Daim (version 1.1.0)

roc.area: Plot the area under the ROC curve

Description

This function plots the ROC curve and fills the area under this curve.

Usage

"roc.area"(x, method=NULL, col="red", area.color=rgb(1,0,0,alpha=0.5), xlab="False positive rate", ylab="True positive rate", density=NULL, angle=4, border=NULL, add=FALSE, ...)
"roc.area"(x, col="black", area.color=rgb(1,0,0,alpha=0.5), xlab="False positive rate", ylab="True positive rate", main="ROC curves", density=NULL, angle=4, border=NULL, add=FALSE, ...)
"roc.area"(x, col="red", area.color=rgb(1,0,0,alpha=0.5), xlab="False positive rate", ylab="True positive rate", main="ROC curve", density=NULL, angle=4, border=NULL, add=FALSE, ...)

Arguments

x
an object of class Daim, Daim.list or Daim.vector.
method
kind of the estimation of the ROC curve: '0.632+', '0.632', 'loob', 'cv', 'sample'
col
the color used to draw the ROC curve.
area.color
the color for filling the area.
xlab
a title for the x axis: see 'title'.
ylab
a title for the y axis: see 'title'.
main
a main title for the plot, see also title.
density
the density of shading lines, in lines per inch. The default value of 'NULL' means that no shading lines are drawn. A zero value of 'density' means no shading nor filling whereas negative values (and 'NA') suppress shading (and so allow color filling).
angle
the slope of shading lines, given as an angle in degrees (counter-clockwise).
border
the color to draw the border. The default, 'NULL', means to use 'par("fg")'. Use 'border = NA' to omit borders.
add
logical specifying if roc-area should be added to an already existing plot.
...
graphical parameters can be given as arguments to 'plot'.

See Also

plot.Daim, auc.Daim

Examples

Run this code

  data(Daim.data1)
  data(Daim.data2)


  perform1 <- performDaim(Daim.data1$prob.oob, Daim.data1$labels, 
                          Daim.data1$prob.app)
  perform2 <- performDaim(Daim.data2$prob.oob, Daim.data2$labels, 
                          Daim.data2$prob.app)
  
  summary(perform1)
  summary(perform2)

  roc.area(perform2)
  roc.area(perform1, area.color=rgb(0,0,1,alpha=0.2), col="blue", add=TRUE)
  legend(0.7, 0.2, c("Model-1","Model-2"), col=c("red","blue"), lty=1, bg="white")

  
  ## Not run:   
#   ## just because of checking time on CRAN
#   
#   
#   ####
#   #### If your device don't support the semi-transparent colors use 
#   #### the PDF Graphics Device.
#   ####
# 
#   pdf("ROC-area.pdf")
# 
#   roc.area(perform2)
#   roc.area(perform1, area.color=rgb(0,0,1,alpha=0.2), col="blue", add=TRUE)
#   legend(0.7, 0.2, c("Model 1","Model 2"), col=c("red","blue"), lty=1, bg="white")
#   dev.off()
#   ## End(Not run)

Run the code above in your browser using DataLab