update

src/populate.py

@@ -11,22 +11,15 @@ from src.leaderboard.filter_models import filter_models_flags
 
 def get_leaderboard_df(results_path: str, requests_path: str, dynamic_path: str,cols: list, benchmark_cols: list) -> pd.DataFrame:
     """Creates a dataframe from all the individual experiment results"""
-    print("results_path", "requests_path", "dynamic_path")
-    print(results_path, requests_path, dynamic_path)
     raw_data = get_raw_eval_results(results_path, requests_path, dynamic_path)
-    print("raw_data", raw_data)
     for v in raw_data:
         print(v.to_dict())
     all_data_json = [v.to_dict() for v in raw_data]
-    print("all_data_json init", all_data_json)
     #all_data_json.append(baseline_row)
     filter_models_flags(all_data_json)
-    print("all_data_json", all_data_json)
     df = pd.DataFrame.from_records(all_data_json)
-    print("df", df)
     print("AutoEvalColumn.average.name",AutoEvalColumn.average.name)
-    #df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
-    print("cols", cols)
+    df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
     df = df[cols].round(decimals=2)
 
     # filter out if any of the benchmarks have not been produced