org.apache.ctakes.ytex.svmlight

Class SVMLightParser

java.lang.Object

org.apache.ctakes.ytex.kernel.BaseClassifierEvaluationParser

org.apache.ctakes.ytex.libsvm.LibSVMParser

org.apache.ctakes.ytex.svmlight.SVMLightParser

All Implemented Interfaces:

ClassifierEvaluationParser

public class SVMLightParser
extends LibSVMParser

same as libsvm with following changes:

• parse output.txt - contains vcdim and number support vectors <

Nested Class Summary

Nested classes/interfaces inherited from class org.apache.ctakes.ytex.kernel.BaseClassifierEvaluationParser

BaseClassifierEvaluationParser.InstanceClassInfo

Nested classes/interfaces inherited from interface org.apache.ctakes.ytex.kernel.ClassifierEvaluationParser

ClassifierEvaluationParser.ParseOption

Field Summary

Fields

Modifier and Type	Field and Description
(package private) static java.util.regex.Pattern	psv
(package private) static java.util.regex.Pattern	pvc

Fields inherited from class org.apache.ctakes.ytex.libsvm.LibSVMParser

labelsPattern, pCost, pDegree, pGamma, pKernel, pWeight, totalSVPattern

Fields inherited from class org.apache.ctakes.ytex.kernel.BaseClassifierEvaluationParser

wsDotPattern, wsPattern

Fields inherited from interface org.apache.ctakes.ytex.kernel.ClassifierEvaluationParser

NO, YES

Constructor Summary

Constructors

Constructor and Description
SVMLightParser()

Method Summary

Methods

Modifier and Type	Method and Description
protected void	parsePredictions(java.lang.String predictionFile, java.lang.String instanceFile, java.util.Properties props, java.lang.String instanceIdFile, SVMClassifierEvaluation eval) Parse svm-classify input (instance file) and predictions (prediction file).
protected void	parseResults(java.io.File dataDir, java.io.File outputDir, java.lang.String model, java.lang.String predict, SVMClassifierEvaluation eval, java.util.Properties props) parse output.txt - contains vcdim and number support vectors
private void	parseTrainOutput(SVMClassifierEvaluation eval, java.lang.String trainOutputFile) Number of SV: 133 (including 0 at upper bound) L1 loss: loss=0.00000 Norm of weight vector: |w|=2.09380 Norm of longest example vector: |x|=16.91153 Estimated VCdim of classifier: VCdim<=684.90185
protected void	storeResults(java.io.File dataDir, java.util.Properties props, SVMClassifierEvaluation eval) store semi supervised results.

Methods inherited from class org.apache.ctakes.ytex.libsvm.LibSVMParser

initClassifierEval, parseClassIds, parseDirectory, parseModel, parseOptions

Methods inherited from class org.apache.ctakes.ytex.kernel.BaseClassifierEvaluationParser

checkFileRead, extractFirstToken, getClassifierEvaluationDao, getFileBaseName, initClassifierEvaluation, initClassifierEvaluationFromProperties, loadClassIdMap, loadClassInfo, loadInstanceClassInfo, loadProps, parseDoubleOption, parseInstanceIds, parseIntOption, setClassifierEvaluationDao, storeSemiSupervised, updateSemiSupervisedPredictions, updateSemiSupervisedPredictions

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

psv

static final java.util.regex.Pattern psv

pvc

static final java.util.regex.Pattern pvc

Constructor Detail

SVMLightParser

public SVMLightParser()

Method Detail

parsePredictions

protected void parsePredictions(java.lang.String predictionFile,
                    java.lang.String instanceFile,
                    java.util.Properties props,
                    java.lang.String instanceIdFile,
                    SVMClassifierEvaluation eval)
                         throws java.io.IOException

Parse svm-classify input (instance file) and predictions (prediction file). instance file has target class id and attributes for each instance. predict file has value less than or greater than 0 for each instance, corresponding to class ids -1 and +1.

Overrides:

parsePredictions in class LibSVMParser

Parameters:

predictionFile -

instanceFile -

instanceIdFile - instance ids corresponding to lines in input data file

Throws:

java.io.IOException

parseTrainOutput

private void parseTrainOutput(SVMClassifierEvaluation eval,
                    java.lang.String trainOutputFile)
                       throws java.io.IOException

 Number of SV: 133 (including 0 at upper bound)
 L1 loss: loss=0.00000
 Norm of weight vector: |w|=2.09380
 Norm of longest example vector: |x|=16.91153
 Estimated VCdim of classifier: VCdim<=684.90185
 

Parameters:

eval -

trainOutputFile -

Throws:

java.io.IOException

parseResults

protected void parseResults(java.io.File dataDir,
                java.io.File outputDir,
                java.lang.String model,
                java.lang.String predict,
                SVMClassifierEvaluation eval,
                java.util.Properties props)
                     throws java.io.IOException

parse output.txt - contains vcdim and number support vectors

Overrides:

parseResults in class LibSVMParser

Throws:

java.io.IOException

storeResults

protected void storeResults(java.io.File dataDir,
                java.util.Properties props,
                SVMClassifierEvaluation eval)

store semi supervised results.

Overrides:

storeResults in class LibSVMParser