fix: pointer problem

app.py

@@ -1,5 +1,4 @@
 import os
-import json
 import requests
 
 import gradio as gr
@@ -8,7 +7,6 @@ from huggingface_hub import HfApi, hf_hub_download, snapshot_download
 from huggingface_hub.repocard import metadata_load
 from apscheduler.schedulers.background import BackgroundScheduler
 
-from tqdm.contrib.concurrent import thread_map
 
 from utils import *
 
@@ -190,55 +188,13 @@ def filter_students(model_ids):
             filtered.append(model_id)
     return filtered
 
-# Parralelized version
-def update_leaderboard_dataset_parallel(rl_env, path):
-    # Get model ids associated with rl_env
-    model_ids = get_model_ids(rl_env)
-    model_ids = filter_students(model_ids)
-
-    def process_model(model_id):
-        meta = get_metadata(model_id)
-        #LOADED_MODEL_METADATA[model_id] = meta if meta is not None else ''
-        if meta is None:
-            return None
-        try:
-            user_id = model_id.split('/')[0]
-            row = {}
-            row["User"] = user_id
-            row["Model"] = model_id
-            accuracy = parse_metrics_accuracy(meta)
-            mean_reward, std_reward = parse_rewards(accuracy)
-            mean_reward = mean_reward if not pd.isna(mean_reward) else 0
-            std_reward = std_reward if not pd.isna(std_reward) else 0
-            row["Results"] = mean_reward - std_reward
-            row["Mean Reward"] = mean_reward
-            row["Std Reward"] = std_reward
-            return row
-        except:
-            return None
-
-    data = list(thread_map(process_model, model_ids, desc="Processing models"))
-
-    # Filter out None results (models with no metadata)
-    data = [row for row in data if row is not None]
-
-    ranked_dataframe = rank_dataframe(pd.DataFrame.from_records(data))
-    new_history = ranked_dataframe
-    file_path = path + "/" + rl_env + ".csv"
-    new_history.to_csv(file_path, index=False)
-
-    return ranked_dataframe
-
 
 def update_leaderboard_dataset(rl_env, path):
     # Get model ids associated with rl_env
     model_ids = get_model_ids(rl_env)
+    model_ids = filter_students(model_ids)
     data = []
     for model_id in model_ids:
-        """
-        readme_path = hf_hub_download(model_id, filename="README.md")
-        meta = metadata_load(readme_path)
-        """
         meta = get_metadata(model_id)
         #LOADED_MODEL_METADATA[model_id] = meta if meta is not None else ''
         if meta is None:
@@ -255,14 +211,15 @@ def update_leaderboard_dataset(rl_env, path):
         row["Mean Reward"] = mean_reward
         row["Std Reward"] = std_reward
         data.append(row)
+    
+    if not data:
+        return
 
     ranked_dataframe = rank_dataframe(pd.DataFrame.from_records(data))
     new_history = ranked_dataframe
     file_path = path + "/" + rl_env + ".csv"
     new_history.to_csv(file_path, index=False)
 
-    return ranked_dataframe
-
 def download_leaderboard_dataset():
     path = snapshot_download(repo_id=DATASET_REPO_ID, repo_type="dataset")
     return path
@@ -273,6 +230,9 @@ def get_data(rl_env, path) -> pd.DataFrame:
     :return: data as a pandas DataFrame
     """
     csv_path = path + "/" + rl_env + ".csv"
+    if not os.path.exists(csv_path):
+        return pd.DataFrame(columns=['Ranking', 'User', 'Model', 'Results', 'Mean Reward', 'Std Reward'])
+
     data = pd.read_csv(csv_path)
 
     for index, row in data.iterrows():
@@ -308,7 +268,7 @@ def run_update_dataset():
     path_ = download_leaderboard_dataset()
     for i in range(0, len(rl_envs)):
         rl_env = rl_envs[i]
-        update_leaderboard_dataset_parallel(rl_env["rl_env"], path_)
+        update_leaderboard_dataset(rl_env["rl_env"], path_)
 
     api.upload_folder(
     folder_path=path_,

requirements.txt

@@ -1,4 +1,5 @@
 APScheduler==3.10.1
-gradio==4.44.1
+gradio==5.49.1
 httpx>=0.24.1
-tqdm
+tqdm
+requests==2.32.5