Backport PR #50396 on branch 1.5.x (BUG/COMPAT: fix assert_* functions for nested arrays with latest numpy) (#50739)

Backport PR #50396: BUG/COMPAT: fix assert_* functions for nested arrays with latest numpy

Co-authored-by: Joris Van den Bossche <jorisvandenbossche@gmail.com>

Author: meeseeksmachine

doc/source/whatsnew/v1.5.3.rst

@@ -31,6 +31,7 @@ Bug fixes
 - Bug in :meth:`Series.quantile` emitting warning from NumPy when :class:`Series` has only ``NA`` values (:issue:`50681`)
 - Bug when chaining several :meth:`.Styler.concat` calls, only the last styler was concatenated (:issue:`49207`)
 - Fixed bug when instantiating a :class:`DataFrame` subclass inheriting from ``typing.Generic`` that triggered a ``UserWarning`` on python 3.11 (:issue:`49649`)
+- Bug in :func:`pandas.testing.assert_series_equal` (and equivalent ``assert_`` functions) when having nested data and using numpy >= 1.25 (:issue:`50360`)
 -
 
 .. ---------------------------------------------------------------------------

pandas/core/dtypes/missing.py

@@ -594,6 +594,10 @@ def _array_equivalent_object(left: np.ndarray, right: np.ndarray, strict_nan: bo
                 if "boolean value of NA is ambiguous" in str(err):
                     return False
                 raise
+            except ValueError:
+                # numpy can raise a ValueError if left and right cannot be
+                # compared (e.g. nested arrays)
+                return False
     return True
 
 

pandas/tests/dtypes/test_missing.py

@@ -525,18 +525,120 @@ def test_array_equivalent_str(dtype):
     )
 
 
-def test_array_equivalent_nested():
+@pytest.mark.parametrize(
+    "strict_nan", [pytest.param(True, marks=pytest.mark.xfail), False]
+)
+def test_array_equivalent_nested(strict_nan):
     # reached in groupby aggregations, make sure we use np.any when checking
     #  if the comparison is truthy
-    left = np.array([np.array([50, 70, 90]), np.array([20, 30, 40])], dtype=object)
-    right = np.array([np.array([50, 70, 90]), np.array([20, 30, 40])], dtype=object)
+    left = np.array([np.array([50, 70, 90]), np.array([20, 30])], dtype=object)
+    right = np.array([np.array([50, 70, 90]), np.array([20, 30])], dtype=object)
 
-    assert array_equivalent(left, right, strict_nan=True)
-    assert not array_equivalent(left, right[::-1], strict_nan=True)
+    assert array_equivalent(left, right, strict_nan=strict_nan)
+    assert not array_equivalent(left, right[::-1], strict_nan=strict_nan)
 
-    left = np.array([np.array([50, 50, 50]), np.array([40, 40, 40])], dtype=object)
+    left = np.empty(2, dtype=object)
+    left[:] = [np.array([50, 70, 90]), np.array([20, 30, 40])]
+    right = np.empty(2, dtype=object)
+    right[:] = [np.array([50, 70, 90]), np.array([20, 30, 40])]
+    assert array_equivalent(left, right, strict_nan=strict_nan)
+    assert not array_equivalent(left, right[::-1], strict_nan=strict_nan)
+
+    left = np.array([np.array([50, 50, 50]), np.array([40, 40])], dtype=object)
     right = np.array([50, 40])
-    assert not array_equivalent(left, right, strict_nan=True)
+    assert not array_equivalent(left, right, strict_nan=strict_nan)
+
+
+@pytest.mark.parametrize(
+    "strict_nan", [pytest.param(True, marks=pytest.mark.xfail), False]
+)
+def test_array_equivalent_nested2(strict_nan):
+    # more than one level of nesting
+    left = np.array(
+        [
+            np.array([np.array([50, 70]), np.array([90])], dtype=object),
+            np.array([np.array([20, 30])], dtype=object),
+        ],
+        dtype=object,
+    )
+    right = np.array(
+        [
+            np.array([np.array([50, 70]), np.array([90])], dtype=object),
+            np.array([np.array([20, 30])], dtype=object),
+        ],
+        dtype=object,
+    )
+    assert array_equivalent(left, right, strict_nan=strict_nan)
+    assert not array_equivalent(left, right[::-1], strict_nan=strict_nan)
+
+    left = np.array([np.array([np.array([50, 50, 50])], dtype=object)], dtype=object)
+    right = np.array([50])
+    assert not array_equivalent(left, right, strict_nan=strict_nan)
+
+
+@pytest.mark.parametrize(
+    "strict_nan", [pytest.param(True, marks=pytest.mark.xfail), False]
+)
+def test_array_equivalent_nested_list(strict_nan):
+    left = np.array([[50, 70, 90], [20, 30]], dtype=object)
+    right = np.array([[50, 70, 90], [20, 30]], dtype=object)
+
+    assert array_equivalent(left, right, strict_nan=strict_nan)
+    assert not array_equivalent(left, right[::-1], strict_nan=strict_nan)
+
+    left = np.array([[50, 50, 50], [40, 40]], dtype=object)
+    right = np.array([50, 40])
+    assert not array_equivalent(left, right, strict_nan=strict_nan)
+
+
+@pytest.mark.xfail(reason="failing")
+@pytest.mark.parametrize("strict_nan", [True, False])
+def test_array_equivalent_nested_mixed_list(strict_nan):
+    # mixed arrays / lists in left and right
+    # https://github.com/pandas-dev/pandas/issues/50360
+    left = np.array([np.array([1, 2, 3]), np.array([4, 5])], dtype=object)
+    right = np.array([[1, 2, 3], [4, 5]], dtype=object)
+
+    assert array_equivalent(left, right, strict_nan=strict_nan)
+    assert not array_equivalent(left, right[::-1], strict_nan=strict_nan)
+
+    # multiple levels of nesting
+    left = np.array(
+        [
+            np.array([np.array([1, 2, 3]), np.array([4, 5])], dtype=object),
+            np.array([np.array([6]), np.array([7, 8]), np.array([9])], dtype=object),
+        ],
+        dtype=object,
+    )
+    right = np.array([[[1, 2, 3], [4, 5]], [[6], [7, 8], [9]]], dtype=object)
+    assert array_equivalent(left, right, strict_nan=strict_nan)
+    assert not array_equivalent(left, right[::-1], strict_nan=strict_nan)
+
+    # same-length lists
+    subarr = np.empty(2, dtype=object)
+    subarr[:] = [
+        np.array([None, "b"], dtype=object),
+        np.array(["c", "d"], dtype=object),
+    ]
+    left = np.array([subarr, None], dtype=object)
+    right = np.array([list([[None, "b"], ["c", "d"]]), None], dtype=object)
+    assert array_equivalent(left, right, strict_nan=strict_nan)
+    assert not array_equivalent(left, right[::-1], strict_nan=strict_nan)
+
+
+@pytest.mark.xfail(reason="failing")
+@pytest.mark.parametrize("strict_nan", [True, False])
+def test_array_equivalent_nested_dicts(strict_nan):
+    left = np.array([{"f1": 1, "f2": np.array(["a", "b"], dtype=object)}], dtype=object)
+    right = np.array(
+        [{"f1": 1, "f2": np.array(["a", "b"], dtype=object)}], dtype=object
+    )
+    assert array_equivalent(left, right, strict_nan=strict_nan)
+    assert not array_equivalent(left, right[::-1], strict_nan=strict_nan)
+
+    right2 = np.array([{"f1": 1, "f2": ["a", "b"]}], dtype=object)
+    assert array_equivalent(left, right2, strict_nan=strict_nan)
+    assert not array_equivalent(left, right2[::-1], strict_nan=strict_nan)
 
 
 @pytest.mark.parametrize(

pandas/tests/util/test_assert_almost_equal.py

@@ -458,3 +458,87 @@ def test_assert_almost_equal_iterable_values_mismatch():
 
     with pytest.raises(AssertionError, match=msg):
         tm.assert_almost_equal([1, 2], [1, 3])
+
+
+subarr = np.empty(2, dtype=object)
+subarr[:] = [np.array([None, "b"], dtype=object), np.array(["c", "d"], dtype=object)]
+
+NESTED_CASES = [
+    # nested array
+    (
+        np.array([np.array([50, 70, 90]), np.array([20, 30])], dtype=object),
+        np.array([np.array([50, 70, 90]), np.array([20, 30])], dtype=object),
+    ),
+    # >1 level of nesting
+    (
+        np.array(
+            [
+                np.array([np.array([50, 70]), np.array([90])], dtype=object),
+                np.array([np.array([20, 30])], dtype=object),
+            ],
+            dtype=object,
+        ),
+        np.array(
+            [
+                np.array([np.array([50, 70]), np.array([90])], dtype=object),
+                np.array([np.array([20, 30])], dtype=object),
+            ],
+            dtype=object,
+        ),
+    ),
+    # lists
+    (
+        np.array([[50, 70, 90], [20, 30]], dtype=object),
+        np.array([[50, 70, 90], [20, 30]], dtype=object),
+    ),
+    # mixed array/list
+    (
+        np.array([np.array([1, 2, 3]), np.array([4, 5])], dtype=object),
+        np.array([[1, 2, 3], [4, 5]], dtype=object),
+    ),
+    (
+        np.array(
+            [
+                np.array([np.array([1, 2, 3]), np.array([4, 5])], dtype=object),
+                np.array(
+                    [np.array([6]), np.array([7, 8]), np.array([9])], dtype=object
+                ),
+            ],
+            dtype=object,
+        ),
+        np.array([[[1, 2, 3], [4, 5]], [[6], [7, 8], [9]]], dtype=object),
+    ),
+    # same-length lists
+    (
+        np.array([subarr, None], dtype=object),
+        np.array([list([[None, "b"], ["c", "d"]]), None], dtype=object),
+    ),
+    # dicts
+    (
+        np.array([{"f1": 1, "f2": np.array(["a", "b"], dtype=object)}], dtype=object),
+        np.array([{"f1": 1, "f2": np.array(["a", "b"], dtype=object)}], dtype=object),
+    ),
+    (
+        np.array([{"f1": 1, "f2": np.array(["a", "b"], dtype=object)}], dtype=object),
+        np.array([{"f1": 1, "f2": ["a", "b"]}], dtype=object),
+    ),
+    # array/list of dicts
+    (
+        np.array(
+            [
+                np.array(
+                    [{"f1": 1, "f2": np.array(["a", "b"], dtype=object)}], dtype=object
+                ),
+                np.array([], dtype=object),
+            ],
+            dtype=object,
+        ),
+        np.array([[{"f1": 1, "f2": ["a", "b"]}], []], dtype=object),
+    ),
+]
+
+
+@pytest.mark.filterwarnings("ignore:elementwise comparison failed:DeprecationWarning")
+@pytest.mark.parametrize("a,b", NESTED_CASES)
+def test_assert_almost_equal_array_nested(a, b):
+    _assert_almost_equal_both(a, b)