Update app.py

app.py

@@ -1,25 +1,40 @@
+import os
 import gradio as gr
 import numpy as np
 import joblib
 from tensorflow.keras.models import load_model
 
 # Paths to your saved models and scaler
-scaler_path = '/Env_ContaminationLevel/blob/main/scaler_X.pkl'
-rf_model_path = '/Env_ContaminationLevel/blob/main/rf_model.pkl'
-mlp_model_path = '/Env_ContaminationLevel/blob/main/mlp_model.h5'
-meta_model_path = '/Env_ContaminationLevel/blob/main/meta_model.pkl'
-try:
-    # Load the scaler and models
-    scaler_X = joblib.load(scaler_path)
-    loaded_rf_model = joblib.load(rf_model_path)
-    loaded_mlp_model = load_model(mlp_model_path)
-    loaded_meta_model = joblib.load(meta_model_path)
-    print("Models and scaler loaded successfully.")
-except Exception as e:
-    print(f"Error loading models or scaler: {e}")
+scaler_path = 'scaler_X.pkl'
+rf_model_path = 'rf_model.pkl'
+mlp_model_path = 'mlp_model.h5'
+meta_model_path = 'meta_model.pkl'
+
+def load_models_and_scaler():
+    try:
+        # Load the scaler and models
+        scaler_X = joblib.load(scaler_path)
+        print("Scaler loaded successfully.")
+        loaded_rf_model = joblib.load(rf_model_path)
+        print("Random Forest model loaded successfully.")
+        loaded_mlp_model = load_model(mlp_model_path)
+        print("MLP model loaded successfully.")
+        loaded_meta_model = joblib.load(meta_model_path)
+        print("Meta model loaded successfully.")
+        return scaler_X, loaded_rf_model, loaded_mlp_model, loaded_meta_model
+    except Exception as e:
+        print(f"Error loading models or scaler: {e}")
+        import traceback
+        traceback.print_exc()
+        return None, None, None, None
+
+scaler_X, loaded_rf_model, loaded_mlp_model, loaded_meta_model = load_models_and_scaler()
 
 def predict_new_values(new_input_data):
     try:
+        if not all([scaler_X, loaded_rf_model, loaded_mlp_model, loaded_meta_model]):
+            raise Exception("Models or scaler not loaded properly.")
+        
         # Ensure the new input data is in the correct format
         print(f"Raw Input Data: {new_input_data}")
         new_input_data = np.array(new_input_data).reshape(1, -1)
@@ -43,6 +58,8 @@ def predict_new_values(new_input_data):
         return loaded_meta_predictions_new[0]
     except Exception as e:
         print(f"Error in prediction: {e}")
+        import traceback
+        traceback.print_exc()
         return ["Error", "Error", "Error", "Error", "Error", "Error"]
 
 def gradio_interface(velocity, temperature, precipitation, humidity):
@@ -61,12 +78,14 @@ def gradio_interface(velocity, temperature, precipitation, humidity):
         ]
     except Exception as e:
         print(f"Error in Gradio interface: {e}")
+        import traceback
+        traceback.print_exc()
         return ["Error", "Error", "Error", "Error", "Error", "Error"]
 
 inputs = [
-    gr.Slider(minimum=0, maximum=100, value=50,step=0.5, label="Velocity (mph)"),
-    gr.Slider(minimum=-30, maximum=50, value=0,step=0.5, label="Temperature (°C)"),
-    gr.Slider(minimum=0, maximum=10, value=0,step=0.01, label="Precipitation (inch)"),
+    gr.Slider(minimum=0, maximum=100, value=50, step=0.5, label="Velocity (mph)"),
+    gr.Slider(minimum=-30, maximum=50, value=0, step=0.5, label="Temperature (°C)"),
+    gr.Slider(minimum=0, maximum=10, value=0, step=0.01, label="Precipitation (inch)"),
     gr.Slider(minimum=0, maximum=100, value=50, label="Humidity (%)")
 ]