Very Fast Machine Learning Toolkit

Based on original work by Hulten, G. and Domingos, P. "VFML -- A toolkit for mining high-speed time-changing data streams" http://www.cs.washington.edu/dm/vfml/. 2003.

Hulten and Domingos' original VFML C code with minor modifications to support compilation on Ubuntu 10.04 and gcc 4.6.3.

Weka implementation of the VFDT and CVFDT tree-based classification algorithms. Developed mainly for educational purposes. For actual streaming classification problems, the Moa VFDT implemention is recommended.

Scripts for downloading and parsing various large datasets suitable for machine learning on massive data streams.