Merge branch 'main' into ref-stringarray

Author: jbrockmendel

ci/code_checks.sh

@@ -239,7 +239,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.api.extensions.ExtensionArray.view SA01" \
         -i "pandas.api.interchange.from_dataframe RT03,SA01" \
         -i "pandas.api.types.is_bool PR01,SA01" \
-        -i "pandas.api.types.is_bool_dtype SA01" \
         -i "pandas.api.types.is_categorical_dtype SA01" \
         -i "pandas.api.types.is_complex PR01,SA01" \
         -i "pandas.api.types.is_complex_dtype SA01" \

pandas/core/dtypes/common.py

@@ -1274,6 +1274,10 @@ def is_bool_dtype(arr_or_dtype) -> bool:
     """
     Check whether the provided array or dtype is of a boolean dtype.
 
+    This function verifies whether a given object is a boolean data type. The input
+    can be an array or a dtype object. Accepted array types include instances
+    of ``np.array``, ``pd.Series``, ``pd.Index``, and similar array-like structures.
+
     Parameters
     ----------
     arr_or_dtype : array-like or dtype
@@ -1284,6 +1288,10 @@ def is_bool_dtype(arr_or_dtype) -> bool:
     boolean
         Whether or not the array or dtype is of a boolean dtype.
 
+    See Also
+    --------
+    api.types.is_bool : Check if an object is a boolean.
+
     Notes
     -----
     An ExtensionArray is considered boolean when the ``_is_boolean``

pandas/tests/io/excel/test_readers.py

@@ -712,7 +712,9 @@ def test_dtype_backend_string(self, read_ext, string_storage, tmp_excel):
                 "b": Series(["x", None], dtype=pd.StringDtype(string_storage)),
             }
         )
-        tm.assert_frame_equal(result, expected)
+        # the storage of the str columns' Index is also affected by the
+        # string_storage setting -> ignore that for checking the result
+        tm.assert_frame_equal(result, expected, check_column_type=False)
 
     @pytest.mark.parametrize("dtypes, exp_value", [({}, 1), ({"a.1": "int64"}, 1)])
     def test_dtype_mangle_dup_cols(self, read_ext, dtypes, exp_value):

pandas/tests/io/json/test_pandas.py

@@ -2194,7 +2194,9 @@ def test_read_json_dtype_backend(
         if orient == "values":
             expected.columns = list(range(8))
 
-        tm.assert_frame_equal(result, expected)
+        # the storage of the str columns' Index is also affected by the
+        # string_storage setting -> ignore that for checking the result
+        tm.assert_frame_equal(result, expected, check_column_type=False)
 
     @pytest.mark.parametrize("orient", ["split", "records", "index"])
     def test_read_json_nullable_series(self, string_storage, dtype_backend, orient):

pandas/tests/io/parser/dtypes/test_dtypes_basic.py

@@ -470,12 +470,12 @@ def test_dtype_backend_string(all_parsers, string_storage):
 """
         result = parser.read_csv(StringIO(data), dtype_backend="numpy_nullable")
 
-    expected = DataFrame(
-        {
-            "a": pd.array(["a", "b"], dtype=pd.StringDtype(string_storage)),
-            "b": pd.array(["x", pd.NA], dtype=pd.StringDtype(string_storage)),
-        }
-    )
+        expected = DataFrame(
+            {
+                "a": pd.array(["a", "b"], dtype=pd.StringDtype(string_storage)),
+                "b": pd.array(["x", pd.NA], dtype=pd.StringDtype(string_storage)),
+            },
+        )
     tm.assert_frame_equal(result, expected)
 
 

pandas/tests/io/parser/test_read_fwf.py

@@ -974,7 +974,9 @@ def test_dtype_backend(string_storage, dtype_backend):
         )
         expected["i"] = ArrowExtensionArray(pa.array([None, None]))
 
-    tm.assert_frame_equal(result, expected)
+    # the storage of the str columns' Index is also affected by the
+    # string_storage setting -> ignore that for checking the result
+    tm.assert_frame_equal(result, expected, check_column_type=False)
 
 
 def test_invalid_dtype_backend():

pandas/tests/io/test_html.py

@@ -207,7 +207,9 @@ def test_dtype_backend(self, string_storage, dtype_backend, flavor_read_html):
                 }
             )
 
-        tm.assert_frame_equal(result, expected)
+        # the storage of the str columns' Index is also affected by the
+        # string_storage setting -> ignore that for checking the result
+        tm.assert_frame_equal(result, expected, check_column_type=False)
 
     @pytest.mark.network
     @pytest.mark.single_cpu

pandas/tests/io/xml/test_xml.py

@@ -2050,7 +2050,9 @@ def test_read_xml_nullable_dtypes(
         )
         expected["g"] = ArrowExtensionArray(pa.array([None, None]))
 
-    tm.assert_frame_equal(result, expected)
+    # the storage of the str columns' Index is also affected by the
+    # string_storage setting -> ignore that for checking the result
+    tm.assert_frame_equal(result, expected, check_column_type=False)
 
 
 def test_invalid_dtype_backend():