An example of ROC curves plotting with ROCR
[This article was first published on Farmacokratia, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.
Decided to start githib with ROC curve plotting example. There is not a one ROC curve but several – according to the number of comparisons (classifications), also legend with maximal and minimal ROC AUC are added to the plot. ROC curves and ROC AUC were calculated with ROCR package.Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.
What else should be added to the plot for ease of understanding?
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# ROC curve(s) with ROCR | |
# Chupakhin Vladimir (chupvl@gmail.com) | |
# loading ROCR library | |
library("ROCR") | |
# loading active compounds, or compounds with label1 | |
active <- read.table("sample.active", sep=",", header=FALSE) | |
# loading inactive compounds, or compounds with label2 | |
inactive <- read.table("sample.inactive", sep=",", header=FALSE) | |
# binding them and converting to matrix because ROCR works with matrix data | |
target_pred <- as.matrix(rbind(active,inactive)) | |
# because number of the colums should be the same - making additional param | |
ncol <- ncol(inactive) | |
# generating classes (1 for active, 0 for inactive, but it can be 1 and -1 - there is no difference) | |
class.active <- matrix(sample(1, (ncol(active)*nrow(active)), replace=T), ncol=ncol) | |
class.inactive <- matrix(sample(0, (ncol(inactive)*nrow(inactive)), replace=T), ncol=ncol) | |
# binding the classes | |
target_class <- rbind(class.active,class.inactive) | |
#target_class1 <- target_class[,1] | |
# calculating the values for ROC curve | |
pred <- prediction(target_pred, target_class) | |
perf <- performance(pred,"tpr","fpr") | |
# changing params for the ROC plot - width, etc | |
par(mar=c(5,5,2,2),xaxs = "i",yaxs = "i",cex.axis=1.3,cex.lab=1.4) | |
# plotting the ROC curve | |
plot(perf,col="black",lty=3, lwd=3) | |
# calculating AUC | |
auc <- performance(pred,"auc") | |
# now converting S4 class to vector | |
auc <- unlist(slot(auc, "y.values")) | |
# adding min and max ROC AUC to the center of the plot | |
minauc<-min(round(auc, digits = 2)) | |
maxauc<-max(round(auc, digits = 2)) | |
minauct <- paste(c("min(AUC) = "),minauc,sep="") | |
maxauct <- paste(c("max(AUC) = "),maxauc,sep="") | |
legend(0.3,0.6,c(minauct,maxauct,"\n"),border="white",cex=1.7,box.col = "white") | |
# |
To leave a comment for the author, please follow the link and comment on their blog: Farmacokratia.
R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.