app.py

import streamlit as st
import pandas as pd
from huggingface_hub import hf_hub_download
import joblib

# Download the model from the Model Hub
model_path = hf_hub_download(repo_id="msubburao/Tourism-Package-model", filename="best_tourism_model_v1.joblib")

# Load the model
model = joblib.load(model_path)

# Streamlit UI for Tourism Package Prediction
st.title("Tourism Package Prediction App")
st.write("The Tourism Package Prediction App is an tool that predicts whether a customer will purchase the newly introduced Tourism Package")
st.write("Kindly enter the customer details to check whether they are likely to purchase the package.")

# Collect user input
Age = st.number_input("Age", min_value=18, max_value=100, value=30)
Gender = st.selectbox("Gender", ["Male", "Female"])
TypeofContact = st.selectbox("Type of Contact",["Company Invited", "Self Inquiry"])
CityTier = st.selectbox("City Tier", [1, 2, 3])
Occupation = st.selectbox("Occupation",["Salaried", "Freelancer", "Small Business", "Large Business"])
NoOfPersonVisiting = st.number_input("Number of Persons Visiting",min_value=1, max_value=10, value=2)
PreferredPropertyStar = st.selectbox("Preferred Property Star",[1, 2, 3, 4, 5])
MaritalStatus = st.selectbox("Marital Status",["Single", "Married", "Divorced"])
NoOfTrips = st.number_input("Number of Trips (per year)",min_value=0, max_value=50, value=2)
Passport = st.selectbox("Has Passport?", ["Yes", "No"])
OwnCar = st.selectbox("Owns a Car?", ["Yes", "No"])
NoOfChildrenVisiting = st.number_input("Number of Children Visiting",min_value=0, max_value=5, value=0)
Designation = st.selectbox("Designation",["Executive", "Manager", "Senior Manager", "VP"])
MonthlyIncome = st.number_input("Monthly Income",min_value=5000, max_value=500000, value=50000)

PitchSatisfactionScore = st.slider("Pitch Satisfaction Score",min_value=1, max_value=5, value=3)
ProductPitched = st.selectbox("Product Pitched",["Basic", "Standard", "Deluxe", "Super Deluxe"])
NoOfFollowups = st.number_input("Number of Follow-ups",min_value=0, max_value=20, value=2)
DurationOfPitch = st.number_input("Duration of Pitch (minutes)",min_value=1, max_value=120, value=15)

# Convert categorical inputs to match model training
input_data = pd.DataFrame([{
    "Age": Age,
    "TypeofContact": TypeofContact,
    "CityTier": CityTier,
    "Occupation": Occupation,
    "Gender": Gender,
    "NumberOfPersonVisiting": NoOfPersonVisiting,
    "PreferredPropertyStar": PreferredPropertyStar,
    "MaritalStatus": MaritalStatus,
    "NumberOfTrips": NoOfTrips,
    "Passport": 1 if Passport == "Yes" else 0,
    "OwnCar": 1 if OwnCar == "Yes" else 0,
    "NumberOfChildrenVisiting": NoOfChildrenVisiting,
    "Designation": Designation,
    "MonthlyIncome": MonthlyIncome,
    "PitchSatisfactionScore": PitchSatisfactionScore,
    "ProductPitched": ProductPitched,
    "NumberOfFollowups": NoOfFollowups,
    "DurationOfPitch": DurationOfPitch
}])

# Set the classification threshold
classification_threshold = 0.5

# Predict button
if st.button("Predict"):
    prediction_proba = model.predict_proba(input_data)[0, 1]
    prediction = (prediction_proba >= classification_threshold).astype(int)

    if prediction == 1:
        st.success("The customer is likely to purchase the package.")
    else:
        st.error("The customer is unlikely to purchase the package.")