What this book covers
Chapter 1, Understanding H2O AutoML Basics, talks about an AutoML technology by H2O.ai named H2O AutoML and implements a basic setup of the technology to see it in action.
Chapter 2, Working with H2O Flow (H2O’s Web UI), explores H2O’s Web UI called H2O Flow and shows how we can set up our H2O AutoML system using the Web UI without writing a single line of code.
Chapter 3, Understanding Data Processing, explores some of the common data processing functionalities that we can perform using H2O’s in-built dataframe manipulation operations.
Chapter 4, Understanding H2O AutoML Training and Architecture, deep dives into understanding the high-level architecture of H2O technology and teaches us how H2O AutoML trains all the models and optimizes their hyperparameters.
Chapter 5, Understanding AutoML Algorithms, explores the various ML algorithms that H2O AutoML uses to train various models.
Chapter 6, Understanding H2O AutoML Leaderboard and Other Performance Metrics, explores the different performance metrics that are used in the AutoML Leaderboard as well as some additional metrics that are important for users to know.
Chapter 7, Working with Model Explainability, explores the H2O explainability interface and helps us to understand the various explainability features that we get as outputs.
Chapter 8, Exploring Optional Parameters for H2O AutoML, looks at some of the optional parameters that are available to us when configuring our AutoML training and shows how we can use them.
Chapter 9, Exploring Miscellaneous Features in H2O AutoML, explores two unique features of H2O AutoML. The first one is H2O AutoML’s compatibility with the scikit-learn library and the second one is H2O AutoML’s inbuilt logging system for debugging AutoML training issues.
Chapter 10, Working with Plain Old Java Objects (POJOs), covers model POJOs and how we can extract and use them to make predictions in production environments.
Chapter 11, Working with Model Object, Optimized (MOJO), covers model MOJOs, how they are different from model POJOs, how to view them, and how we can extract and use them to make predictions in production environments.
Chapter 12, Working with H2O AutoML and Apache Spark, explores in detail how H2O AutoML can be used along with Apache Spark using H2O Sparkling Water.
Chapter 13, Using H2O AutoML with Other Technologies, explores how we can use H2O models in collaboration with other commonly used technologies in the ML domain, such as Spring Boot Web applications and Apache Storm.