Examples with ParameterSpace org.dkpro.lab.task.ParameterSpace used on opensource projects

Example 41 with ParameterSpace

use of org.dkpro.lab.task.ParameterSpace in project dkpro-tc by dkpro.

the class XgboostUnit method getParameterSpace.

public static ParameterSpace getParameterSpace() throws ResourceInitializationException {
    // configure training and test data reader dimension
    Map<String, Object> dimReaders = new HashMap<String, Object>();
    CollectionReaderDescription readerTrain = CollectionReaderFactory.createReaderDescription(TeiReader.class, TeiReader.PARAM_LANGUAGE, "en", TeiReader.PARAM_SOURCE_LOCATION, corpusFilePathTrain, TeiReader.PARAM_PATTERNS, new String[] { INCLUDE_PREFIX + "*.xml", INCLUDE_PREFIX + "*.xml.gz" });
    dimReaders.put(DIM_READER_TRAIN, readerTrain);
    CollectionReaderDescription readerTest = CollectionReaderFactory.createReaderDescription(TeiReader.class, TeiReader.PARAM_LANGUAGE, "en", TeiReader.PARAM_SOURCE_LOCATION, corpusFilePathTrain, TeiReader.PARAM_PATTERNS, new String[] { "*.xml", "*.xml.gz" });
    dimReaders.put(DIM_READER_TEST, readerTest);
    Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(Constants.DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(TokenRatioPerDocument.class), TcFeatureFactory.create(CharacterNGram.class, CharacterNGram.PARAM_NGRAM_LOWER_CASE, false, CharacterNGram.PARAM_NGRAM_USE_TOP_K, 50)));
    Map<String, Object> xgboostConfig = new HashMap<>();
    xgboostConfig.put(DIM_CLASSIFICATION_ARGS, new Object[] { new XgboostAdapter(), "objective=multi:softmax" });
    xgboostConfig.put(DIM_DATA_WRITER, new XgboostAdapter().getDataWriterClass().getName());
    xgboostConfig.put(DIM_FEATURE_USE_SPARSE, new XgboostAdapter().useSparseFeatures());
    Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", xgboostConfig);
    ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(DIM_LEARNING_MODE, LM_SINGLE_LABEL), Dimension.create(DIM_FEATURE_MODE, FM_UNIT), dimFeatureSets, mlas);
    return pSpace;
}

Example 42 with ParameterSpace

use of org.dkpro.lab.task.ParameterSpace in project dkpro-tc by dkpro.

the class WekaSaveAndLoadModelDocumentSingleLabelTest method documentRoundTripWekaSingleLabel.

@Test
public void documentRoundTripWekaSingleLabel() throws Exception {
    DemoUtils.setDkproHome(WekaSaveAndLoadModelDocumentSingleLabelTest.class.getSimpleName());
    File modelFolder = folder.newFolder();
    ParameterSpace docParamSpace = documentGetParameterSpaceSingleLabel();
    documentWriteModel(docParamSpace, modelFolder);
    documentLoadModelSingleLabel(modelFolder);
    // verify created files
    File classifierFile = new File(modelFolder.getAbsolutePath() + "/" + MODEL_CLASSIFIER);
    assertTrue(classifierFile.exists());
    File metaOverride = new File(modelFolder.getAbsolutePath() + "/" + META_COLLECTOR_OVERRIDE);
    assertTrue(metaOverride.exists());
    File extractorOverride = new File(modelFolder.getAbsolutePath() + "/" + META_EXTRACTOR_OVERRIDE);
    assertTrue(extractorOverride.exists());
    File modelMetaFile = new File(modelFolder.getAbsolutePath() + "/" + MODEL_META);
    assertTrue(modelMetaFile.exists());
    File featureMode = new File(modelFolder.getAbsolutePath() + "/" + MODEL_FEATURE_MODE);
    assertTrue(featureMode.exists());
    File learningMode = new File(modelFolder.getAbsolutePath() + "/" + MODEL_LEARNING_MODE);
    assertTrue(learningMode.exists());
    File bipartitionThreshold = new File(modelFolder.getAbsolutePath() + "/" + MODEL_BIPARTITION_THRESHOLD);
    assertTrue(bipartitionThreshold.exists());
    modelFolder.deleteOnExit();
}

Example 43 with ParameterSpace

use of org.dkpro.lab.task.ParameterSpace in project dkpro-tc by dkpro.

the class WekaSaveAndLoadModelDocumentMultiLabelTest method documentGetParameterSpaceMultiLabel.

private ParameterSpace documentGetParameterSpaceMultiLabel() throws ResourceInitializationException {
    Map<String, Object> dimReaders = new HashMap<String, Object>();
    CollectionReaderDescription readerTrain = CollectionReaderFactory.createReaderDescription(ReutersCorpusReader.class, ReutersCorpusReader.PARAM_SOURCE_LOCATION, documentTrainFolderReuters, ReutersCorpusReader.PARAM_GOLD_LABEL_FILE, documentGoldLabelsReuters, ReutersCorpusReader.PARAM_LANGUAGE, "en", ReutersCorpusReader.PARAM_PATTERNS, ReutersCorpusReader.INCLUDE_PREFIX + "*.txt");
    dimReaders.put(DIM_READER_TRAIN, readerTrain);
    Map<String, Object> wekaConfig = new HashMap<>();
    wekaConfig.put(DIM_CLASSIFICATION_ARGS, new Object[] { new MekaAdapter(), MULAN.class.getName(), "-S", "RAkEL2", "-W", RandomForest.class.getName() });
    wekaConfig.put(DIM_DATA_WRITER, new MekaAdapter().getDataWriterClass().getName());
    wekaConfig.put(DIM_FEATURE_USE_SPARSE, new MekaAdapter().useSparseFeatures());
    Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", wekaConfig);
    Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(WordNGram.class, WordNGram.PARAM_NGRAM_USE_TOP_K, 50, WordNGram.PARAM_NGRAM_MIN_N, 1, WordNGram.PARAM_NGRAM_MAX_N, 3), TcFeatureFactory.create(TokenRatioPerDocument.class)));
    ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(DIM_LEARNING_MODE, LM_MULTI_LABEL), Dimension.create(DIM_FEATURE_MODE, FM_DOCUMENT), dimFeatureSets, Dimension.create(DIM_BIPARTITION_THRESHOLD, "0.5"), mlas);
    return pSpace;
}

Example 44 with ParameterSpace

use of org.dkpro.lab.task.ParameterSpace in project dkpro-tc by dkpro.

the class WekaSaveAndLoadModelDocumentRegression method regressionGetParameterSpace.

private ParameterSpace regressionGetParameterSpace() throws Exception {
    Map<String, Object> dimReaders = new HashMap<String, Object>();
    CollectionReaderDescription readerTrain = CollectionReaderFactory.createReaderDescription(LinewiseTextOutcomeReader.class, LinewiseTextOutcomeReader.PARAM_OUTCOME_INDEX, 0, LinewiseTextOutcomeReader.PARAM_TEXT_INDEX, 1, LinewiseTextOutcomeReader.PARAM_SOURCE_LOCATION, "src/main/resources/data/essays/train/essay_train.txt", LinewiseTextOutcomeReader.PARAM_LANGUAGE, "en");
    dimReaders.put(DIM_READER_TRAIN, readerTrain);
    @SuppressWarnings("unchecked") Dimension<List<Object>> dimClassificationArgs = Dimension.create(DIM_CLASSIFICATION_ARGS, Arrays.asList(new Object[] { new WekaAdapter(), LinearRegression.class.getName() }));
    Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(TokenRatioPerDocument.class), TcFeatureFactory.create(SentenceRatioPerDocument.class)));
    ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(DIM_LEARNING_MODE, LM_REGRESSION), Dimension.create(DIM_FEATURE_MODE, FM_DOCUMENT), dimFeatureSets, dimClassificationArgs);
    return pSpace;
}

Example 45 with ParameterSpace

use of org.dkpro.lab.task.ParameterSpace in project dkpro-tc by dkpro.

the class WekaSaveAndLoadModelDocumentRegression method documentRoundTripWekaRegression.

/**
 * This test case trains a regression model on scored essay texts
 */
@Test
public void documentRoundTripWekaRegression() throws Exception {
    DemoUtils.setDkproHome(WekaSaveAndLoadModelDocumentRegression.class.getSimpleName());
    File modelFolder = folder.newFolder();
    ParameterSpace paramSpace = regressionGetParameterSpace();
    regressionExecuteSaveModel(paramSpace, modelFolder);
    regressionLoadModel(modelFolder);
    File metaOverride = new File(modelFolder.getAbsolutePath() + "/" + META_COLLECTOR_OVERRIDE);
    assertTrue(metaOverride.exists());
    File extractorOverride = new File(modelFolder.getAbsolutePath() + "/" + META_EXTRACTOR_OVERRIDE);
    assertTrue(extractorOverride.exists());
    // verify that all expected files have been created
    File classifierFile = new File(modelFolder.getAbsolutePath() + "/" + MODEL_CLASSIFIER);
    assertTrue(classifierFile.exists());
    File modelMetaFile = new File(modelFolder.getAbsolutePath() + "/" + MODEL_META);
    assertTrue(modelMetaFile.exists());
    File featureMode = new File(modelFolder.getAbsolutePath() + "/" + MODEL_FEATURE_MODE);
    assertTrue(featureMode.exists());
    File learningMode = new File(modelFolder.getAbsolutePath() + "/" + MODEL_LEARNING_MODE);
    assertTrue(learningMode.exists());
    File bipartitionThreshold = new File(modelFolder.getAbsolutePath() + "/" + MODEL_BIPARTITION_THRESHOLD);
    assertTrue(bipartitionThreshold.exists());
    modelFolder.deleteOnExit();
}