public abstract class ConditionalSufficientStats
extends java.lang.Object
implements java.io.Serializable
Constructor and Description |
---|
ConditionalSufficientStats() |
Modifier and Type | Method and Description |
---|---|
abstract SplitCandidate |
bestSplit(SplitMetric splitMetric,
java.util.Map<java.lang.String,WeightMass> preSplitDist,
java.lang.String attName)
Return the best split
|
abstract double |
probabilityOfAttValConditionedOnClass(double attVal,
java.lang.String classVal)
Return the probability of an attribute value conditioned on a class value
|
abstract void |
update(double attVal,
java.lang.String classVal,
double weight)
Update this stat with the supplied attribute value and class value
|
public abstract void update(double attVal, java.lang.String classVal, double weight)
attVal
- the value of the attributeclassVal
- the class valueweight
- the weight of this observationpublic abstract double probabilityOfAttValConditionedOnClass(double attVal, java.lang.String classVal)
attVal
- the attribute value to compute the conditional probability
forclassVal
- the class valuepublic abstract SplitCandidate bestSplit(SplitMetric splitMetric, java.util.Map<java.lang.String,WeightMass> preSplitDist, java.lang.String attName)
splitMetric
- the split metric to usepreSplitDist
- the distribution of class values prior to splittingattName
- the name of the attribute being considered for splitting