Luis Torgo

I got this book as text for a class I took on Data Mining with R. Do NOT get into this book without a solid preexisting background in R programming. The book is organized along specific case studies and reviews now well-known data mining techniques (kNN, naive Bayes, random trees, random forests, etc.). The author uses quite a few very specialized R packages and customized functions that beginners will have a hard time following. In addition, the book was published in 2010 and some of the packages and data have been updated since, so, one might not reproduced exactly the same results as those in the book. Fortunately, there is a website to go along with the book, with data sets and R scripts. That way, one can examine the functions at greater length to figure out what they do.

The book itself is not hard to read and the author does a pretty good job of explaining why he is using this or that function. But again, the level of R programming is high (in my estimation) and it seems the author, again, went for highly specialized packages and functions rather than more generic ones (for instance, those used in the MIT MOOC The Analytics Edge.… (meer)