Update app.py

app.py

@@ -5,7 +5,6 @@ import numpy as np
 
 # --- 1. CONFIGURATION ---
 MODEL_FILE = 'hotel_cancellation_prediction_model_v1_0.joblib'
-
 # The list of features (columns) the model was trained on, in order.
 FEATURE_NAMES = [
     'lead_time',
@@ -28,13 +27,12 @@ def load_model():
     except Exception as e:
         st.error(f"Error loading model: {e}. Check if '{MODEL_FILE}' exists.")
         return None
-
 model = load_model()
 
 # --- 3. PREDICTION LOGIC ---
 def predict_cancellation(inputs, loaded_model):
-    """Prepares data and gets the model's prediction."""
-    
+    """Prepares data and gets the model's prediction and confidence score."""
+
     # Map user inputs to the format the model expects
     input_data = {
         'lead_time': inputs['lead_time'],
@@ -44,32 +42,40 @@ def predict_cancellation(inputs, loaded_model):
         'no_of_weekend_nights': inputs['no_of_weekend_nights'],
         'no_of_week_nights': inputs['no_of_week_nights'],
         'arrival_month': inputs['arrival_month'],
-        
+
         # Binary encoding for categorical features
         'market_segment_type_Online': 1.0 if inputs['market_segment_type'] == 'Online' else 0.0,
         'required_car_parking_space': 1.0 if inputs['required_car_parking_space'] == "Yes" else 0.0,
     }
-    
+
     # Create a DataFrame with the correct column order
     input_df = pd.DataFrame([input_data], columns=FEATURE_NAMES)
-    
+
     # Make prediction (0=Not Cancelled, 1=Cancelled)
     prediction = loaded_model.predict(input_df)[0]
+
+    # Get probability scores for each class (0 and 1)
+    # The output is typically [P(Class 0), P(Class 1)]
+    probabilities = loaded_model.predict_proba(input_df)[0]
+    
+    # The confidence score for the predicted class
+    if prediction == 1:
+        confidence_score = probabilities[1] # Probability of being Cancelled (Class 1)
+    else:
+        confidence_score = probabilities[0] # Probability of being Not Cancelled (Class 0)
     
-    return prediction
+    return prediction, confidence_score
 
 # --- 4. STREAMLIT INTERFACE ---
-
 st.title("Hotel Booking Cancellation Predictor")
 
 if model is None:
     st.stop()
-
+    
 st.markdown("Enter booking details to predict if the reservation will be cancelled.")
 st.markdown("---")
 
 # --- Input Fields (Single Column) ---
-
 # Simple number inputs for basic data types
 lead_time = st.number_input("1. Lead Time (Days before arrival)", min_value=0, value=82, step=1)
 arrival_month = st.selectbox("2. Arrival Month (1=Jan to 12=Dec)", list(range(1, 13)), index=6) # Default to July (7)
@@ -83,11 +89,9 @@ no_of_special_requests = st.number_input("7. Number of Special Requests", min_va
 market_segment_type = st.selectbox("8. Market Segment Type", ["Online", "Offline"])
 required_car_parking_space = st.selectbox("9. Required Car Parking Space", ["Yes", "No"])
 
-
 # --- 5. PREDICTION BUTTON AND OUTPUT ---
-
 if st.button("Get Prediction Result", type="primary"):
-    
+
     # Dictionary to pass inputs easily
     user_inputs = {
         'lead_time': lead_time,
@@ -101,12 +105,17 @@ if st.button("Get Prediction Result", type="primary"):
         'required_car_parking_space': required_car_parking_space,
     }
 
-    prediction = predict_cancellation(user_inputs, model)
-    
+    # Get both the prediction and the confidence score
+    prediction, confidence_score = predict_cancellation(user_inputs, model)
+
     st.markdown("---")
     st.subheader("Prediction Result")
-    
+
+    # Display the result based on the prediction
     if prediction == 1:
         st.error("The model predicts the booking will be **CANCELLED**.")
     else:
-        st.success("The model predicts the booking will be **Not Cancelled**.")
+        st.success("The model predicts the booking will be **Not Cancelled**.")
+
+    # Display the confidence score formatted as a percentage
+    st.info(f"Confidence Score: **{confidence_score * 100:.2f}%**")