BUG: Fix assert_frame_equal dtype handling when check_dtype=False (#61473)

Author: iabhi4

doc/source/whatsnew/v3.0.0.rst

@@ -857,6 +857,7 @@ Sparse
 ExtensionArray
 ^^^^^^^^^^^^^^
 - Bug in :class:`Categorical` when constructing with an :class:`Index` with :class:`ArrowDtype` (:issue:`60563`)
+- Bug in :func:`assert_frame_equal` with ``check_dtype=False`` that failed when comparing columns containing ``pd.NA`` with ``Int32`` and ``object`` dtypes. Now handles such comparisons by coercing to ``dtype="object"`` internally. (:issue:`61473`)
 - Bug in :meth:`.arrays.ArrowExtensionArray.__setitem__` which caused wrong behavior when using an integer array with repeated values as a key (:issue:`58530`)
 - Bug in :meth:`ArrowExtensionArray.factorize` where NA values were dropped when input was dictionary-encoded even when dropna was set to False(:issue:`60567`)
 - Bug in :meth:`api.types.is_datetime64_any_dtype` where a custom :class:`ExtensionDtype` would return ``False`` for array-likes (:issue:`57055`)

pandas/_testing/asserters.py

@@ -1014,16 +1014,22 @@ def assert_series_equal(
             pass
         else:
             assert_attr_equal("dtype", left, right, obj=f"Attributes of {obj}")
-    if check_exact:
+
+    if not check_dtype:
+        left_values = left.to_numpy(dtype="object")
+        right_values = right.to_numpy(dtype="object")
+    else:
         left_values = left._values
         right_values = right._values
+
+    if check_exact:
         # Only check exact if dtype is numeric
-        if isinstance(left_values, ExtensionArray) and isinstance(
-            right_values, ExtensionArray
+        if isinstance(left._values, ExtensionArray) and isinstance(
+            right._values, ExtensionArray
         ):
             assert_extension_array_equal(
-                left_values,
-                right_values,
+                left._values,
+                right._values,
                 check_dtype=check_dtype,
                 index_values=left.index,
                 obj=str(obj),
@@ -1051,10 +1057,10 @@ def assert_series_equal(
 
         # datetimelike may have different objects (e.g. datetime.datetime
         # vs Timestamp) but will compare equal
-        if not Index(left._values).equals(Index(right._values)):
+        if not Index(left_values).equals(Index(right_values)):
             msg = (
-                f"[datetimelike_compat=True] {left._values} "
-                f"is not equal to {right._values}."
+                f"[datetimelike_compat=True] {left_values} "
+                f"is not equal to {right_values}."
             )
             raise AssertionError(msg)
     elif isinstance(left.dtype, IntervalDtype) and isinstance(
@@ -1065,8 +1071,8 @@ def assert_series_equal(
         right.dtype, CategoricalDtype
     ):
         _testing.assert_almost_equal(
-            left._values,
-            right._values,
+            left_values,
+            right_values,
             rtol=rtol,
             atol=atol,
             check_dtype=bool(check_dtype),
@@ -1106,8 +1112,8 @@ def assert_series_equal(
         )
     else:
         _testing.assert_almost_equal(
-            left._values,
-            right._values,
+            left_values,
+            right_values,
             rtol=rtol,
             atol=atol,
             check_dtype=bool(check_dtype),
@@ -1124,8 +1130,8 @@ def assert_series_equal(
             right.dtype, CategoricalDtype
         ):
             assert_categorical_equal(
-                left._values,
-                right._values,
+                left_values,
+                right_values,
                 obj=f"{obj} category",
                 check_category_order=check_category_order,
             )

pandas/tests/util/test_assert_frame_equal.py

@@ -395,3 +395,11 @@ def test_assert_frame_equal_set_mismatch():
     msg = r'DataFrame.iloc\[:, 0\] \(column name="set_column"\) values are different'
     with pytest.raises(AssertionError, match=msg):
         tm.assert_frame_equal(df1, df2)
+
+
+def test_assert_frame_equal_with_pdNA_and_check_dtype_false():
+    # GH#61473
+    df1 = DataFrame({"x": pd.Series([pd.NA], dtype="Int32")})
+    df2 = DataFrame({"x": pd.Series([pd.NA], dtype="object")})
+
+    tm.assert_frame_equal(df1, df2, check_dtype=False)