Description
Covariance Regression with Random Forests.
Description
Covariance Regression with Random Forests (CovRegRF) is a random forest method for estimating the covariance matrix of a multivariate response given a set of covariates. Random forest trees are built with a new splitting rule which is designed to maximize the distance between the sample covariance matrix estimates of the child nodes. The method is described in Alakus et al. (2023) <doi:10.1186/s12859-023-05377-y>. 'CovRegRF' uses 'randomForestSRC' package (Ishwaran and Kogalur, 2022) <https://cran.r-project.org/package=randomForestSRC> by freezing at the version 3.1.0. The custom splitting rule feature is utilised to apply the proposed splitting rule. The 'randomForestSRC' package implements 'OpenMP' by default, contingent upon the support provided by the target architecture and operating system. In this package, 'LAPACK' and 'BLAS' libraries are used for matrix decompositions.
README.md
CovRegRF
R package which implements Covariance Regression with Random Forests (CovRegRF).
CovRegRF is a random forest method for estimating the covariance matrix of a multivariate response Y, given a set of covariates X. The forest trees are built with a splitting rule specifically designed to partition the data to maximize the distance between the sample covariance matrix estimates of the child nodes.
For theoretical details and example data analysis, you can look at the vignette from within R by using the following command:
vignette("CovRegRF")
Installation
The package CovRegRF can be installed from GitHub using the devtools package. Run the following code in R to install:
if (!require(devtools)) {
install.packages("devtools")
library(devtools)
}
devtools::install_github('calakus/CovRegRF', build_vignettes = TRUE)
References
- Alakus, C., Larocque, D., and Labbe, A. (2023). Covariance regression with random forests. BMC Bioinformatics 24, 258.