• Fizz Buzz in Tensorflow
    PyData Chicago August 2016 (video forthcoming)

    Fizz Buzz is a ubiquitous, nearly trivial problem used to weed out developer job applicants. Recently I wrote a joking-not-joking blog post about a fictional interviewee who solves it using neural networks. After the blog post went viral, I spent a lot of time thinking about Fizz Buzz as a machine learning problem. It turns out it's surprisingly interesting and subtle! I talk about how and why.

  • PyData Seattle July 2015

    The original talk proposal was "Learning Data Science Using Functional Python". Then once I started writing it it went way off the rails and turned into "Stupid Itertools Tricks". Then I remembered it was for a data conference, so I steered it back to earth. A fun talk about the crazy things you can do with lazy infinite sequences. Less

  • Strata Ignite 2013

    Seattle Fire Department runs a “real-time 911” website that tracks all of its incidents, including location, incident type, time, and which trucks showed up. One could, if one had a good imagination and data skills, think of this site as a “Foursquare” for fire trucks, scrape years worth of data from it, and analyze this data to discover the nature of “fire truck society”. And that’s what I did. Less