Update app.py

app.py

@@ -96,7 +96,7 @@ elif page== "📊 Tabular Data":
         st_lottie(lottie_hello, speed=1, loop=True, height=200)
     
     # Load dataset
-    df = pd.read_csv('/Users/joaopimenta/Downloads/ensemble_test.csv')
+    df = pd.read_csv('/home/user/app/ensemble_test.csv')
     
     # Streamlit App Header
     st.title('🏥 Hospital Readmission Prediction')
@@ -224,8 +224,8 @@ elif page== "📊 Tabular Data":
     # Display Processed Data
     st.markdown("---")
     
-    # Load XGBoost model
-    tabular_model_path = "/Users/joaopimenta/Downloads/final_xgboost_model.pkl"
+    # Load XGBoost model 
+    tabular_model_path = "/home/user/app/final_xgboost_model.pkl"
     tabular_model = joblib.load(tabular_model_path)
     print("✅ XGBoost Tabular Model loaded successfully!")
     
@@ -509,8 +509,8 @@ elif page == "📝 Clinical Text Notes":
                 return self.net(x)
             
         # --- Load MLP Model and PCA ---
-        mlp_model_path = "/Users/joaopimenta/Downloads/Capstone/best_mlp_model_full.pth"
-        pca_path = "/Users/joaopimenta/Downloads/Capstone/best_pca_model.pkl"
+        mlp_model_path = "/home/user/app/best_mlp_model_full.pth"
+        pca_path = "/home/user/app/best_pca_model.pkl"
 
         best_mlp_model = torch.load(mlp_model_path)
         best_mlp_model.to(device)
@@ -701,7 +701,7 @@ elif page == "📝 Clinical Text Notes":
         #st.write(df)
 
         #load lighGBoost model
-        light_path = '/Users/joaopimenta/Downloads/best_lgbm_model.pkl'
+        light_path = '/home/user/app/best_lgbm_model.pkl'
         light_model = joblib.load(light_path)
         #st.write("LightGBoost Model loaded sucessfully!")
 
@@ -764,7 +764,7 @@ elif page == "📝 Clinical Text Notes":
 elif page == "🔀 Ensemble Prediction":
 
     # Load the ensemble model
-    ensemble_model = joblib.load("/Users/joaopimenta/Downloads/best_ensemble_model.pkl")
+    ensemble_model = joblib.load("/home/user/app/best_ensemble_model.pkl")
     #st.write("✅ Ensemble Model loaded successfully!")
 
     # Define models