Upload folder using huggingface_hub

Dockerfile

@@ -1,20 +1,26 @@
-FROM python:3.13.5-slim
+# Use a minimal base image with Python 3.9 installed
+FROM python:3.9
 
+# Set the working directory inside the container to /app
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    git \
-    && rm -rf /var/lib/apt/lists/*
-
-COPY requirements.txt ./
-COPY src/ ./src/
+# Copy all files from the current directory on the host to the container's /app directory
+COPY . .
 
+# Install Python dependencies listed in requirements.txt
 RUN pip3 install -r requirements.txt
 
-EXPOSE 8501
+# Create a non-root user for security
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+# Copy files with proper ownership
+COPY --chown=user . $HOME/app
 
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
+# Define the command to run the Streamlit app on port "8501" and make it accessible externally
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]
 
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]

app.py

@@ -0,0 +1,215 @@
+"""
+Streamlit App for Wellness Tourism Package Prediction
+This application allows users to input customer data and predict
+whether they will purchase the Wellness Tourism Package.
+"""
+
+import streamlit as st
+import pandas as pd
+from huggingface_hub import hf_hub_download
+import joblib
+
+# TODO: Replace with your Hugging Face username
+HF_USERNAME = "BaskaranAIExpert"  # Change this!
+
+# Page configuration
+st.set_page_config(
+    page_title="Wellness Tourism Package Prediction",
+    page_icon="✈️",
+    layout="wide"
+)
+
+# Download and load the model
+@st.cache_resource
+def load_model():
+    """Load the trained model from Hugging Face Hub"""
+    try:
+        model_path = hf_hub_download(
+            repo_id=f"{HF_USERNAME}/wellness-tourism-model",
+            filename="wellness_tourism_model_v1.joblib"
+        )
+        model = joblib.load(model_path)
+        return model
+    except Exception as e:
+        st.error(f"Error loading model: {str(e)}")
+        st.info("Please ensure the model is uploaded to Hugging Face Hub and the username is correct.")
+        return None
+
+# Load model
+model = load_model()
+
+# Streamlit UI
+st.title("✈️ Wellness Tourism Package Prediction App")
+st.markdown("""
+This application predicts whether a customer will purchase the **Wellness Tourism Package** 
+based on their profile and interaction data. Enter the customer information below to get a prediction.
+""")
+
+if model is None:
+    st.stop()
+
+# Create two columns for better layout
+col1, col2 = st.columns(2)
+
+with col1:
+    st.subheader("📋 Customer Details")
+    
+    age = st.number_input("Age", min_value=18, max_value=100, value=35, step=1)
+    gender = st.selectbox("Gender", ["Male", "Female"])
+    marital_status = st.selectbox("Marital Status", ["Single", "Married", "Divorced"])
+    occupation = st.selectbox("Occupation", [
+        "Salaried", "Freelancer", "Small Business", "Large Business", "Other"
+    ])
+    designation = st.selectbox("Designation", [
+        "Executive", "Manager", "Senior Manager", "AVP", "VP", "Other"
+    ])
+    monthly_income = st.number_input(
+        "Monthly Income (₹)", 
+        min_value=0, 
+        max_value=1000000, 
+        value=50000, 
+        step=1000
+    )
+    
+    city_tier = st.selectbox("City Tier", ["Tier 1", "Tier 2", "Tier 3"])
+    number_of_trips = st.number_input(
+        "Number of Trips (Annual Average)", 
+        min_value=0, 
+        max_value=20, 
+        value=2, 
+        step=1
+    )
+    passport = st.selectbox("Has Passport", [0, 1], format_func=lambda x: "Yes" if x == 1 else "No")
+    own_car = st.selectbox("Owns Car", [0, 1], format_func=lambda x: "Yes" if x == 1 else "No")
+
+with col2:
+    st.subheader("👨‍👩‍👧‍👦 Travel Details")
+    
+    number_of_persons = st.number_input(
+        "Number of Persons Visiting", 
+        min_value=1, 
+        max_value=10, 
+        value=2, 
+        step=1
+    )
+    number_of_children = st.number_input(
+        "Number of Children Visiting (Below 5 years)", 
+        min_value=0, 
+        max_value=5, 
+        value=0, 
+        step=1
+    )
+    preferred_property_star = st.selectbox(
+        "Preferred Property Star Rating", 
+        [3, 4, 5], 
+        index=1
+    )
+    
+    st.subheader("📞 Interaction Details")
+    
+    type_of_contact = st.selectbox(
+        "Type of Contact", 
+        ["Company Invited", "Self Inquiry"]
+    )
+    product_pitched = st.selectbox(
+        "Product Pitched", 
+        ["Basic", "Standard", "Deluxe", "Super Deluxe", "King"]
+    )
+    pitch_satisfaction_score = st.slider(
+        "Pitch Satisfaction Score", 
+        min_value=1, 
+        max_value=5, 
+        value=3, 
+        step=1
+    )
+    number_of_followups = st.number_input(
+        "Number of Follow-ups", 
+        min_value=0, 
+        max_value=10, 
+        value=2, 
+        step=1
+    )
+    duration_of_pitch = st.number_input(
+        "Duration of Pitch (minutes)", 
+        min_value=0.0, 
+        max_value=60.0, 
+        value=10.0, 
+        step=0.5
+    )
+
+# Encode categorical variables (matching the preprocessing in prep.py)
+def encode_categorical(value, category_type):
+    """Encode categorical values to match training data encoding"""
+    encodings = {
+        'Gender': {'Male': 0, 'Female': 1},
+        'MaritalStatus': {'Single': 0, 'Married': 1, 'Divorced': 2},
+        'TypeofContact': {'Company Invited': 0, 'Self Inquiry': 1},
+        'CityTier': {'Tier 1': 0, 'Tier 2': 1, 'Tier 3': 2},
+        'Occupation': {
+            'Salaried': 0, 'Freelancer': 1, 'Small Business': 2, 
+            'Large Business': 3, 'Other': 4
+        },
+        'Designation': {
+            'Executive': 0, 'Manager': 1, 'Senior Manager': 2,
+            'AVP': 3, 'VP': 4, 'Other': 5
+        },
+        'ProductPitched': {
+            'Basic': 0, 'Standard': 1, 'Deluxe': 2,
+            'Super Deluxe': 3, 'King': 4
+        }
+    }
+    return encodings.get(category_type, {}).get(value, 0)
+
+# Assemble input into DataFrame
+if st.button("🔮 Predict Purchase Likelihood", type="primary"):
+    input_data = pd.DataFrame([{
+        'Age': age,
+        'TypeofContact': encode_categorical(type_of_contact, 'TypeofContact'),
+        'CityTier': encode_categorical(city_tier, 'CityTier'),
+        'Occupation': encode_categorical(occupation, 'Occupation'),
+        'Gender': encode_categorical(gender, 'Gender'),
+        'NumberOfPersonVisiting': number_of_persons,
+        'PreferredPropertyStar': preferred_property_star,
+        'MaritalStatus': encode_categorical(marital_status, 'MaritalStatus'),
+        'NumberOfTrips': number_of_trips,
+        'Passport': passport,
+        'OwnCar': own_car,
+        'NumberOfChildrenVisiting': number_of_children,
+        'Designation': encode_categorical(designation, 'Designation'),
+        'MonthlyIncome': monthly_income,
+        'PitchSatisfactionScore': pitch_satisfaction_score,
+        'ProductPitched': encode_categorical(product_pitched, 'ProductPitched'),
+        'NumberOfFollowups': number_of_followups,
+        'DurationOfPitch': duration_of_pitch
+    }])
+    
+    try:
+        prediction = model.predict(input_data)[0]
+        prediction_proba = model.predict_proba(input_data)[0]
+        
+        st.markdown("---")
+        st.subheader("📊 Prediction Result")
+        
+        if prediction == 1:
+            st.success(f"✅ **The customer is LIKELY to purchase the Wellness Tourism Package!**")
+            st.info(f"Confidence: {prediction_proba[1]*100:.2f}%")
+        else:
+            st.warning(f"❌ **The customer is NOT LIKELY to purchase the Wellness Tourism Package.**")
+            st.info(f"Confidence: {prediction_proba[0]*100:.2f}%")
+        
+        col_prob1, col_prob2 = st.columns(2)
+        with col_prob1:
+            st.metric("Probability of Purchase", f"{prediction_proba[1]*100:.2f}%")
+        with col_prob2:
+            st.metric("Probability of No Purchase", f"{prediction_proba[0]*100:.2f}%")
+            
+    except Exception as e:
+        st.error(f"Error making prediction: {str(e)}")
+
+st.markdown("---")
+st.markdown("""
+<div style='text-align: center; color: gray;'>
+    <p>Built with ❤️ for Visit with Us | MLOps Pipeline</p>
+</div>
+""", unsafe_allow_html=True)
+

requirements.txt

@@ -1,3 +1,7 @@
-altair
-pandas
-streamlit
+pandas==2.2.2
+huggingface_hub==0.32.6
+streamlit==1.43.2
+joblib==1.5.1
+scikit-learn==1.6.0
+xgboost==2.1.4
+