- User Since
- Feb 1 2017, 10:55 AM (184 w, 1 d)
May 27 2020
I would propose to go with largeBetter, as this is true for the most common metric values (e.g. DSC and Accuracy).
May 19 2020
Ah perfect :) I was looking into a decathlon report which was apparently created with the master branch.
May 14 2020
Yes, this results in Na, but they shouldn't be treated like before; you're right. @wiesenfa: What do you propose for the plots? Should we just remove the warnings?
This is due to the fact that missing values cannot be plotted:
May 11 2020
I think it is interesting to state the number of NAs in the report but this should be the actual number of NAs (not 0).
Apr 30 2020
Apr 20 2020
Seemed to work by restarting it a second time.
It occured with another data set. Will try to reproduce it after restarting RStudio.
Apr 17 2020
Apr 3 2020
Yes and we should also mention you and Laura.