public class LuceneNGramPMetaCollector extends LucenePMetaCollectorBase
| Modifier and Type | Field and Description |
|---|---|
protected boolean |
filterPartialStopwordMatches |
protected boolean |
ngramLowerCase |
protected int |
ngramMaxN |
protected int |
ngramMinN |
protected String |
ngramStopwordsFile |
protected int |
ngramView1MaxN |
protected int |
ngramView1MinN |
protected int |
ngramView2MaxN |
protected int |
ngramView2MinN |
protected Set<String> |
stopwords |
currentDocument, fieldType, LUCENE_DIR, LUCENE_ID_FIELD, PARAM_TARGET_LOCATIONfeatureExtractorName, PARAM_UNIQUE_EXTRACTOR_NAMEBASELINE_MAJORITIY_ID_OUTCOME_KEY, BASELINE_RANDOM_ID_OUTCOME_KEY, CLASS_ATTRIBUTE_NAME, CLASS_ATTRIBUTE_PREFIX, CM_ACTUAL, CM_PREDICTED, CONFUSIONMATRIX_KEY, DIM_APPLY_FEATURE_SELECTION, DIM_APPLY_INSTANCE_WEIGHTING, DIM_ATTRIBUTE_EVALUATOR_ARGS, DIM_BIPARTITION_THRESHOLD, DIM_CLASSIFICATION_ARGS, DIM_CROSS_VALIDATION_MANUAL_FOLDS, DIM_DATA_WRITER, DIM_DEVELOPER_MODE, DIM_ENFORCE_MATCHING_FEATURES_DURING_TESTING, DIM_FEATURE_FILTERS, DIM_FEATURE_MODE, DIM_FEATURE_SEARCHER_ARGS, DIM_FEATURE_SET, DIM_FEATURE_USE_SPARSE, DIM_FILES_ROOT, DIM_FILES_TRAINING, DIM_FILES_VALIDATION, DIM_LABEL_TRANSFORMATION_METHOD, DIM_LEARNING_MODE, DIM_MLA_CONFIGURATIONS, DIM_NUM_LABELS_TO_KEEP, DIM_READER_TEST, DIM_READER_TRAIN, DIM_READERS, DIM_RECORD_CONTEXT, DIM_SKIP_SANITY_CHECKS, EMPTY_PREDICTION, EVAL_FILE_NAME, EVAL_FILE_NAME_PER_FOLD, FILE_COMBINED_BASELINE_MAJORITY_OUTCOME_KEY, FILE_COMBINED_BASELINE_RANDOM_OUTCOME_KEY, FILE_COMBINED_ID_OUTCOME_KEY, FILE_CONFUSION_MATRIX, FILE_SCORE_PER_CATEGORY, FILENAME_DATA_IN_CLASSIFIER_FORMAT, FILENAME_DOCUMENT_META_DATA_LOG, FILENAME_FEATURES, FILENAME_FEATURES_DESCRIPTION, FILENAME_OUTCOMES, FILENAME_PREDICTIONS, FM_DOCUMENT, FM_PAIR, FM_SEQUENCE, FM_UNIT, GENERIC_FEATURE_FILE, ID_CONTEXT_KEY, ID_DETAILED_OUTCOME_KEY, ID_FEATURE_NAME, ID_OUTCOME_KEY, INITIAL_VIEW, LEAVE_ONE_OUT, LM_MULTI_LABEL, LM_REGRESSION, LM_SINGLE_LABEL, META_COLLECTOR_OVERRIDE, META_EXTRACTOR_OVERRIDE, MODEL_BIPARTITION_THRESHOLD, MODEL_CLASS_LABELS, MODEL_CLASSIFIER, MODEL_FEATURE_CLASS_FOLDER, MODEL_FEATURE_EXTRACTOR_CONFIGURATION, MODEL_FEATURE_MODE, MODEL_FEATURE_NAMES, MODEL_FEATURE_NAMES_SERIALIZED, MODEL_LEARNING_MODE, MODEL_META, MODEL_TC_VERSION, NGRAM_GLUE, OUTCOMES_INPUT_KEY, PART_ONE, PART_TWO, PR_CURVE_KEY, PREDICTION_CLASS_LABEL_NAME, PREDICTION_MAP_FILE_NAME, STATISTICS_REPORT_FILENAME, STATISTICS_REPORT_TEST_TASK_FILENAME, SUFFIX_CSV, SUFFIX_EXCEL, SUFFIX_LATEX, TC_OUTCOME_DUMMY_VALUE, TC_TASK_TYPE, TEST_TASK_INPUT_KEY_TEST_DATA, TEST_TASK_INPUT_KEY_TRAINING_DATA, TEST_TASK_OUTPUT_KEY, TRAIN_OUTPUT, UNKNOWN_OUTCOME| Constructor and Description |
|---|
LuceneNGramPMetaCollector() |
| Modifier and Type | Method and Description |
|---|---|
protected String |
getFieldName() |
protected String |
getFieldNameView1() |
protected String |
getFieldNameView2() |
protected de.tudarmstadt.ukp.dkpro.core.api.frequency.util.FrequencyDistribution<String> |
getNgramsFD(org.apache.uima.jcas.JCas jcas)
This is an artifact to be merged with
getNgramsFD(List<JCas> jcases) when pair FEs
are ready. |
protected de.tudarmstadt.ukp.dkpro.core.api.frequency.util.FrequencyDistribution<String> |
getNgramsFD(List<org.apache.uima.jcas.JCas> jcases) |
protected de.tudarmstadt.ukp.dkpro.core.api.frequency.util.FrequencyDistribution<String> |
getNgramsFDView1(org.apache.uima.jcas.JCas view1,
org.dkpro.tc.api.type.TextClassificationTarget aTarget) |
protected de.tudarmstadt.ukp.dkpro.core.api.frequency.util.FrequencyDistribution<String> |
getNgramsFDView2(org.apache.uima.jcas.JCas view2,
org.dkpro.tc.api.type.TextClassificationTarget aTarget) |
void |
initialize(org.apache.uima.UimaContext context) |
addField, processcollectionProcessComplete, getDocumentId, writeToIndexgetRequiredCasInterface, processgetCasInstancesRequired, hasNext, nextprotected int ngramView1MinN
protected int ngramView2MinN
protected int ngramMinN
protected int ngramView1MaxN
protected int ngramView2MaxN
protected int ngramMaxN
protected String ngramStopwordsFile
protected boolean filterPartialStopwordMatches
protected boolean ngramLowerCase
public void initialize(org.apache.uima.UimaContext context)
throws org.apache.uima.resource.ResourceInitializationException
initialize in interface org.apache.uima.analysis_component.AnalysisComponentinitialize in class LuceneMCorg.apache.uima.resource.ResourceInitializationExceptionprotected de.tudarmstadt.ukp.dkpro.core.api.frequency.util.FrequencyDistribution<String> getNgramsFD(List<org.apache.uima.jcas.JCas> jcases) throws org.dkpro.tc.api.exception.TextClassificationException
getNgramsFD in class LucenePMetaCollectorBaseorg.dkpro.tc.api.exception.TextClassificationExceptionprotected de.tudarmstadt.ukp.dkpro.core.api.frequency.util.FrequencyDistribution<String> getNgramsFD(org.apache.uima.jcas.JCas jcas) throws org.dkpro.tc.api.exception.TextClassificationException
getNgramsFD(List<JCas> jcases) when pair FEs
are ready.getNgramsFD in class LuceneMCorg.dkpro.tc.api.exception.TextClassificationExceptionprotected de.tudarmstadt.ukp.dkpro.core.api.frequency.util.FrequencyDistribution<String> getNgramsFDView1(org.apache.uima.jcas.JCas view1, org.dkpro.tc.api.type.TextClassificationTarget aTarget) throws org.dkpro.tc.api.exception.TextClassificationException
getNgramsFDView1 in class LucenePMetaCollectorBaseorg.dkpro.tc.api.exception.TextClassificationExceptionprotected de.tudarmstadt.ukp.dkpro.core.api.frequency.util.FrequencyDistribution<String> getNgramsFDView2(org.apache.uima.jcas.JCas view2, org.dkpro.tc.api.type.TextClassificationTarget aTarget) throws org.dkpro.tc.api.exception.TextClassificationException
getNgramsFDView2 in class LucenePMetaCollectorBaseorg.dkpro.tc.api.exception.TextClassificationExceptionprotected String getFieldName()
getFieldName in class LuceneMCprotected String getFieldNameView1()
getFieldNameView1 in class LucenePMetaCollectorBaseprotected String getFieldNameView2()
getFieldNameView2 in class LucenePMetaCollectorBaseCopyright © 2013–2018 Ubiquitous Knowledge Processing (UKP) Lab. All rights reserved.