prcomp: Principal Components Analysis for "matter" Matrices

In kuwisdelu/matter: Scientific computing for out-of-memory signals and images

Principal Components Analysis for “matter” Matrices

Description

This method allows computation of a truncated principal components analysis of matter_mat and sparse_mat matrices using the implicitly restarted Lanczos method from the “irlba” package.

Usage

## S4 method for signature 'matter_mat'
prcomp(x, k = 3L, retx = TRUE, center = TRUE, scale. = FALSE, ...)

## S4 method for signature 'sparse_mat'
prcomp(x, k = 3L, retx = TRUE, center = TRUE, scale. = FALSE, ...)

prcomp_lanczos(x, k = 3L, retx = TRUE,
    center = TRUE, scale. = FALSE, transpose = FALSE,
    verbose = NA, nchunks = NA, BPPARAM = bpparam(), ...)

Arguments

x	A matter matrix, or any matrix-like object for prcomp_lanczos.
k	The number of principal components to return, must be less than min(dim(x)).
retx	A logical value indicating whether the rotated variables should be returned.
center	A logical value indicating whether the variables should be shifted to be zero-centered, or a centering vector of length equal to the number of columns of x. The centering is performed implicitly and does not change the out-of-memory data in x.
scale.	A logical value indicating whether the variables should be scaled to have unit variance, or a scaling vector of length equal to the number of columns of x. The scaling is performed implicitly and does not change the out-of-memory data in x.
transpose	A logical value indicating whether x should be considered transposed or not. This can be useful if the input matrix is (P x N) instead of (N x P) and storing the transpose is expensive. This is not necessary for matter_mat and sparse_mat objects, but can be useful for large in-memory (P x N) matrices.
verbose	Should progress messages be printed?
nchunks	The number of chunks to use (for centering and scaling only).
...	Additional options passed to irlba or prcomp_lanczos.
BPPARAM	An optional instance of BiocParallelParam. See documentation for bplapply. Currently only used for centering and scaling. Use options(matter.matmul.bpparam=TRUE) to enable parallel matrix multiplication for matter_mat and sparse_mat matrices.

Value

An object of class ‘prcomp’. See ?prcomp for details.

Note

The built-in predict() method (from the stats package) is not compatible with the argument transpose=TRUE.

Author(s)

Kylie A. Bemis

See Also

irlba prcomp_irlba

Examples

register(SerialParam())
set.seed(1)

x <- matter_mat(rnorm(1000), nrow=100, ncol=10)

prcomp(x)

kuwisdelu/matter documentation built on May 1, 2024, 5:17 a.m.