Examples with Instance org.dkpro.tc.api.features.Instance used on opensource projects

Example 41 with Instance

use of org.dkpro.tc.api.features.Instance in project dkpro-tc by dkpro.

the class InstanceTest method instanceInitializationWithListOfOutcomes.

@Test
public void instanceInitializationWithListOfOutcomes() throws Exception {
    Feature f1 = new Feature("feature1", "value1", FeatureType.STRING);
    Feature f2 = new Feature("feature2", "value1", FeatureType.STRING);
    List<Feature> features = new ArrayList<>();
    features.add(f1);
    features.add(f2);
    List<String> outcomes = new ArrayList<>();
    outcomes.add("outcome1");
    outcomes.add("outcome2");
    Instance instance = new Instance(features, outcomes);
    assertEquals(2, instance.getFeatures().size());
    assertEquals(2, instance.getOutcomes().size());
}

Example 42 with Instance

use of org.dkpro.tc.api.features.Instance in project dkpro-tc by dkpro.

the class ExtractFeaturesConnectorTest method extractFeaturesConnectorRegressionTest.

@Test
public void extractFeaturesConnectorRegressionTest() throws Exception {
    File outputPath = folder.newFolder();
    // we do not need parameters here, but in case we do :)
    Object[] parameters = new Object[] { NoopFeatureExtractor.PARAM_UNIQUE_EXTRACTOR_NAME, "123", UnitContextMetaCollector.PARAM_CONTEXT_FOLDER, Constants.ID_CONTEXT_KEY };
    ExternalResourceDescription featureExtractor = ExternalResourceFactory.createExternalResourceDescription(NoopFeatureExtractor.class, parameters);
    List<ExternalResourceDescription> fes = new ArrayList<>();
    fes.add(featureExtractor);
    CollectionReaderDescription reader = CollectionReaderFactory.createReaderDescription(TestReaderRegression.class, TestReaderRegression.PARAM_SOURCE_LOCATION, "src/test/resources/data/*.txt");
    AnalysisEngineDescription segmenter = AnalysisEngineFactory.createEngineDescription(BreakIteratorSegmenter.class);
    AnalysisEngineDescription doc = AnalysisEngineFactory.createEngineDescription(DocumentModeAnnotator.class, DocumentModeAnnotator.PARAM_FEATURE_MODE, Constants.FM_DOCUMENT);
    AnalysisEngineDescription featExtractorConnector = TaskUtils.getFeatureExtractorConnector(outputPath.getAbsolutePath(), JsonDataWriter.class.getName(), Constants.LM_REGRESSION, Constants.FM_DOCUMENT, false, false, false, false, Collections.emptyList(), fes, new String[] {});
    SimplePipeline.runPipeline(reader, segmenter, doc, featExtractorConnector);
    Gson gson = new Gson();
    List<String> lines = FileUtils.readLines(new File(outputPath, JsonDataWriter.JSON_FILE_NAME), "utf-8");
    List<Instance> instances = new ArrayList<>();
    for (String l : lines) {
        instances.add(gson.fromJson(l, Instance.class));
    }
    assertEquals(2, instances.size());
    assertEquals(1, getUniqueOutcomes(instances));
    assertEquals("0.45", instances.get(0).getOutcome());
    System.out.println(FileUtils.readFileToString(new File(outputPath, JsonDataWriter.JSON_FILE_NAME), "utf-8"));
}

Example 43 with Instance

use of org.dkpro.tc.api.features.Instance in project dkpro-tc by dkpro.

the class WordNGramTest method evaluateExtractedFeatures.

@Override
protected void evaluateExtractedFeatures(File output) throws Exception {
    List<Instance> instances = readInstances(output);
    assertEquals(4, instances.size());
    assertEquals(1, getUniqueOutcomes(instances));
    Set<String> featureNames = new HashSet<String>();
    for (Instance i : instances) {
        for (Feature f : i.getFeatures()) {
            featureNames.add(f.getName());
        }
    }
    assertEquals(3, featureNames.size());
    assertTrue(featureNames.contains("ngram_4"));
    assertTrue(featureNames.contains("ngram_5"));
    assertTrue(featureNames.contains("ngram_5_5"));
}

Example 44 with Instance

use of org.dkpro.tc.api.features.Instance in project dkpro-tc by dkpro.

the class LibsvmDataFormatLoadModelConnector method createInputFile.

private File createInputFile(JCas jcas) throws Exception {
    File tempFile = FileUtil.createTempFile("libsvm", ".txt");
    tempFile.deleteOnExit();
    BufferedWriter bw = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(tempFile), "utf-8"));
    InstanceExtractor extractor = new InstanceExtractor(featureMode, featureExtractors, true);
    List<Instance> instances = extractor.getInstances(jcas, true);
    for (Instance instance : instances) {
        bw.write(OUTCOME_PLACEHOLDER);
        bw.write(injectSequenceId(instance));
        for (Feature f : instance.getFeatures()) {
            if (!sanityCheckValue(f)) {
                continue;
            }
            bw.write("\t");
            bw.write(featureMapping.get(f.getName()) + ":" + f.getValue());
        }
        bw.write("\n");
    }
    bw.close();
    return tempFile;
}

Example 45 with Instance

use of org.dkpro.tc.api.features.Instance in project dkpro-tc by dkpro.

the class CrfSuiteDataWriter method writeGenericFormat.

@Override
public void writeGenericFormat(Collection<Instance> instances) throws AnalysisEngineProcessException {
    try {
        initGeneric();
        // bulk-write - in sequence mode this keeps the instances together
        // that
        // belong to the same sequence!
        Instance[] array = instances.toArray(new Instance[0]);
        bw.write(gson.toJson(array) + "\n");
        bw.close();
        bw = null;
    } catch (Exception e) {
        throw new AnalysisEngineProcessException(e);
    }
}