class weights

[p-schaefer]

I left a note here: #35, but thought it might warrant its own issue (if this package is still being developed). scale_pos_weight is only for binary classification, is there an alternative for dealing with class imbalance in multiclass classifications? I don't know mlr well, but perhaps xgboost.DMatrix(..., weight = *weight array for individual weights*), or passing .weights to trainLearner.classif.xgboost, or perhaps there is a better alternative?