How to get a ROC curve and AUC from unsupervised algotithm?
My dataset and the process in the file.zip as following.
In the anomaly detection extension, I use k-NN Global Anomaly Score operator to get the anomaly score of every instance in the dataset. The Generate ROC operator in the extension can only get the true_positive_rate and false positive rate, however, I can't get the ROC curve and AUC. Can I use some operator to directly get the ROC curve and AUC on the basis of my present process in RapidMiner?
In the anomaly detection extension, I use k-NN Global Anomaly Score operator to get the anomaly score of every instance in the dataset. The Generate ROC operator in the extension can only get the true_positive_rate and false positive rate, however, I can't get the ROC curve and AUC. Can I use some operator to directly get the ROC curve and AUC on the basis of my present process in RapidMiner?
Find more posts tagged with
Sort by:
1 - 1 of
11
if your data has labels you can just use the normal AUC from Performance (Binominals).
Beset,
Martin