yuji0710/mlops-telco-churn ? reverse-engineered prompt

Build me a simple machine learning project for telco customer churn prediction.

I want the app to take customer data, train a model to predict whether someone is likely to leave, and save the trained model so it can be reused later. Please set it up so I can run the whole thing locally with a clean workflow, including data prep, training, evaluation, and a way to make predictions from an API.

It would be great if the project also has a basic MLOps style setup, with scripts or pipelines for running the steps in order, plus Docker support so I can run it easily. If it makes sense, add simple monitoring or metrics so I can keep an eye on the service after it is running. Use current best practices and look up anything you need online if the details are missing.

Keep it practical and easy to understand, since I want something I can run and test without a lot of setup.