# Author: Simon-Pierre Boucher — contact@spboucher.ai
"""Paths and global constants for the WP10 pipeline.

All paths are relative to the repository root, so the pipeline runs on any
machine after cloning. Override the root with the ``WP10_ROOT`` environment
variable if the scripts are launched from elsewhere.
"""
import os
from pathlib import Path

ROOT = Path(os.environ.get("WP10_ROOT", Path(__file__).resolve().parents[2]))

RAW_PARQUET = ROOT / "data" / "raw" / "transactions_700k_avec_registre_foncier.parquet"
PROCESSED = ROOT / "data" / "processed"
ANALYSIS_PARQUET = PROCESSED / "analysis.parquet"
FIGURES = ROOT / "figures"
RESULTS = ROOT / "results"
REPRODUCED = RESULTS / "reproduced"
TABLES = RESULTS / "tables"

# ---------------------------------------------------------------- sample
# Residential CUBF use codes kept in the estimation sample
# 1000 Logement | 1100 Chalet ou maison de villégiature | 1211 Maison mobile
# 1990 Autres immeubles résidentiels
RESIDENTIAL_CUBF = {"1000", "1100", "1211", "1990"}

MATCH_MAX_DIST_M = 50.0     # roll–transaction geocoding distance ceiling
MATCH_MIN_SCORE = 150.0     # matcher confidence floor (max attainable: 220)

PRICE_MIN = 50_000          # source feed already truncates below 50k
RATIO_TRIM = (0.01, 0.99)   # symmetric trim on the assessment ratio, by roll vintage

CELL_MIN_OBS = 20           # minimum sales per municipality×roll×year cell (FE cells)
MUNI_MIN_SALES = 100        # minimum sales for municipality-level IAAO statistics

# ---------------------------------------------------------------- inference
SEED_BOOT = 20260809        # bootstrap seed (IAAO confidence intervals)
N_BOOT = 500                # bootstrap replications
QUANTILES = [0.10, 0.25, 0.50, 0.75, 0.90]  # quantile-regression grid

# IAAO (2013) acceptable ranges, quoted in the paper's tables
IAAO_COD_MAX_SF = 15.0      # single-family, heterogeneous areas
IAAO_PRD_RANGE = (0.98, 1.03)
IAAO_PRB_RANGE = (-0.05, 0.05)

# Ten largest markets reported individually in the IAAO table
BIG_CITIES = ["Montréal", "Québec", "Laval", "Gatineau", "Longueuil",
              "Lévis", "Sherbrooke", "Saguenay", "Trois-Rivières", "Terrebonne"]


def ensure_dirs() -> None:
    """Create every output directory the pipeline writes to."""
    for p in (PROCESSED, FIGURES, REPRODUCED, TABLES):
        p.mkdir(parents=True, exist_ok=True)