spb/wp10_uqo Public

1#!/usr/bin/env python32# Author: Simon-Pierre Boucher — contact@spboucher.ai3"""Step 01 — Build the estimation sample.45Reads the raw matched transaction–roll snapshot6(``data/raw/transactions_700k_avec_registre_foncier.parquet``), keeps7residential arm's-length sales with a high-confidence roll match, constructs8the assessment ratio and derived regressors, applies the trims, and writes9``data/processed/analysis.parquet``.1011Usage:  python scripts/01_build_sample.py12"""13import sys14from pathlib import Path1516sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src"))1718from wp10 import sample  # noqa: E402192021def main() -> None:22    s = sample.build_and_save()23    print(f"\nEstimation sample written: {len(s):,} sales")24    print(f"  municipalities : {s['muni'].nunique():,}")25    print(f"  cells          : {s['cell'].nunique():,}")26    print(f"  classes        : {s.groupby('prop_class').size().to_dict()}")27    print(f"  median ratio   : {s['ratio'].median():.3f}")282930if __name__ == "__main__":31    main()32