Our submission contains implementations for decision trees, ada boosting, and random forests. They are contained in the following files:
decision_tree.py ada_boost.py random_forest.py
These files require the following python packages: numpy scipy
Each of these files contains a set of hyperparameters in their main() function that can be specified by the user. All combination of hyperparameters will be run and their error rates will be computed and output to a file. Descriptions of these hyperparameters and what hyperparameters are tunable for each learner is available in our pdf report.