text classification - R package mldr example code outputs error message and different results -

in vignette of package, following example presented demonstrate evaluation function, mldr_evaluate:

# true labels in emotions predictions  <- as.matrix(emotions$dataset[,emotions$labels$index])  # , introduce noise  predictions[sample(1:593, 100),sample(1:6, 100, replace = true) <-sample(0:1, 100, replace = true)  # evaluate predictive performance  res <- mldr_evaluate(emotions, predictions) str(res) ## list of 20  ## $ accuracy : num 0.914  ## $ auc : num 0.916  ## $ averageprecision: num 0.669  ## $ coverage : num 2.73  ## $ fmeasure : num 0.947  ## $ hammingloss : num 0.0863 ## $ macroauc : num 0.915  ## $ macrofmeasure : num 0.865  

however, when run r locally exact same code, get:

library(mldr)   predictions <- as.matrix(emotions$dataset[, emotions$labels$index])  # , introduce noise (alternatively predictions classifier)  predictions[sample(1:593, 100), sample(1:6, 100, replace = true)] <- sample(0:1, 100, replace = true)  # evaluate predictive performance  res <- mldr_evaluate(emotions, predictions)  str(res)   list of 20  $ accuracy        : num 0.915  $ auc             : null  $ averageprecision: num 0.672  $ coverage        : num 2.72  $ fmeasure        : num 0.95  $ hammingloss     : num 0.0854  $ macroauc        : null  $ macrofmeasure   : num 0.866 

alongside many of these error messages, have not been able interpret (what function reports them, line, etc):

 1:   in min(x) :  no non-missing arguments min; returning inf 

finally, sessioninfo():

> sessioninfo() r version 3.3.2 (2016-10-31) platform: x86_64-w64-mingw32/x64 (64-bit) running under: windows server >= 2012 x64 (build 9200) (...) other attached packages: [1] mldr_0.3.22 

clearly, roc curves , drawing, far have gotten, not deeper it.