Summary
In this chapter, we understood the various steps in an ML pipeline and how AutoML plays a part in automating some of those steps. Then, we prepared our system to use H2O AutoML by installing the basic requirements. Once our system was ready, we implemented a simple application in Python and R that uses H2O AutoML to train a model on the Iris flower dataset. Finally, we understood the Leaderboard results and made successful predictions on the ML model that we just trained. All of this helped us test the waters of H2O AutoML, thus opening doors to more advanced concepts of H2O AutoML.
In the next chapter, we will explore H2O’s web User Interface (UI) so that we can understand and observe various ML details using an interactive visual interface.
