Update app.py

app.py

@@ -2,192 +2,111 @@ import streamlit as st
 import joblib
 import pandas as pd
 import numpy as np
-import os
-import time
-
-# --- Constants and Configuration ---
 
+# --- 1. CONFIGURATION ---
 MODEL_FILE = 'hotel_cancellation_prediction_model_v1_0.joblib'
 
-# The exact list of features (columns) the model expects in this specific order
-# Corrected order based on the debugging output and X_train columns
-EXPECTED_FEATURES = [
+# The list of features (columns) the model was trained on, in order.
+FEATURE_NAMES = [
     'lead_time',
     'no_of_special_requests',
     'avg_price_per_room',
     'no_of_adults',
     'no_of_weekend_nights',
-    'required_car_parking_space', # Corrected position
-    'no_of_week_nights',          # Corrected position
-    'arrival_month',              # Corrected position
-    'market_segment_type_Online'  # Corrected position
+    'required_car_parking_space',
+    'no_of_week_nights',
+    'arrival_month',
+    'market_segment_type_Online'
 ]
 
-
-# Define typical ranges based on EDA (adjust as needed)
-# From data.describe().T:
-# lead_time: min=0, max=443, mean=81.61, 75%=118
-# no_of_special_requests: min=0, max=5, mean=0.56, 75%=1
-# avg_price_per_room: min=0, max=540, mean=101.03, 75%=119
-# no_of_adults: min=0, max=4, mean=1.83, 75%=2
-# no_of_weekend_nights: min=0, max=6, mean=0.78, 75%=1
-# no_of_week_nights: min=0, max=17, mean=2.17, 75%=3
-# required_car_parking_space: min=0, max=1
-# arrival_month: min=1, max=12 (based on code)
-
-FEATURE_RANGES = {
-    'lead_time': {'min': 0, 'max': 450, 'default': 82},
-    'no_of_special_requests': {'min': 0, 'max': 5, 'default': 1},
-    'avg_price_per_room': {'min': 0.0, 'max': 600.0, 'default': 101.0},
-    'no_of_adults': {'min': 0, 'max': 4, 'default': 2},
-    'no_of_weekend_nights': {'min': 0, 'max': 7, 'default': 1}, # Adjusted max slightly
-    'no_of_week_nights': {'min': 0, 'max': 20, 'default': 2}, # Adjusted max slightly
-    'arrival_month': {'min': 1, 'max': 12, 'default': 7}, # Default to July based on EDA for example
-}
-
-
-# --- Model Loading (Cached) ---
-
+# --- 2. MODEL LOADING ---
+# Use cache to load the model just once
 @st.cache_resource
-def load_cancellation_model():
+def load_model():
     try:
-        model = joblib.load(MODEL_FILE)
-        return model
+        return joblib.load(MODEL_FILE)
     except Exception as e:
-        st.error(f"Error loading model: {e}")
+        st.error(f"Error loading model: {e}. Check if '{MODEL_FILE}' exists.")
         return None
 
-cancellation_predictor = load_cancellation_model()
-
-# --- Prediction Function (Critical Data Preprocessing) ---
-
-def run_prediction(
-    lead_time, market_segment_type, avg_price_per_room, no_of_adults,
-    no_of_weekend_nights, no_of_week_nights, no_of_special_requests,
-    arrival_month, required_car_parking_space, model
-):
-    """Processes inputs and runs prediction, mimicking the training feature engineering."""
-
-    # 1. Manually construct the input row, using the required feature engineering
-    data_row = {
-        'lead_time': lead_time,
-        'no_of_special_requests': no_of_special_requests,
-        'avg_price_per_room': avg_price_per_room,
-        'no_of_adults': no_of_adults,
-        'no_of_weekend_nights': no_of_weekend_nights,
-        'no_of_week_nights': no_of_week_nights,
-        'arrival_month': arrival_month,
-
-        # One-Hot Encoding for 'market_segment_type' (assuming 'Offline' is the base category)
-        'market_segment_type_Online': 1.0 if market_segment_type == 'Online' else 0.0,
-
-        # Binary Encoding for 'required_car_parking_space'
-        'required_car_parking_space': 1.0 if required_car_parking_space == "Yes" else 0.0,
+model = load_model()
+
+# --- 3. PREDICTION LOGIC ---
+def predict_cancellation(inputs, loaded_model):
+    """Prepares data and gets the model's prediction."""
+    
+    # Map user inputs to the format the model expects
+    input_data = {
+        'lead_time': inputs['lead_time'],
+        'no_of_special_requests': inputs['no_of_special_requests'],
+        'avg_price_per_room': inputs['avg_price_per_room'],
+        'no_of_adults': inputs['no_of_adults'],
+        '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]
+    
+    return prediction
 
-    # 2. Convert dictionary to DataFrame with the correct EXPECTED_FEATURES order and dtypes
-    # Explicitly set the order of columns to match EXPECTED_FEATURES
-    input_df = pd.DataFrame([data_row], columns=EXPECTED_FEATURES)
-
-    # Ensure 'required_car_parking_space' is float64 as expected by the model
-    input_df['required_car_parking_space'] = input_df['required_car_parking_space'].astype('float64')
-
+# --- 4. STREAMLIT INTERFACE ---
 
-    # 3. Make Prediction
-    prediction = model.predict(input_df)[0]
-    # Probabilities are [Prob_Not_Canceled (0), Prob_Canceled (1)]
-    probabilities = model.predict_proba(input_df)[0]
-    prob_cancellation = probabilities[1]
-    prob_kept = probabilities[0]
+st.title("Hotel Booking Cancellation Predictor")
 
+if model is None:
+    st.stop()
 
-    return prediction, prob_cancellation, prob_kept
+st.markdown("Enter booking details to predict if the reservation will be cancelled.")
+st.markdown("---")
 
+# --- Input Fields (Single Column) ---
 
-# --- Streamlit UI ---
+# 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)
+avg_price_per_room = st.number_input("3. Average Price per Room ($)", min_value=0.0, value=101.0, format="%.2f")
+no_of_adults = st.number_input("4. Number of Adults", min_value=0, value=2, step=1)
+no_of_weekend_nights = st.number_input("5. Number of Weekend Nights", min_value=0, value=1, step=1)
+no_of_week_nights = st.number_input("6. Number of Week Nights", min_value=0, value=2, step=1)
+no_of_special_requests = st.number_input("7. Number of Special Requests", min_value=0, value=0, step=1)
 
-st.set_page_config(
-    page_title="Hotel Cancellation Predictor",
-    layout="centered",
-    initial_sidebar_state="expanded"
-)
+# Simple select boxes for categorical data
+market_segment_type = st.selectbox("8. Market Segment Type", ["Online", "Offline"])
+required_car_parking_space = st.selectbox("9. Required Car Parking Space", ["Yes", "No"])
 
-st.title("🛎️ INN Hotels: Booking Cancellation Predictor")
-st.markdown("Use the controls below to input booking details and predict the cancellation risk.")
 
-if cancellation_predictor is None:
-    st.warning("Application stopped due to critical error in model loading.")
-    st.stop()
-
-# --- Input Fields (arranged for better dashboard look) ---
-
-col1, col2 = st.columns(2)
-
-with col1:
-    lead_time = st.slider("1. Lead Time (Days before arrival)",
-                          min_value=FEATURE_RANGES['lead_time']['min'],
-                          max_value=FEATURE_RANGES['lead_time']['max'],
-                          value=FEATURE_RANGES['lead_time']['default'])
-    no_of_adults = st.number_input("4. Number of Adults",
-                                   min_value=FEATURE_RANGES['no_of_adults']['min'],
-                                   max_value=FEATURE_RANGES['no_of_adults']['max'],
-                                   value=FEATURE_RANGES['no_of_adults']['default'],
-                                   step=1)
-    no_of_week_nights = st.slider("6. Number of Week Nights",
-                                  min_value=FEATURE_RANGES['no_of_week_nights']['min'],
-                                  max_value=FEATURE_RANGES['no_of_week_nights']['max'],
-                                  value=FEATURE_RANGES['no_of_week_nights']['default'])
-    arrival_month = st.selectbox("8. Arrival Month (1=Jan to 12=Dec)",
-                                 list(range(FEATURE_RANGES['arrival_month']['min'], FEATURE_RANGES['arrival_month']['max'] + 1)),
-                                 index=FEATURE_RANGES['arrival_month']['default'] - 1) # Adjust index for 0-based list
-
-
-with col2:
-    market_segment_type = st.selectbox("2. Market Segment Type", ["Online", "Offline"], index=0)
-    avg_price_per_room = st.number_input("3. Average Price per Room ($)",
-                                         min_value=FEATURE_RANGES['avg_price_per_room']['min'],
-                                         max_value=FEATURE_RANGES['avg_price_per_room']['max'],
-                                         value=FEATURE_RANGES['avg_price_per_room']['default'],
-                                         format="%.2f")
-    no_of_weekend_nights = st.slider("5. Number of Weekend Nights",
-                                     min_value=FEATURE_RANGES['no_of_weekend_nights']['min'],
-                                     max_value=FEATURE_RANGES['no_of_weekend_nights']['max'],
-                                     value=FEATURE_RANGES['no_of_weekend_nights']['default'])
-    no_of_special_requests = st.number_input("7. Number of Special Requests",
-                                             min_value=FEATURE_RANGES['no_of_special_requests']['min'],
-                                             max_value=FEATURE_RANGES['no_of_special_requests']['max'],
-                                             value=FEATURE_RANGES['no_of_special_requests']['default'],
-                                             step=1)
-    required_car_parking_space = st.selectbox("9. Required Car Parking Space", ["Yes", "No"], index=1)
-
-
-# --- Prediction Button ---
-
-st.markdown("---") # Add a separator
-
-if st.button("PREDICT CANCELLATION RISK", type="primary"):
-
-    # Simple progress indicator for UX
-    with st.spinner('Analyzing booking data...'):
-        time.sleep(0.5)
-
-        prediction, prob_cancellation, prob_kept = run_prediction(
-            lead_time, market_segment_type, avg_price_per_room, no_of_adults,
-            no_of_weekend_nights, no_of_week_nights, no_of_special_requests,
-            arrival_month, required_car_parking_space, cancellation_predictor
-        )
+# --- 5. PREDICTION BUTTON AND OUTPUT ---
 
+if st.button("Get Prediction Result", type="primary"):
+    
+    # Dictionary to pass inputs easily
+    user_inputs = {
+        'lead_time': lead_time,
+        'market_segment_type': market_segment_type,
+        'avg_price_per_room': avg_price_per_room,
+        'no_of_adults': no_of_adults,
+        'no_of_weekend_nights': no_of_weekend_nights,
+        'no_of_week_nights': no_of_week_nights,
+        'no_of_special_requests': no_of_special_requests,
+        'arrival_month': arrival_month,
+        'required_car_parking_space': required_car_parking_space,
+    }
 
+    prediction = predict_cancellation(user_inputs, model)
+    
     st.markdown("---")
     st.subheader("Prediction Result")
-
+    
     if prediction == 1:
-        st.error(f"**High Risk of Cancellation:** The model predicts the booking will be **CANCELLED**.")
+        st.error("The model predicts the booking will be **CANCELLED**.")
     else:
-        st.success(f"**Low Risk:** The model predicts the booking will be **KEPT**.")
-
-    st.markdown(f"**Likelihood of Cancellation: {prob_cancellation*100:.2f}%**")
-    st.markdown(f"Likelihood of Keeping Booking: {prob_kept*100:.2f}%")
-
-    if prediction == 1 and prob_cancellation > 0.70:
-        st.info("💡 **Actionable Insight:** Consider proactively contacting this guest or flagging the room for immediate re-marketing.")
+        st.success("The model predicts the booking will be **Not Cancelled**.")