@Override public void setClass(Attribute att) { super.setClass(att); }
dataSet.setClass(classAtt); } else {
dataSet.setClass(classAtt); } else {
wekaTrainingData.setClass(wekaTrainingData.attribute("class")); classifier.buildClassifier(wekaTrainingData);
boolean assigned = false; if (classAtt != null) { dataSet.setClass(classAtt); assigned = true; } else {
/** * Load data instances from Weka ARFF file to memory for classification * training or testing. * * @param filename * Weka ARFF data file path. * @param className * name used in data to denote attribute which is the class * @return data instances * @throws IOException */ private Instances loadInstancesFromARFF(String filename, String className) throws IOException { DataSource source; try { source = new DataSource(filename); Instances data = source.getDataSet(); Attribute classAttribute = data.attribute(className); data.setClass(classAttribute); return data; } catch (Exception e) { // TODO Auto-generated catch block e.printStackTrace(); } return null; }
boolean assigned = false; if (classAtt != null) { dataSet.setClass(classAtt); assigned = true; } else {
public ToWekaUtils(Dataset data) { classes=new Vector<Object>(); classes.addAll(data.classes()); FastVector att = new FastVector(); for (int i = 0; i < data.noAttributes(); i++) { att.addElement(new Attribute("att" + i)); } classSet = data.classes().size() > 0; Attribute ca = null; if (classSet) { FastVector fvNominalVal = new FastVector(data.classes().size()); for (Object o : data.classes()) { fvNominalVal.addElement(o.toString()); } ca = new Attribute("classAtt", fvNominalVal); att.addElement(ca); } wData = new Instances("generated_from_java-ml_dataset", att, data.size()); if (classSet) { assert (ca != null); wData.setClass(ca); } for (net.sf.javaml.core.Instance i : data) { wData.add(instanceToWeka(i)); } }
instances.setClass(outcomeAttribute);
instances.setClass(outcomeAttribute);
private static Instances getDummyXORData() { List<String> values = new ArrayList<String>(); values.add("0"); values.add("1"); Attribute x1 = new Attribute("x1", values); Attribute x2 = new Attribute("x2", values); Attribute y = new Attribute("y", values); ArrayList<Attribute> attributes = new ArrayList<Attribute>(); attributes.add(x1); attributes.add(x2); attributes.add(y); Instances data = new Instances("xor", attributes, 4); for (int x1val = 0; x1val <= 1; ++x1val) { for (int x2val = 0; x2val <= 1; ++x2val) { for (int yval = 0; yval <= 1; ++yval) { double[] attValues = { x1val, x2val, yval }; DenseInstance instance = new DenseInstance(1.0, attValues); data.add(instance); } } } data.setClass(y); return data; }
Attribute classAttribute = insts.attribute(insts.numAttributes() - 1); InfoGainAttributeEval ig = new InfoGainAttributeEval(); insts.setClass(classAttribute); ig.buildEvaluator(insts);
masterInstance.setClass(outcomeAttribute); saver.setInstances(masterInstance);
masterInstance.setClass(outcomeAttribute); saver.setInstances(masterInstance);
attributeTable.setClass(ClassAttribute);
wekaInstances.setClass(outcomeAttribute);
compTestData.setClass(compTestData .attribute(Constants.CLASS_ATTRIBUTE_NAME + COMPATIBLE_OUTCOME_CLASS)); return compTestData;
compTestData.setClass(compTestData .attribute(Constants.CLASS_ATTRIBUTE_NAME + COMPATIBLE_OUTCOME_CLASS)); return compTestData;
.classAttribute().name(); Attribute classAtt = testData.attribute(className); testData.setClass(classAtt); predictions = evalUtils.getTestPredictions(classifier, testData); success = true;
.classAttribute().name(); Attribute classAtt = testData.attribute(className); testData.setClass(classAtt); predictions = evalUtils.getTestPredictions(classifier, testData); success = true;