Python implementations of concept formation algorithms
Fetching latest commit…
Cannot retrieve the latest commit at this time
This is a python library of algorithms that perform concept formation written by Christopher MacLellan (http://www.christopia.net). In this library, the COBWEB (http://axon.cs.byu.edu/~martinez/classes/678/Papers/Fisher_Cobweb.pdf) and COBWEB/3 (http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.97.4676&rep=rep1&type=pdf) algorithms are implemented. The system accepts a stream of instances, which are represented as hash tables of attributes and values (where values can be both numeric and nominal), and learns a concept hierarchy. Current plans are to extend this library to include the LABYRINTH (http://www.isle.org/~langley/papers/labyrinth.cfb.pdf) algorithm for learning structured concepts with relations and components.