/** * Evaluate the network (must be a binary classifier) on the specified data, using the {@link ROC} class * * @param iterator Data to evaluate on * @param rocThresholdSteps Number of threshold steps to use with {@link ROC} * @return ROC evaluation on the given dataset */ public ROC evaluateROC(DataSetIterator iterator, int rocThresholdSteps) { return doEvaluation(iterator, new ROC(rocThresholdSteps))[0]; }
/** * Evaluate the network (must be a binary classifier) on the specified data, using the {@link ROC} class * * @param iterator Data to evaluate on * @param rocThresholdSteps Number of threshold steps to use with {@link ROC} * @return ROC evaluation on the given dataset */ public ROC evaluateROC(DataSetIterator iterator, int rocThresholdSteps) { return doEvaluation(iterator, new ROC(rocThresholdSteps))[0]; }
/** * Evaluate the network (must be a binary classifier) on the specified data, using the {@link ROC} class * * @param iterator Data to evaluate on * @param rocThresholdSteps Number of threshold steps to use with {@link ROC} * @return ROC evaluation on the given dataset */ public ROC evaluateROC(MultiDataSetIterator iterator, int rocThresholdSteps) { return doEvaluation(iterator, new ROC(rocThresholdSteps))[0]; }
underlying = new ROC[n]; for (int i = 0; i < n; i++) { underlying[i] = new ROC(thresholdSteps, rocRemoveRedundantPts);
underlying = new ROC[n]; for (int i = 0; i < n; i++) { underlying[i] = new ROC(thresholdSteps, rocRemoveRedundantPts);
ROC roc = new ROC(1000);