Learn R Programming

randPedPCA (version 1.1.2)

Fast PCA for Large Pedigrees

Description

Carry out principal component analysis (PCA) of very large pedigrees such as found in breeding populations! This package exploits sparse matrices and randomised linear algebra to deliver a gazillion-times speed-up compared to naive singular value decoposition (SVD) (and eigen decomposition).

Copy Link

Version

Install

install.packages('randPedPCA')

Monthly Downloads

222

Version

1.1.2

License

MIT + file LICENSE

Maintainer

Hannes Becher

Last Published

June 16th, 2025

Functions in randPedPCA (1.1.2)

L inverse matrix of the one-population example pedigree

Add downsampling index to rppca object

L inverse matrix of the two-population example pedigree

Hutch++ trace estimation

getNumVectorsHutchinson

Compute the number of vectors to use for Hutchinson trace estimation

Convert generic sparse matrix to spam format

3D plot of PC scores with projections on coordinate planes

Generate spam object from L inverse file

3D plot using rgl

randTraceHutchinson

Trace estimation for sparse L inverse matrices

Fast pedigree PCA using sparse matrices and randomised linear algebra

Singular value decomposition in sparse triangular matrix

randRangeFinder

Generate range matrix for SVD

Metadata associated with the four-population example pedigree

Metadata associated with one-population example

L inverse matrix of the four-population example pedigree

Metadata associated with the two-population example pedigree