Prints the result of one or more cross-validation run(s)

Share:

Description

This function creates boxplots of the distribution of AUC for each reapeat of the cross-validation. In a second plot the ROC curve of the AUCs is shown. If your result contains more than one cross-validation result these are plotted one after the other.

Usage

1
2
3
4
  ## S3 method for class 'pathClassResult'
plot(x, label = "", toFile = TRUE,
    fname = "Result", switchLabels = FALSE,
    avg = "horizontal", spread.estimate = "boxplot", ...)

Arguments

x

A result of crossval.

label

the main label of the plots.

toFile

Should the results plotted into PDF file(s). If your result contains more than one cross-validation one PDF file is created for each result.

fname

the name of the file to save the results in.

switchLabels

If your AUC is below 0.5 you can switch the labels to get an AUC above 0.5.

avg

the method for averaging the AUCs of several repeats. See 'performance' for more information.

spread.estimate

method to show the variation around the average of the ROC curve. See 'performance' for more information.

...

currently ignored.

Author(s)

Marc Johannes JohannesMarc@gmail.com

Examples

1
2
3
4
5
6
7
8
9
## Not run: 
library(Biobase)
data(sample.ExpressionSet)
x <- t(exprs(sample.ExpressionSet))
y <- factor(pData(sample.ExpressionSet)$sex)
res.rfe <- crossval(x,y,DEBUG=TRUE,theta.fit=fit.rfe,folds=2,repeats=1,parallel=TRUE,Cs=10^(-3:3))
plot(res.rfe, toFile=FALSE)

## End(Not run)