2017-2018 COS 497 Capstone Project
This project was started to better understand the game of hockey from behind the stat sheet and to see how well a neural network can predict the outcome of a game based on the statistics. The entire code base is written in python and taking advantage of the wonderful Keras API, numpy, pandas, matplotlib, and others.
Opening the New Data folder will show all of the raw data collected. The data is stored in JSON files and then filtered and compressed into CSV files. NewData.py compressed the data, kerasMain.py created and saved the keras model and layers. LoadModel.py loads a saved keras model and makes predictions on a set of data.