use of org.dkpro.tc.ml.weka.MekaAdapter 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;
}
use of org.dkpro.tc.ml.weka.MekaAdapter in project dkpro-tc by dkpro.
the class WekaSaveAndLoadModelDocumentMultiLabelTest method documentGetParameterSpaceMultiLabel.
private ParameterSpace documentGetParameterSpaceMultiLabel() throws ResourceInitializationException {
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);
Map<String, Object> wekaConfig = new HashMap<>();
wekaConfig.put(DIM_CLASSIFICATION_ARGS, new Object[] { new MekaAdapter(), MULAN.class.getName(), "-S", "RAkEL2", "-W", RandomForest.class.getName() });
wekaConfig.put(DIM_DATA_WRITER, new MekaAdapter().getDataWriterClass().getName());
wekaConfig.put(DIM_FEATURE_USE_SPARSE, new MekaAdapter().useSparseFeatures());
Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", wekaConfig);
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)));
ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle("readers", dimReaders), Dimension.create(DIM_LEARNING_MODE, LM_MULTI_LABEL), Dimension.create(DIM_FEATURE_MODE, FM_DOCUMENT), dimFeatureSets, Dimension.create(DIM_BIPARTITION_THRESHOLD, "0.5"), mlas);
return pSpace;
}
use of org.dkpro.tc.ml.weka.MekaAdapter in project dkpro-tc by dkpro.
the class MekaSaveAndApplyModelMultilabelDemo 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, 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);
Map<String, Object> config = new HashMap<>();
config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new MekaAdapter(), MULAN.class.getName(), "-S", "RAkEL2", "-W", RandomForest.class.getName() });
config.put(DIM_DATA_WRITER, new MekaAdapter().getDataWriterClass().getName());
config.put(DIM_FEATURE_USE_SPARSE, new MekaAdapter().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(WordNGram.class, WordNGram.PARAM_NGRAM_USE_TOP_K, 100, WordNGram.PARAM_NGRAM_MIN_N, 1, WordNGram.PARAM_NGRAM_MAX_N, 3)));
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);
return pSpace;
}
Aggregations