org.apache.ctakes.assertion.medfacts.cleartk

Class AssertionCleartkAnalysisEngine

java.lang.Object

org.apache.uima.analysis_component.AnalysisComponent_ImplBase

org.apache.uima.analysis_component.Annotator_ImplBase

org.apache.uima.analysis_component.JCasAnnotator_ImplBase

org.apache.uima.fit.component.JCasAnnotator_ImplBase

org.cleartk.ml.CleartkAnnotator<String>

org.apache.ctakes.assertion.medfacts.cleartk.AssertionCleartkAnalysisEngine

All Implemented Interfaces:

org.apache.uima.analysis_component.AnalysisComponent, org.apache.uima.fit.factory.initializable.Initializable

Direct Known Subclasses:

ConditionalCleartkAnalysisEngine, GenericCleartkAnalysisEngine, HistoryCleartkAnalysisEngine, PolarityCleartkAnalysisEngine, SubjectCleartkAnalysisEngine, UncertaintyCleartkAnalysisEngine

public abstract class AssertionCleartkAnalysisEngine
extends org.cleartk.ml.CleartkAnnotator<String>

Author:

swu

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	AssertionCleartkAnalysisEngine.FEATURE_CONFIG

Field Summary

Fields

Modifier and Type	Field and Description
protected static Random	coin
protected List<org.cleartk.ml.feature.extractor.CleartkExtractor<IdentifiedAnnotation,BaseToken>>	contextFeatureExtractors
protected org.cleartk.ml.feature.extractor.CleartkExtractor<IdentifiedAnnotation,BaseToken>	cuePhraseInWindowExtractor
protected List<org.cleartk.ml.feature.extractor.FeatureExtractor1<IdentifiedAnnotation>>	entityFeatureExtractors
protected List<org.cleartk.ml.feature.extractor.FeatureExtractor1<IdentifiedAnnotation>>	entityTreeExtractors
protected AssertionCleartkAnalysisEngine.FEATURE_CONFIG	featConfig
protected static String	FEATURE_SELECTION_NAME
protected List<org.cleartk.ml.feature.function.FeatureFunctionExtractor<IdentifiedAnnotation>>	featureFunctionExtractors
protected FeatureSelection<String>	featureSelection
protected Float	featureSelectionThreshold
protected URI	featureSelectionURI
protected FedaFeatureFunction	ffDomainAdaptor
static String	FILE_TO_DOMAIN_MAP
protected String	fileDomainMap
protected Map<String,String>	fileToDomain
protected String	goldViewName
protected String	lastLabel
static String	PARAM_FEATURE_CONFIG
static String	PARAM_FEATURE_SELECTION_THRESHOLD
static String	PARAM_FEATURE_SELECTION_URI
static String	PARAM_GOLD_VIEW_NAME
static String	PARAM_PORTION_OF_DATA_TO_USE
static String	PARAM_PRINT_ERRORS
static String	PARAM_PROBABILITY_OF_KEEPING_DEFAULT_EXAMPLE
protected double	portionOfDataToUse
protected double	probabilityOfKeepingADefaultExample
static int	relationId
protected List<org.cleartk.ml.feature.extractor.CleartkExtractor<IdentifiedAnnotation,BaseToken>>	tokenCleartkExtractors
protected List<org.cleartk.ml.feature.extractor.CleartkExtractor<IdentifiedAnnotation,BaseToken>>	tokenContextFeatureExtractors

Fields inherited from class org.cleartk.ml.CleartkAnnotator

classifier, dataWriter, PARAM_CLASSIFIER_FACTORY_CLASS_NAME, PARAM_DATA_WRITER_FACTORY_CLASS_NAME, PARAM_IS_TRAINING

Constructor Summary

Constructors

Constructor and Description
AssertionCleartkAnalysisEngine()

Method Summary

Modifier and Type	Method and Description
static org.apache.uima.analysis_engine.AnalysisEngineDescription	getDescription(Object... additionalConfiguration)
Map<String,String>	getTrainFileToDomain()
void	initialize(org.apache.uima.UimaContext context)
protected abstract void	initializeFeatureSelection()
static String	normalizeToDomain(String dir) Looks in the domain string (path) for meaningful corpus names
void	process(org.apache.uima.jcas.JCas jCas)
abstract void	setClassLabel(IdentifiedAnnotation entityMention, org.cleartk.ml.Instance<String> instance)
void	setTrainFileToDomain(Map<String,String> trainFileToDomain)

Methods inherited from class org.cleartk.ml.CleartkAnnotator

collectionProcessComplete, isTraining

Methods inherited from class org.apache.uima.fit.component.JCasAnnotator_ImplBase

getLogger

Methods inherited from class org.apache.uima.analysis_component.JCasAnnotator_ImplBase

getRequiredCasInterface, process

Methods inherited from class org.apache.uima.analysis_component.Annotator_ImplBase

getCasInstancesRequired, hasNext, next

Methods inherited from class org.apache.uima.analysis_component.AnalysisComponent_ImplBase

batchProcessComplete, destroy, getContext, getResultSpecification, reconfigure, setResultSpecification

Methods inherited from class java.lang.Object

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

Field Detail

PARAM_GOLD_VIEW_NAME

public static final String PARAM_GOLD_VIEW_NAME

See Also:

Constant Field Values

relationId

public static int relationId

FILE_TO_DOMAIN_MAP

public static final String FILE_TO_DOMAIN_MAP

See Also:

Constant Field Values

goldViewName

protected String goldViewName

PARAM_PRINT_ERRORS

public static final String PARAM_PRINT_ERRORS

See Also:

Constant Field Values

PARAM_PROBABILITY_OF_KEEPING_DEFAULT_EXAMPLE

public static final String PARAM_PROBABILITY_OF_KEEPING_DEFAULT_EXAMPLE

See Also:

Constant Field Values

probabilityOfKeepingADefaultExample

protected double probabilityOfKeepingADefaultExample

PARAM_PORTION_OF_DATA_TO_USE

public static final String PARAM_PORTION_OF_DATA_TO_USE

See Also:

Constant Field Values

portionOfDataToUse

protected double portionOfDataToUse

PARAM_FEATURE_SELECTION_THRESHOLD

public static final String PARAM_FEATURE_SELECTION_THRESHOLD

See Also:

Constant Field Values

featureSelectionThreshold

protected Float featureSelectionThreshold

PARAM_FEATURE_CONFIG

public static final String PARAM_FEATURE_CONFIG

See Also:

Constant Field Values

featConfig

protected AssertionCleartkAnalysisEngine.FEATURE_CONFIG featConfig

PARAM_FEATURE_SELECTION_URI

public static final String PARAM_FEATURE_SELECTION_URI

See Also:

Constant Field Values

featureSelectionURI

protected URI featureSelectionURI

coin

protected static Random coin

FEATURE_SELECTION_NAME

protected static final String FEATURE_SELECTION_NAME

See Also:

Constant Field Values

fileDomainMap

protected String fileDomainMap

fileToDomain

protected Map<String,String> fileToDomain

lastLabel

protected String lastLabel

contextFeatureExtractors

protected List<org.cleartk.ml.feature.extractor.CleartkExtractor<IdentifiedAnnotation,BaseToken>> contextFeatureExtractors

tokenContextFeatureExtractors

protected List<org.cleartk.ml.feature.extractor.CleartkExtractor<IdentifiedAnnotation,BaseToken>> tokenContextFeatureExtractors

tokenCleartkExtractors

protected List<org.cleartk.ml.feature.extractor.CleartkExtractor<IdentifiedAnnotation,BaseToken>> tokenCleartkExtractors

entityFeatureExtractors

protected List<org.cleartk.ml.feature.extractor.FeatureExtractor1<IdentifiedAnnotation>> entityFeatureExtractors

entityTreeExtractors

protected List<org.cleartk.ml.feature.extractor.FeatureExtractor1<IdentifiedAnnotation>> entityTreeExtractors

cuePhraseInWindowExtractor

protected org.cleartk.ml.feature.extractor.CleartkExtractor<IdentifiedAnnotation,BaseToken> cuePhraseInWindowExtractor

featureFunctionExtractors

protected List<org.cleartk.ml.feature.function.FeatureFunctionExtractor<IdentifiedAnnotation>> featureFunctionExtractors

ffDomainAdaptor

protected FedaFeatureFunction ffDomainAdaptor

featureSelection

protected FeatureSelection<String> featureSelection

Constructor Detail

AssertionCleartkAnalysisEngine

public AssertionCleartkAnalysisEngine()

Method Detail

setClassLabel

public abstract void setClassLabel(IdentifiedAnnotation entityMention,
                                   org.cleartk.ml.Instance<String> instance)
                            throws org.apache.uima.analysis_engine.AnalysisEngineProcessException

Throws:

org.apache.uima.analysis_engine.AnalysisEngineProcessException

initializeFeatureSelection

protected abstract void initializeFeatureSelection()
                                            throws org.apache.uima.resource.ResourceInitializationException

Throws:

org.apache.uima.resource.ResourceInitializationException

initialize

public void initialize(org.apache.uima.UimaContext context)
                throws org.apache.uima.resource.ResourceInitializationException

Specified by:

initialize in interface org.apache.uima.analysis_component.AnalysisComponent

Specified by:

initialize in interface org.apache.uima.fit.factory.initializable.Initializable

Overrides:

initialize in class org.cleartk.ml.CleartkAnnotator<String>

Throws:

org.apache.uima.resource.ResourceInitializationException

process

public void process(org.apache.uima.jcas.JCas jCas)
             throws org.apache.uima.analysis_engine.AnalysisEngineProcessException

Specified by:

process in class org.apache.uima.analysis_component.JCasAnnotator_ImplBase

Throws:

org.apache.uima.analysis_engine.AnalysisEngineProcessException

getDescription

public static org.apache.uima.analysis_engine.AnalysisEngineDescription getDescription(Object... additionalConfiguration)
                                                                                throws org.apache.uima.resource.ResourceInitializationException

Throws:

org.apache.uima.resource.ResourceInitializationException

getTrainFileToDomain

public Map<String,String> getTrainFileToDomain()

setTrainFileToDomain

public void setTrainFileToDomain(Map<String,String> trainFileToDomain)

normalizeToDomain

public static String normalizeToDomain(String dir)

Looks in the domain string (path) for meaningful corpus names

Parameters:

dir -

Returns: