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

scripts/audit_sales_catalog.py

@@ -0,0 +1,20 @@
+import pandas as pd
+
+FILE_PATH = "data/master_sales_17k_verified.csv"
+df = pd.read_csv(FILE_PATH)
+
+print(f"Total rows in dataset: {len(df):,}")
+print("\n--- PROVENANCE BREAKDOWN ---")
+print(df["provenance"].value_counts())
+
+verified_df = df[df["provenance"] != "UNVERIFIED_NO_RECORDS"]
+print(f"\nTotal Verified Artists: {len(verified_df):,} ({(len(verified_df)/len(df))*100:.2f}%)")
+print(f"Total Unverified Artists: {len(df) - len(verified_df):,}")
+
+top_cols = ["sales_rank", "artist_name", "audited_sales_units", "provenance"]
+
+print("\n--- TOP 20 ARTISTS BY AUDITED SALES ---")
+print(verified_df[top_cols].sort_values("sales_rank").head(20).to_string(index=False))
+
+print("\n--- BOTTOM 5 VERIFIED ARTISTS (THRESHOLD CHECK) ---")
+print(verified_df[top_cols].sort_values("sales_rank", ascending=False).head(5).to_string(index=False))