use of org.dkpro.lab.task.ParameterSpace in project dkpro-tc by dkpro.
the class WekaExternalResourceDemo method main.
public static void main(String[] args) throws Exception {
// This is used to ensure that the required DKPRO_HOME environment
// variable is set.
// Ensures that people can run the experiments even if they haven't read
// the setup
// instructions first :)
// Don't use this in real experiments! Read the documentation and set
// DKPRO_HOME as
// explained there.
DemoUtils.setDkproHome(WekaExternalResourceDemo.class.getSimpleName());
ParameterSpace pSpace = getParameterSpace();
WekaExternalResourceDemo experiment = new WekaExternalResourceDemo();
experiment.runTrainTest(pSpace);
}
use of org.dkpro.lab.task.ParameterSpace in project dkpro-tc by dkpro.
the class WekaExternalResourceDemo 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(PairTwentyNewsgroupsReader.class, PairTwentyNewsgroupsReader.PARAM_LISTFILE, listFilePathTrain, PairTwentyNewsgroupsReader.PARAM_LANGUAGE_CODE, languageCode);
dimReaders.put(DIM_READER_TRAIN, readerTrain);
CollectionReaderDescription readerTest = CollectionReaderFactory.createReaderDescription(PairTwentyNewsgroupsReader.class, PairTwentyNewsgroupsReader.PARAM_LISTFILE, listFilePathTest, PairTwentyNewsgroupsReader.PARAM_LANGUAGE_CODE, languageCode);
dimReaders.put(DIM_READER_TEST, readerTest);
// Create the External Resource here:
ExternalResourceDescription gstResource = ExternalResourceFactory.createExternalResourceDescription(CosineSimilarityResource.class, CosineSimilarityResource.PARAM_NORMALIZATION, NormalizationMode.L2.toString());
Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(SimilarityPairFeatureExtractor.class, SimilarityPairFeatureExtractor.PARAM_TEXT_SIMILARITY_RESOURCE, gstResource)));
Map<String, Object> config = new HashMap<>();
config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new WekaAdapter(), SMO.class.getName() });
config.put(DIM_DATA_WRITER, new WekaAdapter().getDataWriterClass().getName());
config.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().useSparseFeatures());
Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", config);
ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle(DIM_READERS, dimReaders), Dimension.create(DIM_LEARNING_MODE, LM_SINGLE_LABEL), Dimension.create(DIM_FEATURE_MODE, FM_PAIR), dimFeatureSets, mlas);
return pSpace;
}
use of org.dkpro.lab.task.ParameterSpace in project dkpro-tc by dkpro.
the class SemanticTextSimilarityDemo method getParameterSpace.
public static ParameterSpace getParameterSpace() throws ResourceInitializationException {
// configure training data reader dimension
Map<String, Object> dimReaders = new HashMap<String, Object>();
CollectionReaderDescription readerTrain = CollectionReaderFactory.createReaderDescription(STSReader.class, STSReader.PARAM_INPUT_FILE, inputFileTrain, STSReader.PARAM_GOLD_FILE, goldFileTrain);
dimReaders.put(DIM_READER_TRAIN, readerTrain);
CollectionReaderDescription readerTest = CollectionReaderFactory.createReaderDescription(STSReader.class, STSReader.PARAM_INPUT_FILE, inputFileTest, STSReader.PARAM_GOLD_FILE, goldFileTest);
dimReaders.put(DIM_READER_TEST, readerTest);
Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(DiffNrOfTokensPairFeatureExtractor.class)));
Map<String, Object> config = new HashMap<>();
config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new WekaAdapter(), SMOreg.class.getName() });
config.put(DIM_DATA_WRITER, new WekaAdapter().getDataWriterClass().getName());
config.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().useSparseFeatures());
Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", config);
ParameterSpace pSpace = new ParameterSpace(Dimension.createBundle(Constants.DIM_READER_TRAIN, dimReaders), Dimension.create(Constants.DIM_FEATURE_MODE, Constants.FM_PAIR), Dimension.create(Constants.DIM_LEARNING_MODE, Constants.LM_REGRESSION), dimFeatureSets, mlas);
return pSpace;
}
use of org.dkpro.lab.task.ParameterSpace in project dkpro-tc by dkpro.
the class MinimalWorkingExample 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> config = new HashMap<>();
config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new WekaAdapter(), NaiveBayes.class.getName() });
config.put(DIM_DATA_WRITER, new WekaAdapter().getDataWriterClass().getName());
config.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().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.dkpro.lab.task.ParameterSpace in project dkpro-tc by dkpro.
the class DeepLearning4jDocumentTrainTest method main.
public static void main(String[] args) throws Exception {
// DemoUtils.setDkproHome(DeepLearningTestDummy.class.getSimpleName());
System.setProperty("DKPRO_HOME", System.getProperty("user.home") + "/Desktop");
ParameterSpace pSpace = getParameterSpace();
DeepLearning4jDocumentTrainTest experiment = new DeepLearning4jDocumentTrainTest();
experiment.runTrainTest(pSpace);
}
Aggregations