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

Format python

Browse source
This commit is contained in:
Andras Schmelczer 2026-01-31 13:07:09 +00:00
parent 85f5770e09
commit 4c258018c3
17 changed files with 348 additions and 248 deletions
Download patch file Download diff file Expand all files Collapse all files

12
pipeline/download/arcgis.py
View file

@ -35,7 +35,6 @@ def download_with_progress(url: str, output_path: Path) -> None:
return
def extract_zip(zip_path: Path, extract_path: Path) -> None:
extract_path.mkdir(exist_ok=True)
@ -44,7 +43,7 @@ def extract_zip(zip_path: Path, extract_path: Path) -> None:
def convert_to_parquet(data_path: Path, parquet_path: Path) -> None:
df = pl.scan_csv(data_path / 'Data/NSPL_MAY_2025_UK.csv', try_parse_dates=True)
df = pl.scan_csv(data_path / "Data/NSPL_MAY_2025_UK.csv", try_parse_dates=True)
print(f"Columns: {df.collect_schema().names()}")
parquet_path.parent.mkdir(parents=True, exist_ok=True)
df.sink_parquet(parquet_path, compression="zstd")
@ -52,8 +51,12 @@ def convert_to_parquet(data_path: Path, parquet_path: Path) -> None:
def main() -> None:
parser = argparse.ArgumentParser(description="Download and convert ArcGIS postcode data")
parser.add_argument("--output", type=Path, required=True, help="Output parquet file path")
parser = argparse.ArgumentParser(
description="Download and convert ArcGIS postcode data"
)
parser.add_argument(
"--output", type=Path, required=True, help="Output parquet file path"
)
args = parser.parse_args()
with tempfile.TemporaryDirectory() as cache_dir:
@ -64,5 +67,6 @@ def main() -> None:
extract_zip(download_path, extract_path)
convert_to_parquet(extract_path, args.output)
if __name__ == "__main__":
main()