"""
scripts/audit_weights.py
Audits dynamic weight allocation, platform presence tiers, and high-rank evidence.
"""
from pathlib import Path
import pandas as pd
import numpy as np

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

if not DATASET_PATH.exists():
    raise FileNotFoundError(f"Master cohort not found at {DATASET_PATH}")

df = pd.read_csv(DATASET_PATH)

# Explicitly define platform presence (YouTube, Spotify presence, Instagram presence)
df["has_youtube"] = df["production_hiffi_score"].notna()
df["has_spotify"] = df["spotify_monthly_listeners"].notna()
df["has_instagram"] = df["instagram_followers"].notna()

df["verified_platform_count"] = (
    df["has_youtube"].astype(int) +
    df["has_spotify"].astype(int) +
    df["has_instagram"].astype(int)
)

print("=" * 70)
print("1. VERIFIED PLATFORM PRESENCE TIERS")
print("=" * 70)
tier_summary = df.groupby("verified_platform_count")["hiffi_xp_score"].agg(
    count="count",
    mean="mean",
    std="std",
    min="min",
    max="max"
).round(2)
print(tier_summary)

print("\n" + "=" * 70)
print("2. TOP 50 PLATFORM EVIDENCE DISTRIBUTION")
print("=" * 70)
top_50 = df[df["hiffi_xp_rank"] <= 50]
top_50_dist = top_50["verified_platform_count"].value_counts().sort_index(ascending=False)
for tier, count in top_50_dist.items():
    print(f"Tier {tier} Platforms Verified: {count:2d} artists ({count / len(top_50) * 100:4.1f}%)")

print("\n" + "=" * 70)
print("3. TOP 10 PLATFORM EVIDENCE DISTRIBUTION")
print("=" * 70)
top_10 = df[df["hiffi_xp_rank"] <= 10]
top_10_dist = top_10["verified_platform_count"].value_counts().sort_index(ascending=False)
for tier, count in top_10_dist.items():
    print(f"Tier {tier} Platforms Verified: {count:2d} artists ({count / len(top_10) * 100:4.1f}%)")

print("\n" + "=" * 70)
print("4. RANK DELTA EXTREMES & AUDIT TRAIL")
print("=" * 70)
cols = ["name", "production_hiffi_rank", "hiffi_xp_rank", "rank_delta", "verified_platform_count"]
top_gainers = df.sort_values(by="rank_delta", ascending=False).head(3)[cols]
top_fallers = df.sort_values(by="rank_delta", ascending=True).head(3)[cols]

print("Top 3 Gainers:")
print(top_gainers.to_string(index=False))
print("\nTop 3 Fallers:")
print(top_fallers.to_string(index=False))
print("=" * 70)