Examples with Instances weka.core.Instances used on opensource projects

Example 11 with Instances

use of weka.core.Instances in project dkpro-tc by dkpro.

the class WekaUtilTest method tcInstanceToWekaInstanceTest.

@Test
public void tcInstanceToWekaInstanceTest() throws Exception {
    List<String> outcomeValues = Arrays.asList(new String[] { "outc_1", "outc_2", "outc_3" });
    Instance i1 = new Instance();
    i1.addFeature(new Feature("feature1", 2, FeatureType.NUMERIC));
    i1.addFeature(new Feature("feature2", 2, FeatureType.NUMERIC));
    i1.addFeature(new Feature("feature3_{{", "a", FeatureType.STRING));
    Instance i2 = new Instance();
    i2.addFeature(new Feature("feature1", 1, FeatureType.NUMERIC));
    i2.addFeature(new Feature("feature4", "val_1", FeatureType.STRING));
    i2.addFeature(new Feature("feature3_{{", "b", FeatureType.STRING));
    ArrayList<Attribute> attributes = new ArrayList<Attribute>();
    attributes.add(new Attribute("feature5"));
    attributes.add(new Attribute("feature2"));
    attributes.add(new Attribute("feature4", Arrays.asList(new String[] { "val_1", "val_2" })));
    attributes.add(new Attribute("feature1"));
    attributes.add(new Attribute("outcome", outcomeValues));
    Instances trainingData = new Instances("test", attributes, 0);
    weka.core.Instance wekaInstance1 = WekaUtils.tcInstanceToWekaInstance(i1, trainingData, outcomeValues, false);
    weka.core.Instance wekaInstance2 = WekaUtils.tcInstanceToWekaInstance(i2, trainingData, outcomeValues, false);
    assertEquals(true, wekaInstance1.equalHeaders(wekaInstance2));
    assertEquals(5, wekaInstance1.numAttributes());
    wekaInstance1.dataset().add(wekaInstance1);
    wekaInstance2.dataset().add(wekaInstance2);
    System.out.println(wekaInstance1.dataset() + "\n");
    System.out.println(wekaInstance2.dataset() + "\n");
}

Example 12 with Instances

use of weka.core.Instances in project dkpro-tc by dkpro.

the class WekaUtilTest method tcInstanceToWekaInstanceFailTest.

@Test(expected = IllegalArgumentException.class)
public void tcInstanceToWekaInstanceFailTest() throws Exception {
    List<String> outcomeValues = Arrays.asList(new String[] { "outc_1", "outc_2", "outc_3" });
    Instance i1 = new Instance();
    i1.addFeature(new Feature("feature1", 2, FeatureType.NUMERIC));
    i1.addFeature(new Feature("feature4", "val_1", FeatureType.STRING));
    i1.addFeature(new Feature("feature3_{{", "a", FeatureType.STRING));
    ArrayList<Attribute> attributes = new ArrayList<Attribute>();
    attributes.add(new Attribute("feature2"));
    attributes.add(new Attribute("feature4", Arrays.asList(new String[] { "val_4", "val_2" })));
    attributes.add(new Attribute("outcome", outcomeValues));
    Instances trainingData = new Instances("test", attributes, 0);
    @SuppressWarnings("unused") weka.core.Instance wekaInstance1 = WekaUtils.tcInstanceToWekaInstance(i1, trainingData, outcomeValues, false);
}

Example 13 with Instances

use of weka.core.Instances in project dkpro-tc by dkpro.

the class WekaOutcomeIDReport method execute.

@Override
public void execute() throws Exception {
    init();
    File arff = WekaUtils.getFile(getContext(), "", FILENAME_PREDICTIONS, AccessMode.READONLY);
    mlResults = WekaUtils.getFile(getContext(), "", WekaTestTask.evaluationBin, AccessMode.READONLY);
    Instances predictions = WekaUtils.getInstances(arff, isMultiLabel);
    List<String> labels = getLabels(isMultiLabel, isRegression);
    Properties props;
    if (isMultiLabel) {
        MultilabelResult r = WekaUtils.readMlResultFromFile(mlResults);
        props = generateMlProperties(predictions, labels, r);
    } else {
        Map<Integer, String> documentIdMap = loadDocumentMap();
        props = generateSlProperties(predictions, isRegression, isUnit, documentIdMap, labels);
    }
    FileWriterWithEncoding fw = null;
    try {
        fw = new FileWriterWithEncoding(getTargetOutputFile(), "utf-8");
        props.store(fw, generateHeader(labels));
    } finally {
        IOUtils.closeQuietly(fw);
    }
}

Example 14 with Instances

use of weka.core.Instances in project dkpro-tc by dkpro.

the class WekaSerliazeModelConnector method writeWekaSpecificInformation.

private void writeWekaSpecificInformation(TaskContext aContext) throws Exception {
    boolean isMultiLabel = learningMode.equals(Constants.LM_MULTI_LABEL);
    boolean isRegression = learningMode.equals(Constants.LM_REGRESSION);
    File arffFileTrain = new File(aContext.getFolder(TEST_TASK_INPUT_KEY_TRAINING_DATA, AccessMode.READONLY).getPath() + "/" + Constants.FILENAME_DATA_IN_CLASSIFIER_FORMAT);
    Instances trainData = WekaUtils.getInstances(arffFileTrain, isMultiLabel);
    trainData = WekaUtils.removeInstanceId(trainData, isMultiLabel);
    // FEATURE SELECTION
    if (!isMultiLabel) {
        if (featureSearcher != null && attributeEvaluator != null) {
            // Logger.getLogger(getClass()).info("APPLYING FEATURE SELECTION");
            throw new Exception("Feature Selection is currently not supported in Save Model mode.");
        }
    } else {
        if (attributeEvaluator != null && labelTransformationMethod != null && numLabelsToKeep > 0) {
            // Logger.getLogger(getClass()).info("APPLYING FEATURE SELECTION");
            throw new Exception("Feature Selection is currently not supported in Save Model mode.");
        }
    }
    // write training data header
    ObjectOutputStream outT = new ObjectOutputStream(new FileOutputStream(new File(outputFolder, "training_data")));
    Instances emptyTrainCopy = new Instances(trainData);
    emptyTrainCopy.delete();
    outT.writeObject(emptyTrainCopy);
    outT.close();
    // write model file
    Classifier cl = WekaUtils.getClassifier(learningMode, classificationArguments);
    cl.buildClassifier(trainData);
    File model = new File(outputFolder, MODEL_CLASSIFIER);
    mkdir(model.getParentFile());
    weka.core.SerializationHelper.write(model.getAbsolutePath(), cl);
    // write class labels file
    List<String> classLabels;
    if (!isRegression) {
        classLabels = WekaUtils.getClassLabels(trainData, isMultiLabel);
        String classLabelsString = StringUtils.join(classLabels, "\n");
        FileUtils.writeStringToFile(new File(outputFolder, MODEL_CLASS_LABELS), classLabelsString, "utf-8");
    }
}

Example 15 with Instances

use of weka.core.Instances in project dkpro-tc by dkpro.

the class WekaUtils method instanceListToArffFileMultiLabel.

/**
 * Converts a feature store to a list of instances. Multi-label case.
 *
 * @param outputFile
 *            the output file
 * @param instances
 *            the instances to convert
 * @param useDenseInstances
 *            dense features
 * @param useWeights
 *            use weights
 * @throws Exception
 *             in case of errors
 */
public static void instanceListToArffFileMultiLabel(File outputFile, List<Instance> instances, boolean useDenseInstances, boolean useWeights) throws Exception {
    // Filter preprocessingFilter = new ReplaceMissingValuesWithZeroFilter();
    AttributeStore attributeStore = WekaFeatureEncoder.getAttributeStore(instances);
    List<String> outcomes = new ArrayList<>();
    for (Instance i : instances) {
        outcomes.add(i.getOutcome());
    }
    List<Attribute> outcomeAttributes = createOutcomeAttributes(new ArrayList<String>(outcomes));
    // in Meka, class label attributes have to go on top
    for (Attribute attribute : outcomeAttributes) {
        attributeStore.addAttributeAtBegin(attribute.name(), attribute);
    }
    // for Meka-internal use
    Instances wekaInstances = new Instances(RELATION_NAME + ": -C " + outcomeAttributes.size() + " ", attributeStore.getAttributes(), instances.size());
    wekaInstances.setClassIndex(outcomeAttributes.size());
    if (!outputFile.exists()) {
        outputFile.mkdirs();
        outputFile.createNewFile();
    }
    ArffSaver saver = new ArffSaver();
    // preprocessingFilter.setInputFormat(wekaInstances);
    saver.setRetrieval(Saver.INCREMENTAL);
    saver.setFile(outputFile);
    saver.setCompressOutput(true);
    saver.setInstances(wekaInstances);
    for (int i = 0; i < instances.size(); i++) {
        Instance instance = instances.get(i);
        double[] featureValues = getFeatureValues(attributeStore, instance);
        // set class label values
        List<String> instanceOutcome = instance.getOutcomes();
        for (Attribute label : outcomeAttributes) {
            String labelname = label.name();
            featureValues[attributeStore.getAttributeOffset(labelname)] = instanceOutcome.contains(labelname.split(CLASS_ATTRIBUTE_PREFIX)[1]) ? 1.0d : 0.0d;
        }
        weka.core.Instance wekaInstance;
        if (useDenseInstances) {
            wekaInstance = new DenseInstance(1.0, featureValues);
        } else {
            wekaInstance = new SparseInstance(1.0, featureValues);
        }
        wekaInstance.setDataset(wekaInstances);
        Double instanceWeight = instance.getWeight();
        if (useWeights) {
            wekaInstance.setWeight(instanceWeight);
        }
        // preprocessingFilter.input(wekaInstance);
        // saver.writeIncremental(preprocessingFilter.output());
        saver.writeIncremental(wekaInstance);
    }
    // finishes the incremental saving process
    saver.writeIncremental(null);
}