Resampling Algorithms for Multi-Label Datasets

Collection of the state of the art multi-label resampling algorithms. The objective of these algorithms is to achieve balance in multi-label datasets.

mldr.resampling

Collection of the state of the art multilabel resampling algorithms. The objective of these algorithms is to achieve balance in multilabel datasets.

Installation

Use install.packages to install mldr.resampling and its dependencies:

install.packages("mldr.resampling")

Alternatively, you can install it via install_github from the devtools package.

devtools::install_github("madr0008/mldr.resampling")

Building from source

Use devtools::build from devtools to build the package:

devtools::build(args = "--compact-vignettes=gs+qpdf")

Usage and examples

This package has an interface function that can be called in order to execute the desired algorithms, on the desired mldr datasets. This function can be called as follows:

library(mldr.resampling)

resample(birds, c("MLSOL", "MLeNN"), P=30, k=5, TH=0.4)

For more examples and detailed explanation on available functions, please refer to the documentation.