changes

pipeline/transform/price_estimation/utils.py

@@ -1,7 +1,6 @@
 """Shared utilities for price estimation modules."""
 
 from datetime import date
-from pathlib import Path
 
 import numpy as np
 import polars as pl
@@ -9,7 +8,6 @@ import polars as pl
 CURRENT_YEAR = 2026
 _today = date.today()
 CURRENT_FRAC_YEAR = _today.year + (_today.month - 1) / 12
-CURRENT_MONTH = _today.month
 
 # Cap on log(index_ratio) to prevent wild estimates from thin sectors
 MAX_LOG_ADJUSTMENT = 3.0  # ~20x max price change
@@ -181,53 +179,3 @@ def join_type_stratified_index(
     ).drop(_typed, _all)
 
     return df
-
-
-def compute_seasonal_factors(
-    input_path: Path, max_sale_year: int | None = None
-) -> np.ndarray:
-    """Compute 12 multiplicative monthly price factors from price-per-sqm.
-
-    Detrends by normalizing median £/sqm within each year, then averages
-    across years. Returns array of 12 factors (index 0 = January).
-    Normalized so mean = 1.0.
-    """
-    query = (
-        pl.scan_parquet(input_path)
-        .select("Last known price", "Total floor area (sqm)", "Date of last transaction")
-        .filter(
-            pl.col("Last known price").is_not_null(),
-            pl.col("Last known price") > 0,
-            pl.col("Total floor area (sqm)").is_not_null(),
-            pl.col("Total floor area (sqm)") > 0,
-            pl.col("Date of last transaction").is_not_null(),
-        )
-        .with_columns(
-            (
-                pl.col("Last known price").cast(pl.Float64)
-                / pl.col("Total floor area (sqm)").cast(pl.Float64)
-            ).alias("psm"),
-            pl.col("Date of last transaction").dt.month().alias("month"),
-            pl.col("Date of last transaction").dt.year().alias("year"),
-        )
-    )
-    if max_sale_year is not None:
-        query = query.filter(pl.col("year") < max_sale_year)
-
-    monthly = (
-        query.group_by("year", "month")
-        .agg(pl.col("psm").median().alias("median_psm"))
-        .with_columns(
-            pl.col("median_psm").mean().over("year").alias("year_mean"),
-        )
-        .with_columns(
-            (pl.col("median_psm") / pl.col("year_mean")).alias("ratio"),
-        )
-        .group_by("month")
-        .agg(pl.col("ratio").mean().alias("factor"))
-        .sort("month")
-        .collect()
-    )
-
-    factors = monthly["factor"].to_numpy().astype(np.float64)
-    return factors / factors.mean()