REGR: assert_index_equal raising with non matching pd.NA (pandas-dev#…

…48608) * REGR: assert_index_equal raising with non matching pd.NA * Fix gh ref * Fix * Fix ci * Move whatsnew * Fix categorical
noatamir · Nov 9, 2022 · ccc22ab · ccc22ab
1 parent 127beb0
commit ccc22ab
Show file tree

Hide file tree

Showing 4 changed files with 20 additions and 0 deletions.
diff --git a/doc/source/whatsnew/v1.5.1.rst b/doc/source/whatsnew/v1.5.1.rst
@@ -86,6 +86,7 @@ Bug fixes
 ~~~~~~~~~
 - Bug in :meth:`Series.__getitem__` not falling back to positional for integer keys and boolean :class:`Index` (:issue:`48653`)
 - Bug in :meth:`DataFrame.to_hdf` raising ``AssertionError`` with boolean index (:issue:`48667`)
+- Bug in :func:`assert_index_equal` for extension arrays with non matching ``NA`` raising ``ValueError`` (:issue:`48608`)
 - Bug in :meth:`DataFrame.pivot_table` raising unexpected ``FutureWarning`` when setting datetime column as index (:issue:`48683`)
 -
 

diff --git a/pandas/_libs/testing.pyx b/pandas/_libs/testing.pyx
@@ -182,6 +182,10 @@ cpdef assert_almost_equal(a, b,
         # nan / None comparison
         return True
 
+    if isna(a) and not isna(b) or not isna(a) and isna(b):
+        # boolean value of pd.NA is ambigous
+        raise AssertionError(f"{a} != {b}")
+
     if a == b:
         # object comparison
         return True

diff --git a/pandas/_testing/asserters.py b/pandas/_testing/asserters.py
@@ -398,6 +398,9 @@ def _get_ilevel_values(index, level):
         if not left.equals(right):
             mismatch = left._values != right._values
 
+            if is_extension_array_dtype(mismatch):
+                mismatch = cast("ExtensionArray", mismatch).fillna(True)
+
             diff = np.sum(mismatch.astype(int)) * 100.0 / len(left)
             msg = f"{obj} values are different ({np.round(diff, 5)} %)"
             raise_assert_detail(obj, msg, left, right)

diff --git a/pandas/tests/util/test_assert_index_equal.py b/pandas/tests/util/test_assert_index_equal.py
@@ -280,3 +280,15 @@ def test_assert_index_equal_object_ints_order_false():
     idx1 = Index([1, 3], dtype="object")
     idx2 = Index([3, 1], dtype="object")
     tm.assert_index_equal(idx1, idx2, check_order=False)
+
+
+@pytest.mark.parametrize("check_categorical", [True, False])
+@pytest.mark.parametrize("check_names", [True, False])
+def test_assert_ea_index_equal_non_matching_na(check_names, check_categorical):
+    # GH#48608
+    idx1 = Index([1, 2], dtype="Int64")
+    idx2 = Index([1, NA], dtype="Int64")
+    with pytest.raises(AssertionError, match="50.0 %"):
+        tm.assert_index_equal(
+            idx1, idx2, check_names=check_names, check_categorical=check_categorical
+        )