BUG: String[pyarrow] comparison with mixed object (pandas-dev#62424)

Co-authored-by: Joris Van den Bossche <jorisvandenbossche@gmail.com>

Author: 2 people

doc/source/whatsnew/v2.3.3.rst

@@ -47,7 +47,7 @@ Bug fixes
 - Fix regression in ``~Series.str.contains``, ``~Series.str.match`` and ``~Series.str.fullmatch``
   with a compiled regex and custom flags (:issue:`62240`)
 - Fix :meth:`Series.str.match` and :meth:`Series.str.fullmatch` not matching patterns with groups correctly for the Arrow-backed string dtype (:issue:`61072`)
-
+- Fix comparing a :class:`StringDtype` Series with mixed objects raising an error (:issue:`60228`)
 
 Improvements and fixes for Copy-on-Write
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

pandas/core/arrays/arrow/array.py

@@ -883,22 +883,27 @@ def _cmp_method(self, other, op) -> ArrowExtensionArray:
         ltype = self._pa_array.type
 
         if isinstance(other, (ExtensionArray, np.ndarray, list)):
-            boxed = self._box_pa(other)
-            rtype = boxed.type
-            if (pa.types.is_timestamp(ltype) and pa.types.is_date(rtype)) or (
-                pa.types.is_timestamp(rtype) and pa.types.is_date(ltype)
-            ):
-                # GH#62157 match non-pyarrow behavior
-                result = ops.invalid_comparison(self, other, op)
-                result = pa.array(result, type=pa.bool_())
+            try:
+                boxed = self._box_pa(other)
+            except pa.lib.ArrowInvalid:
+                # e.g. GH#60228 [1, "b"] we have to operate pointwise
+                res_values = [op(x, y) for x, y in zip(self, other)]
+                result = pa.array(res_values, type=pa.bool_(), from_pandas=True)
             else:
-                try:
-                    result = pc_func(self._pa_array, boxed)
-                except pa.ArrowNotImplementedError:
-                    # TODO: could this be wrong if other is object dtype?
-                    #  in which case we need to operate pointwise?
+                rtype = boxed.type
+                if (pa.types.is_timestamp(ltype) and pa.types.is_date(rtype)) or (
+                    pa.types.is_timestamp(rtype) and pa.types.is_date(ltype)
+                ):
+                    # GH#62157 match non-pyarrow behavior
                     result = ops.invalid_comparison(self, other, op)
                     result = pa.array(result, type=pa.bool_())
+                else:
+                    try:
+                        result = pc_func(self._pa_array, boxed)
+                    except pa.ArrowNotImplementedError:
+                        result = ops.invalid_comparison(self, other, op)
+                        result = pa.array(result, type=pa.bool_())
+
         elif is_scalar(other):
             if (isinstance(other, datetime) and pa.types.is_date(ltype)) or (
                 type(other) is date and pa.types.is_timestamp(ltype)

pandas/tests/extension/test_string.py

@@ -288,3 +288,19 @@ def test_searchsorted_with_na_raises(data_for_sorting, as_series):
     )
     with pytest.raises(ValueError, match=msg):
         arr.searchsorted(b)
+
+
+def test_mixed_object_comparison(dtype):
+    # GH#60228
+    ser = pd.Series(["a", "b"], dtype=dtype)
+
+    mixed = pd.Series([1, "b"], dtype=object)
+
+    result = ser == mixed
+    expected = pd.Series([False, True], dtype=bool)
+    if dtype.storage == "python" and dtype.na_value is pd.NA:
+        expected = expected.astype("boolean")
+    elif dtype.storage == "pyarrow" and dtype.na_value is pd.NA:
+        expected = expected.astype("bool[pyarrow]")
+
+    tm.assert_series_equal(result, expected)