pROC 1.1 released
I am releasing the version 1.1 of pROC.
lines.roc family of functions allows to add a ROC curve to an existing plot with
lines. Until now you had to use
add = TRUE. More informations with
?lines.roc. For instance:
library(pROC) data(aSAH) rocs100 <- roc(aSAH$outcome, aSAH$s100) rocwfns <- roc(aSAH$outcome, aSAH$wfns) plot(rocs100) lines(rocwfns)
Two additions were made to the
plot.roc function. First the
type argument, which is directly forwarded to
par, allows to change the line type.
print.auc.col allows to change the color of the printed AUC independently from the ROC curve. Here is an example of what you can do now:
plot(rocs100, print.auc=TRUE, print.auc.col="blue", type="o")
Here is the full change log:
lines.rocfunctions for ROC.
typeargument for both
- Fixed a warning in
roc.test.defaultwhen the class of
predictor1had several elements.
- Fixed an encoding failure during the checks on MacOS X (R only).
You can find the new version on ExPASy and on the CRAN. To update, type
install.packages("pROC") if you want to update pROC only.
Published Thursday, May 6, 2010 08:23 CEST