This creates a decision tree for classifying data, using the training data provided as XML and using information entropy to judge which attributes to use at each node of the tree.
This is still very much in development so there's no UI at all yet. The repository in its current state will generate a decision tree for classifying movie data based on a set of sample movies (data is provided as XML.) The data input syntax is quite flexible if not verbose.
No documentation at all so far... sorry! The logic for displaying the tree is currently embedded in the constructor until I get round to make that a separate entity.
Currently, data output is presented through stdout as a simple visualisation. LaTeX output to follow soon.