Hands-On Machine Learning with R (Chapman & Hall/CRC The R Series)

**Note that I bought this in mid 2022 and had zero issues with the color or print quality. I'm reading this book as an overview of classic ML up through deep learning so that I can dive in further in certain areas. I've been implementing selected chapters in a language other than R and it has been a joy. Having read hundreds of technical books the last 20 years, this one has very clear explanations and example code. The pluses/minuses and interpretation take-home points in each section are gold.

This is a great book to consolidate knowledge or serve as the base for further learning. Each method is explained, along with the theoretical underpinnings and then practical examples of real code. Scattered throughout are helpful practical tips.

Brad and Brandon are excellent instructors and have practical experience working in industry (this can be a rare combo). Their students and colleagues consistently give them high marks on their teaching style and the content they present. This book gives readers the same experience. It's approachable and practical, and curates several important methods and R packages into one place. Recent stats grads or analysts looking to strengthen their machine learning skills would learn a lot here. I particularly like: Chapter 13: Deep Learning Chapter 15: Stacked Models Chapter 16: Interpretable Machine Learning (my favorite chapter) Chapter 19: Autoencoders And as a comment on another review, the print quality has been fixed. All images and figures are in color.

This book takes you through the basics of supervised and unsupervised machine learning, using state-of-the-art libraries available in R. Readable, approachable, and thorough. Highly recommended.

The binding isn’t even attached! The first couple of pages are already ripped away from the binding at the seam, and I have opened the book once. For almost $70, I would expect the cover to at least be attached! Inexcusably poor quality.

This book includes many applied examples of common real-world ML approaches implemented with popular R packages, sometimes w/ base R equivalents when available and/or appropriate. Examples are all performed using small/medium size datasets and feasible with a decent-quality personal computer. The Rmarkdown notebooks for all examples and the datasets are available via GitHub, and a free, web-only version of the text is also available. CONTENT: 4.5/5 stars. I like having a physical copy as opposed to the free online version, but the print version of this book is WAY overpriced given the production quality. I speak as a former print professional, and I know what I'm talking about here. The print version is produced entirely in black & white/greyscale. The authors/publishers made no adjustments to the color graphics of the online version, which makes plots often COMPLETELY UNREADABLE. No TRUE code highlighting either, which wouldn't be a big deal except that the authors/publishers again simply rendered the color code blocks from the online version in greyscale, yielding low-contrast code blocks that are difficult to read in less-than-bright light (and may be unreadable to some with vision impairment). It is "hardcover" is the sense that the cover is indeed heavyweight cardboard. However, it is perfect-bound, w/ glued-in single pages just like a paperback, NOT case-bound with saddle-sewn signatures like I would expect from a $90 "hardback" product. So it's basically a b&w paperback w/ a heavy cover glued on (& decent paper, I'll give them that) for $90. Compare to Wickham's Advanced R color paperback @ $35 FROM THE SAME PUBLISHER. Physical product quality: 1/5 stars given the price. Overall, 3/5 stars, a weighted average of 4.5 for content, 1 for the production quality at this price point. If you like physical copies to reference like me, I would STRONGLY suggest waiting for an edition in color & working through the free online version or choosing an alternative text. The ebook may be acceptable, I don't know. If there is a future edition or print run, the authors & publishers should consider recoloring plots for readability in greyscale & rendering code blocks as solid black text against a solid white background. Or simply producing a color, print-on-demand paperback at a reasonable price point like they did with Wickham's Advanced R. The print version as-is is a rip-off.

Hv been into machine learning and was a WEKA user for long time. This excellent book has really tuned me to jump start in to R for machine learning. I wish it had few chapters about text data. Otherwise, I really loved it!

The book is written with recent R packages and costumes in coding. Great overview with examples to do analysis on your own data set with the tools mentioned. It's available online but I like to just read the book to get the overview. Paper is easier on the eye. Then when I need the code I can refer to its online version instead of typing it.

This is a fantastic desktop reference that contains all commonly used models and goes into a good level of detail about each one and how to apply them in R.

Excellent book.

It was delivered as advertised.