Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix test_hash_agg_with_nan_keys floating point sum failure #10148

Merged
merged 2 commits into from
Jan 4, 2024
Merged

fix test_hash_agg_with_nan_keys floating point sum failure #10148

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8171fda
fix test_hash_agg_with_nan_keys floating point sum failure
jbrennan333 Jan 3, 2024
bd13e2a
update copyrights
jbrennan333 Jan 3, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 2 additions & 3 deletions integration_tests/src/main/python/hash_aggregate_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down Expand Up @@ -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,
Expand Down Expand Up @@ -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),
Expand Down