Fix output from assert_frame_equal when indexes differ and check_like=True

Author: amilbourne

pandas/_testing.py

@@ -667,6 +667,7 @@ def assert_index_equal(
     check_less_precise: Union[bool, int] = no_default,
     check_exact: bool = True,
     check_categorical: bool = True,
+    check_order: bool = True,
     rtol: float = 1.0e-5,
     atol: float = 1.0e-8,
     obj: str = "Index",
@@ -696,6 +697,10 @@ def assert_index_equal(
         Whether to compare number exactly.
     check_categorical : bool, default True
         Whether to compare internal Categorical exactly.
+    check_order : bool, default True
+        Whether to compare the order of index entries as well as their values.
+        If True, both indexes must contain the same elements, in the same order.
+        If False, both indexes must contain the same elements, but in any order.
     rtol : float, default 1e-5
         Relative tolerance. Only used when check_exact is False.
 
@@ -762,6 +767,11 @@ def _get_ilevel_values(index, level):
         msg3 = f"{len(right)}, {right}"
         raise_assert_detail(obj, msg1, msg2, msg3)
 
+    # If order doesn't matter then sort the index entries
+    if not check_order:
+        left = left.sort_values()
+        right = right.sort_values()
+
     # MultiIndex special comparison for little-friendly error messages
     if left.nlevels > 1:
         left = cast(MultiIndex, left)
@@ -1582,9 +1592,6 @@ def assert_frame_equal(
             obj, f"{obj} shape mismatch", f"{repr(left.shape)}", f"{repr(right.shape)}"
         )
 
-    if check_like:
-        left, right = left.reindex_like(right), right
-
     if check_flags:
         assert left.flags == right.flags, f"{repr(left.flags)} != {repr(right.flags)}"
 
@@ -1596,6 +1603,7 @@ def assert_frame_equal(
         check_names=check_names,
         check_exact=check_exact,
         check_categorical=check_categorical,
+        check_order=not check_like,
         rtol=rtol,
         atol=atol,
         obj=f"{obj}.index",
@@ -1609,11 +1617,15 @@ def assert_frame_equal(
         check_names=check_names,
         check_exact=check_exact,
         check_categorical=check_categorical,
+        check_order=not check_like,
         rtol=rtol,
         atol=atol,
         obj=f"{obj}.columns",
     )
 
+    if check_like:
+        left, right = left.reindex_like(right), right
+
     # compare by blocks
     if by_blocks:
         rblocks = right._to_dict_of_blocks()

pandas/tests/util/test_assert_frame_equal.py

@@ -145,7 +145,8 @@ def test_empty_dtypes(check_dtype):
         tm.assert_frame_equal(df1, df2, **kwargs)
 
 
-def test_frame_equal_index_mismatch(obj_fixture):
+@pytest.mark.parametrize("check_like", [True, False])
+def test_frame_equal_index_mismatch(check_like, obj_fixture):
     msg = f"""{obj_fixture}\\.index are different
 
 {obj_fixture}\\.index values are different \\(33\\.33333 %\\)
@@ -156,10 +157,11 @@ def test_frame_equal_index_mismatch(obj_fixture):
     df2 = DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]}, index=["a", "b", "d"])
 
     with pytest.raises(AssertionError, match=msg):
-        tm.assert_frame_equal(df1, df2, obj=obj_fixture)
+        tm.assert_frame_equal(df1, df2, check_like=check_like, obj=obj_fixture)
 
 
-def test_frame_equal_columns_mismatch(obj_fixture):
+@pytest.mark.parametrize("check_like", [True, False])
+def test_frame_equal_columns_mismatch(check_like, obj_fixture):
     msg = f"""{obj_fixture}\\.columns are different
 
 {obj_fixture}\\.columns values are different \\(50\\.0 %\\)
@@ -170,7 +172,7 @@ def test_frame_equal_columns_mismatch(obj_fixture):
     df2 = DataFrame({"A": [1, 2, 3], "b": [4, 5, 6]}, index=["a", "b", "c"])
 
     with pytest.raises(AssertionError, match=msg):
-        tm.assert_frame_equal(df1, df2, obj=obj_fixture)
+        tm.assert_frame_equal(df1, df2, check_like=check_like, obj=obj_fixture)
 
 
 def test_frame_equal_block_mismatch(by_blocks_fixture, obj_fixture):