mlr: what exactly does the function getBMRTuneResults?

Question

I'm doing nested resampling with a 4x3 setup (4-fold cross-validation in the outer loop, and 3-fold cross-validation in the inner loop). For now, I only use Support Vector Machines (ksvm from kernlab). In the inner loop, I'm looking for the optimal tuning parameters C and sigma.

Calling getBMRPerformances() then outputs me the performances on the 4 individual outer test data sets. The function getBMRTuneResults() outputs 4 values for the measure I am using (in my case cohen's kappa) as well but they differ from the output of getBMRPerformances() and I don't understand what the second output actually is.

Answer 1

As the function name indicates, it outputs the results from tuning. So the performance values correspond to the performances calculated during the tuning (inner loop).

The four values in particular here are the performances reached by the best performing hyperparameter setting for a particular fold of your outer loop.