Re: pROC 1.17.0.1

2021-07-23T13:04:16+02:00

Hi! I have installed the pROC package a month ago with the following code without problems:
#load and call the necessary package.
install.packages ("pROC")
library ("pROC")

#import the excel.
library (readxl)
dfcor <- read_excel ("C: /Users/pe3re/Downloads/Curvas-COR-master/Curvas-COR-master/FCM.xlsx", col_types = c ("numeric", "numeric"))

roc <-roc (dfcor $ true, dfcor $ pred)

plot (roc)

auc (roc)

#we draw the curve beautiful.
#insert AUC and IC
rocobj <- plot.roc (dfcor $ true, dfcor $ pred, main = "Confidence intervals", percent = TRUE, ci = TRUE, print.auc = TRUE)

#we create object to plot the default CI at 95% CI. Boots Default: 2000.
ciobj <- ci.se (rocobj, specificities = seq (0, 100, 5))
#insert the IC
plot (ciobj, type = "shape", col = "# 1c61b6AA") # plot as a blue shape

Today I have updated to the new version and it has given me problems. I have followed the code on the page and I get the same error again when using the confidence intervals:

roc1 <- roc (true ~ pred, dfcor, percent = TRUE,
ci = TRUE, boot.n = 100, ci.alpha = 0.9, stratified = FALSE,
plot = TRUE, auc.polygon = TRUE, max.auc.polygon = TRUE, grid = TRUE,
print.auc = TRUE, show.thres = TRUE)

Error in delongPlacementsCpp (roc):
package 'Rcpp_precious_remove' does not offer function 'Rcpp'

Xavablog – Commentaires sur pROC 1.17.0.1

Re: pROC 1.17.0.1

Re: pROC 1.17.0.1