impute.RF {imp4p}

Imputing missing values using Random Forest.

Description

Imputing missing values using the algorithm proposed by Stekhoven and Buehlmann (2012). The function is based on the missForest function of the R package missForest.

Usage

impute.RF(tab, conditions,
                    maxiter = 10, ntree = 100, variablewise = FALSE,
                    decreasing = FALSE, verbose = FALSE,
                    mtry = floor(sqrt(ncol(tab))), replace = TRUE,
                    classwt = NULL, cutoff = NULL, strata = NULL,
                    sampsize = NULL, nodesize = NULL, maxnodes = NULL,
                    xtrue = NA, parallelize = c('no', 'variables', 'forests'))

Arguments

tab

A data matrix containing numeric and missing values. Each column of this matrix is assumed to correspond to an experimental sample, and each row to an identified peptide.

conditions

A vector of factors indicating the biological condition to which each sample belongs.

maxiter

parameter of the missForest function (missForest R package).

ntree

parameter of the missForest function (missForest R package).

variablewise

parameter of the missForest function (missForest R package).

decreasing

parameter of the missForest function (missForest R package).

verbose

parameter of the missForest function (missForest R package).

mtry

parameter of the missForest function (missForest R package).

replace

parameter of the missForest function (missForest R package).

classwt

parameter of the missForest function (missForest R package).

cutoff

parameter of the missForest function (missForest R package).

strata

parameter of the missForest function (missForest R package).

sampsize

parameter of the missForest function (missForest R package).

nodesize

parameter of the missForest function (missForest R package).

maxnodes

parameter of the missForest function (missForest R package).

xtrue

parameter of the missForest function (missForest R package).

parallelize

parameter of the missForest function (missForest R package).

Details

See Stekhoven and Buehlmann (2012) for the theory. It is built from functions proposed in the R package missForest.

Value

The input matrix tab with imputed values instead of missing values.

Author(s)

Quentin Giai Gianetto <[e-mail]>

References

Stekhoven, D.J. and Buehlmann, P. (2012), 'MissForest - nonparametric missing value imputation for mixed-type data', Bioinformatics, 28(1) 2012, 112-118, doi: 10.1093/bioinformatics/btr597

Examples

#Simulating data
res.sim=sim.data(nb.pept=2000,nb.miss=600,nb.cond=2);

#Imputation of missing values with Random Forest
dat.rf=impute.RF(tab=res.sim$dat.obs,conditions=res.sim$condition);