From 4e0c16ee1a86391e00f48fe430f0bb17c2466180 Mon Sep 17 00:00:00 2001 From: Jim Brennan Date: Thu, 4 Jan 2024 08:26:46 -0600 Subject: [PATCH] fix test_hash_agg_with_nan_keys floating point sum failure (#10148) Signed-off-by: Jim Brennan --- integration_tests/src/main/python/hash_aggregate_test.py | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/integration_tests/src/main/python/hash_aggregate_test.py b/integration_tests/src/main/python/hash_aggregate_test.py index 3fe7bae2a28..e5835a998b8 100644 --- a/integration_tests/src/main/python/hash_aggregate_test.py +++ b/integration_tests/src/main/python/hash_aggregate_test.py @@ -1,4 +1,4 @@ -# Copyright (c) 2020-2023, NVIDIA CORPORATION. +# Copyright (c) 2020-2024, NVIDIA CORPORATION. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. @@ -159,7 +159,7 @@ _grpkey_doubles_with_nan_zero_grouping_keys = [ ('a', RepeatSeqGen(DoubleGen(nullable=(True, 10.0), special_cases=_nan_zero_double_special_cases), length=50)), - ('b', FloatGen(nullable=(True, 10.0))), + ('b', IntegerGen(nullable=(True, 10.0))), ('c', LongGen())] # Schema for xfail cases @@ -1154,7 +1154,6 @@ def test_hash_multiple_filters(data_gen, conf): 'min(a), max(b) filter (where c > 250) from hash_agg_table group by a', conf) -@datagen_overrides(seed=0, reason='https://github.com/NVIDIA/spark-rapids/issues/10026') @approximate_float @ignore_order @pytest.mark.parametrize('data_gen', [_grpkey_floats_with_nan_zero_grouping_keys, @@ -1222,7 +1221,7 @@ def test_hash_agg_with_struct_of_array_fallback(data_gen): @approximate_float @ignore_order -@pytest.mark.parametrize('data_gen', [ _grpkey_doubles_with_nan_zero_grouping_keys], ids=idfn) +@pytest.mark.parametrize('data_gen', [ _grpkey_floats_with_nulls_and_nans ], ids=idfn) def test_count_distinct_with_nan_floats(data_gen): assert_gpu_and_cpu_are_equal_sql( lambda spark : gen_df(spark, data_gen, length=1024),