We describe a parallel implementation in R of the weighted subspace random forest algorithm (Xu, Huang, Williams, Wang, and Ye 2012) available as the wsrf package. A novel variable weighting method is used for variable subspace selection in place of the traditional approach of random variable sampling. This new approach is particularly useful in building models for high dimensional data - often consisting of thousands of variables. Parallel computation is used to take advantage of multi-core machines and clusters of machines to build random forest models from high dimensional data in considerably shorter times. A series of experiments presented in this paper demonstrates that wsrf is faster than existing packages whilst retaining and often improving on the classification performance, particularly for high dimensional data.
展开▼
