upgrade leaderboard

app.py

@@ -802,10 +802,12 @@ def filter_by_model_type(df, selected_types):
 
 def format_dataframe(df, dataset):
     print(df)
+    print("----- *** ------")
     columns = ['Method'] + [col for col in df.columns if dataset in col]
     filtered_df = df[columns].copy()
     filtered_df.columns = [col.split('_')[-1] if '_' in col else col for col in filtered_df.columns]
     print(filtered_df)
+    print("----- ### ------")
     # filtered_df = filtered_df.sort_values('MRR', ascending=False)
     filtered_df = filtered_df.sort_values('Kappa', ascending=False)
     return filtered_df
@@ -826,7 +828,8 @@ def update_tables(selected_types):
     outputs = []
     # for df in [filtered_df_full, filtered_df_10, filtered_df_human]:
     for df in [filtered_df_full]:
-        for dataset in ['DL2023', 'MAG', 'PRIME']:
+        # for dataset in ['DL2023', 'MAG', 'PRIME']:
+        for dataset in ['DL2023']:
             outputs.append(format_dataframe(df, f"LLMJudge-{dataset}"))
     
     return outputs