feat: finalize empirical ordinal tier rankings, fix entity collisions, and dual-mode dashboard

scripts/apply_catalog_intelligence_tiers.py

@@ -0,0 +1,32 @@
+import os
+import pandas as pd
+
+DATA_DIR = "data"
+SALES_PATH = os.path.join(DATA_DIR, "master_sales_17k_verified.csv")
+OUTPUT_PATH = os.path.join(DATA_DIR, "master_artists_intelligence_17k.csv")
+
+df = pd.read_csv(SALES_PATH)
+
+
+def assign_tier(row):
+  prov = str(row.get("provenance", ""))
+  units = row.get("audited_sales_units", 0)
+
+  if prov == "VERIFIED_CSPC":
+    return "TIER_1_GLOBAL_SUPERSTAR_CSPC"
+  elif prov == "VERIFIED_RIAA":
+    if pd.notna(units) and units >= 10_000_000:
+      return "TIER_2A_MAJOR_COMMERCIAL_CORE"
+    return "TIER_2B_CERTIFIED_CATALOG"
+
+  # Provenance UNVERIFIED_NO_RECORDS
+  return "TIER_3_UNAUDITED_DIGITAL_CATALOG"
+
+
+df["catalog_intelligence_tier"] = df.apply(assign_tier, axis=1)
+
+print("--- CATALOG INTELLIGENCE TIER DISTRIBUTION ---")
+print(df["catalog_intelligence_tier"].value_counts())
+
+df.to_csv(OUTPUT_PATH, index=False)
+print(f"\nFinal catalog exported to: {OUTPUT_PATH}")