Extract common download utils

This commit is contained in:
Andras Schmelczer 2026-01-31 19:52:21 +00:00
parent 6ddb3d2121
commit 3b9ad11d71
9 changed files with 152 additions and 161 deletions

View file

@ -10,6 +10,17 @@ import polars as pl
NAPTAN_CSV_URL = "https://naptan.api.dft.gov.uk/v1/access-nodes?dataFormat=csv"
STOP_TYPES = {
'AIR': "Airport",
'FTD': "Ferry",
"RSE": "Rail station",
"BCT": "Bus stop",
"BCE": "Bus station",
"TXR": "Taxi rank",
"TMU": "Metro or Tram stop",
}
def download_naptan(output: Path) -> None:
output.parent.mkdir(parents=True, exist_ok=True)
@ -26,10 +37,11 @@ def download_naptan(output: Path) -> None:
pl.col("Longitude").cast(pl.Float64, strict=False),
)
.drop_nulls(subset=["Latitude", "Longitude"])
.filter(pl.col("StopType").is_in(list(STOP_TYPES.keys())))
.select(
pl.col("ATCOCode").alias("id"),
pl.col("CommonName").alias("name"),
pl.col("StopType").alias("category"),
pl.col("StopType").replace(STOP_TYPES).alias("category"),
pl.col("Latitude").alias("lat"),
pl.col("Longitude").alias("lng"),
)