andras/perfect-postcode
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 2 Wiki Activity Actions

Fix checkpoint postcode duplication

Browse source
This commit is contained in:
Andras Schmelczer 2026-02-01 13:10:56 +00:00
parent 627ba5496a
commit ccb7c8fbd7
1 changed files with 5 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

7
pipeline/journey_times/__main__.py
View file

@ -71,9 +71,12 @@ def main():
prior_results: list[JourneyResult] = [] prior_results: list[JourneyResult] = []
if checkpoint_path.exists(): if checkpoint_path.exists():
checkpoint_df = pl.read_parquet(checkpoint_path) checkpoint_df = pl.read_parquet(checkpoint_path)
completed_postcodes = set( # Deduplicate checkpoint rows per postcode, preferring rows with data
checkpoint_df.filter(pl.col("public_transport_easy_minutes").is_not_null())["postcode"].to_list() checkpoint_df = (
checkpoint_df.sort("public_transport_quick_minutes", nulls_last=True)
.unique(subset=["postcode"], keep="first")
) )
completed_postcodes = set(checkpoint_df["postcode"].to_list())
prior_results = [ prior_results = [
JourneyResult( JourneyResult(
postcode=row["postcode"], postcode=row["postcode"],