Package com.tibco.patterns.learn.rlink

Class ConfStats

  • All Implemented Interfaces:
    Confidence
    public class ConfStats
extends java.lang.Object
implements Confidence
    Confidence measure based on submodel statistics. Immutable class.

    For older Learn models this is the only measure available. It is based on the number of true and false training pairs seen for the subset with each label. It does not take into account the particular scores involved. The confidence is the same for all feature scores in the same subset.

    • Constructor Summary

      Constructors 
      Constructor Description
      ConfStats()
      Create an instance with default values.
      ConfStats​(int halfCount, double balanceWeight)
      Create an instance with specific parameter values.

    • Method Summary

      All Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      int getConfType()
      Return the confidence type.
      double getDblArg​(int idx)
      Return a double parameter.
      int getIntArg​(int idx)
      Return an integer parameter.
      java.lang.String toString()  

      • Methods inherited from class java.lang.Object

        clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

    • Constructor Detail

      • ConfStats

        public ConfStats()
        Create an instance with default values.

      • ConfStats

        public ConfStats​(int halfCount,
                 double balanceWeight)
        Create an instance with specific parameter values.
        Parameters:
        halfCount - The number of training pairs needed to reach a confidence measure of 0.5. The default value is 5000. Note this is a count of the total number of pairs in the entire training session. Not the number of pairs in a single training iteration. Use -1 to let it default.
        balanceWeight - The proportion of the final measure attributed to the balance of yes and no labels seen. The default value is 0.3. Use -1.0 to let it default.

    • Method Detail

      • toString

        public java.lang.String toString()
        Overrides:
        toString in class java.lang.Object

      • getConfType

        public int getConfType()
        Return the confidence type.
        Specified by:
        getConfType in interface Confidence
        Returns:
        the confidence type for the Stats measure.

      • getIntArg

        public int getIntArg​(int idx)
        Return an integer parameter. The first parameter is the halfCount.
        Specified by:
        getIntArg in interface Confidence
        Parameters:
        idx - the integer parameter index, zero based.
        Returns:
        The half_count value for index 0, -1 otherwise.

      • getDblArg

        public double getDblArg​(int idx)
        Return a double parameter. The first parameter is the balance weight.
        Specified by:
        getDblArg in interface Confidence
        Parameters:
        idx - the double parameter index, zero based.
        Returns:
        balance weight for index 0, -1.0 for all others.