Class DiscreteEstimatorBayes
java.lang.Object
weka.estimators.Estimator
weka.classifiers.bayes.net.estimate.DiscreteEstimatorBayes
- All Implemented Interfaces:
Serializable
,Cloneable
,Scoreable
,CapabilitiesHandler
,CapabilitiesIgnorer
,OptionHandler
,RevisionHandler
- Direct Known Subclasses:
DiscreteEstimatorFullBayes
Symbolic probability estimator based on symbol counts and a prior.
- Version:
- $Revision: 8034 $
- Author:
- Remco Bouckaert (rrb@xm.co.nz)
- See Also:
-
Field Summary
-
Constructor Summary
-
Method Summary
Modifier and TypeMethodDescriptionvoid
addValue
(double data, double weight) Add a new data value to the current estimator.double
getCount
(double data) Get a counts for a valueint
Gets the number of symbols this estimator operates withdouble
getProbability
(double data) Get a probability estimate for a valueReturns the revision string.double
logScore
(int nType, int nCardinality) Gets the log score contribution of this distributionstatic void
Main method for testing this class.toString()
Display a representation of this estimatorMethods inherited from class weka.estimators.Estimator
addValues, addValues, addValues, addValues, buildEstimator, buildEstimator, clone, debugTipText, doNotCheckCapabilitiesTipText, equals, forName, getCapabilities, getDebug, getDoNotCheckCapabilities, getOptions, listOptions, makeCopies, makeCopy, setDebug, setDoNotCheckCapabilities, setOptions, testCapabilities
-
Constructor Details
-
DiscreteEstimatorBayes
public DiscreteEstimatorBayes(int nSymbols, double fPrior) Constructor- Parameters:
nSymbols
- the number of possible symbols (remember to include 0)fPrior
-
-
-
Method Details
-
addValue
public void addValue(double data, double weight) Add a new data value to the current estimator. -
getProbability
public double getProbability(double data) Get a probability estimate for a value- Specified by:
getProbability
in classEstimator
- Parameters:
data
- the value to estimate the probability of- Returns:
- the estimated probability of the supplied value
-
getCount
public double getCount(double data) Get a counts for a value- Parameters:
data
- the value to get the counts for- Returns:
- the count of the supplied value
-
getNumSymbols
public int getNumSymbols()Gets the number of symbols this estimator operates with- Returns:
- the number of estimator symbols
-
logScore
public double logScore(int nType, int nCardinality) Gets the log score contribution of this distribution -
toString
Display a representation of this estimator -
getRevision
Returns the revision string.- Specified by:
getRevision
in interfaceRevisionHandler
- Overrides:
getRevision
in classEstimator
- Returns:
- the revision
-
main
Main method for testing this class.- Parameters:
argv
- should contain a sequence of integers which will be treated as symbolic.
-