A Good R Book, from Bruno Ombreux
I am reading Data Analysis and Graphics Using R by John Maindonald and John Braun, and really liking it so far. There are almost no mathematical formulas, but there is a lot of illustrative R code, so it is perfect for those that don't like the hermetism of some stat books, but can write a computer program. It is also written by two authors who are obviously practitioners of statistics, as opposed to theoreticians, which makes it very practical.
Denis Vako remarks:
The most practical one gets in programming is when one has source code and a debugger; these two make magic in terms of knowledge discovered, which feels better than a good book. The downside — you see what and how, but sometimes cannot figure out why. I also think statistical software help files are a treasure, e.g. those of NCSS.