import streamlit as st
import pandas as pd
import numpy as np
from tensorflow.keras.models import load_model
from sklearn.preprocessing import StandardScaler

# Load the trained model
model = load_model('best_dnn_model')

# Load the scaler
scaler = StandardScaler()

# Define function to preprocess input data
def preprocess_data(data):
    data = np.array(data).reshape(1, -1)
    data = scaler.transform(data)
    return data

# Streamlit app
st.title('Bank Churn: DNN Model Deployment')

# Collect user input
user_input = st.text_area("Enter your input data (comma-separated)")

# Process the input and make prediction
if st.button('Predict'):
    try:
        data = [float(i) for i in user_input.split(',')]
        data = preprocess_data(data)
        prediction = model.predict(data)
        st.write(f"Prediction: {prediction}")
    except Exception as e:
        st.write(f"Error: {e}")