Added hardcoded list of configs for PELCRA due to gated access

app.py

@@ -94,9 +94,13 @@ with analysis_bigos_pelcra:
 
     dataset_short_name = "PELCRA"
 
-    dataset_configs = get_dataset_config_names(dataset_name,trust_remote_code=True)
+    # local version with granted gated access
+    #dataset_configs = get_dataset_config_names(dataset_name,trust_remote_code=True)
     # remove "all" subset, which is always the last config type
-    dataset_configs.pop()
+    #dataset_configs.pop()
+    
+    # remote version with hardcoded access
+    dataset_configs = ['ul-diabiz_poleval-22', 'ul-spokes_mix_emo-18', 'ul-spokes_mix_luz-18', 'ul-spokes_mix_parl-18', 'ul-spokes_biz_bio-23', 'ul-spokes_biz_int-23', 'ul-spokes_biz_luz-23', 'ul-spokes_biz_pod-23', 'ul-spokes_biz_pres-23', 'ul-spokes_biz_vc-23', 'ul-spokes_biz_vc2-23', 'ul-spokes_biz_wyw-23']
     print(dataset_configs)
     # read the reports for public and secret datasets
     [stats_dict_public, contents_dict_public] = read_reports(dataset_name)

utils.py

@@ -539,7 +539,7 @@ def dict_to_multindex_df_all_splits(dict_in):
     return(df)
 
 
-def extract_stats_to_agg(df_multindex_per_split, metrics):
+def extract_stats_to_agg(df_multindex_per_split, metrics, add_total=True):
     # input - multiindex dataframe has three indexes - dataset, metric, split 
     
     # select only relevant metrics
@@ -558,6 +558,9 @@ def extract_stats_to_agg(df_multindex_per_split, metrics):
     # move rows corresponding to specific metrics into specific columns
     df_agg_splits = df_agg_splits.unstack(level ='metric')
     df_agg_splits.columns = df_agg_splits.columns.droplevel(0)
+    
+    if(add_total):
+        df_agg_splits = df_agg_splits
            
     return(df_agg_splits)
 
@@ -577,7 +580,7 @@ def extract_stats_all_splits(df_multiindex_all_splits, metrics):
 
 def extract_stats_for_dataset_card(df_multindex_per_split, subset, metrics, add_total=False):
     
-    print(df_multindex_per_split)
+    #print(df_multindex_per_split)
     df_metrics_subset = df_multindex_per_split
     
     df_metrics_subset = df_metrics_subset.unstack(level ='split')