single.predictor: Parameter sweeps of svm, random forest, and elastic net...

In graim/PLATYPUS: Multiple view and task learning

Description

Parameter sweeps of svm, random forest, and elastic net models for config generation.

Usage

single.predictor(X, y, model, ignore.label = "intermediate")

Arguments

X	Feature matrix (sample per row)
y	Named vector of labels
model	Type of single predictor model to build. Choose from en (elastic net), rf (random forest), or svm (support vector machine)
ignore.label	Label class to ignore. Will be removed from labels set before training.

Value

list containing optimal model summary

Examples

X <- matrix(rnorm(10000), nrow=100)
y <- c(rep('MOO',50),rep('OINK',50))
names(y) <- paste0('Sample',seq(nrow(X)))
rownames(X) <- paste0('Sample',seq(nrow(X)))
colnames(X) <- paste0('Feature',seq(ncol(X)))
y <- factor(y)
res <- single.predictor(X,y,model='rf')
res <- single.predictor(X,y,model='en')
res <- single.predictor(X,y,model='svm')

graim/PLATYPUS documentation built on Oct. 4, 2019, 2:05 p.m.