Skip to content

Commit

Permalink
Set context
Browse files Browse the repository at this point in the history
  • Loading branch information
Jay Chia committed Dec 5, 2024
1 parent beee36f commit ec7f660
Showing 1 changed file with 3 additions and 0 deletions.
3 changes: 3 additions & 0 deletions .github/working-dir/dedup.py
Original file line number Diff line number Diff line change
Expand Up @@ -96,6 +96,8 @@ def components(df: DataFrame) -> DataFrame:


if __name__ == "__main__":
daft.set_execution_config(enable_ray_tracing=True)

df = daft.read_parquet("s3://eventual-dev-benchmarking-fixtures/redpajama-parquet/v1.0.0/sample-0.01")
df = dedupe(
df,
Expand All @@ -109,6 +111,7 @@ def components(df: DataFrame) -> DataFrame:
col("v").alias("original_doc_id"),
)

print(daft.context.get_context())
print(df.explain(True))
df.collect()
print(df)

0 comments on commit ec7f660

Please sign in to comment.