perfCalc {netDx} | R Documentation |
Computes variety of predictor evaluation measures based on the confusion matrix
perfCalc(dat)
dat |
(data.frame): 5 columns: score, tp, fp, tn, fn. One row per cutoff score for feature selection |
(list) stats (data.frame): score, f1, ppv, precision and recall. One row per cutoff for feature selection auc (numeric between 0 and 1): AUC of overall ROC curve prauc (numeric between 0 and 1): AUC of overall precision-recall curve
data(confmat) x <- perfCalc(confmat)