Waikato / moa

MOA is an open source framework for Big Data stream mining. It includes a collection of machine learning algorithms (classification, regression, clustering, outlier detection, concept drift detection and recommender systems) and tools for evaluation.
http://moa.cms.waikato.ac.nz/
GNU General Public License v3.0
614 stars 355 forks source link

AMRules and RandomAMRules #1

Closed joaomaiaduarte closed 10 years ago

joaomaiaduarte commented 10 years ago

-AMRules now uses weights for examples in all its extent. -New: RandomAMRules ensemble method. Uses bagging to perturb training set (using AMRules support for weights), and at each rule expansion a different subset of the attributes is used. -Fixed minor RandomRules bugs.

Main difference between RandomRules and RandomAMRules: each model of the former sees a different subset of the attributes while the latter uses different subset of the attributes for expanding each rule.