Search in sources :

Example 46 with CollectionReaderDescription

use of org.apache.uima.collection.CollectionReaderDescription in project dkpro-tc by dkpro.

the class WekaDocumentPlain 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;
}
Also used : CollectionReaderDescription(org.apache.uima.collection.CollectionReaderDescription) NaiveBayes(weka.classifiers.bayes.NaiveBayes) HashMap(java.util.HashMap) ParameterSpace(org.dkpro.lab.task.ParameterSpace) TcFeatureSet(org.dkpro.tc.api.features.TcFeatureSet) HashMap(java.util.HashMap) Map(java.util.Map) WekaAdapter(org.dkpro.tc.ml.weka.WekaAdapter)

Example 47 with CollectionReaderDescription

use of org.apache.uima.collection.CollectionReaderDescription in project dkpro-tc by dkpro.

the class WekaManualFoldCrossValidation method getParameterSpace.

public static ParameterSpace getParameterSpace(boolean manualFolds) throws ResourceInitializationException {
    Map<String, Object> dimReaders = new HashMap<String, Object>();
    dimReaders.put(DIM_READER_TRAIN, BrownCorpusReader.class);
    CollectionReaderDescription readerTrain = CollectionReaderFactory.createReaderDescription(BrownCorpusReader.class, BrownCorpusReader.PARAM_LANGUAGE, "de", BrownCorpusReader.PARAM_SOURCE_LOCATION, corpusFilePathTrain, BrownCorpusReader.PARAM_PATTERNS, INCLUDE_PREFIX + "*.xml");
    dimReaders.put(DIM_READER_TRAIN, readerTrain);
    Dimension<TcFeatureSet> dimFeatureSets = Dimension.create(DIM_FEATURE_SET, new TcFeatureSet(TcFeatureFactory.create(CharacterNGram.class, CharacterNGram.PARAM_NGRAM_MIN_N, 2, CharacterNGram.PARAM_NGRAM_MAX_N, 3, CharacterNGram.PARAM_NGRAM_USE_TOP_K, 750)));
    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_UNIT), dimFeatureSets, mlas, /*
                 * MANUAL CROSS VALIDATION FOLDS - i.e. the cas created by your reader will be used
                 * as is to make folds
                 */
    Dimension.create(DIM_CROSS_VALIDATION_MANUAL_FOLDS, manualFolds));
    return pSpace;
}
Also used : CollectionReaderDescription(org.apache.uima.collection.CollectionReaderDescription) NaiveBayes(weka.classifiers.bayes.NaiveBayes) HashMap(java.util.HashMap) ParameterSpace(org.dkpro.lab.task.ParameterSpace) TcFeatureSet(org.dkpro.tc.api.features.TcFeatureSet) HashMap(java.util.HashMap) Map(java.util.Map) WekaAdapter(org.dkpro.tc.ml.weka.WekaAdapter)

Example 48 with CollectionReaderDescription

use of org.apache.uima.collection.CollectionReaderDescription in project dkpro-tc by dkpro.

the class WekaTwentyNewsgroupsInstanceWeightingDemo 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(WeightedTwentyNewsgroupsCorpusReader.class, WeightedTwentyNewsgroupsCorpusReader.PARAM_SOURCE_LOCATION, corpusFilePathTrain, WeightedTwentyNewsgroupsCorpusReader.PARAM_WEIGHT_FILE_LOCATION, corpusFilePathTrain + weightsFile, WeightedTwentyNewsgroupsCorpusReader.PARAM_LANGUAGE, LANGUAGE_CODE, WeightedTwentyNewsgroupsCorpusReader.PARAM_PATTERNS, Arrays.asList(WeightedTwentyNewsgroupsCorpusReader.INCLUDE_PREFIX + "*/*.txt"));
    dimReaders.put(DIM_READER_TRAIN, readerTrain);
    CollectionReaderDescription readerTest = CollectionReaderFactory.createReaderDescription(WeightedTwentyNewsgroupsCorpusReader.class, WeightedTwentyNewsgroupsCorpusReader.PARAM_SOURCE_LOCATION, corpusFilePathTest, WeightedTwentyNewsgroupsCorpusReader.PARAM_WEIGHT_FILE_LOCATION, corpusFilePathTest + weightsFile, WeightedTwentyNewsgroupsCorpusReader.PARAM_LANGUAGE, LANGUAGE_CODE, WeightedTwentyNewsgroupsCorpusReader.PARAM_PATTERNS, WeightedTwentyNewsgroupsCorpusReader.INCLUDE_PREFIX + "*/*.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, 2, WordNGram.PARAM_NGRAM_MAX_N, 3)));
    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("readers", dimReaders), Dimension.create(DIM_LEARNING_MODE, LM_SINGLE_LABEL), Dimension.create(DIM_FEATURE_MODE, FM_DOCUMENT), dimFeatureSets, mlas, Dimension.create(DIM_APPLY_INSTANCE_WEIGHTING, true));
    return pSpace;
}
Also used : CollectionReaderDescription(org.apache.uima.collection.CollectionReaderDescription) SMO(weka.classifiers.functions.SMO) HashMap(java.util.HashMap) ParameterSpace(org.dkpro.lab.task.ParameterSpace) TcFeatureSet(org.dkpro.tc.api.features.TcFeatureSet) HashMap(java.util.HashMap) Map(java.util.Map) WekaAdapter(org.dkpro.tc.ml.weka.WekaAdapter)

Example 49 with CollectionReaderDescription

use of org.apache.uima.collection.CollectionReaderDescription in project dkpro-tc by dkpro.

the class PairModeWekaDemo 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);
    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(), 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_PAIR), dimFeatureSets, mlas);
    return pSpace;
}
Also used : CollectionReaderDescription(org.apache.uima.collection.CollectionReaderDescription) NaiveBayes(weka.classifiers.bayes.NaiveBayes) HashMap(java.util.HashMap) ParameterSpace(org.dkpro.lab.task.ParameterSpace) TcFeatureSet(org.dkpro.tc.api.features.TcFeatureSet) HashMap(java.util.HashMap) Map(java.util.Map) WekaAdapter(org.dkpro.tc.ml.weka.WekaAdapter)

Example 50 with CollectionReaderDescription

use of org.apache.uima.collection.CollectionReaderDescription 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;
}
Also used : HashMap(java.util.HashMap) RandomForest(weka.classifiers.trees.RandomForest) TcFeatureSet(org.dkpro.tc.api.features.TcFeatureSet) CollectionReaderDescription(org.apache.uima.collection.CollectionReaderDescription) MekaAdapter(org.dkpro.tc.ml.weka.MekaAdapter) MULAN(meka.classifiers.multilabel.MULAN) ParameterSpace(org.dkpro.lab.task.ParameterSpace) HashMap(java.util.HashMap) Map(java.util.Map)

Aggregations

CollectionReaderDescription (org.apache.uima.collection.CollectionReaderDescription)78 HashMap (java.util.HashMap)53 ParameterSpace (org.dkpro.lab.task.ParameterSpace)51 TcFeatureSet (org.dkpro.tc.api.features.TcFeatureSet)40 Map (java.util.Map)35 AnalysisEngineDescription (org.apache.uima.analysis_engine.AnalysisEngineDescription)25 File (java.io.File)19 WekaAdapter (org.dkpro.tc.ml.weka.WekaAdapter)17 Test (org.junit.Test)14 ArrayList (java.util.ArrayList)13 LiblinearAdapter (org.dkpro.tc.ml.liblinear.LiblinearAdapter)9 NaiveBayes (weka.classifiers.bayes.NaiveBayes)9 ExternalResourceDescription (org.apache.uima.resource.ExternalResourceDescription)7 LibsvmAdapter (org.dkpro.tc.ml.libsvm.LibsvmAdapter)7 Gson (com.google.gson.Gson)6 Instance (org.dkpro.tc.api.features.Instance)6 JsonDataWriter (org.dkpro.tc.core.io.JsonDataWriter)6 XgboostAdapter (org.dkpro.tc.ml.xgboost.XgboostAdapter)6 JCasIterable (org.apache.uima.fit.pipeline.JCasIterable)5 JCas (org.apache.uima.jcas.JCas)5