fix(dtypes): ensure consistent behavior of is_string_dtype for Categorical

pandas/core/dtypes/common.py

@@ -635,6 +635,16 @@ def is_string_dtype(arr_or_dtype) -> bool:
     >>> is_string_dtype(pd.Series([1, 2], dtype=object))
     False
     """
+    # Handle Categorical series and CategoricalDtype consistently
+    # - both should return False
+    if hasattr(arr_or_dtype, "dtype") and isinstance(
+        arr_or_dtype.dtype, CategoricalDtype
+    ):
+        return False
+
+    if isinstance(arr_or_dtype, CategoricalDtype):
+        return False
+
     if hasattr(arr_or_dtype, "dtype") and _get_dtype(arr_or_dtype).kind == "O":
         return is_all_strings(arr_or_dtype)
 

pandas/tests/dtypes/test_categorical_string_dtype.py

@@ -0,0 +1,50 @@
+import numpy as np
+
+from pandas.core.dtypes.common import is_string_dtype
+from pandas.core.dtypes.dtypes import CategoricalDtype
+
+import pandas as pd
+
+
+def test_is_string_dtype_categorical_consistency():
+    """Test that is_string_dtype returns consistent results for
+    Categorical series and dtype."""
+    # Test with CategoricalDtype directly
+    categorical_dtype = CategoricalDtype()
+    assert not is_string_dtype(categorical_dtype)
+
+    # Test with Series containing Categorical
+    categorical_series = pd.Series(pd.Categorical(["a", "b", "c"]))
+    assert not is_string_dtype(categorical_series)
+
+    # Test with ordered CategoricalDtype
+    ordered_categorical_dtype = CategoricalDtype(ordered=True)
+    assert not is_string_dtype(ordered_categorical_dtype)
+
+    # Test with Series containing ordered Categorical
+    ordered_categorical_series = pd.Series(
+        pd.Categorical(["a", "b", "c"], ordered=True)
+    )
+    assert not is_string_dtype(ordered_categorical_series)
+
+    # Test with CategoricalDtype with specific categories
+    specific_categorical_dtype = CategoricalDtype(categories=["x", "y", "z"])
+    assert not is_string_dtype(specific_categorical_dtype)
+
+    # Test with Series containing Categorical with specific categories
+    specific_categorical_series = pd.Series(
+        pd.Categorical(["x", "y", "z"], categories=["x", "y", "z"])
+    )
+    assert not is_string_dtype(specific_categorical_series)
+
+    # Test with empty Categorical
+    empty_categorical = pd.Series(pd.Categorical([]))
+    assert not is_string_dtype(empty_categorical)
+
+    # Test with Categorical containing NaN values
+    nan_categorical = pd.Series(pd.Categorical([np.nan, "a", "b"]))
+    assert not is_string_dtype(nan_categorical)
+
+    # Test with numeric Categorical
+    numeric_categorical = pd.Series(pd.Categorical([1, 2, 3]))
+    assert not is_string_dtype(numeric_categorical)

pandas/tests/frame/test_query_eval.py

@@ -168,7 +168,7 @@ def test_query_duplicate_column_name(self, engine, parser):
             }
         ).rename(columns={"B": "A"})
 
-        res = df.query('C == 1', engine=engine, parser=parser)
+        res = df.query("C == 1", engine=engine, parser=parser)
 
         expect = DataFrame(
             [[1, 1, 1]],
@@ -1411,7 +1411,7 @@ def test_expr_with_column_name_with_backtick_and_hash(self):
     def test_expr_with_column_name_with_backtick(self):
         # GH 59285
         df = DataFrame({"a`b": (1, 2, 3), "ab": (4, 5, 6)})
-        result = df.query("`a``b` < 2")  # noqa
+        result = df.query("`a``b` < 2")
         # Note: Formatting checks may wrongly consider the above ``inline code``.
         expected = df[df["a`b"] < 2]
         tm.assert_frame_equal(result, expected)