"""
pipeline/generate_report.py
Generates executive audit summaries and identifies movers between the 
verified Production YouTube rank and the Experimental HIFFI-XP model.
"""

import sys
from pathlib import Path

PROJECT_ROOT = Path(__file__).resolve().parent.parent
if str(PROJECT_ROOT) not in sys.path:
    sys.path.insert(0, str(PROJECT_ROOT))

import pandas as pd

CSV_PATH = PROJECT_ROOT / "data" / "hiffi_multiplatform_500.csv"
df = pd.read_csv(CSV_PATH)

df["rank_delta"] = df["production_hiffi_rank"] - df["hiffi_xp_rank"]

verified_spotify_count = df["spotify_monthly_listeners"].notna().sum()
verified_ig_count = df["instagram_followers"].notna().sum()
complete_signals_count = df["has_complete_multiplatform_signals"].sum()

print("=" * 90)
print("SUPERLABS HIFFI: 500-ARTIST AUDITED MULTI-PLATFORM SUMMARY")
print("=" * 90)
print(f"Total Cohort Processed:            {len(df)}")
print(f"Resolved Spotify Candidate URIs:   {(df['spotify_id'] != 'N/A').sum()} (100.0%)")
print(f"Spotify Verified Telemetry Ingest: {verified_spotify_count} / {len(df)} (kworb_public_aggregator)")
print(f"Instagram Live Follower Signals:   {verified_ig_count} / {len(df)} ({(verified_ig_count / len(df)):.1%})")
print(f"Complete 3-Platform Signals:       {complete_signals_count} / {len(df)}")
print("-" * 90)

print("\nTOP 10 GAINERS (Lifted by Validated Multi-Platform Footprint):")
gainers = df[df["production_hiffi_rank"].notna()].sort_values("rank_delta", ascending=False).head(10)
display_cols = ["name", "production_hiffi_rank", "hiffi_xp_rank", "rank_delta", "instagram_followers", "hiffi_xp_score"]
print(gainers[display_cols].to_string(index=False))

print("\nTOP 10 FALLERS (Strong YouTube Velocity, but Awaiting/Lacking Social Reach):")
fallers = df[df["production_hiffi_rank"].notna()].sort_values("rank_delta", ascending=True).head(10)
print(fallers[display_cols].to_string(index=False))
print("=" * 90)