Documentation of 'edu.uci.jforests.eval.ranking.URiskAwareEval' Java class
URiskAwareEval
edu.uci.jforests.eval.ranking

Class URiskAwareEval

  • Direct Known Subclasses:
    TRiskAwareSAROEval


    public class URiskAwareEval
    extends RankingEvaluationMetric
    Implements the URisk risk-sensitive evaluation metric, as defined by Wang et al. See Lidan Wang, Paul Bennet and Kevyn Collin-Thompson, SIGIR 2012.

    Implementation Details

    It is assumed that the natural ordering of documents for each query defines the baseline.

    • Constructor Detail

      • URiskAwareEval

        public URiskAwareEval(EvaluationMetric _parent,
                              double alpha)
    • Method Detail

      • measure

        public double measure(double[] predictions,
                              Sample sample)
                       throws java.lang.Exception
        Overrides:
        measure in class RankingEvaluationMetric
        Throws:
        java.lang.Exception
      • getSwapScorer

        public RankingEvaluationMetric.SwapScorer getSwapScorer(double[] targets,
                                                                int[] boundaries,
                                                                int trunc,
                                                                int[][] labelCounts)
                                                         throws java.lang.Exception
        Specified by:
        getSwapScorer in class RankingEvaluationMetric
        Parameters:
        targets - Targets of all documents in dataset. Equals Dataset.*.length
        boundaries - Start and end indices of each query within the dataset.
        trunc - Truncation level for evaluation measure
        labelCounts - How many of each label value
        Throws:
        java.lang.Exception - if things go pear shaped

DMelt 3.0 © DataMelt by jWork.ORG

You see the box below because you did not login.