bcv: Calculate bi-cross-validation

In jonalim/mfBiclust: Pipelines for Bi-Clustering Using Matrix Factorization

Description

Calculates the bi-cross-validation of a Singular value decmoposition of matrix Y.

Usage

bcv(Y, ks = seq_len(min(nrow(Y), ncol(Y)) - 1), holdouts = 10L,
  interactive = TRUE)

Arguments

Y	the input matrix
ks	a vector of bicluster quantities to evaluate
holdouts	the number of row and column partitions. The true number of holdouts will be holdouts ^ 2.
interactive	prompt before running if Y is missing values

Details

It is recommended to use auto_bcv to perform and analyze several replications of bi-cross-validation.

Value

A named vector of BCV values corresponding to the various numbers of biclusters evaluated.

See Also

auto_bcv()

Examples

# Set seed for reproducibility
set.seed(12345)
bcv(yeast_benchmark[[1]])

jonalim/mfBiclust documentation built on May 4, 2019, 4:13 a.m.