DataSource trainSource = null, testSource = null;
ObjectInputStream objectInputStream = null;
BufferedInputStream xmlInputStream = null;
CostMatrix costMatrix = null;
StringBuffer schemeOptionsText = null;
Range attributesToOutput = null;
long trainTimeStart = 0, trainTimeElapsed = 0,
testTimeStart = 0, testTimeElapsed = 0;
String xml = "";
String[] optionsTmp = null;
Classifier classifierBackup;
Classifier classifierClassifications = null;
boolean printDistribution = false;
int actualClassIndex = -1; // 0-based class index
String splitPercentageString = "";
int splitPercentage = -1;
boolean preserveOrder = false;
boolean trainSetPresent = false;
boolean testSetPresent = false;
String thresholdFile;
String thresholdLabel;
StringBuffer predsBuff = null; // predictions from cross-validation
// help requested?
if (Utils.getFlag("h", options) || Utils.getFlag("help", options)) {
throw new Exception("\nHelp requested." + makeOptionString(classifier));
}
try {
// do we get the input from XML instead of normal parameters?
xml = Utils.getOption("xml", options);
if (!xml.equals("")) {
options = new XMLOptions(xml).toArray();
}
// is the input model only the XML-Options, i.e. w/o built model?
optionsTmp = new String[options.length];
for (int i = 0; i < options.length; i++) {
optionsTmp[i] = options[i];
}
if (Utils.getOption('l', optionsTmp).toLowerCase().endsWith(".xml")) {
// load options from serialized data ('-l' is automatically erased!)
XMLClassifier xmlserial = new XMLClassifier();
Classifier cl = (Classifier) xmlserial.read(Utils.getOption('l', options));
// merge options
optionsTmp = new String[options.length + cl.getOptions().length];
System.arraycopy(cl.getOptions(), 0, optionsTmp, 0, cl.getOptions().length);
System.arraycopy(options, 0, optionsTmp, cl.getOptions().length, options.length);
options = optionsTmp;
}
noCrossValidation = Utils.getFlag("no-cv", options);
// Get basic options (options the same for all schemes)
classIndexString = Utils.getOption('c', options);
if (classIndexString.length() != 0) {
if (classIndexString.equals("first")) {
classIndex = 1;
} else if (classIndexString.equals("last")) {
classIndex = -1;
} else {
classIndex = Integer.parseInt(classIndexString);
}
}
trainFileName = Utils.getOption('t', options);
objectInputFileName = Utils.getOption('l', options);
objectOutputFileName = Utils.getOption('d', options);
testFileName = Utils.getOption('T', options);
foldsString = Utils.getOption('x', options);
if (foldsString.length() != 0) {
folds = Integer.parseInt(foldsString);
}
seedString = Utils.getOption('s', options);
if (seedString.length() != 0) {
seed = Integer.parseInt(seedString);
}
if (trainFileName.length() == 0) {
if (objectInputFileName.length() == 0) {
throw new Exception("No training file and no object " +
"input file given.");
}
if (testFileName.length() == 0) {
throw new Exception("No training file and no test " +
"file given.");
}
} else if ((objectInputFileName.length() != 0) &&
((!(classifier instanceof UpdateableClassifier)) ||
(testFileName.length() == 0))) {
throw new Exception("Classifier not incremental, or no " +
"test file provided: can't " +
"use both train and model file.");
}
try {
if (trainFileName.length() != 0) {
trainSetPresent = true;
trainSource = new DataSource(trainFileName);
}
if (testFileName.length() != 0) {
testSetPresent = true;
testSource = new DataSource(testFileName);
}
if (objectInputFileName.length() != 0) {
InputStream is = new FileInputStream(objectInputFileName);
if (objectInputFileName.endsWith(".gz")) {
is = new GZIPInputStream(is);
}
// load from KOML?
if (!(objectInputFileName.endsWith(".koml") && KOML.isPresent())) {
objectInputStream = new ObjectInputStream(is);
xmlInputStream = null;
} else {
objectInputStream = null;
xmlInputStream = new BufferedInputStream(is);
}
}
} catch (Exception e) {
throw new Exception("Can't open file " + e.getMessage() + '.');
}
if (testSetPresent) {
template = test = testSource.getStructure();
if (classIndex != -1) {
test.setClassIndex(classIndex - 1);
} else {
if ((test.classIndex() == -1) || (classIndexString.length() != 0)) {
test.setClassIndex(test.numAttributes() - 1);
}
}
actualClassIndex = test.classIndex();
} else {
// percentage split
splitPercentageString = Utils.getOption("split-percentage", options);
if (splitPercentageString.length() != 0) {
if (foldsString.length() != 0) {
throw new Exception(
"Percentage split cannot be used in conjunction with " + "cross-validation ('-x').");
}
splitPercentage = Integer.parseInt(splitPercentageString);
if ((splitPercentage <= 0) || (splitPercentage >= 100)) {
throw new Exception("Percentage split value needs be >0 and <100.");
}
} else {
splitPercentage = -1;
}
preserveOrder = Utils.getFlag("preserve-order", options);
if (preserveOrder) {
if (splitPercentage == -1) {
throw new Exception("Percentage split ('-percentage-split') is missing.");
}
}
// create new train/test sources
if (splitPercentage > 0) {
testSetPresent = true;
Instances tmpInst = trainSource.getDataSet(actualClassIndex);
if (!preserveOrder) {
tmpInst.randomize(new Random(seed));
}
int trainSize = tmpInst.numInstances() * splitPercentage / 100;
int testSize = tmpInst.numInstances() - trainSize;
Instances trainInst = new Instances(tmpInst, 0, trainSize);
Instances testInst = new Instances(tmpInst, trainSize, testSize);
trainSource = new DataSource(trainInst);
testSource = new DataSource(testInst);
template = test = testSource.getStructure();
if (classIndex != -1) {
test.setClassIndex(classIndex - 1);
} else {
if ((test.classIndex() == -1) || (classIndexString.length() != 0)) {
test.setClassIndex(test.numAttributes() - 1);
}
}
actualClassIndex = test.classIndex();
}
}
if (trainSetPresent) {
template = train = trainSource.getStructure();
if (classIndex != -1) {
train.setClassIndex(classIndex - 1);
} else {
if ((train.classIndex() == -1) || (classIndexString.length() != 0)) {
train.setClassIndex(train.numAttributes() - 1);
}
}
actualClassIndex = train.classIndex();
if ((testSetPresent) && !test.equalHeaders(train)) {
throw new IllegalArgumentException("Train and test file not compatible!");
}
}
if (template == null) {
throw new Exception("No actual dataset provided to use as template");
}
costMatrix = handleCostOption(
Utils.getOption('m', options), template.numClasses());
classStatistics = Utils.getFlag('i', options);
noOutput = Utils.getFlag('o', options);
trainStatistics = !Utils.getFlag('v', options);
printComplexityStatistics = Utils.getFlag('k', options);
printMargins = Utils.getFlag('r', options);
printGraph = Utils.getFlag('g', options);
sourceClass = Utils.getOption('z', options);
printSource = (sourceClass.length() != 0);
printDistribution = Utils.getFlag("distribution", options);
thresholdFile = Utils.getOption("threshold-file", options);
thresholdLabel = Utils.getOption("threshold-label", options);
// Check -p option
try {
attributeRangeString = Utils.getOption('p', options);
} catch (Exception e) {
throw new Exception(e.getMessage() + "\nNOTE: the -p option has changed. " +
"It now expects a parameter specifying a range of attributes " +
"to list with the predictions. Use '-p 0' for none.");
}
if (attributeRangeString.length() != 0) {
printClassifications = true;
if (!attributeRangeString.equals("0")) {
attributesToOutput = new Range(attributeRangeString);
}
}
if (!printClassifications && printDistribution) {
throw new Exception("Cannot print distribution without '-p' option!");