I recently updated my baseball event database. It creates a sqlite3 database out of all of the xml event files from http://gd2.mlb.com/components/game/mlb.

I created some simple examples to show how to use the database as well.

I hope to build more notebooks over time, extend the database and start doing independent verification of people who claim to be doing sabermetric advice. Perchance even using some of the newer techniques from Deep Learning on the dataset.