Class AdaBoost

  • All Implemented Interfaces:

    public class AdaBoost
    extends Classifier
    AdaBoost Robert E. Schapire. "The boosting approach to machine learning: An overview." In MSRI Workshop on Nonlinear Estimation and Classification, 2002.
    Andrew McCallum
    See Also:
    Serialized Form
    • Constructor Detail

      • AdaBoost

        public AdaBoost​(Pipe instancePipe,
                        Classifier[] weakClassifiers,
                        double[] alphas)
    • Method Detail

      • getNumWeakClassifiers

        public int getNumWeakClassifiers()
        Get the number of weak classifiers in this ensemble classifier
      • getTrimmedClassifier

        public AdaBoost getTrimmedClassifier​(int numWeakClassifiersToUse)
        Return an AdaBoost classifier that uses only the first numWeakClassifiersToUse weak learners.

        The returned classifier's Pipe and weak classifiers are backed by the respective objects of this classifier, so changes to the returned classifier's Pipe and weak classifiers are reflected in this classifier, and vice versa.

      • classify

        public Classification classify​(Instance inst,
                                       int numWeakClassifiersToUse)
        Classify the given instance using only the first numWeakClassifiersToUse classifiers trained during boosting