DataSource source = new DataSource(System.in); i = source.getDataSet(); System.out.println(i.toSummaryString()); DataSource source = new DataSource(args[0]); i = source.getDataSet(); System.out.println(i.toSummaryString()); DataSource source1 = new DataSource(args[1]); DataSource source2 = new DataSource(args[2]); i = Instances .mergeInstances(source1.getDataSet(), source2.getDataSet()); System.out.println(i); DataSource source1 = new DataSource(args[1]); DataSource source2 = new DataSource(args[2]); String msg = source1.getStructure().equalHeadersMsg( source2.getStructure()); if (msg != null) { throw new Exception("The two datasets have different headers:\n" + msg); Instances structure = source1.getStructure(); System.out.println(source1.getStructure()); while (source1.hasMoreElements(structure)) { System.out.println(source1.nextElement(structure)); structure = source2.getStructure(); while (source2.hasMoreElements(structure)) {
Instances data = DataSource.read(args[0]); MLUtils.prepareData(data);
/** * for testing only - takes a data file as input. * * @param args the commandline arguments * @throws Exception if something goes wrong */ public static void main(String[] args) throws Exception { if (args.length != 1) { System.out.println("\nUsage: " + DataSource.class.getName() + " <file>\n"); System.exit(1); } DataSource loader = new DataSource(args[0]); System.out.println("Incremental? " + loader.isIncremental()); System.out.println("Loader: " + loader.getLoader().getClass().getName()); System.out.println("Data:\n"); Instances structure = loader.getStructure(); System.out.println(structure); while (loader.hasMoreElements(structure)) { System.out.println(loader.nextElement(structure)); } Instances inst = loader.getDataSet(); loader = new DataSource(inst); System.out.println("\n\nProxy-Data:\n"); System.out.println(loader.getStructure()); while (loader.hasMoreElements(structure)) { System.out.println(loader.nextElement(inst)); } }
template = test = new DataSource(testFileName).getStructure(); if (classIndex != -1) { test.setClassIndex(classIndex - 1); template = train = new DataSource(trainFileName).getStructure(); if (classIndex != -1) { train.setClassIndex(classIndex - 1); if ((classifier instanceof UpdateableClassifier) && !forceBatchTraining) { // Build classifier incrementally trainTimeStart = System.currentTimeMillis(); DataSource trainSource = new DataSource(trainFileName); trainSource.getStructure(); // Need to advance in the file to get to the data if (objectInputFileName.length() <= 0) { // Only need to initialize classifier if we haven't loaded one classifier.buildClassifier(new Instances(train, 0)); while (trainSource.hasMoreElements(train)) { ((UpdateableClassifier) classifier).updateClassifier(trainSource.nextElement(train)); } else if (classifier instanceof IterativeClassifier && continueIteratingIterative) { IterativeClassifier iClassifier = (IterativeClassifier)classifier; Instances tempTrain = new DataSource(trainFileName).getDataSet(actualClassIndex); iClassifier.initializeClassifier(tempTrain); while (iClassifier.next()){ Instances tempTrain = new DataSource(trainFileName).getDataSet(actualClassIndex); if (classifier instanceof weka.classifiers.misc.InputMappedClassifier) { Instances mappedClassifierDataset = ((weka.classifiers.misc.InputMappedClassifier) classifier) if (testFileName.length() > 0) { // CASE 1: SEPARATE TEST SET
source = new DataSource(m_TestLoader); userTestStructure = source.getStructure(); userTestStructure.setClassIndex(m_TestClassIndex); break; case 4: // Test on user split if (source.isIncremental()) { outBuff.append("user supplied test set: " + " size unknown (reading incrementally)\n"); } else { outBuff.append("user supplied test set: " + source.getDataSet().numInstances() + " instances\n"); while (source.hasMoreElements(userTestStructure)) { instance = source.nextElement(userTestStructure);
template = test = new DataSource(testFileName).getStructure(); if (classIndex != -1) { test.setClassIndex(classIndex - 1); template = train = new DataSource(trainFileName).getStructure(); if (classIndex != -1) { train.setClassIndex(classIndex - 1); if ((classifier instanceof UpdateableClassifier) && !forceBatchTraining) { // Build classifier incrementally trainTimeStart = System.currentTimeMillis(); DataSource trainSource = new DataSource(trainFileName); trainSource.getStructure(); // Need to advance in the file to get to the data if (objectInputFileName.length() <= 0) { // Only need to initialize classifier if we haven't loaded one classifier.buildClassifier(new Instances(train, 0)); while (trainSource.hasMoreElements(train)) { ((UpdateableClassifier) classifier).updateClassifier(trainSource.nextElement(train)); Instances tempTrain = new DataSource(trainFileName).getDataSet(actualClassIndex); if (classifier instanceof weka.classifiers.misc.InputMappedClassifier) { Instances mappedClassifierDataset = ((weka.classifiers.misc.InputMappedClassifier) classifier) if (testFileName.length() > 0) { // CASE 1: SEPARATE TEST SET predsBuff.append("\n=== Predictions on test data ===\n\n"); classificationOutput.print(classifier, new DataSource(testFileName)); } else if (splitPercentage > 0) { // CASE 2: PERCENTAGE SPLIT Instances tmpInst = new DataSource(trainFileName).getDataSet(actualClassIndex); if (!preserveOrder) { tmpInst.randomize(new Random(seed));
source = new DataSource(m_TestLoader); userTestStructure = source.getStructure(); userTestStructure.setClassIndex(m_TestClassIndex); break; case 4: // Test on user split if (source.isIncremental()) { outBuff.append("user supplied test set: " + " size unknown (reading incrementally)\n"); } else { outBuff.append("user supplied test set: " + source.getDataSet().numInstances() + " instances\n"); while (source.hasMoreElements(userTestStructure)) { instance = source.nextElement(userTestStructure);
((ArffLoader) m_TestLoader).setRetainStringVals(true); source = new DataSource(m_TestLoader); userTestStructure = source.getStructure(); userTestStructure.setClassIndex(m_TestClassIndex); } else { outBuff.append("Instances: " + source.getDataSet().numInstances() + "\n"); while (source.hasMoreElements(userTestStructure)) { instance = source.nextElement(userTestStructure);
((ArffLoader) m_TestLoader).setRetainStringVals(true); source = new DataSource(m_TestLoader); userTestStructure = source.getStructure(); userTestStructure.setClassIndex(m_TestClassIndex); } else { outBuff.append("Instances: " + source.getDataSet().numInstances() + "\n"); while (source.hasMoreElements(userTestStructure)) { instance = source.nextElement(userTestStructure);
source = new DataSource(trainFileName); train = source.getStructure(); clusterer.buildClusterer(source.getStructure()); while (source.hasMoreElements(train)) { inst = source.nextElement(train); ((UpdateableClusterer) clusterer).updateClusterer(inst); clusterer.buildClusterer(source.getDataSet()); clusterer.buildClusterer(clusterTrain); trainHeader = clusterTrain; while (source.hasMoreElements(train)) { inst = source.nextElement(train); removeClass.input(inst); removeClass.batchFinished(); } else { Instances clusterTrain = Filter.useFilter(source.getDataSet(), removeClass); clusterer.buildClusterer(clusterTrain); trainHeader = clusterTrain; DataSource test = new DataSource(testFileName); Instances testStructure = test.getStructure(); if (!trainHeader.equalHeaders(testStructure)) { throw new Exception("Training and testing data are not compatible\n" train = source.getDataSet();
source = new DataSource(trainFileName); train = source.getStructure(); clusterer.buildClusterer(source.getStructure()); while (source.hasMoreElements(train)) { inst = source.nextElement(train); ((UpdateableClusterer) clusterer).updateClusterer(inst); clusterer.buildClusterer(source.getDataSet()); clusterer.buildClusterer(clusterTrain); trainHeader = clusterTrain; while (source.hasMoreElements(train)) { inst = source.nextElement(train); removeClass.input(inst); removeClass.batchFinished(); } else { Instances clusterTrain = Filter.useFilter(source.getDataSet(), removeClass); clusterer.buildClusterer(clusterTrain); trainHeader = clusterTrain; DataSource test = new DataSource(testFileName); Instances testStructure = test.getStructure(); if (!trainHeader.equalHeaders(testStructure)) { throw new Exception("Training and testing data are not compatible\n" train = source.getDataSet();
firstInput = new DataSource(fileName); } else { throw new Exception("No first input file given.\n"); secondInput = new DataSource(fileName); } else { throw new Exception("No second input file given.\n"); throw new Exception("Help requested.\n"); firstData = firstInput.getStructure(); secondData = secondInput.getStructure(); if (!secondData.equalHeaders(firstData)) { throw new Exception("Input file formats differ.\n" while (firstInput.hasMoreElements(firstData)) { inst = firstInput.nextElement(firstData); if (filter.input(inst)) { if (!printedHeader) { while (secondInput.hasMoreElements(secondData)) { inst = secondInput.nextElement(secondData); if (filter.input(inst)) { if (!printedHeader) {
input = new DataSource(infileName); } else { input = new DataSource(System.in); data = input.getStructure(); if (classIndex.length() != 0) { if (classIndex.equals("first")) { while (input.hasMoreElements(data)) { inst = input.nextElement(data); if (debug) { System.err.println("Input instance to filter");
firstInput = new DataSource(fileName); } else { throw new Exception("No first input file given.\n"); secondInput = new DataSource(fileName); } else { throw new Exception("No second input file given.\n"); throw new Exception("Help requested.\n"); firstData = firstInput.getStructure(); secondData = secondInput.getStructure(); if (!secondData.equalHeaders(firstData)) { throw new Exception("Input file formats differ.\n" while (firstInput.hasMoreElements(firstData)) { inst = firstInput.nextElement(firstData); if (filter.input(inst)) { if (!printedHeader) { while (secondInput.hasMoreElements(secondData)) { inst = secondInput.nextElement(secondData); if (filter.input(inst)) { if (!printedHeader) {
input = new DataSource(infileName); } else { input = new DataSource(System.in); data = input.getStructure(); if (classIndex.length() != 0) { if (classIndex.equals("first")) { while (input.hasMoreElements(data)) { inst = input.nextElement(data); if (debug) { System.err.println("Input instance to filter");
source = new DataSource(testFileName); } else { source = new DataSource(test); testRaw = source.getStructure(test.classIndex()); : new Instances(source.getStructure(), 0); i = 0; while (source.hasMoreElements(testRaw)) { inst = source.nextElement(testRaw); if (filter != null) { filter.input(inst);
DataSource source = new DataSource(System.in); i = source.getDataSet(); System.out.println(i.toSummaryString()); DataSource source = new DataSource(args[0]); i = source.getDataSet(); System.out.println(i.toSummaryString()); DataSource source1 = new DataSource(args[1]); DataSource source2 = new DataSource(args[2]); i = Instances .mergeInstances(source1.getDataSet(), source2.getDataSet()); System.out.println(i); DataSource source1 = new DataSource(args[1]); DataSource source2 = new DataSource(args[2]); String msg = source1.getStructure().equalHeadersMsg( source2.getStructure()); if (msg != null) { throw new Exception("The two datasets have different headers:\n" + msg); Instances structure = source1.getStructure(); System.out.println(source1.getStructure()); while (source1.hasMoreElements(structure)) { System.out.println(source1.nextElement(structure)); structure = source2.getStructure(); while (source2.hasMoreElements(structure)) {
source = new DataSource(testFileName); } else { source = new DataSource(test); testRaw = source.getStructure(test.classIndex()); : new Instances(source.getStructure(), 0); i = 0; while (source.hasMoreElements(testRaw)) { inst = source.nextElement(testRaw); if (filter != null) { filter.input(inst);
DataSource source = new DataSource(fileName); Instances structure = source.getStructure(); Instances forBatchPredictors = (clusterer instanceof BatchPredictor && ((BatchPredictor) clusterer) .implementsMoreEfficientBatchPrediction()) ? new Instances( source.getStructure(), 0) : null; while (source.hasMoreElements(structure)) { inst = source.nextElement(structure); if (forBatchPredictors != null) { forBatchPredictors.add(inst);
DataSource source = new DataSource(getInitFile().getAbsolutePath()); Instances data = source.getDataSet(); m_InitFileClassIndex.setUpper(data.numAttributes() - 1); data.setClassIndex(m_InitFileClassIndex.getIndex());