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

Example 26 with Instances

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

the class WekaUtilTest method makeOutcomeClassesCompatibleTest.

@Test
public void makeOutcomeClassesCompatibleTest() throws Exception {
    Instances train = WekaUtils.getInstances(new File("src/test/resources/utils/train.arff"), false);
    Instances test = WekaUtils.getInstances(new File("src/test/resources/utils/test.arff"), false);
    Instances testCompatible = WekaUtils.makeOutcomeClassesCompatible(train, test, false);
    System.out.println(WekaUtils.getClassLabels(testCompatible, false));
    assertEquals(2, WekaUtils.getClassLabels(testCompatible, false).size());
}

Example 27 with Instances

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

the class WekaUtilTest method tcInstanceToWekaInstanceRegressionTest.

@Test
public void tcInstanceToWekaInstanceRegressionTest() throws Exception {
    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"));
    Instances trainingData = new Instances("test", attributes, 0);
    weka.core.Instance wekaInstance1 = WekaUtils.tcInstanceToWekaInstance(i1, trainingData, null, true);
    weka.core.Instance wekaInstance2 = WekaUtils.tcInstanceToWekaInstance(i2, trainingData, null, true);
    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 28 with Instances

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

the class WekaTestTask method execute.

@Override
public void execute(TaskContext aContext) throws Exception {
    boolean multiLabel = learningMode.equals(Constants.LM_MULTI_LABEL);
    File arffFileTrain = WekaUtils.getFile(aContext, TEST_TASK_INPUT_KEY_TRAINING_DATA, Constants.FILENAME_DATA_IN_CLASSIFIER_FORMAT, AccessMode.READONLY);
    File arffFileTest = WekaUtils.getFile(aContext, TEST_TASK_INPUT_KEY_TEST_DATA, Constants.FILENAME_DATA_IN_CLASSIFIER_FORMAT, AccessMode.READONLY);
    Instances trainData = WekaUtils.getInstances(arffFileTrain, multiLabel);
    Instances testData = WekaUtils.getInstances(arffFileTest, multiLabel);
    // do not balance in regression experiments
    if (!learningMode.equals(Constants.LM_REGRESSION)) {
        testData = WekaUtils.makeOutcomeClassesCompatible(trainData, testData, multiLabel);
    }
    Instances copyTestData = new Instances(testData);
    trainData = WekaUtils.removeInstanceId(trainData, multiLabel);
    testData = WekaUtils.removeInstanceId(testData, multiLabel);
    // FEATURE SELECTION
    if (!learningMode.equals(Constants.LM_MULTI_LABEL)) {
        if (featureSearcher != null && attributeEvaluator != null) {
            AttributeSelection attSel = WekaUtils.featureSelectionSinglelabel(aContext, trainData, featureSearcher, attributeEvaluator);
            File file = WekaUtils.getFile(aContext, "", WekaTestTask.featureSelectionFile, AccessMode.READWRITE);
            FileUtils.writeStringToFile(file, attSel.toResultsString(), "utf-8");
            if (applySelection) {
                Logger.getLogger(getClass()).info("APPLYING FEATURE SELECTION");
                trainData = attSel.reduceDimensionality(trainData);
                testData = attSel.reduceDimensionality(testData);
            }
        }
    } else {
        if (attributeEvaluator != null && labelTransformationMethod != null && numLabelsToKeep > 0) {
            Remove attSel = WekaUtils.featureSelectionMultilabel(aContext, trainData, attributeEvaluator, labelTransformationMethod, numLabelsToKeep);
            if (applySelection) {
                Logger.getLogger(getClass()).info("APPLYING FEATURE SELECTION");
                trainData = WekaUtils.applyAttributeSelectionFilter(trainData, attSel);
                testData = WekaUtils.applyAttributeSelectionFilter(testData, attSel);
            }
        }
    }
    // build classifier
    Classifier cl = WekaUtils.getClassifier(learningMode, classificationArguments);
    // file to hold prediction results
    File evalOutput = WekaUtils.getFile(aContext, "", evaluationBin, AccessMode.READWRITE);
    // evaluation & prediction generation
    if (multiLabel) {
        // we don't need to build the classifier - meka does this
        // internally
        Result r = WekaUtils.getEvaluationMultilabel(cl, trainData, testData, threshold);
        WekaUtils.writeMlResultToFile(new MultilabelResult(r.allTrueValues(), r.allPredictions(), threshold), evalOutput);
        testData = WekaUtils.getPredictionInstancesMultiLabel(testData, cl, WekaUtils.getMekaThreshold(threshold, r, trainData));
        testData = WekaUtils.addInstanceId(testData, copyTestData, true);
    } else {
        // train the classifier on the train set split - not necessary in multilabel setup, but
        // in single label setup
        cl.buildClassifier(trainData);
        weka.core.SerializationHelper.write(evalOutput.getAbsolutePath(), WekaUtils.getEvaluationSinglelabel(cl, trainData, testData));
        testData = WekaUtils.getPredictionInstancesSingleLabel(testData, cl);
        testData = WekaUtils.addInstanceId(testData, copyTestData, false);
    }
    // Write out the prediction - the data sink expects an .arff ending file so we game it a bit
    // and rename the file afterwards to .txt
    File predictionFile = WekaUtils.getFile(aContext, "", Constants.FILENAME_PREDICTIONS, AccessMode.READWRITE);
    File arffDummy = new File(predictionFile.getParent(), "prediction.arff");
    DataSink.write(arffDummy.getAbsolutePath(), testData);
    FileUtils.moveFile(arffDummy, predictionFile);
}

Example 29 with Instances

use of weka.core.Instances in project iobserve-analysis by research-iobserve.

the class TVectorQuantizationClustering method printInstances.

private void printInstances(final ClusteringResults results) {
    results.printClusteringResults();
    final Instances centroids = results.getClusteringMetrics().getCentroids();
    for (int i = 0; i < centroids.numInstances(); i++) {
        String logString = "";
        logString += "***************************";
        logString += "Cluster " + i;
        logString += "***************************";
        final Instance instance = centroids.instance(i);
        for (int a = 0; a < instance.numAttributes(); a++) {
            logString += centroids.attribute(a).name() + " : " + instance.value(a);
        }
        TVectorQuantizationClustering.LOGGER.info(logString);
    }
}

Example 30 with Instances

use of weka.core.Instances in project iobserve-analysis by research-iobserve.

the class ClusterMerger method execute.

/*
     * (non-Javadoc)
     *
     * @see teetime.framework.AbstractConsumerStage#execute(java.lang.Object)
     */
@Override
protected void execute(final Map<Integer, List<Pair<Instance, Double>>> clustering) throws Exception {
    /**
     * simply pick the first instance of every cluster lookup attributes to build a new
     * instances Object
     */
    Instance instance = clustering.entrySet().iterator().next().getValue().get(0).getElement1();
    final FastVector attributes = new FastVector();
    for (int j = 0; j < instance.numAttributes(); j++) {
        attributes.addElement(instance.attribute(j));
    }
    final Instances result = new Instances("Clustering Result", attributes, clustering.size());
    for (final List<Pair<Instance, Double>> entry : clustering.values()) {
        if (!entry.isEmpty()) {
            instance = entry.get(0).getElement1();
            result.add(instance);
        }
    }
    this.printInstances(result);
    this.outputPort.send(result);
}