spb/wp2_uqo Public
UQO Working Paper No. 2 — Decoding Real Estate Descriptions: text-based hedonic analysis of housing listings.
TeX 73.8%
Python 26%
1#!/usr/bin/env python32# Author: Simon-Pierre Boucher — contact@spboucher.ai3#4"""Step 1 — Extract the house sample from data/raw/louka.db.56Output: data/processed/houses.parquet (n = 17,087 rows expected).7"""89import sys10from pathlib import Path1112sys.path.insert(0, str(Path(__file__).resolve().parents[1]))1314from src import config15from src.data import load_houses161718def main():19 print(f"Reading {config.DB_PATH} ...")20 df = load_houses(config.DB_PATH)21 print(f" {len(df):,} houses with a valid price and description")22 print(f" price: min=${df['price'].min():,.0f} "23 f"median=${df['price'].median():,.0f} max=${df['price'].max():,.0f}")2425 config.DATA_PROCESSED.mkdir(parents=True, exist_ok=True)26 df.to_parquet(config.HOUSES_PARQUET, index=False)27 print(f" -> {config.HOUSES_PARQUET}")282930if __name__ == "__main__":31 main()32