No, the current implementation doesn't support weighted examples (yet ?), and you can't get the score for a prediction
________________________________ De : Yang Zhang <[email protected]> À : [email protected] Envoyé le : Samedi 7 Mai 2011 6h36 Objet : Re : Random forest questions I've been playing around with the RF implementation and I had a couple questions: - Does this RF implementation support weighted examples? (If so how do I specify weights?) - How do I get the RF score (confidence, probability, etc.) of a prediction? Thanks!
