BUG (string dtype): comparison of string column to mixed object column fails #60228

Author: TEARFEAR

doc/source/whatsnew/v3.0.0.rst

@@ -768,6 +768,7 @@ Styler
 Other
 ^^^^^
 - Bug in :class:`DataFrame` when passing a ``dict`` with a NA scalar and ``columns`` that would always return ``np.nan`` (:issue:`57205`)
+- Bug in :func:`comparison_op` where comparing a ``string`` dtype array with an ``object`` dtype array containing mixed types would raise a ``TypeError`` when PyArrow-based strings are enabled. (:issue:`60228`)
 - Bug in :func:`eval` on :class:`ExtensionArray` on including division ``/`` failed with a ``TypeError``. (:issue:`58748`)
 - Bug in :func:`eval` where the names of the :class:`Series` were not preserved when using ``engine="numexpr"``. (:issue:`10239`)
 - Bug in :func:`eval` with ``engine="numexpr"`` returning unexpected result for float division. (:issue:`59736`)

pandas/core/ops/array_ops.py

@@ -38,9 +38,9 @@
     is_bool_dtype,
     is_list_like,
     is_numeric_v_string_like,
-    is_string_dtype,
     is_object_dtype,
     is_scalar,
+    is_string_dtype,
 )
 from pandas.core.dtypes.generic import (
     ABCExtensionArray,
@@ -54,7 +54,10 @@
 
 from pandas.core import roperator
 from pandas.core.computation import expressions
-from pandas.core.construction import ensure_wrapped_if_datetimelike, array
+from pandas.core.construction import (
+    array as pd_array,
+    ensure_wrapped_if_datetimelike,
+)
 from pandas.core.ops import missing
 from pandas.core.ops.dispatch import should_extension_dispatch
 from pandas.core.ops.invalid import invalid_comparison
@@ -322,16 +325,15 @@ def comparison_op(left: ArrayLike, right: Any, op) -> ArrayLike:
                 "Lengths must match to compare", lvalues.shape, rvalues.shape
             )
 
-    if (
-            (is_string_dtype(lvalues) and is_object_dtype(rvalues)) or
-            (is_object_dtype(lvalues) and is_string_dtype(rvalues))
+    if (is_string_dtype(lvalues) and is_object_dtype(rvalues)) or (
+        is_object_dtype(lvalues) and is_string_dtype(rvalues)
     ):
         if lvalues.dtype.name == "string" and rvalues.dtype == object:
             lvalues = lvalues.astype("string")
-            rvalues = array(rvalues, dtype="string")
+            rvalues = pd_array(rvalues, dtype="string")
         elif rvalues.dtype.name == "string" and lvalues.dtype == object:
             rvalues = rvalues.astype("string")
-            lvalues = array(lvalues, dtype="string")
+            lvalues = pd_array(lvalues, dtype="string")
 
     if should_extension_dispatch(lvalues, rvalues) or (
         (isinstance(rvalues, (Timedelta, BaseOffset, Timestamp)) or right is NaT)

pandas/tests/series/methods/test_compare.py

@@ -139,7 +139,9 @@ def test_compare_datetime64_and_string():
     tm.assert_series_equal(result_eq2, expected_eq)
     tm.assert_series_equal(result_neq, expected_neq)
 
+
 def test_comparison_string_mixed_object():
+    # Issue https://github.com/pandas-dev/pandas/issues/60228
     pd.options.future.infer_string = True
 
     ser_string = pd.Series(["a", "b"], dtype="string")
@@ -149,4 +151,4 @@ def test_comparison_string_mixed_object():
     expected = pd.Series([False, True], dtype="boolean")
     tm.assert_series_equal(result, expected)
 
-    pd.options.future.infer_string = False
+    pd.options.future.infer_string = False