epca is an R package for comprehending any data matrix that contains low-rank and sparse underlying signals of interest. The package currently features two key tools:

• sca for sparse principal component analysis.
• sma for sparse matrix approximation, a two-way data analysis for simultaneously row and column dimensionality reductions.

You can install the released version of epca from CRAN with:

install.packages("epca")

or the development version from GitHub with:

# install.packages("devtools")
devtools::install_github("fchen365/epca")

The usage of sca and sma is straightforward. For example, to find k sparse PCs of a data matrix X:

sca(X, k)

Similarly, we can find a rank-k sparse matrix decomposition by

sma(X, k)

For more examples, please see the vignette:

vignette("epca")

If you encounter a clear bug, please file an issue with a minimal reproducible example on GitHub.

Chen, F., & Rohe, K. (2023). A New Basis for Sparse Principal Component Analysis. Journal of Computational and Graphical Statistics, 1-14. (DOI)