It’s really easy for me to want to re-invent the wheel.  I like the scientific process and learning on my own.  However, it is not an efficient way to approach projects, like the NFL play-by-play machine learning project I’m working on.

I tried to develop my own API that gets me the play-by-play data from NFL GameCenter.  This was a futile effort, but one helluva learning experience.  I learned to use Python libraries like BeautifulSoup and URLlib.  Valuable tools I hope to use later for data mining.  I also learned more about JSON objects, and that the NFL publishes all play-by-play data to JSON objects.  Good to keep in mind for future reference, and a project I’ve got for reference on GitHub (https://github.com/mooneyj3/football-play-agger)

Alas, my goal is not to develop API’s, my goal is to analyze play-by-play data using machine learning.  I reached out to a professor at Western Washington University early on in this project, and I gave him an update.  He was kind to remind me to use my existing data to extrapolate machine learning methods first and develop a model — up-to-date play-by-play would come later.

Stay Focused on the Goal: Machine Learning with NFL Play-by-Play data

Leave a Reply

Your email address will not be published. Required fields are marked *