Attributes of classperf objects in matlab [original]

1. classlabels: Type ID. The first label is POs, and the second label is neg.

2. groundtruth: The observed values of each experiment, that is, the actual values.

3. validationcounter: number of tests

4. sampledistribution: the number of times each sample is used as a test set sample. K-fold-validation is used.

5. errordistribution: Number of times each sample was misjudged during the test

In K-fold-valiation, We can find samples with many false positives.

6. sampledistributionbyclass: number of samples in the test set

7. errordistributionbyclass: number of samples in the misjudgment Sample Set

8. countingmatrix: the first two rows indicate TP, FP; TN, FN; the last row is inconclusive results.

9. correctrate: (TP + FN)/(p + n)

10. errorrate: 1-correctrate

11. sensiti.pdf: TP/(TP + FP) =Recall=FDR (failure detective rate)

12. Specificity: FN/(TN + FN) =1-far (false alarm rate)

13. positivepredictivevalue: TP/(TP + Tn) =Precision

14. negativepredictivevalue: FN/(FP + FN)

15. Prevalence: TP/(TP + FP + tn + FN)

16. diagnostictable: Same as countingmatrix

Recall, precision, far, and FDR are required.

Attributes of classperf objects in matlab [original]