Principal component analysis (PCA) based on partial singular value decomposition (SVD).

getPC() uses irlba's partial SVD. When ncomp is at least half of the smaller dimension of X, where irlba can be inaccurate, or when the smaller dimension is at most 100, it uses a full SVD of a dense copy of X instead. On such small matrices irlba may not converge, and its result then depends on its random start; the full SVD does not.

getPC(X, ncomp, center = TRUE, scale = FALSE, sparse = FALSE)

Arguments

X: Matrix.
ncomp: Integer.
center: Logic.
scale: Logic.
sparse: Use sparse matrix or not.

Value

A list containing

scores: Score matrix for X.
loadings: Laoding matrix for X.
sdev: Standard deviations of the principal components.
totVar: Total variance of X after the requested centring and scaling.
props: Proportion of totVar explained by each component.
accuProps: Cumulative sum of props.
ncomp: Number of components.
Xmeans: Column means used for centring, or NULL.
Xscals: Column standard deviations used for scaling, or NULL.

Examples

set.seed(1)
X <- matrix(rnorm(100 * 10), 100, 10)
pc <- getPC(X, ncomp = 3)
dim(pc$scores)
pc$props