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

Example 1 with TcFeatureSet

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

the class LiblinearSaveAndLoadModelDocumentRegression 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_LANGUAGE, "en", 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 LiblinearAdapter(), "-s", "6" }));
    Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(SentenceRatioPerDocument.class), TcFeatureFactory.create(WordNGram.class), TcFeatureFactory.create(TokenRatioPerDocument.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 2 with TcFeatureSet

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

the class SVMHMMSaveAndLoadModelTest method getParameterSpace.

private ParameterSpace getParameterSpace() throws ResourceInitializationException {
    DemoUtils.setDkproHome(this.getClass().getName());
    String trainFolder = "src/main/resources/data/brown_tei/";
    // 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(BrownCorpusReader.class, BrownCorpusReader.PARAM_LANGUAGE, "en", BrownCorpusReader.PARAM_SOURCE_LOCATION, trainFolder, BrownCorpusReader.PARAM_LANGUAGE, "en", BrownCorpusReader.PARAM_PATTERNS, "*.xml");
    dimReaders.put(DIM_READER_TRAIN, readerTrain);
    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)));
    Map<String, Object> wekaConfig = new HashMap<>();
    wekaConfig.put(DIM_CLASSIFICATION_ARGS, new Object[] { new SvmHmmAdapter() });
    wekaConfig.put(DIM_DATA_WRITER, new SvmHmmAdapter().getDataWriterClass().getName());
    wekaConfig.put(DIM_FEATURE_USE_SPARSE, new SvmHmmAdapter().useSparseFeatures());
    Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", wekaConfig);
    ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(DIM_LEARNING_MODE, LM_SINGLE_LABEL), Dimension.create(DIM_FEATURE_MODE, FM_SEQUENCE), dimFeatureSets, mlas);
    return pSpace;
}

Example 3 with TcFeatureSet

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

the class WekaComplexConfigurationSingleDemo 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(FolderwiseDataReader.class, FolderwiseDataReader.PARAM_SOURCE_LOCATION, CORPUS_FILEPATH_TRAIN, 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, COPRUS_FILEPATH_TEST, FolderwiseDataReader.PARAM_LANGUAGE, LANGUAGE_CODE, FolderwiseDataReader.PARAM_PATTERNS, "*/*.txt");
    dimReaders.put(DIM_READER_TEST, readerTest);
    Map<String, Object> config1 = new HashMap<>();
    config1.put(DIM_CLASSIFICATION_ARGS, new Object[] { new WekaAdapter(), SMO.class.getName(), "-C", "1.0", "-K", PolyKernel.class.getName() + " " + "-C -1 -E 2" });
    config1.put(DIM_DATA_WRITER, new WekaAdapter().getDataWriterClass().getName());
    config1.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().useSparseFeatures());
    Map<String, Object> config2 = new HashMap<>();
    config2.put(DIM_CLASSIFICATION_ARGS, new Object[] { new WekaAdapter(), RandomForest.class.getName(), "-I", "5" });
    config2.put(DIM_DATA_WRITER, new WekaAdapter().getDataWriterClass().getName());
    config2.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().useSparseFeatures());
    Map<String, Object> config3 = new HashMap<>();
    config3.put(DIM_CLASSIFICATION_ARGS, new Object[] { new WekaAdapter(), Bagging.class.getName(), "-I", "2", "-W", J48.class.getName(), "--", "-C", "0.5", "-M", "2" });
    config3.put(DIM_DATA_WRITER, new WekaAdapter().getDataWriterClass().getName());
    config3.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().useSparseFeatures());
    Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", config1, config2, config3);
    // We configure 2 sets of feature extractors, one consisting of 3 extractors, and one with
    // only 1
    Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(TokenRatioPerDocument.class), TcFeatureFactory.create(WordNGram.class, WordNGram.PARAM_NGRAM_USE_TOP_K, 50, WordNGram.PARAM_NGRAM_MIN_N, 1, WordNGram.PARAM_NGRAM_MAX_N, 3)), 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)));
    // single-label feature selection (Weka specific options), reduces the feature set to 10
    Map<String, Object> dimFeatureSelection = new HashMap<String, Object>();
    dimFeatureSelection.put(DIM_FEATURE_SEARCHER_ARGS, asList(new String[] { Ranker.class.getName(), "-N", "10" }));
    dimFeatureSelection.put(DIM_ATTRIBUTE_EVALUATOR_ARGS, asList(new String[] { InfoGainAttributeEval.class.getName() }));
    dimFeatureSelection.put(DIM_APPLY_FEATURE_SELECTION, true);
    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, Dimension.createBundle("featureSelection", dimFeatureSelection));
    return pSpace;
}

Example 4 with TcFeatureSet

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

the class WekaUniformClassDistributionDemo method getParameterSpace.

@SuppressWarnings("unchecked")
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);
    Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(TokenRatioPerDocument.class), TcFeatureFactory.create(WordNGram.class, WordNGram.PARAM_NGRAM_USE_TOP_K, 50, WordNGram.PARAM_NGRAM_MIN_N, 1, WordNGram.PARAM_NGRAM_MAX_N, 3)));
    Dimension<List<String>> dimFeatureFilters = Dimension.create(DIM_FEATURE_FILTERS, Arrays.asList(new String[] { UniformClassDistributionFilter.class.getName() }));
    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);
    ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(DIM_LEARNING_MODE, LM_SINGLE_LABEL), Dimension.create(DIM_FEATURE_MODE, FM_DOCUMENT), dimFeatureSets, dimFeatureFilters, mlas);
    return pSpace;
}

Example 5 with TcFeatureSet

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

the class MekaComplexConfigurationMultiDemo 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(ReutersCorpusReader.class, ReutersCorpusReader.PARAM_SOURCE_LOCATION, FILEPATH_TRAIN, ReutersCorpusReader.PARAM_GOLD_LABEL_FILE, FILEPATH_GOLD_LABELS, ReutersCorpusReader.PARAM_LANGUAGE, LANGUAGE_CODE, ReutersCorpusReader.PARAM_PATTERNS, ReutersCorpusReader.INCLUDE_PREFIX + "*.txt");
    dimReaders.put(DIM_READER_TRAIN, readerTrain);
    CollectionReaderDescription readerTest = CollectionReaderFactory.createReaderDescription(ReutersCorpusReader.class, ReutersCorpusReader.PARAM_SOURCE_LOCATION, FILEPATH_TEST, ReutersCorpusReader.PARAM_GOLD_LABEL_FILE, FILEPATH_GOLD_LABELS, ReutersCorpusReader.PARAM_LANGUAGE, LANGUAGE_CODE, ReutersCorpusReader.PARAM_PATTERNS, ReutersCorpusReader.INCLUDE_PREFIX + "*.txt");
    dimReaders.put(DIM_READER_TEST, readerTest);
    // Config 1
    Map<String, Object> config1 = new HashMap<>();
    config1.put(DIM_CLASSIFICATION_ARGS, new Object[] { new MekaAdapter(), BR.class.getName(), "-W", NaiveBayes.class.getName() });
    config1.put(DIM_DATA_WRITER, new MekaAdapter().getDataWriterClass().getName());
    config1.put(DIM_FEATURE_USE_SPARSE, new MekaAdapter().useSparseFeatures());
    Map<String, Object> config2 = new HashMap<>();
    config2.put(DIM_CLASSIFICATION_ARGS, new Object[] { new MekaAdapter(), CCq.class.getName(), "-P", "0.9" });
    config2.put(DIM_DATA_WRITER, new MekaAdapter().getDataWriterClass().getName());
    config2.put(DIM_FEATURE_USE_SPARSE, new MekaAdapter().useSparseFeatures());
    Map<String, Object> config3 = new HashMap<>();
    config3.put(DIM_CLASSIFICATION_ARGS, new Object[] { new MekaAdapter(), PSUpdateable.class.getName(), "-B", "900", "-S", "9" });
    config3.put(DIM_DATA_WRITER, new MekaAdapter().getDataWriterClass().getName());
    config3.put(DIM_FEATURE_USE_SPARSE, new MekaAdapter().useSparseFeatures());
    Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", config1, config2, config3);
    // We configure 2 sets of feature extractors, one consisting of 2 extractors, and one with
    // only one
    Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(TokenRatioPerDocument.class), TcFeatureFactory.create(WordNGram.class, WordNGram.PARAM_NGRAM_USE_TOP_K, 600, WordNGram.PARAM_NGRAM_MIN_N, 1, WordNGram.PARAM_NGRAM_MAX_N, 3)));
    // multi-label feature selection (Mulan specific options), reduces the feature set to 10
    Map<String, Object> dimFeatureSelection = new HashMap<String, Object>();
    dimFeatureSelection.put(DIM_LABEL_TRANSFORMATION_METHOD, "BinaryRelevanceAttributeEvaluator");
    dimFeatureSelection.put(DIM_ATTRIBUTE_EVALUATOR_ARGS, asList(new String[] { InfoGainAttributeEval.class.getName() }));
    dimFeatureSelection.put(DIM_NUM_LABELS_TO_KEEP, 10);
    dimFeatureSelection.put(DIM_APPLY_FEATURE_SELECTION, true);
    ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(DIM_LEARNING_MODE, LM_MULTI_LABEL), Dimension.create(DIM_FEATURE_MODE, FM_DOCUMENT), Dimension.create(DIM_BIPARTITION_THRESHOLD, BIPARTITION_THRESHOLD), dimFeatureSets, mlas, Dimension.createBundle("featureSelection", dimFeatureSelection));
    return pSpace;
}