Package weka.classifiers.trees.j48
Class GainRatioSplitCrit
java.lang.Object
weka.classifiers.trees.j48.SplitCriterion
weka.classifiers.trees.j48.EntropyBasedSplitCrit
weka.classifiers.trees.j48.GainRatioSplitCrit
- All Implemented Interfaces:
Serializable,RevisionHandler
Class for computing the gain ratio for a given distribution.
- Version:
- $Revision: 10169 $
- Author:
- Eibe Frank (eibe@cs.waikato.ac.nz)
- See Also:
-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionReturns the revision string.final doublesplitCritValue(Distribution bags) This method is a straightforward implementation of the gain ratio criterion for the given distribution.final doublesplitCritValue(Distribution bags, double totalnoInst, double numerator) This method computes the gain ratio in the same way C4.5 does.Methods inherited from class weka.classifiers.trees.j48.EntropyBasedSplitCrit
lnFunc, newEnt, oldEnt, splitEntMethods inherited from class weka.classifiers.trees.j48.SplitCriterion
splitCritValue, splitCritValue, splitCritValue
-
Constructor Details
-
GainRatioSplitCrit
public GainRatioSplitCrit()
-
-
Method Details
-
splitCritValue
This method is a straightforward implementation of the gain ratio criterion for the given distribution.- Overrides:
splitCritValuein classSplitCriterion- Returns:
- value of splitting criterion. 0 by default
-
splitCritValue
This method computes the gain ratio in the same way C4.5 does.- Parameters:
bags- the distributiontotalnoInst- the weight of ALL instancesnumerator- the info gain
-
getRevision
Returns the revision string.- Returns:
- the revision
-