From 360d4115ddb1ea19dd1cd1f1686e58411da3c41e Mon Sep 17 00:00:00 2001 From: Jay Chia <17691182+jaychia@users.noreply.github.com> Date: Fri, 20 Sep 2024 15:48:32 -0700 Subject: [PATCH] [CHORE] Update documentation for config variables --- daft/context.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/daft/context.py b/daft/context.py index 61b69284af..32ba5a5c65 100644 --- a/daft/context.py +++ b/daft/context.py @@ -299,7 +299,7 @@ def set_execution_config( broadcast_join_size_bytes_threshold: int | None = None, parquet_split_row_groups_max_files: int | None = None, sort_merge_join_sort_with_aligned_boundaries: bool | None = None, - hash_join_partition_size_leniency: bool | None = None, + hash_join_partition_size_leniency: float | None = None, sample_size_for_sort: int | None = None, num_preview_rows: int | None = None, parquet_target_filesize: int | None = None, @@ -344,7 +344,7 @@ def set_execution_config( parquet_inflation_factor: Inflation Factor of parquet files (In-Memory-Size / File-Size) ratio. Defaults to 3.0 csv_target_filesize: Target File Size when writing out CSV Files. Defaults to 512MB csv_inflation_factor: Inflation Factor of CSV files (In-Memory-Size / File-Size) ratio. Defaults to 0.5 - shuffle_aggregation_default_partitions: Minimum number of partitions to create when performing aggregations. Defaults to 200, unless the number of input partitions is less than 200. + shuffle_aggregation_default_partitions: Maximum number of partitions to create when performing aggregations. Defaults to 200, unless the number of input partitions is less than 200. shuffle_join_default_partitions: Minimum number of partitions to create when performing joins. Defaults to 16, unless the number of input partitions is greater than 16. read_sql_partition_size_bytes: Target size of partition when reading from SQL databases. Defaults to 512MB enable_aqe: Enables Adaptive Query Execution, Defaults to False