Examples with CollectionReaderDescription org.apache.uima.collection.CollectionReaderDescription used on opensource projects

Example 61 with CollectionReaderDescription

use of org.apache.uima.collection.CollectionReaderDescription in project dkpro-tc by dkpro.

the class KerasRegression method getParameterSpace.

public static ParameterSpace getParameterSpace(String pythonPath) 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(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/train/essay_test.txt", LinewiseTextOutcomeReader.PARAM_LANGUAGE, "en");
    dimReaders.put(DIM_READER_TEST, readerTest);
    ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(DIM_FEATURE_MODE, Constants.FM_DOCUMENT), Dimension.create(DIM_LEARNING_MODE, Constants.LM_REGRESSION), Dimension.create(DeepLearningConstants.DIM_PYTHON_INSTALLATION, pythonPath), Dimension.create(DeepLearningConstants.DIM_USER_CODE, "src/main/resources/kerasCode/regression/essay.py"), Dimension.create(DeepLearningConstants.DIM_MAXIMUM_LENGTH, 100), Dimension.create(DeepLearningConstants.DIM_VECTORIZE_TO_INTEGER, true), Dimension.create(DeepLearningConstants.DIM_PRETRAINED_EMBEDDINGS, "src/test/resources/wordvector/glove.6B.50d_250.txt"));
    return pSpace;
}

Example 62 with CollectionReaderDescription

use of org.apache.uima.collection.CollectionReaderDescription in project dkpro-tc by dkpro.

the class CRFSuiteBrownPosDemoSimpleDkproReader method getParameterSpace.

public static ParameterSpace getParameterSpace(String featureMode, String learningMode, Dimension<Map<String, Object>> config, Dimension<List<String>> dimFilters) throws ResourceInitializationException {
    // configure training and test data reader dimension
    Map<String, Object> dimReaders = new HashMap<String, Object>();
    CollectionReaderDescription train = CollectionReaderFactory.createReaderDescription(TeiReader.class, TeiReader.PARAM_LANGUAGE, "en", TeiReader.PARAM_SOURCE_LOCATION, corpusFilePathTrain, TeiReader.PARAM_PATTERNS, asList(INCLUDE_PREFIX + "a01.xml"));
    dimReaders.put(DIM_READER_TRAIN, train);
    CollectionReaderDescription test = CollectionReaderFactory.createReaderDescription(TeiReader.class, TeiReader.PARAM_LANGUAGE, "en", TeiReader.PARAM_SOURCE_LOCATION, corpusFilePathTrain, TeiReader.PARAM_PATTERNS, asList(INCLUDE_PREFIX + "a02.xml"));
    dimReaders.put(DIM_READER_TEST, test);
    Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(TokenRatioPerDocument.class), TcFeatureFactory.create(CharacterNGram.class, CharacterNGram.PARAM_NGRAM_MIN_N, 2, CharacterNGram.PARAM_NGRAM_MAX_N, 4, CharacterNGram.PARAM_NGRAM_USE_TOP_K, 50)));
    ParameterSpace pSpace;
    if (dimFilters != null) {
        pSpace = new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(DIM_LEARNING_MODE, learningMode), Dimension.create(DIM_FEATURE_MODE, featureMode), dimFilters, dimFeatureSets, config);
    } else {
        pSpace = new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(DIM_LEARNING_MODE, learningMode), Dimension.create(DIM_FEATURE_MODE, featureMode), dimFeatureSets, config);
    }
    return pSpace;
}

Example 63 with CollectionReaderDescription

use of org.apache.uima.collection.CollectionReaderDescription in project dkpro-tc by dkpro.

the class KerasRegressionWassa method getParameterSpace.

public static ParameterSpace getParameterSpace(String python3) 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(LinewiseTextOutcomeReader.class, LinewiseTextOutcomeReader.PARAM_SOURCE_LOCATION, "src/main/resources/data/wassa2017/train/", LinewiseTextOutcomeReader.PARAM_LANGUAGE, "en", LinewiseTextOutcomeReader.PARAM_PATTERNS, "*.txt", LinewiseTextOutcomeReader.PARAM_OUTCOME_INDEX, 3, LinewiseTextOutcomeReader.PARAM_TEXT_INDEX, 1);
    dimReaders.put(DIM_READER_TRAIN, readerTrain);
    CollectionReaderDescription readerTest = CollectionReaderFactory.createReaderDescription(LinewiseTextOutcomeReader.class, LinewiseTextOutcomeReader.PARAM_SOURCE_LOCATION, "src/main/resources/data/wassa2017/dev/", LinewiseTextOutcomeReader.PARAM_LANGUAGE, "en", LinewiseTextOutcomeReader.PARAM_PATTERNS, "*.txt", LinewiseTextOutcomeReader.PARAM_OUTCOME_INDEX, 3, LinewiseTextOutcomeReader.PARAM_TEXT_INDEX, 1);
    dimReaders.put(DIM_READER_TEST, readerTest);
    ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(DIM_FEATURE_MODE, Constants.FM_DOCUMENT), Dimension.create(DIM_LEARNING_MODE, Constants.LM_REGRESSION), Dimension.create(DeepLearningConstants.DIM_PYTHON_INSTALLATION, python3), Dimension.create(DeepLearningConstants.DIM_USER_CODE, "src/main/resources/kerasCode/regression/wassa.py"), Dimension.create(DeepLearningConstants.DIM_MAXIMUM_LENGTH, 50), Dimension.create(DeepLearningConstants.DIM_VECTORIZE_TO_INTEGER, true), Dimension.create(DeepLearningConstants.DIM_PRETRAINED_EMBEDDINGS, "src/test/resources/wordvector/glove.6B.50d_250.txt"));
    return pSpace;
}

Example 64 with CollectionReaderDescription

use of org.apache.uima.collection.CollectionReaderDescription in project dkpro-tc by dkpro.

the class LiblinearUnitDemo 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[] { INCLUDE_PREFIX + "*.xml", INCLUDE_PREFIX + "*.xml.gz" });
    dimReaders.put(DIM_READER_TEST, readerTest);
    Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(TokenRatioPerDocument.class), TcFeatureFactory.create(CharacterNGram.class, CharacterNGram.PARAM_NGRAM_USE_TOP_K, 50)));
    Map<String, Object> config = new HashMap<>();
    config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new LiblinearAdapter() });
    config.put(DIM_DATA_WRITER, new LiblinearAdapter().getDataWriterClass().getName());
    config.put(DIM_FEATURE_USE_SPARSE, new LiblinearAdapter().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_UNIT), dimFeatureSets, mlas);
    return pSpace;
}

Example 65 with CollectionReaderDescription

use of org.apache.uima.collection.CollectionReaderDescription in project dkpro-tc by dkpro.

the class SvmHmmBrownPosDemo method getDimReaders.

public static Map<String, Object> getDimReaders() throws ResourceInitializationException {
    // configure training and test data reader dimension
    Map<String, Object> results = new HashMap<>();
    CollectionReaderDescription readerTrain = CollectionReaderFactory.createReaderDescription(BrownCorpusReader.class, BrownCorpusReader.PARAM_LANGUAGE, "en", BrownCorpusReader.PARAM_SOURCE_LOCATION, corpusFilePathTrain, BrownCorpusReader.PARAM_PATTERNS, "a01.xml");
    CollectionReaderDescription readerTest = CollectionReaderFactory.createReaderDescription(BrownCorpusReader.class, BrownCorpusReader.PARAM_LANGUAGE, "en", BrownCorpusReader.PARAM_LANGUAGE, "en", BrownCorpusReader.PARAM_SOURCE_LOCATION, corpusFilePathTrain, BrownCorpusReader.PARAM_PATTERNS, "a02.xml");
    results.put(Constants.DIM_READER_TRAIN, readerTrain);
    results.put(Constants.DIM_READER_TEST, readerTest);
    return results;
}