Feature Selection and Ranking by Simultaneous Perturbation Stochastic Approximation

An implementation of feature selection and ranking via simultaneous perturbation stochastic approximation (SPSA-FSR) based on works by V. Aksakalli and M. Malekipirbazari (2015) and Zeren D. Yenice and et al. (2018) . The SPSA-FSR algorithm searches for a locally optimal set of features that yield the best predictive performance using a specified error measure such as mean squared error (for regression problems) and accuracy rate (for classification problems). This package requires an object of class 'task' and an object of class 'Learner' from the 'mlr' package.


News

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("spFSR")

1.0.0 by Vural Aksakalli, 9 months ago


https://www.featureranking.com/, https://arxiv.org/abs/1804.05589


Report a bug at https://github.com/yongkai17/spFSR/issues


Browse source code at https://github.com/cran/spFSR


Authors: Vural Aksakalli [aut, cre] , Babak Abbasi [aut, ctb] , Yong Kai Wong [aut, ctb] , Zeren D. Yenice [ctb]


Documentation:   PDF Manual  


GPL-3 license


Imports ggplot2, class, mlbench

Depends on mlr, parallelMap, parallel, tictoc

Suggests caret, MASS, knitr, rmarkdown


See at CRAN