testing once more

src/leaderboard/read_evals.py

@@ -109,7 +109,6 @@ class EvalResult:
             AutoEvalColumn.still_on_hub.name: self.still_on_hub,
         }
 
-        print(self.track, self.results.keys())
         if self.track.lower() == "multimodal":
             taskset = TasksMultimodal
         else:
@@ -117,7 +116,6 @@ class EvalResult:
         for task in taskset:
             data_dict[task.value.col_name] = self.results[task.value.benchmark]
 
-        print("Made it for track", self.track)
         return data_dict
 
 
@@ -181,5 +179,4 @@ def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResu
         except KeyError:  # not all eval values present
             continue
 
-    print(results, len(results))
     return results

src/populate.py

@@ -14,13 +14,14 @@ def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchm
     all_data_json = [v.to_dict() for v in raw_data]
     all_data_json_filtered = []
     for item in all_data_json:
+        print(benchmark_cols, "|||", item.keys())
         if "VQA" in benchmark_cols and "vqa" in item:
             all_data_json_filtered.append(item)
         if "VQA" not in benchmark_cols and "vqa" not in item:
             all_data_json_filtered.append(item)
     all_data_json = all_data_json_filtered
 
-    print(all_data_json)
+    print("Filtered:", all_data_json, len(all_data_json))
     df = pd.DataFrame.from_records(all_data_json)
     print(df)
     # df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)