This commit is contained in:
Andras Schmelczer 2026-03-15 21:22:28 +00:00
parent 479ef92236
commit c38d654ac7
44 changed files with 2526 additions and 701 deletions

View file

@ -105,9 +105,7 @@ def extract_pairs(input_path: Path, max_year2: int | None = None) -> pl.DataFram
.alias("log_ratio"),
(
1.0
/ (pl.col("frac_year2") - pl.col("frac_year1"))
.cast(pl.Float64)
.sqrt()
/ (pl.col("frac_year2") - pl.col("frac_year1")).cast(pl.Float64).sqrt()
).alias("weight"),
)
.filter(pl.col("log_ratio").abs() <= OUTLIER_THRESHOLD)
@ -453,8 +451,12 @@ def main():
description="Build improved repeat-sales price index"
)
parser.add_argument("--input", type=Path, required=True)
parser.add_argument("--postcodes", type=Path, required=True,
help="Path to postcode.parquet (for lat/lon centroids)")
parser.add_argument(
"--postcodes",
type=Path,
required=True,
help="Path to postcode.parquet (for lat/lon centroids)",
)
parser.add_argument("--output", type=Path, required=True)
args = parser.parse_args()