Since we first announced there have been lots of discussions about the right way to have this meetup. Eventually after thinking about DataFest it was decided that we should do a 2-part meetup.
Part 1 consists of a workshop where we will interactively go through a dataset and figure some stuff out about it and build some basic classifiers.
Part 2 will occur one week later (May 14th) where you folks all come back and we see who has built the best classifier in a sort of show-and-tell complete with leaderboard.
Because Part 1 has an interactive software side, and I don't think I can handle a workshop with more than 30 to 35 people, there is a qualifying round to attend. You have to get R and scikit-learn installed on your computer.
How will I know you did this?
I have uploaded a subset of the data we will be exploring and two scripts that process in at https://www.dropbox.com/s/gf2qrh1md2wwhfi/hack_night.zip . These scripts each spit out a number, you must give me the sum of these numbers when you RSVP as it will be one of the questions I ask. I will periodically cancel your RSVP if the correct answer isn't present.
Note you will not need to do anything other than run these two scripts. There is no coding required.
