SMO confidence measure in weka

问题

I'm writing a classification code using the smo class of weka. But what i'm yet to find is a confidence measure of the classification of an instance. It always either returns 0 or 1 when distributionForInstance is called. I have two classes to be classified into. Any idea how i can get this measure? Thanks.

回答1:

Ok I figured out how to get this in case it might help someone. Get the source code for SMO.java and add it to your package. Resolve imports if any. Set m_fitLogisticModels to true. Change smo.buildClassifier(train, cl1, cl2, false, -1, -1); to smo.buildClassifier(train, cl1, cl2, true, -1, -1);. And viola ! distributionForInstance returns confidence scores instead of a hard 0/1.

来源：https://stackoverflow.com/questions/9686562/smo-confidence-measure-in-weka