update

util/evaluation.py

@@ -20,6 +20,7 @@ def statistical_tests(data):
     # Calculate average ranks
     rank_columns = [v + rank_suffix for v in variables]
     average_ranks = data[rank_columns].mean()
+    average_scores = data[[v + score_suffix for v in variables]].mean()
 
     # Statistical tests
     rank_data = [data[col] for col in rank_columns]
@@ -56,6 +57,7 @@ def statistical_tests(data):
 
     results = {
         "Average Ranks": average_ranks.to_dict(),
+        "Average Scores": average_scores.to_dict(),
         "Friedman Test": {
             "Statistic": friedman_stat,
             "p-value": friedman_p,