import gradio as gr import pandas as pd import joblib import numpy as np # 1. Load the model model = joblib.load('model.pkl') # 2. Define the prediction function def predict_churn(age, tenure, balance, salary): # Prepare the input in the same format as your training data X input_data = np.array([[age, tenure, balance, salary]]) # Get prediction prediction = model.predict(input_data) # Return human-readable result return "Likely to EXIT" if prediction[0] == 1 else "Likely to STAY" # 3. Create the Gradio Interface demo = gr.Interface( fn=predict_churn, inputs=[ gr.Number(label="Age (Years)"), gr.Slider(0, 10, step=1, label="Tenure (Years)"), gr.Number(label="Account Balance"), gr.Number(label="Estimated Annual Salary") ], outputs="text", title="Customer Churn Predictor", description="This model uses a Decision Tree (Optimized) to predict customer retention." ) # 4. Launch if __name__ == "__main__": demo.launch()