use of org.apache.uima.collection.CollectionReaderDescription in project dkpro-tc by dkpro.
the class KerasMultiLabel 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(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);
CollectionReaderDescription readerTest = 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_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_MULTI_LABEL), Dimension.create(DIM_BIPARTITION_THRESHOLD, 0.5), Dimension.create(DeepLearningConstants.DIM_PYTHON_INSTALLATION, "/usr/local/bin/python3"), Dimension.create(DeepLearningConstants.DIM_USER_CODE, "src/main/resources/kerasCode/multiLabel/multi.py"), Dimension.create(DeepLearningConstants.DIM_MAXIMUM_LENGTH, 250), 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;
}
use of org.apache.uima.collection.CollectionReaderDescription in project dkpro-tc by dkpro.
the class KerasSeq2SeqTrainTest method getParameterSpace.
public static ParameterSpace getParameterSpace() 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);
// Careful - we need at least 2 sequences in the testing file otherwise things will crash
CollectionReaderDescription test = 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_TEST, test);
ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(DIM_FEATURE_MODE, Constants.FM_SEQUENCE), Dimension.create(DIM_LEARNING_MODE, Constants.LM_SINGLE_LABEL), Dimension.create(DeepLearningConstants.DIM_PYTHON_INSTALLATION, "/usr/local/bin/python3"), Dimension.create(DeepLearningConstants.DIM_MAXIMUM_LENGTH, 75), Dimension.create(DeepLearningConstants.DIM_VECTORIZE_TO_INTEGER, true), Dimension.create(DeepLearningConstants.DIM_USER_CODE, "src/main/resources/kerasCode/seq/posTaggingLstm.py"));
return pSpace;
}
use of org.apache.uima.collection.CollectionReaderDescription in project dkpro-tc by dkpro.
the class CRFSuiteNERSequenceDemo method getParameterSpace.
public static ParameterSpace getParameterSpace() throws ResourceInitializationException {
CollectionReaderDescription readerTrain = CollectionReaderFactory.createReaderDescription(SequenceOutcomeReader.class, SequenceOutcomeReader.PARAM_LANGUAGE, "de", SequenceOutcomeReader.PARAM_SOURCE_LOCATION, corpusFilePathTrain, SequenceOutcomeReader.PARAM_TOKEN_INDEX, 1, SequenceOutcomeReader.PARAM_OUTCOME_INDEX, 2, SequenceOutcomeReader.PARAM_SKIP_LINES_START_WITH_STRING, "#", SequenceOutcomeReader.PARAM_PATTERNS, INCLUDE_PREFIX + "*.txt");
CollectionReaderDescription readerTest = CollectionReaderFactory.createReaderDescription(SequenceOutcomeReader.class, SequenceOutcomeReader.PARAM_LANGUAGE, "de", SequenceOutcomeReader.PARAM_SOURCE_LOCATION, corpusFilePathTest, SequenceOutcomeReader.PARAM_TOKEN_INDEX, 1, SequenceOutcomeReader.PARAM_OUTCOME_INDEX, 2, SequenceOutcomeReader.PARAM_SKIP_LINES_START_WITH_STRING, "#", SequenceOutcomeReader.PARAM_PATTERNS, INCLUDE_PREFIX + "*.txt");
Map<String, Object> dimReaders = new HashMap<String, Object>();
dimReaders.put(DIM_READER_TRAIN, readerTrain);
dimReaders.put(DIM_READER_TEST, readerTest);
Map<String, Object> config = new HashMap<>();
config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new CrfSuiteAdapter(), CrfSuiteAdapter.ALGORITHM_LBFGS, "-p", "max_iterations=5" });
config.put(DIM_DATA_WRITER, new CrfSuiteAdapter().getDataWriterClass().getName());
config.put(DIM_FEATURE_USE_SPARSE, new CrfSuiteAdapter().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(InitialCharacterUpperCase.class)));
ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(DIM_LEARNING_MODE, Constants.LM_SINGLE_LABEL), Dimension.create(DIM_FEATURE_MODE, Constants.FM_SEQUENCE), dimFeatureSets, mlas);
return pSpace;
}
use of org.apache.uima.collection.CollectionReaderDescription in project dkpro-tc by dkpro.
the class LiblinearDocumentPlain method getParameterSpace.
public static ParameterSpace getParameterSpace() throws ResourceInitializationException {
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, 50, WordNGram.PARAM_NGRAM_MIN_N, 1, WordNGram.PARAM_NGRAM_MAX_N, 3)));
Map<String, Object> config = new HashMap<>();
config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new LiblinearAdapter(), "-s", "4", "-c", "100" });
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_DOCUMENT), dimFeatureSets, mlas);
return pSpace;
}
use of org.apache.uima.collection.CollectionReaderDescription in project dkpro-tc by dkpro.
the class LibsvmDocumentPlain method getParameterSpace.
public static ParameterSpace getParameterSpace() throws ResourceInitializationException {
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, 50, WordNGram.PARAM_NGRAM_MIN_N, 1, WordNGram.PARAM_NGRAM_MAX_N, 3)));
Map<String, Object> config = new HashMap<>();
config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new LibsvmAdapter(), "-s", "1", "-c", "1000", "-t", "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);
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;
}
Aggregations