Examples with TcFeatureSet org.dkpro.tc.api.features.TcFeatureSet used on opensource projects

Example 11 with TcFeatureSet

use of org.dkpro.tc.api.features.TcFeatureSet in project dkpro-tc by dkpro.

the class SvmHmmBrownPosDemo method getParameterSpace.

public static ParameterSpace getParameterSpace() throws ResourceInitializationException {
    // configure training and test data reader dimension
    Map<String, Object> dimReaders = getDimReaders();
    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, 20, CharacterNGram.PARAM_NGRAM_MIN_N, 2, CharacterNGram.PARAM_NGRAM_MAX_N, 3)));
    Map<String, Object> config = new HashMap<>();
    config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new SvmHmmAdapter(), "-c", "5.0", "-t", "1", "-m", "0" });
    config.put(DIM_DATA_WRITER, new SvmHmmAdapter().getDataWriterClass().getName());
    config.put(DIM_FEATURE_USE_SPARSE, new SvmHmmAdapter().useSparseFeatures());
    Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", config);
    return new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(Constants.DIM_LEARNING_MODE, Constants.LM_SINGLE_LABEL), Dimension.create(Constants.DIM_FEATURE_MODE, Constants.FM_SEQUENCE), dimFeatureSets, mlas);
}

Example 12 with TcFeatureSet

use of org.dkpro.tc.api.features.TcFeatureSet in project dkpro-tc by dkpro.

the class WekaAblationDemo method getParameterSpace.

public static ParameterSpace getParameterSpace() throws ResourceInitializationException {
    // configure training and test data reader dimension
    // train/test will use both, while cross-validation will only use the
    // train part
    Map<String, Object> dimReaders = new HashMap<String, Object>();
    CollectionReaderDescription readerTrain = CollectionReaderFactory.createReaderDescription(FolderwiseDataReader.class, FolderwiseDataReader.PARAM_SOURCE_LOCATION, corpusFilePathTrain, FolderwiseDataReader.PARAM_LANGUAGE, LANGUAGE_CODE, FolderwiseDataReader.PARAM_PATTERNS, "*/*.txt");
    dimReaders.put(DIM_READER_TRAIN, readerTrain);
    CollectionReaderDescription readerTest = CollectionReaderFactory.createReaderDescription(FolderwiseDataReader.class, FolderwiseDataReader.PARAM_SOURCE_LOCATION, corpusFilePathTest, FolderwiseDataReader.PARAM_LANGUAGE, LANGUAGE_CODE, FolderwiseDataReader.PARAM_PATTERNS, "*/*.txt");
    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 = ExperimentUtil.getAblationTestFeatures(TcFeatureFactory.create(TokenRatioPerDocument.class), TcFeatureFactory.create(EmoticonRatio.class), TcFeatureFactory.create(NumberOfHashTags.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;
}

Example 13 with TcFeatureSet

use of org.dkpro.tc.api.features.TcFeatureSet in project dkpro-tc by dkpro.

the class XgboostRegression method getParameterSpace.

public static ParameterSpace getParameterSpace() throws ResourceInitializationException {
    // configure training and test data reader dimension
    // train/test will use both, while cross-validation will only use the train part
    // The reader is also responsible for setting the labels/outcome on all
    // documents/instances it creates.
    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);
    CollectionReaderDescription readerTest = CollectionReaderFactory.createReaderDescription(LinewiseTextOutcomeReader.class, LinewiseTextOutcomeReader.PARAM_OUTCOME_INDEX, 0, LinewiseTextOutcomeReader.PARAM_TEXT_INDEX, 1, LinewiseTextOutcomeReader.PARAM_SOURCE_LOCATION, "src/main/resources/data/essays/test/essay_test.txt", LinewiseTextOutcomeReader.PARAM_LANGUAGE, "en");
    dimReaders.put(DIM_READER_TEST, readerTest);
    Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(SentenceRatioPerDocument.class), TcFeatureFactory.create(TokenRatioPerDocument.class)));
    Map<String, Object> xgboostConfig = new HashMap<>();
    xgboostConfig.put(DIM_CLASSIFICATION_ARGS, new Object[] { new XgboostAdapter(), "booster=gbtree", "reg:linear" });
    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_REGRESSION), Dimension.create(DIM_FEATURE_MODE, FM_DOCUMENT), dimFeatureSets, mlas);
    return pSpace;
}

Example 14 with TcFeatureSet

use of org.dkpro.tc.api.features.TcFeatureSet 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 15 with TcFeatureSet

use of org.dkpro.tc.api.features.TcFeatureSet 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;
}