shifting away from tasks.loop (discord reliant) for heavy I/O operations (hub stat updates)

app.py

@@ -104,6 +104,7 @@ def update_google_sheet():
 executor = ThreadPoolExecutor(max_workers=2)
 scheduler = BackgroundScheduler(executors={'default': executor})
 scheduler.add_job(update_google_sheet, trigger='interval', minutes=1, max_instances=2)
+scheduler.add_job(update_hub_stats, trigger='interval', minutes=1, max_instances=2)
 scheduler.start()
 
 
@@ -613,20 +614,19 @@ async def remove_huggingfolks():
 #---------------------------------------------------------------------------------------------
 # UPDATE dataframe WITH HFAPI INFO on a timer
 
-@tasks.loop(minutes=1)
-async def update_hub_stats():
+#@tasks.loop(minutes=1) tasks.loop leads to heartbeat blocked issues (merging calculations too much with normal discord bot functions)
+def update_hub_stats():
     try:
         global global_df
-        
-        #updated_df = global_df.copy()
+        print("Updating hub stats...")
+        print(f"------------------------------------------------------------------------")
+
         for index, row in global_df.iterrows():
-        # fill blank values with n/a for now? then replace if they try to verify
-        #column = global_df['hf_user_name']
+            # fill blank values with n/a for now? then replace if they try to verify
 
             # data type of value?
+            # may need this to be fairly long -> complete cycles successfully before starting new job
             
-            #for index, user in column:
-            #print(f"index: {index}")
             user = row['hf_user_name']
             if pd.notna(user):
                 print(f"user: {user}")
@@ -659,23 +659,16 @@ async def update_hub_stats():
                     except Exception as e:
                         print(f"{e} error updating the dataframe")
                 
-        
-                    #sheet1.update(f'I{i+1}:O{i+1}',[[likes, models, datasets, spaces, discussions, papers, upvotes]])
-                    # update df instead
-                    #updated_df.loc[index, ['likes', 'models', 'datasets', 'spaces', 'discussions', 'papers', 'upvotes']] = [likes, models, datasets, spaces, discussions, papers, upvotes]
-                    #print(f"likes: {likes}")
-                    #global_df.loc[index, 'likes'] = likes
-                    #print(f"updated row {index} for user {user}")
                 else:
                     print(f"Failed to retrieve data for user {user}. Status code: {response.status_code}")        
 
-        #print(global_df)
 
     except Exception as e:
         print(f"Failed to parse data for user {user}. {e}")
-
-
-
+    timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+    print(f"------------------------------------------------------------------------")
+    print(f"Hub stats successfully updated at {timestamp}! \n{global_df}")
+    print(f"------------------------------------------------------------------------")
 
         
 #---------------------------------------------------------------------------------------------