Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,28 @@
+# Use a Python base image with a stable version
+FROM python:3.9
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy dependency files first for better Docker caching
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the application logic and the serialized model file
+COPY app.py .
+# Ensure this file name matches the joblib dump file name
+COPY hotel_cancellation_prediction_model_v1_0.joblib .
+
+# Recommended security practice
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+WORKDIR $HOME/app
+COPY --chown=user . $HOME/app
+
+# Define the command to run the Streamlit app on port "7860" 
+# and explicitly disable XSRF protection (critical for Hugging Face Spaces file uploads)
+CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]

app.py

@@ -0,0 +1,133 @@
+import streamlit as st
+import joblib
+import pandas as pd
+import numpy as np
+import os
+import time
+
+# --- Constants and Configuration ---
+
+MODEL_FILE = 'hotel_cancellation_prediction_model_v1_0.joblib'
+
+# The exact list of features (columns) the model expects in this specific order
+EXPECTED_FEATURES = [
+    'lead_time', 
+    'no_of_special_requests', 
+    'avg_price_per_room', 
+    'no_of_adults', 
+    'no_of_weekend_nights', 
+    'no_of_week_nights', 
+    'arrival_month', 
+    'market_segment_type_Online',
+    'required_car_parking_space'
+]
+
+# --- Model Loading (Cached) ---
+
+@st.cache_resource
+def load_cancellation_model():
+    try:
+        model = joblib.load(MODEL_FILE)
+        return model
+    except Exception as e:
+        st.error(f"Error loading model: {e}")
+        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,
+    }
+
+    # 2. Convert dictionary to DataFrame with the correct EXPECTED_FEATURES order
+    input_df = pd.DataFrame([data_row], columns=EXPECTED_FEATURES)
+
+    # 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]
+
+    return prediction, prob_cancellation, prob_kept
+
+
+# --- Streamlit UI ---
+
+st.set_page_config(
+    page_title="Hotel Cancellation Predictor",
+    layout="centered",
+    initial_sidebar_state="expanded"
+)
+
+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 ---
+
+st.sidebar.header("Booking Parameters")
+
+with st.sidebar:
+    lead_time = st.number_input("1. Lead Time (Days before arrival)", min_value=0, max_value=730, value=50)
+    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=0.0, value=100.0, format="%.2f")
+    no_of_adults = st.number_input("4. Number of Adults", min_value=0, max_value=10, value=2)
+    no_of_weekend_nights = st.number_input("5. Number of Weekend Nights", min_value=0, max_value=7, value=1)
+    no_of_week_nights = st.number_input("6. Number of Week Nights", min_value=0, max_value=30, value=2)
+    no_of_special_requests = st.number_input("7. Number of Special Requests", min_value=0, max_value=5, value=0)
+    arrival_month = st.selectbox("8. Arrival Month (1=Jan to 12=Dec)", list(range(1, 13)), index=5)
+    required_car_parking_space = st.selectbox("9. Required Car Parking Space", ["Yes", "No"], index=1)
+
+# --- Prediction Button ---
+
+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
+        )
+    
+    st.markdown("---")
+    st.subheader("Prediction Result")
+    
+    if prediction == 1:
+        st.error(f"**High Risk of Cancellation:** 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.")

requirements.txt

@@ -0,0 +1,5 @@
+streamlit==1.49.1
+pandas==2.2.2
+numpy==1.26.4
+scikit-learn==1.6.1
+joblib==1.5.2