Summary: Data Analysis with Open Source Tools is a reference book that explains in detail the many ways to make sense of data. You will find ways to interpret data using statistics, plots, and mathematics. It also covers traditional data mining (simulation, clustering) and fun topics on modeling for making estimates.
You should get this book if your education was below average in statistics and math, or if it was average and you forgot about it already. It is quite good to refresh your memory and to learn interesting stuff that is good to know in case you need it. For example, the time value of money is clearly explained. The author goes in length to warn you of common mistakes in processing data. Every graduate student in a science major should know about the topics covered in this book. That is, read about it once, you will know what it is when someone mentions it (such as k-means), and if needed, go back again to the book for details or pointers for further information.
Once you reach 80% of the book, there are two big appendixes left: one is a refresher on math, the other on additional details on working on data. Throughout, the book has workshops/exercises, but unless you are familiar with Phyton, you might as well skip them (not too big of a loss).
Disclaimer: I was provided a electronic-copy of the book from O’Reilly for review.