This 430-page book contains an excellent collection of information on the subject of practical algorithms used in data science. The authors present the algorithms in the context of applications. The discussion of each algorithm starts with some basic concepts, followed by a tutorial with real datasets and detailed code examples in Python or R. Each chapter has a set of exercise problems so readers can practice the concepts learned in the chapter.

After a brief introduction to the book and the subject, the 12 remaining chapters are divided into three parts, each of which concentrates on a category of data science tasks. The subjects of discussion in these three parts are data reduction, extracting information from data, and predictive analysis. Each and every chapter follows a similar pattern of presentation: a discussion of the topic, followed by a number of tutorials with working code examples to guide readers through how in practice these algorithms can be used. The examples used in the book cover a wide range of topics with real datasets, including politics, healthcare, Medicare, government, finance, and text analysis.

The two most striking features of the book are the clarity of writing and extensive, accessible real datasets and related code examples. The authors carefully created many real-life-based tutorials to make the learning exciting and real. Readers will find that the book is easy to understand, and the examples are excellent starting points for any real data analysis tasks.

This book can be a good reference for practitioners, or a good textbook for graduate or upper-class undergraduate students. The book does not assume a heavy-duty computing background, or extensive knowledge in statistics or mathematics. I wish the authors had provided a repository for the code examples in the book, so readers wouldn’t have to type in everything. However, if this is used as a textbook, maybe it’s not a good idea to supply the actual code.