Machine Learning in R: Start with an End-to-End Test

As a data scientist, you will likely be asked one day to automate your analysis and port your models to production environments. When that happens you cross the blurry line between data science and software engineering, and become a machine learning engineer. I'd like to share a few tips on how to make that transition as successful as possible. Let's first discuss testing, and let's assume without loss of generality that you develop your machine learning application in R. Just like any other software system, your application needs to be thoroughly tested before being deployed. But how do you ensure that your application will perform as expected when dealing with real data?