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

Example 56 with CollectionReaderDescription

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

the class XgboostDocumentPlain 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);
    Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet("DummyFeatureSet", TcFeatureFactory.create(TokenRatioPerDocument.class), TcFeatureFactory.create(WordNGram.class, WordNGram.PARAM_NGRAM_USE_TOP_K, 20, WordNGram.PARAM_NGRAM_MIN_N, 1, WordNGram.PARAM_NGRAM_MAX_N, 3)));
    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_DOCUMENT), dimFeatureSets, mlas);
    return pSpace;
}

Example 57 with CollectionReaderDescription

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

the class MultiRegressionWekaLibsvmLiblinear 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);
    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());
    Map<String, Object> liblinearConfig = new HashMap<>();
    liblinearConfig.put(DIM_CLASSIFICATION_ARGS, new Object[] { new LiblinearAdapter(), "-s", "6" });
    liblinearConfig.put(DIM_DATA_WRITER, new LiblinearAdapter().getDataWriterClass().getName());
    liblinearConfig.put(DIM_FEATURE_USE_SPARSE, new LiblinearAdapter().useSparseFeatures());
    Map<String, Object> libsvmConfig = new HashMap<>();
    libsvmConfig.put(DIM_CLASSIFICATION_ARGS, new Object[] { new LibsvmAdapter(), "-s", "3", "-c", "10" });
    libsvmConfig.put(DIM_DATA_WRITER, new LibsvmAdapter().getDataWriterClass().getName());
    libsvmConfig.put(DIM_FEATURE_USE_SPARSE, new LibsvmAdapter().useSparseFeatures());
    Map<String, Object> wekaConfig = new HashMap<>();
    wekaConfig.put(DIM_CLASSIFICATION_ARGS, new Object[] { new WekaAdapter(), LinearRegression.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", xgboostConfig, liblinearConfig, libsvmConfig, wekaConfig);
    Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(SentenceRatioPerDocument.class), TcFeatureFactory.create(LengthFeatureNominal.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, mlas);
    return pSpace;
}

Example 58 with CollectionReaderDescription

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

the class CRFSuiteSaveAndLoadModelTest method getParameterSpace.

private ParameterSpace getParameterSpace(Dimension<Map<String, Object>> mlas) 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(CharacterNGram.class, CharacterNGram.PARAM_NGRAM_USE_TOP_K, 50, CharacterNGram.PARAM_NGRAM_MIN_N, 1, CharacterNGram.PARAM_NGRAM_MAX_N, 3), // :)
    TcFeatureFactory.create(BrownClusterFeature.class, BrownClusterFeature.PARAM_BROWN_CLUSTERS_LOCATION, "src/test/resources/brownCluster/enTweetBrownC1000F40"), 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_SEQUENCE), dimFeatureSets, mlas);
    return pSpace;
}

Example 59 with CollectionReaderDescription

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

the class LibsvmSaveAndLoadModelDocumentRegression 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);
    Map<String, Object> config = new HashMap<>();
    config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new LibsvmAdapter(), "-s", "3" });
    config.put(DIM_DATA_WRITER, new LibsvmAdapter().getDataWriterClass().getName());
    config.put(DIM_FEATURE_USE_SPARSE, new LibsvmAdapter().useSparseFeatures());
    Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", config);
    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, mlas);
    return pSpace;
}

Example 60 with CollectionReaderDescription

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

the class KerasDocumentTrainTest 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(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);
    ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(DIM_FEATURE_MODE, Constants.FM_DOCUMENT), Dimension.create(DIM_LEARNING_MODE, Constants.LM_SINGLE_LABEL), Dimension.create(DeepLearningConstants.DIM_PYTHON_INSTALLATION, "/usr/local/bin/python3"), Dimension.create(DeepLearningConstants.DIM_USER_CODE, "src/main/resources/kerasCode/singleLabel/imdb_cnn_lstm.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;
}