update

util/evaluation.py

@@ -98,10 +98,11 @@ def statistical_tests(data):
 
     for (var1, var2) in pairs:
         pair_name_score = f'{var1}{score_suffix} vs {var2}{score_suffix}'
+        pair_rank_score = f'{var1}{rank_suffix} vs {var2}{rank_suffix}'
 
         # Bootstrapped T-test for independent samples
         t_stat, t_p = bootstrap_t_test(data[f'{var1}{rank_suffix}'], data[f'{var2}{rank_suffix}'])
-        pairwise_results['T-Test'][pair_name_score] = {"Statistic": t_stat, "p-value": t_p}
+        pairwise_results['T-Test'][pair_rank_score] = {"Statistic": t_stat, "p-value": t_p}
 
     # Friedman test
     friedman_stat, friedman_p = friedmanchisquare(*rank_data)