use of org.dkpro.tc.ml.weka.WekaAdapter in project dkpro-tc by dkpro.
the class CRFSuiteSaveAndLoadModelTest method loadModelArowParameters.
@Test
public void loadModelArowParameters() throws Exception {
Map<String, Object> config = new HashMap<>();
config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new CrfSuiteAdapter(), CrfSuiteAdapter.ALGORITHM_ADAPTIVE_REGULARIZATION_OF_WEIGHT_VECTOR, "-p", "max_iterations=2" });
config.put(DIM_DATA_WRITER, new CrfSuiteAdapter().getDataWriterClass().getName());
config.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().useSparseFeatures());
Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", config);
// create a model
File modelFolder = folder.newFolder();
ParameterSpace pSpace = getParameterSpace(mlas);
executeSaveModelIntoTemporyFolder(pSpace, modelFolder);
JCas jcas = JCasFactory.createJCas();
jcas.setDocumentText("This is an example text. It has 2 sentences.");
jcas.setDocumentLanguage("en");
AnalysisEngine tokenizer = AnalysisEngineFactory.createEngine(BreakIteratorSegmenter.class);
AnalysisEngine tcAnno = AnalysisEngineFactory.createEngine(TcAnnotator.class, TcAnnotator.PARAM_TC_MODEL_LOCATION, modelFolder.getAbsolutePath(), TcAnnotator.PARAM_NAME_SEQUENCE_ANNOTATION, Sentence.class.getName(), TcAnnotator.PARAM_NAME_UNIT_ANNOTATION, Token.class.getName());
tokenizer.process(jcas);
tcAnno.process(jcas);
List<TextClassificationOutcome> outcomes = new ArrayList<>(JCasUtil.select(jcas, TextClassificationOutcome.class));
// 9 token + 2 punctuation marks
assertEquals(11, outcomes.size());
for (TextClassificationOutcome o : outcomes) {
assertTrue(postags.contains(o.getOutcome()));
}
}
use of org.dkpro.tc.ml.weka.WekaAdapter in project dkpro-tc by dkpro.
the class WekaComplexConfigurationSingleDemo 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(FolderwiseDataReader.class, FolderwiseDataReader.PARAM_SOURCE_LOCATION, CORPUS_FILEPATH_TRAIN, 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, COPRUS_FILEPATH_TEST, FolderwiseDataReader.PARAM_LANGUAGE, LANGUAGE_CODE, FolderwiseDataReader.PARAM_PATTERNS, "*/*.txt");
dimReaders.put(DIM_READER_TEST, readerTest);
Map<String, Object> config1 = new HashMap<>();
config1.put(DIM_CLASSIFICATION_ARGS, new Object[] { new WekaAdapter(), SMO.class.getName(), "-C", "1.0", "-K", PolyKernel.class.getName() + " " + "-C -1 -E 2" });
config1.put(DIM_DATA_WRITER, new WekaAdapter().getDataWriterClass().getName());
config1.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().useSparseFeatures());
Map<String, Object> config2 = new HashMap<>();
config2.put(DIM_CLASSIFICATION_ARGS, new Object[] { new WekaAdapter(), RandomForest.class.getName(), "-I", "5" });
config2.put(DIM_DATA_WRITER, new WekaAdapter().getDataWriterClass().getName());
config2.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().useSparseFeatures());
Map<String, Object> config3 = new HashMap<>();
config3.put(DIM_CLASSIFICATION_ARGS, new Object[] { new WekaAdapter(), Bagging.class.getName(), "-I", "2", "-W", J48.class.getName(), "--", "-C", "0.5", "-M", "2" });
config3.put(DIM_DATA_WRITER, new WekaAdapter().getDataWriterClass().getName());
config3.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().useSparseFeatures());
Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", config1, config2, config3);
// We configure 2 sets of feature extractors, one consisting of 3 extractors, and one with
// only 1
Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet(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)), 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)));
// single-label feature selection (Weka specific options), reduces the feature set to 10
Map<String, Object> dimFeatureSelection = new HashMap<String, Object>();
dimFeatureSelection.put(DIM_FEATURE_SEARCHER_ARGS, asList(new String[] { Ranker.class.getName(), "-N", "10" }));
dimFeatureSelection.put(DIM_ATTRIBUTE_EVALUATOR_ARGS, asList(new String[] { InfoGainAttributeEval.class.getName() }));
dimFeatureSelection.put(DIM_APPLY_FEATURE_SELECTION, true);
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, Dimension.createBundle("featureSelection", dimFeatureSelection));
return pSpace;
}
use of org.dkpro.tc.ml.weka.WekaAdapter in project dkpro-tc by dkpro.
the class WekaUniformClassDistributionDemo method getParameterSpace.
@SuppressWarnings("unchecked")
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(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)));
Dimension<List<String>> dimFeatureFilters = Dimension.create(DIM_FEATURE_FILTERS, Arrays.asList(new String[] { UniformClassDistributionFilter.class.getName() }));
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, dimFeatureFilters, mlas);
return pSpace;
}
use of org.dkpro.tc.ml.weka.WekaAdapter in project dkpro-tc by dkpro.
the class MultiSvmUsingWekaLibsvmLiblinear 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);
Map<String, Object> config = new HashMap<>();
config.put(DIM_CLASSIFICATION_ARGS, new Object[] { new WekaAdapter(), SMO.class.getName(), "-C", "1.0", "-K", PolyKernel.class.getName() + " " + "-C -1 -E 2" });
config.put(DIM_DATA_WRITER, new WekaAdapter().getDataWriterClass().getName());
config.put(DIM_FEATURE_USE_SPARSE, new WekaAdapter().useSparseFeatures());
Map<String, Object> config2 = new HashMap<>();
config2.put(DIM_CLASSIFICATION_ARGS, new Object[] { new LiblinearAdapter(), "-s", "4", "-c", "100" });
config2.put(DIM_DATA_WRITER, new LiblinearAdapter().getDataWriterClass().getName());
config2.put(DIM_FEATURE_USE_SPARSE, new LiblinearAdapter().useSparseFeatures());
Map<String, Object> config3 = new HashMap<>();
config3.put(DIM_CLASSIFICATION_ARGS, new Object[] { new LibsvmAdapter(), "-s", "1", "-c", "1000", "-t", "3" });
config3.put(DIM_DATA_WRITER, new LibsvmAdapter().getDataWriterClass().getName());
config3.put(DIM_FEATURE_USE_SPARSE, new LibsvmAdapter().useSparseFeatures());
Dimension<Map<String, Object>> mlas = Dimension.createBundle("config", config, config2, config3);
Dimension<String> dimLearningMode = Dimension.create(DIM_LEARNING_MODE, LM_SINGLE_LABEL);
Dimension<String> dimFeatureMode = Dimension.create(DIM_FEATURE_MODE, FM_DOCUMENT);
Dimension<TcFeatureSet> dimFeatureSet = Dimension.create(DIM_FEATURE_SET, getFeatureSet());
ParameterSpace ps = new ParameterSpace(dimLearningMode, dimFeatureMode, dimFeatureMode, dimFeatureSet, mlas, Dimension.createBundle(DIM_READERS, dimReaders));
return ps;
}
use of org.dkpro.tc.ml.weka.WekaAdapter in project dkpro-tc by dkpro.
the class WekaAblationDemo 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);
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);
Dimension<TcFeatureSet> dimFeatureSets = ExperimentUtil.getAblationTestFeatures(TcFeatureFactory.create(TokenRatioPerDocument.class), TcFeatureFactory.create(EmoticonRatio.class), TcFeatureFactory.create(NumberOfHashTags.class));
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