"""
update_ranking_and_anomalies.py
Synchronizes all multi-platform metrics through HIFFIRankingEngine.
Re-computes XP scores, dynamic weights, statistical anomaly flags, and published ranks.
"""

from pathlib import Path
import pandas as pd

from core.ranking_engine import HIFFIRankingEngine

DATA_PATH = Path("data/hiffi_multiplatform_500.csv")


def run_ranking_update():
    if not DATA_PATH.exists():
        print(f"File not found: {DATA_PATH}")
        return

    df = pd.read_csv(DATA_PATH)
    print(f"Loaded master dataset with {len(df)} artists.")

    engine = HIFFIRankingEngine()

    print("[1/4] Calculating baseline production rankings...")
    df = engine.score_and_rank(df)

    print("[2/4] Computing HIFFI-XP composite scores & dynamic weight redistribution...")
    df = engine.calculate_hiffi_xp(df)

    print("[3/4] Running statistical anomaly detection...")
    df = engine.detect_metric_anomalies(df)

    print("[4/4] Applying publication eligibility gates & tier constraints...")
    df = engine.apply_publication_eligibility_gates(df)

    # Clean display types
    if "hiffi_xp_published_rank" in df.columns:
        df["hiffi_xp_published_rank"] = df["hiffi_xp_published_rank"].astype(int)

    df.to_csv(DATA_PATH, index=False)

    anomaly_counts = (df["anomaly_flags"] != "CLEAN").sum()
    tier_counts = df["platform_evidence_tier"].value_counts().to_dict()

    print("\n==========================================")
    print("Multi-Platform Ranking & Anomaly Sync Complete!")
    print(f"Evidence Tiers Distribution: {tier_counts}")
    print(f"Statistical Anomalies Detected: {anomaly_counts} (Auditable Outliers)")
    print(f"Clean Normal Records:          {len(df) - anomaly_counts}")
    print(f"Master CSV updated: {DATA_PATH}")
    print("==========================================")


if __name__ == "__main__":
    run_ranking_update()