eu.openminted.uc.socialsciences.variabledetection.features

Class LuceneLemmaNGram

java.lang.Object

org.apache.uima.resource.Resource_ImplBase

org.apache.uima.fit.component.Resource_ImplBase

org.dkpro.tc.api.features.FeatureExtractorResource_ImplBase

org.dkpro.tc.features.ngram.base.NGramFeatureExtractorBase

org.dkpro.tc.features.ngram.base.LuceneFeatureExtractorBase

org.dkpro.tc.features.ngram.LuceneNGram

eu.openminted.uc.socialsciences.variabledetection.features.LuceneLemmaNGram

All Implemented Interfaces:

org.apache.uima.fit.component.ExternalResourceAware, org.apache.uima.resource.Resource, org.dkpro.tc.api.features.FeatureExtractor, org.dkpro.tc.api.features.meta.MetaDependent

public class LuceneLemmaNGram
extends org.dkpro.tc.features.ngram.LuceneNGram
implements org.dkpro.tc.api.features.FeatureExtractor

Extracts token n-grams within the given text classification unit

Field Summary

Fields inherited from class org.dkpro.tc.features.ngram.base.LuceneFeatureExtractorBase

LUCENE_NGRAM_FIELD, luceneDir, PARAM_SOURCE_LOCATION

Fields inherited from class org.dkpro.tc.features.ngram.base.NGramFeatureExtractorBase

dfStore, filterPartialStopwordMatches, ngramFreqThreshold, ngramLowerCase, ngramMaxN, ngramMinN, ngramStopwordsFile, ngramUseTopK, PARAM_FILTER_PARTIAL_STOPWORD_MATCHES, PARAM_NGRAM_FREQ_THRESHOLD, PARAM_NGRAM_LOWER_CASE, PARAM_NGRAM_MAX_N, PARAM_NGRAM_MIN_N, PARAM_NGRAM_STOPWORDS_FILE, PARAM_NGRAM_USE_TOP_K, PARAM_TF_IDF_CALCULATION, prefix, stopwords, tfIdfCalculation, topKSet

Fields inherited from class org.dkpro.tc.api.features.FeatureExtractorResource_ImplBase

featureExtractorName, PARAM_UNIQUE_EXTRACTOR_NAME, requiredTypes

Fields inherited from interface org.apache.uima.resource.Resource

PARAM_AGGREGATE_SOFA_MAPPINGS, PARAM_CONFIG_MANAGER, PARAM_CONFIG_PARAM_SETTINGS, PARAM_EXTERNAL_OVERRIDE_SETTINGS, PARAM_PERFORMANCE_TUNING_SETTINGS, PARAM_RESOURCE_MANAGER, PARAM_UIMA_CONTEXT

Constructor Summary

Constructors

Constructor and Description
LuceneLemmaNGram()

Method Summary

Modifier and Type	Method and Description
Set<org.dkpro.tc.api.features.Feature>	extract(org.apache.uima.jcas.JCas jcas, org.dkpro.tc.api.type.TextClassificationTarget target)
protected String	getFeaturePrefix()

Methods inherited from class org.dkpro.tc.features.ngram.LuceneNGram

getFieldName, getMetaCollectorClasses, getTopN, logSelectionProcess

Methods inherited from class org.dkpro.tc.features.ngram.base.LuceneFeatureExtractorBase

getTopNgrams, passesScreening

Methods inherited from class org.dkpro.tc.features.ngram.base.NGramFeatureExtractorBase

initialize

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

afterResourcesInitialized, getLogger, getResourceName

Methods inherited from class org.apache.uima.resource.Resource_ImplBase

destroy, getCasManager, getMetaData, getRelativePathResolver, getResourceManager, getUimaContext, getUimaContextAdmin, setLogger, setMetaData

Methods inherited from class java.lang.Object

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

Constructor Detail

LuceneLemmaNGram

public LuceneLemmaNGram()

Method Detail

extract

public Set<org.dkpro.tc.api.features.Feature> extract(org.apache.uima.jcas.JCas jcas,
                                                      org.dkpro.tc.api.type.TextClassificationTarget target)
                                               throws org.dkpro.tc.api.exception.TextClassificationException

Specified by:

extract in interface org.dkpro.tc.api.features.FeatureExtractor

Overrides:

extract in class org.dkpro.tc.features.ngram.LuceneNGram

Throws:

org.dkpro.tc.api.exception.TextClassificationException

getFeaturePrefix

protected String getFeaturePrefix()

Overrides:

getFeaturePrefix in class org.dkpro.tc.features.ngram.LuceneNGram