This is the difference in temperatures for North American weather stations over the periods of their observations. This is from the NOAH Global Summary of the Day, and it is used in chapter2, on GIS analysis.

This is the cleaned-up UFO dataset from Infochimps with textual descriptions of the objects. This is used in chapter 4, on classifying UFO descriptions.

This is the random sample of data from the StackOverflow data dump. This is used in chapter 9, on social network data.