61 lines
1.9 KiB
Python
61 lines
1.9 KiB
Python
"""Download Census 2021 usual resident population by LSOA.
|
|
|
|
Source: NOMIS (ONS Census 2021 — TS001 dataset)
|
|
License: Open Government Licence v3.0
|
|
"""
|
|
|
|
import argparse
|
|
from pathlib import Path
|
|
|
|
import polars as pl
|
|
|
|
from pipeline.utils import ENGLAND_LSOA_COUNT_2021, download_nomis_csv
|
|
|
|
# NOMIS API: Census 2021 TS001 (usual residents) by LSOA 2021 (TYPE151)
|
|
# c2021_restype_3=0 selects "Total: All usual residents"
|
|
BASE_URL = "https://www.nomisweb.co.uk/api/v01/dataset/NM_2021_1.data.csv?date=latest&geography=TYPE151&measures=20100&c2021_restype_3=0&select=GEOGRAPHY_CODE,OBS_VALUE"
|
|
|
|
|
|
def download_and_convert(output_path: Path) -> None:
|
|
print("Downloading Census 2021 LSOA population from NOMIS...")
|
|
df = download_nomis_csv(BASE_URL)
|
|
print(f"Total rows: {df.height}")
|
|
|
|
result = df.rename(
|
|
{"GEOGRAPHY_CODE": "lsoa21", "OBS_VALUE": "population"}
|
|
).with_columns(
|
|
pl.col("population").cast(pl.UInt32),
|
|
)
|
|
|
|
# Filter to England only (E prefix)
|
|
result = result.filter(pl.col("lsoa21").str.starts_with("E"))
|
|
|
|
print(f"England LSOAs: {result.height}")
|
|
if result.height != ENGLAND_LSOA_COUNT_2021:
|
|
raise ValueError(
|
|
f"Expected {ENGLAND_LSOA_COUNT_2021} England LSOAs, "
|
|
f"got {result.height}: truncated NOMIS download?"
|
|
)
|
|
print(
|
|
f"Population range: {result['population'].min()} - {result['population'].max()}"
|
|
)
|
|
print(f"Mean population: {result['population'].mean():.0f}")
|
|
|
|
output_path.parent.mkdir(parents=True, exist_ok=True)
|
|
result.write_parquet(output_path, compression="zstd")
|
|
print(f"Saved to {output_path}")
|
|
|
|
|
|
def main() -> None:
|
|
parser = argparse.ArgumentParser(
|
|
description="Download Census 2021 population by LSOA"
|
|
)
|
|
parser.add_argument(
|
|
"--output", type=Path, required=True, help="Output parquet file path"
|
|
)
|
|
args = parser.parse_args()
|
|
download_and_convert(args.output)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|