learning-curve-plots-caret-parallel.R breaks in method = "parRF",

[tobigithub]

Probably dependent on older or newer library. Fresh install of all caret dependencies gives errors below. Older packages would just work fine. Method worked fine on other independent install.

LINK to learning-curve-plots-caret-parallel.R

> set.seed(29510)
> rf_data <- learning_curve_dat(dat = class_dat, outcome = "Class",
+                              test_prop = 1/4, 
+                              ## `train` arguments
+                              method = "parRF", 
+                              metric = "ROC",
+                              tuneLength = 4,
+                              trControl = trainControl(classProbs = TRUE, 
+                                                       method = "boot632",
+                                                       summaryFunction = twoClassSummary))
Training for 10% (n = 150)
Something is wrong; all the ROC metric values are missing:
      ROC           Sens          Spec      ROCApparent   SensApparent  SpecApparent
 Min.   : NA   Min.   : NA   Min.   : NA   Min.   : NA   Min.   : NA   Min.   : NA  
 1st Qu.: NA   1st Qu.: NA   1st Qu.: NA   1st Qu.: NA   1st Qu.: NA   1st Qu.: NA  
 Median : NA   Median : NA   Median : NA   Median : NA   Median : NA   Median : NA  
 Mean   :NaN   Mean   :NaN   Mean   :NaN   Mean   :NaN   Mean   :NaN   Mean   :NaN  
 3rd Qu.: NA   3rd Qu.: NA   3rd Qu.: NA   3rd Qu.: NA   3rd Qu.: NA   3rd Qu.: NA  
 Max.   : NA   Max.   : NA   Max.   : NA   Max.   : NA   Max.   : NA   Max.   : NA  
 NA's   :4     NA's   :4     NA's   :4     NA's   :4     NA's   :4     NA's   :4    
Error in train.default(x = dat[in_mod, colnames(dat) != outcome, drop = FALSE],  : 
  Stopping
In addition: Warning messages:
1: In nominalTrainWorkflow(x = x, y = y, wts = weights, info = trainInfo,  :
  There were missing values in the apparent performance measures.
2: In nominalTrainWorkflow(x = x, y = y, wts = weights, info = trainInfo,  :
  There were missing values in resampled performance measures.

[tobigithub]

maybe load pROC, no does not help.

[tobigithub]

tnx, can you show the correct solution as R script? Best T.