added scheduler, logging and optimization updates

app.py

@@ -73,7 +73,6 @@ def load_and_preprocess_data():
     followers = fetch_table('followers', 'id, following')
     users = fetch_table('profiles', 'id')
 
-    # Use native Python for merging instead of pandas
     follower_dict = {f['id']: f['following'] for f in followers}
     user_set = {u['id'] for u in users}
     merged = [
@@ -89,12 +88,8 @@ def create_graph_dataframe(merged_data):
     G.add_edges_from(edges)
     user_ids = sorted(G.nodes())
     
-    # Use sparse identity matrix for features
-    features = torch.sparse_coo_tensor(
-        torch.arange(len(user_ids)).repeat(2, 1),
-        torch.ones(len(user_ids)),
-        (len(user_ids), len(user_ids))
-    )
+    # Use dense identity matrix for features (sparse not supported by SAGEConv)
+    features = torch.eye(len(user_ids))
     logger.info(f"Created graph with {len(user_ids)} nodes")
     return G, features, user_ids
 
@@ -164,7 +159,7 @@ def train_model(model, data, pos_edges, neg_edges, epochs=200, patience=20):
                 break
 
     logger.info("Model training completed")
-    return model.to('cpu')  # Move back to CPU for inference
+    return model.to('cpu')
 
 def get_recommendations(user_id, model, data, G, user_ids, top_k=10):
     if user_id not in user_ids:
@@ -187,7 +182,7 @@ def get_recommendations(user_id, model, data, G, user_ids, top_k=10):
 
 def rebuild_model():
     global G, features, user_ids, pyg_data, trained_model
-    logger.info("Starting model rebuild at 3:30 AM")
+    logger.info("Starting model rebuild at 3:30 AM Pacific Time")
     try:
         merged_data = load_and_preprocess_data()
         G, features, user_ids = create_graph_dataframe(merged_data)
@@ -214,7 +209,6 @@ async def get_recommendations_handler(user_id: str = Query(...)):
 
     recommendations = get_recommendations(user_id, trained_model, pyg_data, G, user_ids)
     
-    # Stream the response
     def generate():
         yield '{"status": "success", "recommendations": ['
         for i, rec in enumerate(recommendations):
@@ -229,11 +223,11 @@ async def get_recommendations_handler(user_id: str = Query(...)):
 async def health_check():
     return {"status": "success", "message": "Recommendation service operational"}
 
-# Scheduler setup
+# Scheduler setup with Pacific Time Zone
 scheduler = BackgroundScheduler(timezone="America/Los_Angeles")
 scheduler.add_job(
     rebuild_model,
-    trigger=CronTrigger(hour=3, minute=30),  # Run at 3:30 AM every day
+    trigger=CronTrigger(hour=3, minute=30),  # Run at 3:30 AM Pacific Time every day
     id='daily_model_rebuild',
     replace_existing=True
 )
@@ -242,7 +236,7 @@ scheduler.add_job(
 async def startup_event():
     rebuild_model()  # Initial build on startup
     scheduler.start()
-    logger.info("Scheduler started, model will rebuild daily at 3:30 AM")
+    logger.info("Scheduler started, model will rebuild daily at 3:30 AM Pacific Time")
 
 @app.on_event("shutdown")
 async def shutdown_event():