use of org.dkpro.tc.ml.svmhmm.SvmHmmAdapter 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;
}
use of org.dkpro.tc.ml.svmhmm.SvmHmmAdapter 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);
}
Aggregations