app.py

from flask import Flask, request, jsonify
import joblib
import numpy as np

# Initialize the Flask app
app = Flask(__name__)

# Load the trained model
model = joblib.load('random_forest_model.pkl')

@app.route('/')
def home():
    return "Welcome to the Customer Churn Prediction API!"

# Define the prediction endpoint
@app.route('/predict', methods=['POST'])
def predict():
    try:
        # Get the JSON data from the request
        data = request.get_json()

        # Extract features from the input JSON
        features = [
            data.get("gender"),
            data.get("SeniorCitizen"),
            data.get("Partner"),
            data.get("Dependents"),
            data.get("tenure"),
            data.get("PhoneService"),
            data.get("MultipleLines"),
            data.get("InternetService"),
            data.get("OnlineSecurity"),
            data.get("OnlineBackup"),
            data.get("DeviceProtection"),
            data.get("TechSupport"),
            data.get("StreamingTV"),
            data.get("StreamingMovies"),
            data.get("Contract"),
            data.get("PaperlessBilling"),
            data.get("PaymentMethod"),
            data.get("MonthlyCharges"),
            data.get("TotalCharges")
        ]

        # Convert the features to a NumPy array for the model
        features_array = np.array([features])

        # Perform prediction
        prediction = model.predict(features_array)
        prediction_probability = model.predict_proba(features_array)

        # Map prediction result to a human-readable label
        churn_label = "Yes" if prediction[0] == 1 else "No"
        response = {
            "prediction": churn_label,
            "probability": {
                "No": prediction_probability[0][0],
                "Yes": prediction_probability[0][1]
            }
        }

        return jsonify(response)

    except Exception as e:
        return jsonify({"error": str(e)})

# Run the app
if __name__ == '__main__':
    app.run(debug=True)