From bbb4c712d4120801f4009347a1fd1da818fc55b5 Mon Sep 17 00:00:00 2001 From: Hendrik Makait Date: Thu, 15 Aug 2024 12:43:59 +0200 Subject: [PATCH] Use 50 GB Parquet+PyArrow dataset --- AB_environments/config.yaml | 4 ++-- tests/benchmarks/test_h2o.py | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/AB_environments/config.yaml b/AB_environments/config.yaml index 83c0d2fc01..28317c98c9 100644 --- a/AB_environments/config.yaml +++ b/AB_environments/config.yaml @@ -35,8 +35,8 @@ h2o_datasets: # - 0.5 GB (parquet) # - 5 GB (parquet) # - 50 GB (parquet) - - 5 GB (parquet+pyarrow) - # - 50 GB (parquet+pyarrow) + # - 5 GB (parquet+pyarrow) + - 50 GB (parquet+pyarrow) # - 500 GB (parquet+pyarrow) # AWS implements limiters to how many EC2 instances you can spawn in parallel on the diff --git a/tests/benchmarks/test_h2o.py b/tests/benchmarks/test_h2o.py index a0e5178333..0f0b4f702a 100644 --- a/tests/benchmarks/test_h2o.py +++ b/tests/benchmarks/test_h2o.py @@ -31,7 +31,7 @@ raise ValueError("Unknown h2o dataset(s): ", unknown_datasets) else: enabled_datasets = { - "5 GB (parquet)", + "50 GB (parquet+pyarrow)", }