Practical Automated Machine Learning Using H2O.ai: Discover the power of automated machine learning, from experimentation through to deployment to production

Description

Accelerate the adoption of machine learning by automating away the complex parts of the ML pipeline using H2O.ai Key FeaturesLearn how to train the best models with a single click using H2O AutoMLGet a simple explanation of model performance using H2O ExplainabilityEasily deploy your trained models to production using H2O MOJO and POJOBook Description With the huge amount of data being generated over the internet and the benefits that Machine Learning (ML) predictions bring to businesses, ML implementation has become a low-hanging fruit that everyone is striving for. The complex mathematics behind it, however, can be discouraging for a lot of users. This is where H2O comes in – it automates various repetitive steps, and this encapsulation helps developers focus on results rather than handling complexities. You'll begin by understanding how H2O's AutoML simplifies the implementation of ML by providing a simple, easy-to-use interface to train and use ML models. Next, you'll see how AutoML automates the entire process of training multiple models, optimizing their hyperparameters, as well as explaining their performance. As you advance, you'll find out how to leverage a Plain Old Java Object (POJO) and Model Object, Optimized (MOJO) to deploy your models to production. Throughout this book, you'll take a hands-on approach to implementation using H2O that'll enable you to set up your ML systems in no time. By the end of this H2O book, you'll be able to train and use your ML models using H2O AutoML, right from experimentation all the way to production without a single need to understand complex statistics or data science. What you will learnGet to grips with H2O AutoML and learn how to use itExplore the H2O Flow Web UIUnderstand how H2O AutoML trains the best models and automates hyperparameter optimizationFind out how H2O Explainability helps understand model performanceExplore H2O integration with scikit-learn, the Spring Framework, and Apache StormDiscover how to use H2O with Spark using H2O Sparkling WaterWho this book is for This book is for engineers and data scientists who want to quickly adopt machine learning into their products without worrying about the internal intricacies of training ML models. If you're someone who wants to incorporate machine learning into your software system but don't know where to start or don't have much expertise in the domain of ML, then you'll find this book useful. Basic knowledge of statistics and programming is beneficial. Some understanding of ML and Python will be helpful. Table of ContentsUnderstanding H2O AutoML BasicsWorking with H2O Flow (H2O's Web UI)Understanding Data ProcessingUnderstanding H2O AutoML Training and Architecture Understanding AutoML AlgorithmsUnderstanding H2O AutoML Leaderboard and Other Performance MetricsWorking with Model ExplainabilityExploring Optional Parameters for H2O AutoMLExploring Miscellaneous Features in H2O AutoMLWorking with Plain Old Java Objects (POJOs)Working with Model Object, Optimized (MOJO)Working with H2O AutoML and Apache SparkUsing H2O AutoML with Other Technologies Cover Title Page Copyright and Credits Contributors Table of Contents Preface Part 1: H2O AutoML Basics Chapter 1: Understanding H2O AutoML Basics Technical requirements Understanding AutoML and H2O AutoML AutoML H2O AutoML Minimum system requirements to use H2O AutoML Installing Java Basic implementation of H2O using Python Installing Python Installing H2O using Python Basic implementation of H2O using R Installing R Installing H2O using R Training your first ML model using H2O AutoML Understanding the Iris flower dataset Model training Summary Chapter 2: Working with H2O Flow(H2O’s Web UI) Technical requirements Understanding the basics of H2O Flow Downloading and launching H2O Flow Exploring H2O Flow Working with data functions in H2O Flow Importing the dataset Parsing the dataset Observing the dataframe Splitting a dataframe Working with model training functions in H2O Flow Understanding the AutoML parameters in H2O Flow Training and understanding models using AutoML in H2O Flow Working with prediction functions in H2O Flow Making predictions using H2O Flow Understanding the prediction results Summary  Part 2: H2O AutoMLDeep Dive Chapter 3: Understanding Data Processing Technical requirements Reframing your dataframe Combining columns from two dataframes Combining rows from two dataframes Merging two dataframes Handling missing values in the dataframe Filling NA values Replacing values in a frame Imputation Manipulating feature columns of the dataframe Sorting columns Changing column types Tokenization of textual data Encoding data using target encoding Summary Chapter 4: Understanding H2O AutoML Architecture and Training Observing the high-level architecture of H2O Observing the client layer Observing the JVM component layer Learning about the flow of interaction between the client and the H2O service Learning about H2O client-server interactions during the ingestion of data Knowing the sequence of interactions in H2O during model training Understanding how H2O AutoML performs hyperparameter optimization and training Understanding hyperparameters Understanding hyperparameter optimization Summary Chapter 5: Understanding AutoML Algorithms Understanding the different types of ML algorithms Understanding the Generalized Linear Model algorithm Introduction to linear regression Understanding the assumptions of linear regression Working with a Generalized Linear Model Understanding the Distributed Random Forest algorithm Introduction to decision trees Introduction to Random Forest Understanding Extremely Randomized Trees Understanding the Gradient Boosting Machine algorithm Building a Gradient Boosting Machine Understanding what is Deep Learning Understanding neural networks Summary Chapter 6: Understanding H2O AutoML Leaderboard and Other Performance Metrics Exploring the H2O AutoML leaderboard performance metrics Understanding the mean squared error and the root mean squared error Working with the confusion matrix Calculating the receiver operating characteristic and its area under the curve (ROC-AUC) Calculating the precision-recall curve and its area under the curve (AUC-PR) Working with log loss Exploring other model performance metrics Understanding the F1 score performance metric Calculating the absolute Matthews correlation coefficient Measuring the R2 performance metric Summary Chapter 7: Working with Model Explainability Technical requirements Working with the model explainability interface Implementing the model explainability interface in Python Implementing the model explainability interface in R Exploring the various explainability features Understanding residual analysis Understanding variable importance Understanding feature importance heatmaps Understanding model correlation heatmaps Understanding partial dependency plots Understanding SHAP summary plots Understanding individual conditional expectation plots Understanding learning curve plots Summary Part 3: H2O AutoML Advanced Implementation and Productization Chapter 8: Exploring Optional Parameters for H2O AutoML Technical requirements Experimenting with parameters that support imbalanced classes Understanding undersampling the majority class Understanding oversampling the minority class Working with class balancing parameters in H2O AutoML Experimenting with parameters that support early stopping Understanding early stopping Working with early stopping parameters in H2O AutoML Experimenting with parameters that support cross-validation Understanding cross-validation Working with cross-validation parameters in H2O AutoML Summary Chapter 9: Exploring Miscellaneous Features in H2O AutoML Technical requirements Understanding H2O AutoML integration in scikit-learn Building and installing scikit-learn Experimenting with scikit-learn Using H2O AutoML in scikit-learn Understanding H2O AutoML event logging Summary Chapter 10: Working with Plain Old Java Objects (POJOs) Technical requirements Introduction to POJOs Extracting H2O models as POJOs Downloading H2O models as POJOs in Python Downloading H2O models as POJOs in R Downloading H2O models as POJOs in H2O Flow Using a H2O model as a POJO Summary Chapter 11: Working with Model Object, Optimized (MOJO) Technical requirements Understanding what a MOJO is Extracting H2O models as MOJOs Extracting H2O models as MOJOs in Python Extracting H2O models as MOJOs in R Extracting H2O models as MOJOs in H2O Flow Viewing model MOJOs Using H2O AutoML model MOJOs to make predictions Summary Chapter 12: Working with H2O AutoML and Apache Spark Technical requirements Exploring Apache Spark Understanding the components of Apache Spark Understanding the Apache Spark architecture Understanding what a Resilient Distributed Dataset is Exploring H2O Sparkling Water Downloading and installing H2O Sparkling Water Implementing Spark and H2O AutoML using H2O Sparkling Water Summary Chapter 13: Using H2O AutoML with Other Technologies Technical requirements Using H2O AutoML and Spring Boot Understanding the problem statement Designing the architecture Working on the implementation Using H2O AutoML and Apache Storm What is Apache Storm? Understanding the problem statement Designing the architecture Working on the implementation Summary Index Other Books You May Enjoy