feat: complete multiplatform pipeline hardening, neutral anchor scoring, and automated health checks

pipeline/generate_report.py

@@ -16,20 +16,23 @@ import pandas as pd
 CSV_PATH = PROJECT_ROOT / "data" / "hiffi_multiplatform_500.csv"
 df = pd.read_csv(CSV_PATH)
 
-# Compute Rank Delta: Positive = climbed in XP rank; Negative = dropped
 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 Ingestion Telemetry:       0 / {len(df)} (BLOCKED_HTTP_403_PREMIUM_REQUIRED)")
-print(f"Instagram Live Follower Signals:   {df['instagram_followers'].notna().sum()} ({(df['instagram_followers'].notna().mean()):.1%})")
-print(f"Complete Cross-Platform Signals:   {df['has_complete_multiplatform_signals'].sum()} (Awaiting Spotify Credential)")
+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 Social Audience Footprint):")
+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))