Skip to content

Commit 8a1ecdd

Browse files
committed
Support querying partitioned dataset
1 parent e33ea90 commit 8a1ecdd

File tree

2 files changed

+10
-1
lines changed

2 files changed

+10
-1
lines changed

queries/common_utils.py

Lines changed: 9 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -23,7 +23,15 @@
2323
def get_table_path(table_name: str) -> Path:
2424
"""Return the path to the given table."""
2525
ext = settings.run.io_type if settings.run.include_io else "parquet"
26-
return settings.dataset_base_dir / f"{table_name}.{ext}"
26+
if settings.num_batches is None:
27+
return settings.dataset_base_dir / f"{table_name}.{ext}"
28+
return (
29+
settings.dataset_base_dir
30+
/ str(settings.num_batches)
31+
/ table_name
32+
/ "*"
33+
/ f"part.{ext}"
34+
)
2735

2836

2937
def log_query_timing(

settings.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -77,6 +77,7 @@ class Plot(BaseSettings):
7777

7878
class Settings(BaseSettings):
7979
scale_factor: float = 1.0
80+
num_batches: int | None = None
8081

8182
paths: Paths = Paths()
8283
plot: Plot = Plot()

0 commit comments

Comments
 (0)