# Author: Simon-Pierre Boucher — contact@spboucher.ai
"""Paths and global constants for the WP11 pipeline.

All paths are relative to the repository root; override with ``WP11_ROOT``.
"""
import os
from pathlib import Path

ROOT = Path(os.environ.get("WP11_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 = {"1000", "1100", "1211", "1990"}
MATCH_MAX_DIST_M = 50.0
MATCH_MIN_SCORE = 150.0
PRICE_MIN = 50_000
TRIM = (0.01, 0.99)          # price and floor-area tails, within sale year
AGE_MAX = 150
GRID_DEG = 0.01              # ~1.1 km spatial grid cells for high-dim FE
GRID5_DEG = 0.05             # ~5.5 km grid, mid-granularity spatial FE

# ---------------------------------------------------------------- splits
SEED = 20260809
TEST_SHARE = 0.20            # random holdout
TEMPORAL_CUTOFF = "2025-01-01"  # train < cutoff, test >= cutoff

# Box-Cox profile-likelihood grid
BOXCOX_GRID = [-0.50, -0.25, 0.0, 0.25, 0.50, 0.75, 1.0]

# Learning-curve training sizes
LEARNING_SIZES = [10_000, 25_000, 50_000, 100_000, 200_000, 400_000]

# Minimum predicted price when inverting level/Box-Cox models
PRED_FLOOR = 20_000.0


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)