Despite growing interest in data stream mining the most successful incremental learners, such as VFDT, still use periodic recomputation to update attribute information gains and Gini indices. This note provides simple incremental formulas and algorithms for computing entropy and Gini index from time-changing data streams.
@article{arxiv.1403.6348,
title = {Updating Formulas and Algorithms for Computing Entropy and Gini Index from Time-Changing Data Streams},
author = {Blaz Sovdat},
journal= {arXiv preprint arXiv:1403.6348},
year = {2016}
}
Comments
Added directions future work; more consistent notation; fixed the errors in the updating algorithms for entropy; fixed an error in the statement of theorem 5; added two references to related work; fixed a few typos