From d50c9107da35ef40e8262e4cbac5e48fdd1747a4 Mon Sep 17 00:00:00 2001
From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>
Date: Tue, 20 Feb 2024 03:57:05 -1000
Subject: [PATCH] xfail tests in test_udf_masked_ops due to pandas 2.2 bug
 (#15071)

Due to a change in pandas 2.2 with how NA is handled (incorrectly) in UDFs https://github.com/pandas-dev/pandas/issues/57390

Authors:
  - Matthew Roeschke (https://github.com/mroeschke)

Approvers:
  - GALI PREM SAGAR (https://github.com/galipremsagar)

URL: https://github.com/rapidsai/cudf/pull/15071
---
 python/cudf/cudf/tests/test_udf_masked_ops.py | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/python/cudf/cudf/tests/test_udf_masked_ops.py b/python/cudf/cudf/tests/test_udf_masked_ops.py
index 0e29d2bfdcc..ed3461578fd 100644
--- a/python/cudf/cudf/tests/test_udf_masked_ops.py
+++ b/python/cudf/cudf/tests/test_udf_masked_ops.py
@@ -7,6 +7,7 @@
 from numba import cuda
 
 import cudf
+from cudf.core._compat import PANDAS_GE_220
 from cudf.core.missing import NA
 from cudf.core.udf._ops import (
     arith_ops,
@@ -482,6 +483,9 @@ def func(x):
     run_masked_udf_series(func, data, check_dtype=False)
 
 
+@pytest.mark.xfail(
+    PANDAS_GE_220, reason="https://github.com/pandas-dev/pandas/issues/57390"
+)
 def test_series_apply_null_conditional():
     def func(x):
         if x is NA:
@@ -506,6 +510,9 @@ def func(x):
     run_masked_udf_series(func, data, check_dtype=False)
 
 
+@pytest.mark.xfail(
+    PANDAS_GE_220, reason="https://github.com/pandas-dev/pandas/issues/57390"
+)
 @pytest.mark.parametrize("op", comparison_ops)
 def test_series_compare_masked_vs_masked(op):
     """
@@ -562,6 +569,9 @@ def func(x):
     run_masked_udf_series(func, data, check_dtype=False)
 
 
+@pytest.mark.xfail(
+    PANDAS_GE_220, reason="https://github.com/pandas-dev/pandas/issues/57390"
+)
 def test_series_masked_is_null_conditional():
     def func(x):
         if x is NA:
@@ -742,8 +752,14 @@ def func(x, c):
     ],
 )
 @pytest.mark.parametrize("op", arith_ops + comparison_ops)
-def test_masked_udf_scalar_args_binops_multiple_series(data, op):
+def test_masked_udf_scalar_args_binops_multiple_series(request, data, op):
     data = cudf.Series(data)
+    request.applymarker(
+        pytest.mark.xfail(
+            op in comparison_ops and PANDAS_GE_220 and data.dtype.kind != "b",
+            reason="https://github.com/pandas-dev/pandas/issues/57390",
+        )
+    )
 
     def func(data, c, k):
         x = op(data, c)