perfect-postcode/pipeline/download/naptan.py

91 lines
2.8 KiB
Python

"""Download NaPTAN data and extract railway/metro station POIs."""
import argparse
import io
import urllib.request
from pathlib import Path
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",
"MET": "Metro or Tram stop",
}
def download_naptan(output: Path) -> None:
output.parent.mkdir(parents=True, exist_ok=True)
print(f"Downloading NaPTAN data from {NAPTAN_CSV_URL}")
with urllib.request.urlopen(NAPTAN_CSV_URL) as resp:
raw = resp.read()
print(f"Downloaded {len(raw) / (1024 * 1024):.1f} MB")
df = (
pl.read_csv(io.BytesIO(raw), infer_schema_length=0)
.with_columns(
pl.col("Latitude").cast(pl.Float64, strict=False),
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").replace(STOP_TYPES).alias("category"),
pl.col("Latitude").alias("lat"),
pl.col("Longitude").alias("lng"),
pl.col("NptgLocalityCode").alias("locality"),
)
)
before = len(df)
# Deduplicate: one record per name+category+locality
# (merges entrances, bus stop pairs on opposite sides of the road, etc.)
has_loc = df.filter(
pl.col("locality").is_not_null() & (pl.col("locality") != "")
)
no_loc = df.filter(
pl.col("locality").is_null() | (pl.col("locality") == "")
)
cols = ["id", "name", "category", "lat", "lng"]
deduped = has_loc.group_by("name", "category", "locality").agg(
pl.col("id").first(),
pl.col("lat").mean(),
pl.col("lng").mean(),
)
df = pl.concat([deduped.select(cols), no_loc.select(cols)])
print(f"Deduplicated {before:,}{len(df):,} stops (by name+category+locality)")
df.write_parquet(output)
size_mb = output.stat().st_size / (1024 * 1024)
print(f"Wrote {output} ({size_mb:.1f} MB, {len(df):,} stations)")
counts = df.group_by("category").len().sort("len", descending=True)
for row in counts.iter_rows(named=True):
print(f" {row['category']}: {row['len']:,}")
def main() -> None:
parser = argparse.ArgumentParser(description="Download NaPTAN station data")
parser.add_argument(
"--output", type=Path, required=True, help="Output parquet file path"
)
args = parser.parse_args()
download_naptan(args.output)
if __name__ == "__main__":
main()