I am using Spark 1.5.0 MLlib Random Forest algorithm (Scala code) to do two-class classification. As the dataset I am using is highly imbalanced, so the majority class is down sampled at 10% sampling rate.
Is it possible to use the sampling weight (10 in this case) in the Spark Random Forest training? I don't see weight among the input parameters for trainClassifier() in Random Forest.
