:`~DataFrame.to_hdf` now round-trip with ``StringDtype``  (:issue:`60663`)
-- The :meth:`~Series.cumsum`, :meth:`~Series.cummin`, and :meth:`~Series.cummax` reductions are now implemented for ``StringDtype`` columns (:issue:`60633`, :issue:`???`)
+- The :meth:`~Series.cumsum`, :meth:`~Series.cummin`, and :meth:`~Series.cummax` reductions are now implemented for ``StringDtype`` columns (:issue:`60633`, :issue:`60633`)
 - The :meth:`~Series.sum` reduction is now implemented for ``StringDtype`` columns (:issue:`59853`)
 
 .. ---------------------------------------------------------------------------

pandas/core/arrays/string_.py

@@ -49,6 +49,7 @@
 )
 
 from pandas.core import (
+    missing,
     nanops,
     ops,
 )
@@ -907,8 +908,6 @@ def _str_accumulate(
     ) -> StringArray:
         """
         Accumulate implementation for strings, see `_accumulate` docstring for details.
-
-        pyarrow.compute does not implement these methods for strings.
         """
         if name == "cumprod":
             msg = f"operation '{name}' not supported for dtype '{self.dtype}'"
@@ -924,8 +923,6 @@ def _str_accumulate(
             "cummax": np.maximum.accumulate,
         }[name]
 
-        from pandas.core import missing
-
         if self._hasna:
             na_mask = isna(ndarray)
             if np.all(na_mask):

pandas/tests/apply/test_str.py

@@ -161,17 +161,10 @@ def test_agg_cython_table_series(series, func, expected):
         ),
     ),
 )
-def test_agg_cython_table_transform_series(request, series, func, expected):
+def test_agg_cython_table_transform_series(series, func, expected):
     # GH21224
     # test transforming functions in
     # pandas.core.base.SelectionMixin._cython_table (cumprod, cumsum)
-    # if series.dtype == "string" and func == "cumsum" and not HAS_PYARROW:
-    #     request.applymarker(
-    #         pytest.mark.xfail(
-    #             raises=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/groupby/test_categorical.py

@@ -325,9 +325,9 @@ def test_observed(request, using_infer_string, observed):
     # gh-8138 (back-compat)
     # gh-8869
 
-    # if using_infer_string and not observed:
-    #     # TODO(infer_string) this fails with filling the string column with 0
-    #     request.applymarker(pytest.mark.xfail(reason="TODO(infer_string)"))
+    if using_infer_string and not observed:
+        # TODO(infer_string) this fails with filling the string column with 0
+        request.applymarker(pytest.mark.xfail(reason="TODO(infer_string)"))
 
     cat1 = Categorical(["a", "a", "b", "b"], categories=["a", "b", "z"], ordered=True)
     cat2 = Categorical(["c", "d", "c", "d"], categories=["c", "d", "y"], ordered=True)
@@ -355,12 +355,9 @@ def test_observed(request, using_infer_string, observed):
     )
     result = gb.sum()
     if not observed:
-        fill_value = "" if using_infer_string else 0
         expected = cartesian_product_for_groupers(
-            expected, [cat1, cat2], list("AB"), fill_value=fill_value
+            expected, [cat1, cat2], list("AB"), fill_value=0
         )
-    print(result)
-    print(expected)
     tm.assert_frame_equal(result, expected)
 
 

pandas/tests/series/test_cumulative.py

@@ -265,10 +265,11 @@ def test_cumprod_timedelta(self):
             ([pd.NA, pd.NA, pd.NA], "cummax", False, [pd.NA, pd.NA, pd.NA]),
         ],
     )
-    def test_cum_methods_pyarrow_strings(
+    def test_cum_methods_ea_strings(
         self, string_dtype_no_object, data, op, skipna, expected_data
     ):
-        # https://github.com/pandas-dev/pandas/pull/60633
+        # https://github.com/pandas-dev/pandas/pull/60633 - pyarrow
+        # https://github.com/pandas-dev/pandas/pull/60938 - Python
         ser = pd.Series(data, dtype=string_dtype_no_object)
         method = getattr(ser, op)
         expected = pd.Series(expected_data, dtype=string_dtype_no_object)