Learn R Programming

spFSR (version 2.0.4)

Feature Selection and Ranking via Simultaneous Perturbation Stochastic Approximation

Description

An implementation of feature selection, weighting and ranking via simultaneous perturbation stochastic approximation (SPSA). The SPSA-FSR algorithm searches for a locally optimal set of features that yield the best predictive performance using some error measures such as mean squared error (for regression problems) and accuracy rate (for classification problems).

Copy Link

Version

Install

install.packages('spFSR')

Monthly Downloads

193

Version

2.0.4

License

GPL-3

Maintainer

David Akman

Last Published

March 17th, 2023

Functions in spFSR (2.0.4)

getImportance

Extracting feature importance data from a spFSR object
getBestModel

Extracting the wrapped model of the best performing features from a spFSR object
spFSR.default

Default Function of SP-FSR for Feature Selection and Ranking
plot.spFSR

Ploting a spFSR object
spFeatureSelection

SPSA-FSR for Feature Selection and Ranking
summary.spFSR

Summarising a spFSR object
plotImportance

Ploting importance ranks of best performing features from a spFSR object