eu.openminted.uc.socialsciences.variabledetection.pipelines

Class DetectionOnlyTrainingPipeline

java.lang.Object

eu.openminted.uc.socialsciences.variabledetection.pipelines.AbstractPipeline

eu.openminted.uc.socialsciences.variabledetection.pipelines.DetectionOnlyTrainingPipeline

All Implemented Interfaces:

org.dkpro.tc.core.Constants

public class DetectionOnlyTrainingPipeline
extends AbstractPipeline
implements org.dkpro.tc.core.Constants

Pipeline for training a machine learning model using the training data and saving the model. The pipeline uses several textual features to train a model using DKPro-TC.

Field Summary

Fields

Modifier and Type	Field and Description
static File	modelPath

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

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_BASELINE_CLASSIFICATION_ARGS, DIM_BASELINE_FEATURE_SET, DIM_BASELINE_PIPELINE_PARAMS, DIM_BIPARTITION_THRESHOLD, DIM_CLASSIFICATION_ARGS, DIM_CROSS_VALIDATION_MANUAL_FOLDS, DIM_DEVELOPER_MODE, DIM_FEATURE_FILTERS, DIM_FEATURE_MODE, DIM_FEATURE_SEARCHER_ARGS, DIM_FEATURE_SET, DIM_FEATURE_STORE, DIM_FILES_ROOT, DIM_FILES_TRAINING, DIM_FILES_VALIDATION, DIM_LABEL_TRANSFORMATION_METHOD, DIM_LEARNING_MODE, DIM_NUM_LABELS_TO_KEEP, DIM_READER_TEST, DIM_READER_TRAIN, DIM_RECORD_CONTEXT, DISCRIMINATORS_KEY_TEMP, EMPTY_PREDICTION, EVAL_FILE_NAME, FILENAME_FEATURES, FM_DOCUMENT, FM_PAIR, FM_SEQUENCE, FM_UNIT, HOMOGENIZING_MISSING_VALUE, ID_CONTEXT_KEY, ID_DETAILED_OUTCOME_KEY, ID_FEATURE_NAME, ID_HOMOGENIZED_OUTCOME_KEY, 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, PART_ONE, PART_TWO, PR_CURVE_KEY, PREDICTION_CLASS_LABEL_NAME, PREDICTION_MAP_FILE_NAME, SERIALIZED_ID_OUTCOME_KEY, STATISTICS_REPORT_FILENAME, STATISTICS_REPORT_TEST_TASK_FILENAME, SUFFIX_CSV, SUFFIX_EXCEL, SUFFIX_LATEX, TC_OUTCOME_DUMMY_VALUE, TEST_TASK_INPUT_KEY_TEST_DATA, TEST_TASK_INPUT_KEY_TRAINING_DATA, TEST_TASK_OUTPUT_KEY, UNKNOWN_OUTCOME

Constructor Summary

Constructors

Constructor and Description
DetectionOnlyTrainingPipeline()

Method Summary

Modifier and Type	Method and Description
static org.dkpro.lab.task.ParameterSpace	getParameterSpace() Creates the the parameter space (ParameterSpace) for the experiment.
protected org.apache.uima.analysis_engine.AnalysisEngineDescription	getPreprocessing()
static void	main(String[] args) Starts the experiment.
protected void	runTrainSaveModel(org.dkpro.lab.task.ParameterSpace pSpace)

Methods inherited from class eu.openminted.uc.socialsciences.variabledetection.pipelines.AbstractPipeline

assertDkproHomeVariableIsSet

Methods inherited from class java.lang.Object

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

Field Detail

modelPath

public static final File modelPath

Constructor Detail

DetectionOnlyTrainingPipeline

public DetectionOnlyTrainingPipeline()

Method Detail

main

public static void main(String[] args)
                 throws Exception

Starts the experiment.

Throws:

Exception

getParameterSpace

public static org.dkpro.lab.task.ParameterSpace getParameterSpace()
                                                           throws org.apache.uima.resource.ResourceInitializationException

Creates the the parameter space (ParameterSpace) for the experiment. The parameter space describes the experiment input(s), classifier(s), feature extractor(s), and feature selector(s).

Throws:

org.apache.uima.resource.ResourceInitializationException

runTrainSaveModel

protected void runTrainSaveModel(org.dkpro.lab.task.ParameterSpace pSpace)
                          throws Exception

Throws:

Exception

getPreprocessing

protected org.apache.uima.analysis_engine.AnalysisEngineDescription getPreprocessing()
                                                                              throws org.apache.uima.resource.ResourceInitializationException

Throws:

org.apache.uima.resource.ResourceInitializationException