From cb830b08cab4b5a1ab5be704e2a07ba149b6ff08 Mon Sep 17 00:00:00 2001 From: Balaji Veeramani Date: Fri, 22 Nov 2024 15:45:00 -0800 Subject: [PATCH 1/3] Initial commit Signed-off-by: Balaji Veeramani --- python/ray/data/_internal/planner/exchange/sort_task_spec.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/python/ray/data/_internal/planner/exchange/sort_task_spec.py b/python/ray/data/_internal/planner/exchange/sort_task_spec.py index 827c4a2c7a51..7c67b3dbdefe 100644 --- a/python/ray/data/_internal/planner/exchange/sort_task_spec.py +++ b/python/ray/data/_internal/planner/exchange/sort_task_spec.py @@ -81,8 +81,9 @@ def validate_schema(self, schema: Optional[Union[type, "pyarrow.lib.Schema"]]): for column in self._columns: if column not in schema_names_set: raise ValueError( - "The column '{}' does not exist in the " - "schema '{}'.".format(column, schema) + f"You specified the column '{column}', but there's no such " + "column in the dataset. The dataset has columns: " + f"{schema_names_set}" ) @property From 23b72cee2c95a73d3c98156e472d745a4a0746c1 Mon Sep 17 00:00:00 2001 From: Balaji Veeramani Date: Wed, 18 Dec 2024 16:56:48 -0800 Subject: [PATCH 2/3] Initial commit Signed-off-by: Balaji Veeramani --- release/release_data_tests.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/release/release_data_tests.yaml b/release/release_data_tests.yaml index 87285793f1de..bfc922e02644 100644 --- a/release/release_data_tests.yaml +++ b/release/release_data_tests.yaml @@ -417,7 +417,7 @@ cluster_compute: autoscaling_hetero_compute.yaml run: - timeout: 3600 + timeout: 4800 script: > python gpu_batch_inference.py --data-directory 10T-image-data-synthetic-raw-parquet --data-format parquet From 7526c050ed37ecdabe10f8c1b43e3d476c58bda4 Mon Sep 17 00:00:00 2001 From: Balaji Veeramani Date: Thu, 19 Dec 2024 13:19:30 -0800 Subject: [PATCH 3/3] Bump timeout Signed-off-by: Balaji Veeramani --- release/release_data_tests.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/release/release_data_tests.yaml b/release/release_data_tests.yaml index bfc922e02644..9b6bbb389a96 100644 --- a/release/release_data_tests.yaml +++ b/release/release_data_tests.yaml @@ -417,7 +417,7 @@ cluster_compute: autoscaling_hetero_compute.yaml run: - timeout: 4800 + timeout: 7200 script: > python gpu_batch_inference.py --data-directory 10T-image-data-synthetic-raw-parquet --data-format parquet