perfect-postcode/pipeline/download/ethnicity.py
Andras Schmelczer 349a6c1d53
Some checks failed
CI / Python (lint + test) (push) Failing after 3m38s
CI / Rust (lint + test) (push) Failing after 3m32s
CI / Frontend (lint + typecheck) (push) Failing after 4m12s
Build and publish Docker image / build-and-push (push) Failing after 4m48s
Fun changes
2026-04-04 22:59:44 +01:00

112 lines
3.9 KiB
Python

import argparse
from pathlib import Path
import httpx
import polars as pl
pl.Config.set_tbl_cols(-1)
URL = "https://www.ethnicity-facts-figures.service.gov.uk/uk-population-by-ethnicity/national-and-regional-populations/regional-ethnic-diversity/latest/downloads/population-by-ethnicity-and-local-authority-2021.csv"
def download_and_convert(output_path: Path) -> None:
print("Downloading ethnicity data...")
response = httpx.get(URL, follow_redirects=True, timeout=60)
response.raise_for_status()
df = pl.read_csv(response.content)
print(f"Raw shape: {df.head(100)}")
# Use the detailed 19+1 breakdown to get sub-categories for Asian ethnicity,
# then aggregate back to the broad groups plus South Asian / East Asian split.
detailed = df.filter(
(pl.col("Ethnicity_type") == "ONS 2021 19+1") & (pl.col("Ethnicity") != "All")
)
# Map detailed categories to our output groups
group_map = {
# White
"White British": "White",
"White Irish": "White",
"Gypsy Or Irish Traveller": "White",
"Roma": "White",
"Any Other White Background": "White",
# South Asian
"Indian": "South Asian",
"Pakistani": "South Asian",
"Bangladeshi": "South Asian",
"Any Other Asian Background": "South Asian",
# East Asian
"Chinese": "East Asian",
# Black
"Black African": "Black",
"Black Caribbean": "Black",
"Any Other Black Background": "Black",
# Mixed
"Mixed White And Asian": "Mixed",
"Mixed White And Black African": "Mixed",
"Mixed White And Black Caribbean": "Mixed",
"Any Other Mixed/Multiple Ethnic Background": "Mixed",
# Other
"Arab": "Other",
"Any Other Ethnic Background": "Other",
}
detailed = detailed.with_columns(
pl.col("Ethnicity").replace_strict(group_map).alias("group"),
)
# Sum percentages within each group per local authority (keep full precision)
grouped = detailed.group_by("Geography_code", "group").agg(pl.col("Value1").sum())
wide = grouped.pivot(on="group", index="Geography_code", values="Value1")
# Normalize so each row sums to exactly 100%, then round using largest-remainder
# method to preserve the sum. Independent rounding of 6 values can drift ±0.3.
group_cols = [c for c in wide.columns if c != "Geography_code"]
row_total = sum(pl.col(c) for c in group_cols)
# Scale each group so they sum to exactly 100
wide = wide.with_columns(
[(pl.col(c) / row_total * 100.0).alias(c) for c in group_cols]
)
# Round to 1 decimal, then adjust the largest group to absorb residual
rounded_cols = [pl.col(c).round(1).alias(c) for c in group_cols]
wide = wide.with_columns(rounded_cols)
rounded_sum = sum(pl.col(c) for c in group_cols)
residual = (100.0 - rounded_sum).round(1)
# Find which group is largest per row and add the residual there
largest_col = pl.concat_list(group_cols).list.arg_max()
wide = wide.with_columns(
[
pl.when(largest_col == i)
.then(pl.col(c) + residual)
.otherwise(pl.col(c))
.alias(c)
for i, c in enumerate(group_cols)
]
)
# Rename columns to be descriptive
rename_map = {col: f"% {col}" for col in wide.columns if col != "Geography_code"}
wide = wide.rename(rename_map)
print(f"Output shape: {wide.shape}")
print(f"Columns: {wide.columns}")
wide.write_parquet(output_path, compression="zstd")
print(f"Saved to {output_path}")
def main() -> None:
parser = argparse.ArgumentParser(
description="Download and convert ethnicity by local authority data"
)
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()