ipapercodes/FGSPCA: Feature Grouping and Sparse Principal Component Analysis (FGSPCA)

Sparse principal component analysis (SPCA) attempts to find sparse weight vectors (loadings), i.e., a loading vector with only a few 'active' (nonzero) values. The SPCA approach provides better interpretability for the principal components in high-dimensional data settings. Because the principal components are formed as a linear combination of only a few of the original variables. This package provides a modified sparse principal component analysis, Feature Grouping and Sparse Principal Component Analysis (FGSPCA), which considers additional structure information among loadings (feature grouping) as well as the sparsity (feature selection) property among loadings.

install.packages("remotes")
remotes::install_github("ipapercodes/FGSPCA")