kazantsev-maksim commented on code in PR #3044:
URL: https://github.com/apache/datafusion-comet/pull/3044#discussion_r2694860679
##########
dev/benchmarks/tpcbench.py:
##########
@@ -146,15 +146,16 @@ def main(benchmark: str, data_path: str, query_path: str,
iterations: int, outpu
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="DataFusion benchmark derived
from TPC-H / TPC-DS")
- parser.add_argument("--benchmark", required=True, help="Benchmark to run
(tpch or tpcds)")
+ parser.add_argument("--benchmark", required=True, default="tpch",
help="Benchmark to run (tpch or tpcds)")
parser.add_argument("--data", required=True, help="Path to data files")
parser.add_argument("--queries", required=True, help="Path to query files")
parser.add_argument("--iterations", required=False, default="1", help="How
many iterations to run")
parser.add_argument("--output", required=True, help="Path to write output")
parser.add_argument("--name", required=True, help="Prefix for result file
e.g. spark/comet/gluten")
parser.add_argument("--query", required=False, type=int, help="Specific
query number to run (1-based). If not specified, all queries will be run.")
parser.add_argument("--write", required=False, help="Path to save query
results to, in Parquet format.")
+ parser.add_argument("--format", required=True, default="parquet",
help="Input file format (parquet, csv, json)")
Review Comment:
For CSV:
tpcbench.py \
--name spark \
--benchmark tpch \
--data $TPCH_DATA \
--queries $TPCH_QUERIES \
--output . \
--iterations 1 \
--format csv
--options '{"header": "true", "delimiter": ","}'
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
