org.dkpro.tc.ml.vowpalwabbit.serialization

Class VowpalWabbitLoadModelConnector

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.dkpro.tc.core.ml.ModelSerialization_ImplBase

org.dkpro.tc.ml.vowpalwabbit.serialization.VowpalWabbitLoadModelConnector

All Implemented Interfaces:

org.apache.uima.analysis_component.AnalysisComponent, Constants, ModelVersionIO, ConnectorConstants

public class VowpalWabbitLoadModelConnector
extends ModelSerialization_ImplBase

Field Summary

Fields

Modifier and Type	Field and Description
protected FeatureExtractorResource_ImplBase[]	featureExtractors
protected String	featureMode
protected Map<String,String>	integer2OutcomeMapping
protected String	learningMode
protected File	model
protected Map<String,String>	stringValue2IntegerMapping
protected File	tcModelLocation

Fields inherited from class org.dkpro.tc.core.ml.ModelSerialization_ImplBase

logger, outputDirectory, PARAM_OUTPUT_DIRECTORY

Fields inherited from interface org.dkpro.tc.core.task.uima.ConnectorConstants

PARAM_APPLY_WEIGHTING, PARAM_BIPARTITION_THRESHOLD, PARAM_DATA_WRITER_CLASS, PARAM_ENFORCE_MATCHING_FEATURES, PARAM_FEATURE_EXTRACTORS, PARAM_FEATURE_FILTERS, PARAM_FEATURE_MODE, PARAM_IS_TESTING, PARAM_LEARNING_MODE, PARAM_OUTCOMES, PARAM_REQUIRED_TYPES, PARAM_USE_SPARSE_FEATURES

Fields inherited from interface org.dkpro.tc.core.ml.ModelVersionIO

TCVERSION

Fields inherited from interface org.dkpro.tc.core.Constants

BASELINE_MAJORITIY_ID_OUTCOME_KEY, BASELINE_RANDOM_ID_OUTCOME_KEY, CLASS_ATTRIBUTE_NAME, CLASS_ATTRIBUTE_PREFIX, CM_ACTUAL, CM_PREDICTED, CONFIGURATION_DKPRO_LAB, 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_NUM_TRAINING_FOLDS, 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_CONFIGURATION_MAPPING, 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, MACHINE_LEARNING_BACKEND_NAME, 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, STATISTICS_REPORT_FILENAME, STATISTICS_REPORT_TEST_TASK_FILENAME, 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 Summary

Constructors

Constructor and Description
VowpalWabbitLoadModelConnector()

Method Summary

Modifier and Type	Method and Description
protected File	createInputFile(org.apache.uima.jcas.JCas aJCas, boolean isSequenceMod)
protected void	determineTheMaxStringsIntIdValue()
protected List<org.dkpro.tc.api.type.TextClassificationOutcome>	getOutcomeAnnotations(org.apache.uima.jcas.JCas aJCas)
void	initialize(org.apache.uima.UimaContext context)
protected boolean	isRegression()
protected boolean	isSequence()
protected Map<String,String>	loadMapping(File tcModelLocation, String key)
protected String	loadProperty(File file, String key)
protected String	mapStringValues(FeatureType featureType, String value)
void	process(org.apache.uima.jcas.JCas aJCas)
protected List<String>	runPrediction(File tempFile, boolean isSequence)

Methods inherited from class org.dkpro.tc.core.ml.ModelSerialization_ImplBase

initMachineLearningAdapter, loadTcVersionFromModel, verifyTcVersion

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, collectionProcessComplete, destroy, getContext, getResultSpecification, reconfigure, setResultSpecification

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.dkpro.tc.core.ml.ModelVersionIO

getCurrentTcVersionFromJar, getCurrentTcVersionFromWorkspace, writeCurrentVersionOfDKProTC, writeFeatureMode, writeLearningMode, writeModelParameter

Field Detail

tcModelLocation

protected File tcModelLocation

featureExtractors

protected FeatureExtractorResource_ImplBase[] featureExtractors

model

protected File model

featureMode

protected String featureMode

integer2OutcomeMapping

protected Map<String,String> integer2OutcomeMapping

stringValue2IntegerMapping

protected Map<String,String> stringValue2IntegerMapping

learningMode

protected String learningMode

Constructor Detail

VowpalWabbitLoadModelConnector

public VowpalWabbitLoadModelConnector()

Method Detail

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

Overrides:

initialize in class org.apache.uima.fit.component.JCasAnnotator_ImplBase

Throws:

org.apache.uima.resource.ResourceInitializationException

determineTheMaxStringsIntIdValue

protected void determineTheMaxStringsIntIdValue()

loadProperty

protected String loadProperty(File file,
                              String key)
                       throws IOException

Throws:

IOException

loadMapping

protected Map<String,String> loadMapping(File tcModelLocation,
                                         String key)
                                  throws IOException

Throws:

IOException

isRegression

protected boolean isRegression()

process

public void process(org.apache.uima.jcas.JCas aJCas)
             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

getOutcomeAnnotations

protected List<org.dkpro.tc.api.type.TextClassificationOutcome> getOutcomeAnnotations(org.apache.uima.jcas.JCas aJCas)

runPrediction

protected List<String> runPrediction(File tempFile,
                                     boolean isSequence)
                              throws org.apache.uima.analysis_engine.AnalysisEngineProcessException

Throws:

org.apache.uima.analysis_engine.AnalysisEngineProcessException

createInputFile

protected File createInputFile(org.apache.uima.jcas.JCas aJCas,
                               boolean isSequenceMod)
                        throws org.apache.uima.analysis_engine.AnalysisEngineProcessException

Throws:

org.apache.uima.analysis_engine.AnalysisEngineProcessException

mapStringValues

protected String mapStringValues(FeatureType featureType,
                                 String value)

isSequence

protected boolean isSequence()