I've got a series of blog posts going as a "gentle introduction" to Cascading, over at "Cascading for the Impatient". This includes sample code in a GitHub repo, and progresses from a distributed file copy, to yet-another Word Count, to a full TF-IDF implementation in MapReduce, complete with TDD features.

Related to this, see also some recent content:

I will also be speaking at some upcoming conferences, all listed on my Lanyrd profile:
  • Splunk conference in Las Vegas, 9/13
  • Cloud Con Expo in SF, 10/3
  • ACM Data Mining, 10/13
  • SpringOne in DC, 10/17
  • DC Data Science, 10/17
...and for more info about Cascading, please join us at the new Cascading Meetup group.