All Packages  Class Hierarchy  This Package  Previous  Next  Index  WEKA's home

Class weka.estimators.DDConditionalEstimator 

java.lang.Object
   |
   +----weka.estimators.DDConditionalEstimator
public class DDConditionalEstimator
extends Object
implements ConditionalEstimator
Conditional probability estimator for a discrete domain conditional upon a discrete domain.

Version:
$Revision: 1.2 $
Author:
Len Trigg (trigg@cs.waikato.ac.nz)

Constructor Index

o DDConditionalEstimator(int, int, boolean)
Constructor

Method Index

o addValue(double, double, double)
Add a new data value to the current estimator.
o getEstimator(double)
Get a probability estimator for a value
o getProbability(double, double)
Get a probability estimate for a value
o main(String[])
Main method for testing this class.
o toString()
Display a representation of this estimator

Constructors

o DDConditionalEstimator 
 public DDConditionalEstimator(int numSymbols,
                               int numCondSymbols,
                               boolean laplace)
Constructor

Parameters:
numSymbols - the number of possible symbols (remember to include 0)
numCondSymbols - the number of conditioning symbols
laplace - if true, sub-estimators will use laplace

Methods

o addValue 
 public 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
o getEstimator 
 public Estimator getEstimator(double given)
Get a probability estimator for a 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
o getProbability 
 public double getProbability(double data,
                              double given)
Get a probability estimate for a value

Parameters:
data - the value to estimate the probability of
given - the new value that data is conditional upon
Returns:
the estimated probability of the supplied value
o toString 
 public String toString()
Display a representation of this estimator

Overrides:
toString in class Object
o main 
 public static void main(String argv[])
Main method for testing this class.

Parameters:
argv - should contain a sequence of pairs of integers which will be treated as symbolic. 
All Packages  Class Hierarchy  This Package  Previous  Next  Index  WEKA's home