testing

src/leaderboard/read_evals.py

@@ -76,7 +76,7 @@ class EvalResult:
                 if task_result is not None:
                     results[task.benchmark] = task_result
 
-
+        print(results)
         return self(
             eval_name=eval_name,
             full_model=full_model,
@@ -144,11 +144,13 @@ def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResu
     """From the path of the results folder root, extract all needed info for results"""
     model_result_filepaths = []
 
+    print(results_path)
     for root, _, files in os.walk(results_path):
         # We should only have json files in model results
+        print(files)
         if len(files) == 0 or any([not f.endswith(".json") for f in files]):
             continue
-
+        
         # Sort the files by date
         try:
             files.sort(key=lambda x: x.removesuffix(".json").removeprefix("results_")[:-7])
@@ -158,6 +160,7 @@ def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResu
         for file in files:
             model_result_filepaths.append(os.path.join(root, file))
 
+    print(model_result_filepaths)
     eval_results = {}
     for model_result_filepath in model_result_filepaths:
         # Creation of result

src/populate.py

@@ -13,10 +13,8 @@ def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchm
     raw_data = get_raw_eval_results(results_path, requests_path)
     print(raw_data)
     all_data_json = [v.to_dict() for v in raw_data]
-    print(all_data_json)
 
     df = pd.DataFrame.from_records(all_data_json)
-    print(df)
     # df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
     df = df[cols].round(decimals=1)
 
@@ -25,7 +23,7 @@ def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchm
     return df
 
 def get_evaluation_queue_df(save_path: str, cols: list) -> list[pd.DataFrame]:
-    """Creates the different dataframes for the evaluation queues requestes"""
+    """Creates the different dataframes for the evaluation queues requests"""
     entries = [entry for entry in os.listdir(save_path) if not entry.startswith(".")]
     all_evals = []