Update src/populate.py

src/populate.py

@@ -1,68 +1,68 @@
 # src/populate.py
-
 import json
-import os
-
+import os 
 import pandas as pd
 
-# 원래 있던 local `make_clickable_model` 제거하고,
 # 외부에서 정의된 함수를 import 해옵니다.
 from src.display.formatting import has_no_nan_values, make_clickable_model
 from src.display.utils import AutoEvalColumn, EvalQueueColumn
-from src.leaderboard.read_evals import get_raw_eval_results
-
-
-def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchmark_cols: list) -> pd.DataFrame:
-    raw_data = get_raw_eval_results(results_path, requests_path)
-    all_data_json = [v.to_dict() for v in raw_data]
-
-    df = pd.DataFrame.from_records(all_data_json)
-    df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
-    df = df[cols].round(decimals=2)
+from src.leaderboard.read_evals import get_raw_eval_results 
 
+def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchmark_cols: list) -> pd.DataFrame: 
+    raw_data = get_raw_eval_results(results_path, requests_path) 
+    all_data_json = [v.to_dict() for v in raw_data] 
+    df = pd.DataFrame.from_records(all_data_json) 
+    df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False) 
+    df = df[cols].round(decimals=2) 
+    
     # "model" 컬럼에 make_clickable_model 적용
+    # 반드시 원본 모델명이 보존되도록 합니다
     if "model" in df.columns:
+        # 원본 모델명 임시 저장
+        df["original_model_name"] = df["model"].copy()
+        # 하이퍼링크 적용
         df["model"] = df["model"].apply(make_clickable_model)
-
+    
     # 모든 벤치마크가 생산되지 않은 행을 필터링
     df = df[has_no_nan_values(df, benchmark_cols)]
     return df
 
-
 def get_evaluation_queue_df(save_path: str, cols: list) -> list[pd.DataFrame]:
     """평가 대기열에 대한 각 DataFrame을 생성합니다."""
     entries = [entry for entry in os.listdir(save_path) if not entry.startswith(".")]
     all_evals = []
-
+    
     for entry in entries:
         if ".json" in entry:
             file_path = os.path.join(save_path, entry)
             with open(file_path) as fp:
                 data = json.load(fp)
-
-            data[EvalQueueColumn.model.name] = make_clickable_model(data["model"])
-            data[EvalQueueColumn.revision.name] = data.get("revision", "main")
-
-            all_evals.append(data)
+                # 원본 모델명 저장
+                original_model = data.get("model", "")
+                data[EvalQueueColumn.model.name] = make_clickable_model(original_model)
+                data[EvalQueueColumn.revision.name] = data.get("revision", "main")
+                all_evals.append(data)
         elif ".md" not in entry:
             # 폴더인 경우: 파일 여부를 확인할 때 전체 경로를 사용
             sub_entries = [
-                e for e in os.listdir(os.path.join(save_path, entry))
+                e for e in os.listdir(os.path.join(save_path, entry)) 
                 if os.path.isfile(os.path.join(save_path, entry, e)) and not e.startswith(".")
             ]
             for sub_entry in sub_entries:
                 file_path = os.path.join(save_path, entry, sub_entry)
                 with open(file_path) as fp:
                     data = json.load(fp)
-
-                data[EvalQueueColumn.model.name] = make_clickable_model(data["model"])
-                data[EvalQueueColumn.revision.name] = data.get("revision", "main")
-                all_evals.append(data)
-
+                    original_model = data.get("model", "")
+                    data[EvalQueueColumn.model.name] = make_clickable_model(original_model)
+                    data[EvalQueueColumn.revision.name] = data.get("revision", "main")
+                    all_evals.append(data)
+    
     pending_list = [e for e in all_evals if e["status"] in ["PENDING", "RERUN"]]
     running_list = [e for e in all_evals if e["status"] == "RUNNING"]
     finished_list = [e for e in all_evals if e["status"].startswith("FINISHED") or e["status"] == "PENDING_NEW_EVAL"]
+    
     df_pending = pd.DataFrame.from_records(pending_list, columns=cols)
     df_running = pd.DataFrame.from_records(running_list, columns=cols)
     df_finished = pd.DataFrame.from_records(finished_list, columns=cols)
-    return df_finished[cols], df_running[cols], df_pending[cols]
+    
+    return df_finished[cols], df_running[cols], df_pending[cols]