Shift operating point of classifier
V = SHIFTOP(D,E,C)
If D = A*W, with A a test dataset and W a trained classifier, then an ROC curve can be computed and plotted by ER = PRROC(D,C), PLOTE(ER). C is the desired class number for which the error is plotted along the horizontal axis. The classifier W can be given any operating point along this curve by W = W*SHIFTOP(D,E,C). Alternatively, an overall error TYPE can be optimised. Currently we have
The class index C refers to its position in the label list of the dataset A used for training the classifier that yielded D. The relation to LABEL is LABEL = CLASSNAME(A,C); C = GETCLASSI(A,LABEL).
In case the same dataset A is used to train an untrained classifier U as well as to determine D to