Updated Basketball eigenspectra

In a recent post I talked about applying principal components analysis to SportsVU player tracking data and generating “eigenspectra”.  I sort of ran into a wall with that because the data are too numerous to analyze on my personal machine. I thought about setting up an AWS instance, and Chris Long generously agreed to run the code for me on his sports-analytics cluster. However, I was able to extend the method to more data by using on online estimate of the covariance. The results are available in an interactive form here, and illustrated in the gif below

eigen1

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s