Can't even keep track anymore

pipeline/download/rental_prices.py

@@ -0,0 +1,89 @@
+import argparse
+import tempfile
+
+import polars as pl
+from pathlib import Path
+
+from pipeline.utils import download
+
+URL = "https://www.ons.gov.uk/file?uri=/peoplepopulationandcommunity/housing/datasets/privaterentalmarketsummarystatisticsinengland/october2022toseptember2023/privaterentalmarketstatistics231220.xls"
+
+# Sheets 12-16 are LA-level breakdowns: Studio, 1 Bed, 2 Bed, 3 Bed, 4+ Bed
+# (Sheet 11 is "Room" — shared house rooms, not self-contained, so skip it)
+BEDROOM_SHEETS = {
+    12: 0,  # Studio
+    13: 1,  # One Bedroom
+    14: 2,  # Two Bedrooms
+    15: 3,  # Three Bedrooms
+    16: 4,  # Four or more Bedrooms
+}
+
+# Local authority district codes in England
+LA_PREFIXES = ("E06", "E07", "E08", "E09")
+
+
+def _read_sheet(xls_path: Path, sheet_id: int, bedrooms: int) -> pl.DataFrame:
+    """Read one bedroom category sheet, extract LA-level median rents."""
+    df = pl.read_excel(xls_path, sheet_id=sheet_id)
+
+    # Columns are unnamed; positional:
+    # 0=LA Code, 1=Area Code, 2=Area Name, 3=Count, 4=Mean, 5=LQ, 6=Median, 7=UQ
+    # First 4 rows are headers (title, notes, bedroom label, column headers)
+    df = df.slice(4)
+
+    area_code_col = df.columns[1]
+    median_col = df.columns[6]
+
+    return (
+        df.select(
+            pl.col(area_code_col).alias("area_code"),
+            pl.col(median_col).alias("median_monthly_rent"),
+        )
+        .filter(
+            pl.col("area_code").is_not_null()
+            & pl.col("area_code").str.starts_with("E06")
+            | pl.col("area_code").str.starts_with("E07")
+            | pl.col("area_code").str.starts_with("E08")
+            | pl.col("area_code").str.starts_with("E09")
+        )
+        .with_columns(
+            # Suppressed values are ".." — cast will turn them to null
+            pl.col("median_monthly_rent").cast(pl.Float32, strict=False),
+            pl.lit(bedrooms).cast(pl.UInt8).alias("bedrooms"),
+        )
+    )
+
+
+def convert_to_parquet(xls_path: Path, parquet_path: Path) -> None:
+    frames = []
+    for sheet_id, bedrooms in BEDROOM_SHEETS.items():
+        df = _read_sheet(xls_path, sheet_id, bedrooms)
+        print(f"  Sheet {sheet_id} (bedrooms={bedrooms}): {df.height} rows")
+        frames.append(df)
+
+    combined = pl.concat(frames)
+    print(f"Combined: {combined.shape}")
+    print(f"Non-null medians: {combined['median_monthly_rent'].drop_nulls().len()}")
+    print(combined.head(10))
+
+    combined.write_parquet(parquet_path, compression="zstd")
+    print(f"Saved to {parquet_path}")
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Download and convert ONS private rental market statistics"
+    )
+    parser.add_argument(
+        "--output", type=Path, required=True, help="Output parquet file path"
+    )
+    args = parser.parse_args()
+
+    with tempfile.TemporaryDirectory() as cache_dir:
+        xls_path = Path(cache_dir) / "rental_prices.xls"
+        download(URL, xls_path, timeout=60)
+        convert_to_parquet(xls_path, args.output)
+
+
+if __name__ == "__main__":
+    main()