Examples with WekaAdapter org.dkpro.tc.ml.weka.WekaAdapter used on opensource projects

Example 16 with WekaAdapter

use of org.dkpro.tc.ml.weka.WekaAdapter in project dkpro-tc by dkpro.

the class CRFSuiteSaveAndLoadModelTest method saveModel.

@Test
public void saveModel() throws Exception {
    Map<String, Object> config = new HashMap<>();
    config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new CrfSuiteAdapter(), CrfSuiteAdapter.ALGORITHM_ADAPTIVE_REGULARIZATION_OF_WEIGHT_VECTOR, "-p", "max_iterations=2" });
    config.put(DIM_DATA_WRITER, new CrfSuiteAdapter().getDataWriterClass().getName());
    config.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().useSparseFeatures());
    Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", config);
    File modelFolder = folder.newFolder();
    ParameterSpace pSpace = getParameterSpace(mlas);
    executeSaveModelIntoTemporyFolder(pSpace, modelFolder);
    File classifierFile = new File(modelFolder.getAbsolutePath() + "/" + MODEL_CLASSIFIER);
    assertTrue(classifierFile.exists());
    File parameterFile = new File(modelFolder.getAbsolutePath() + "/" + MODEL_FEATURE_EXTRACTOR_CONFIGURATION);
    assertTrue(parameterFile.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 tcversion = new File(modelFolder.getAbsolutePath() + "/" + MODEL_TC_VERSION);
    assertTrue(tcversion.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());
    modelFolder.deleteOnExit();
}

Example 17 with WekaAdapter

use of org.dkpro.tc.ml.weka.WekaAdapter in project dkpro-tc by dkpro.

the class CRFSuiteSaveAndLoadModelTest method loadModelArow.

@Test
public void loadModelArow() throws Exception {
    Map<String, Object> config = new HashMap<>();
    config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new CrfSuiteAdapter(), CrfSuiteAdapter.ALGORITHM_ADAPTIVE_REGULARIZATION_OF_WEIGHT_VECTOR, "-p", "max_iterations=2" });
    config.put(DIM_DATA_WRITER, new CrfSuiteAdapter().getDataWriterClass().getName());
    config.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().useSparseFeatures());
    Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", config);
    // create a model
    File modelFolder = folder.newFolder();
    ParameterSpace pSpace = getParameterSpace(mlas);
    executeSaveModelIntoTemporyFolder(pSpace, modelFolder);
    JCas jcas = JCasFactory.createJCas();
    jcas.setDocumentText("This is an example text. It has 2 sentences.");
    jcas.setDocumentLanguage("en");
    AnalysisEngine tokenizer = AnalysisEngineFactory.createEngine(BreakIteratorSegmenter.class);
    AnalysisEngine tcAnno = AnalysisEngineFactory.createEngine(TcAnnotator.class, TcAnnotator.PARAM_TC_MODEL_LOCATION, modelFolder.getAbsolutePath(), TcAnnotator.PARAM_NAME_SEQUENCE_ANNOTATION, Sentence.class.getName(), TcAnnotator.PARAM_NAME_UNIT_ANNOTATION, Token.class.getName());
    tokenizer.process(jcas);
    tcAnno.process(jcas);
    List<TextClassificationOutcome> outcomes = new ArrayList<>(JCasUtil.select(jcas, TextClassificationOutcome.class));
    // 9 token + 2 punctuation marks
    assertEquals(11, outcomes.size());
    for (TextClassificationOutcome o : outcomes) {
        String label = o.getOutcome();
        assertTrue(postags.contains(label));
    }
}

Example 18 with WekaAdapter

use of org.dkpro.tc.ml.weka.WekaAdapter in project dkpro-tc by dkpro.

the class WekaBrownUnitPosDemo 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(BrownCorpusReader.class, BrownCorpusReader.PARAM_LANGUAGE, "en", BrownCorpusReader.PARAM_SOURCE_LOCATION, corpusFilePathTrain, BrownCorpusReader.PARAM_PATTERNS, new String[] { INCLUDE_PREFIX + "*.xml", INCLUDE_PREFIX + "*.xml.gz" });
    dimReaders.put(DIM_READER_TRAIN, readerTrain);
    CollectionReaderDescription readerTest = CollectionReaderFactory.createReaderDescription(BrownCorpusReader.class, BrownCorpusReader.PARAM_LANGUAGE, "en", BrownCorpusReader.PARAM_SOURCE_LOCATION, corpusFilePathTrain, BrownCorpusReader.PARAM_PATTERNS, new String[] { "*.xml", "*.xml.gz" });
    dimReaders.put(DIM_READER_TEST, readerTest);
    Map<String, Object> config = new HashMap<>();
    config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new WekaAdapter(), NaiveBayes.class.getName() });
    config.put(DIM_DATA_WRITER, new WekaAdapter().getDataWriterClass().getName());
    config.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().useSparseFeatures());
    Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", config);
    Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(Constants.DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(TokenRatioPerDocument.class), TcFeatureFactory.create(CharacterNGram.class, CharacterNGram.PARAM_NGRAM_USE_TOP_K, 50)));
    ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle(DIM_READERS, dimReaders), Dimension.create(DIM_LEARNING_MODE, LM_SINGLE_LABEL), Dimension.create(DIM_FEATURE_MODE, FM_UNIT), dimFeatureSets, mlas);
    return pSpace;
}

Example 19 with WekaAdapter

use of org.dkpro.tc.ml.weka.WekaAdapter in project dkpro-tc by dkpro.

the class WekaSaveAndLoadModelDocumentPairRegression method pairGetParameterSpace.

private static ParameterSpace pairGetParameterSpace() throws ResourceInitializationException {
    Map<String, Object> dimReaders = new HashMap<String, Object>();
    Object readerTrain = CollectionReaderFactory.createReaderDescription(STSReader.class, STSReader.PARAM_INPUT_FILE, pairTrainFiles, STSReader.PARAM_GOLD_FILE, pairGoldFiles);
    dimReaders.put(DIM_READER_TRAIN, readerTrain);
    @SuppressWarnings("unchecked") Dimension<List<Object>> dimClassificationArgs = Dimension.create(Constants.DIM_CLASSIFICATION_ARGS, Arrays.asList(new Object[] { new WekaAdapter(), SMOreg.class.getName() }));
    Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(DiffNrOfTokensPairFeatureExtractor.class)));
    ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(DIM_LEARNING_MODE, LM_REGRESSION), Dimension.create(DIM_FEATURE_MODE, FM_PAIR), dimFeatureSets, dimClassificationArgs);
    return pSpace;
}

Example 20 with WekaAdapter

use of org.dkpro.tc.ml.weka.WekaAdapter in project dkpro-tc by dkpro.

the class WekaSaveAndLoadModelDocumentSingleLabelTest method documentGetParameterSpaceSingleLabel.

private ParameterSpace documentGetParameterSpaceSingleLabel() throws ResourceInitializationException {
    Map<String, Object> dimReaders = new HashMap<String, Object>();
    CollectionReaderDescription readerTrain = CollectionReaderFactory.createReaderDescription(FolderwiseDataReader.class, FolderwiseDataReader.PARAM_SOURCE_LOCATION, documentTrainFolder, FolderwiseDataReader.PARAM_LANGUAGE, "en", FolderwiseDataReader.PARAM_PATTERNS, "*/*.txt");
    dimReaders.put(DIM_READER_TRAIN, readerTrain);
    Map<String, Object> wekaConfig = new HashMap<>();
    wekaConfig.put(DIM_CLASSIFICATION_ARGS, new Object[] { new WekaAdapter(), NaiveBayes.class.getName() });
    wekaConfig.put(DIM_DATA_WRITER, new WekaAdapter().getDataWriterClass().getName());
    wekaConfig.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().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_SINGLE_LABEL), Dimension.create(DIM_FEATURE_MODE, FM_DOCUMENT), dimFeatureSets, mlas);
    return pSpace;
}