Package weka.estimators

Interface ConditionalEstimator

  • All Superinterfaces:
    RevisionHandler
    All Known Implementing Classes:
    DDConditionalEstimator, DKConditionalEstimator, DNConditionalEstimator, KDConditionalEstimator, KKConditionalEstimator, NDConditionalEstimator, NNConditionalEstimator
    public interface ConditionalEstimator
extends RevisionHandler
    Interface for conditional probability estimators. Example code: 

       NNConditionalEstimator newEst = new NNConditionalEstimator();

   // Create 50 random points and add them
   Random r = new Random(seed);
   for(int i = 0; i < 50; i++) {
     int x = Math.abs(r.nextInt() % 100);
     int y = Math.abs(r.nextInt() % 100);
     System.out.println("# " + x + "  " + y);
     newEst.addValue(x, y, 1);
   }

   // Pick a random conditional value
   int cond = Math.abs(r.nextInt() % 100);
   System.out.println("## Conditional = " + cond);

   // Print the probabilities conditional on that value
   Estimator result = newEst.getEstimator(cond);
   for(int i = 0; i <= 100; i+= 5) {
     System.out.println(" " + i + "  " + result.getProbability(i));
   }
    Version:
    $Revision: 1.7 $
    Author:
    Len Trigg (trigg@cs.waikato.ac.nz)

    • Method Detail

      • addValue

        void addValue​(double data,
              double given,
              double weight)
        Add a new data value to the current estimator.
        Parameters:
        data - the new data value
        given - the new value that data is conditional upon
        weight - the weight assigned to the data value

      • getEstimator

        Estimator getEstimator​(double given)
        Get a probability estimator for a value
        Parameters:
        given - the new value that data is conditional upon
        Returns:
        the estimator for the supplied value given the condition

      • getProbability

        double getProbability​(double data,
                      double given)
        Get a probability for a value conditional on another value
        Parameters:
        data - the value to estimate the probability of
        given - the new value that data is conditional upon
        Returns:
        the estimator for the supplied value given the condition