Package opennlp.tools.util.eval

Class FMeasure

  • public final class FMeasure
extends java.lang.Object
    The FMeasure is an utility class for evaluators which measure precision, recall and the resulting f-measure. Evaluation results are the arithmetic mean of the precision scores calculated for each reference sample and the arithmetic mean of the recall scores calculated for each reference sample.

    • Constructor Summary

      Constructors 
      Constructor Description
      FMeasure()  

    • Method Summary

      All Methods Static Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      double getFMeasure()
      Retrieves the f-measure score.
      double getPrecisionScore()
      Retrieves the arithmetic mean of the precision scores calculated for each evaluated sample.
      double getRecallScore()
      Retrieves the arithmetic mean of the recall score calculated for each evaluated sample.
      void mergeInto​(FMeasure measure)
      Merge results into fmeasure metric.
      static double precision​(java.lang.Object[] references, java.lang.Object[] predictions)
      Calculates the precision score for the given reference and predicted spans.
      static double recall​(java.lang.Object[] references, java.lang.Object[] predictions)
      Calculates the recall score for the given reference and predicted spans.
      java.lang.String toString()
      Creates a human read-able String representation.
      void updateScores​(java.lang.Object[] references, java.lang.Object[] predictions)
      Updates the score based on the number of true positives and the number of predictions and references.

      • Methods inherited from class java.lang.Object

        equals, getClass, hashCode, notify, notifyAll, wait, wait, wait

    • Constructor Detail

      • FMeasure

        public FMeasure()

    • Method Detail

      • getPrecisionScore

        public double getPrecisionScore()
        Retrieves the arithmetic mean of the precision scores calculated for each evaluated sample.
        Returns:
        the arithmetic mean of all precision scores

      • getRecallScore

        public double getRecallScore()
        Retrieves the arithmetic mean of the recall score calculated for each evaluated sample.
        Returns:
        the arithmetic mean of all recall scores

      • getFMeasure

        public double getFMeasure()
        Retrieves the f-measure score. f-measure = 2 * precision * recall / (precision + recall)
        Returns:
        the f-measure or -1 if precision + recall <= 0

      • updateScores

        public void updateScores​(java.lang.Object[] references,
                         java.lang.Object[] predictions)
        Updates the score based on the number of true positives and the number of predictions and references.
        Parameters:
        references - the provided references
        predictions - the predicted spans

      • mergeInto

        public void mergeInto​(FMeasure measure)
        Merge results into fmeasure metric.
        Parameters:
        measure - the fmeasure

      • toString

        public java.lang.String toString()
        Creates a human read-able String representation.
        Overrides:
        toString in class java.lang.Object
        Returns:
        the results

      • precision

        public static double precision​(java.lang.Object[] references,
                               java.lang.Object[] predictions)
        Calculates the precision score for the given reference and predicted spans.
        Parameters:
        references - the gold standard spans
        predictions - the predicted spans
        Returns:
        the precision score or NaN if there are no predicted spans

      • recall

        public static double recall​(java.lang.Object[] references,
                            java.lang.Object[] predictions)
        Calculates the recall score for the given reference and predicted spans.
        Parameters:
        references - the gold standard spans
        predictions - the predicted spans
        Returns:
        the recall score or NaN if there are no reference spans