Update app.py

app.py

@@ -9,18 +9,12 @@ MODEL_REPO_ID = "nansri/engine-predictive-maintenance-model"
 
 @st.cache_resource
 def load_model():
-    try:
-        model_path = hf_hub_download(
-            repo_id=MODEL_REPO_ID,
-            filename="best_model.joblib",
-            repo_type="model"
-        )
-        return joblib.load(model_path)
-    except Exception as e:
-        st.error(f"Model could not be loaded: {e}")
-        return None
-
-model = load_model()
+    model_path = hf_hub_download(
+        repo_id=MODEL_REPO_ID,
+        filename="best_model.joblib",
+        repo_type="model"
+    )
+    return joblib.load(model_path)
 
 st.title("Predictive Maintenance for Engine Health")
 st.write("Enter the engine sensor values below to predict engine condition.")
@@ -33,8 +27,10 @@ lub_oil_temp = st.number_input("Lub Oil Temperature", min_value=0.0, value=78.0)
 coolant_temp = st.number_input("Coolant Temperature", min_value=0.0, value=80.5)
 
 if st.button("Predict Engine Condition"):
-    if model is not None:
-        try:
+    try:
+        with st.spinner("Loading model and generating prediction..."):
+            model = load_model()
+
             input_df = pd.DataFrame([{
                 "Engine_rpm": engine_rpm,
                 "Lub_oil_pressure": lub_oil_pressure,
@@ -46,13 +42,13 @@ if st.button("Predict Engine Condition"):
 
             prediction = model.predict(input_df)[0]
 
-            if prediction == 1:
-                st.error("Prediction: Engine may require maintenance.")
-            else:
-                st.success("Prediction: Engine appears to be operating normally.")
+        if prediction == 1:
+            st.error("Prediction: Engine may require maintenance.")
+        else:
+            st.success("Prediction: Engine appears to be operating normally.")
 
-            st.write("Input dataframe used for prediction:")
-            st.dataframe(input_df)
+        st.write("Input dataframe used for prediction:")
+        st.dataframe(input_df)
 
-        except Exception as e:
-            st.error(f"Prediction failed: {e}")
+    except Exception as e:
+        st.error(f"Prediction failed: {e}")