I am cleaning data for the class Getting and Cleaning Data offered by Johns Hopkins University on Coursera.org
I download data taken by Samsung phones during various activities, and I manipulate it with the run_anaysis.R script, extracting a "clean" dataset that summarizes the mean value of feature variables for each combination of subject and exercise. I have a good amount of comments in the script to explain how the script works. It's better to see it there than here, in my opinion!
The CodeBook.md explains what the variables measure, their units etc., and why I chose to keep the variable names of the researchers.