printMargins = false, printComplexityStatistics = false,
printGraph = false, classStatistics = false, printSource = false;
StringBuffer text = new StringBuffer();
DataSource trainSource = null, testSource = null;
ObjectInputStream objectInputStream = null;
BufferedInputStream xmlInputStream = null;
CostMatrix costMatrix = null;
StringBuffer schemeOptionsText = null;
long trainTimeStart = 0, trainTimeElapsed = 0,
testTimeStart = 0, testTimeElapsed = 0;
String xml = "";
String[] optionsTmp = null;
Classifier classifierBackup;
Classifier classifierClassifications = null;
int actualClassIndex = -1; // 0-based class index
String splitPercentageString = "";
double splitPercentage = -1;
boolean preserveOrder = false;
boolean trainSetPresent = false;
boolean testSetPresent = false;
String thresholdFile;
String thresholdLabel;
StringBuffer predsBuff = null; // predictions from cross-validation
AbstractOutput classificationOutput = null;
// help requested?
if (Utils.getFlag("h", options) || Utils.getFlag("help", options)) {
// global info requested as well?
boolean globalInfo = Utils.getFlag("synopsis", options) ||
Utils.getFlag("info", options);
throw new Exception("\nHelp requested."
+ makeOptionString(classifier, globalInfo));
}
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];
String tmpO = Utils.getOption('l', optionsTmp);
//if (Utils.getOption('l', optionsTmp).toLowerCase().endsWith(".xml")) {
if (tmpO.endsWith(".xml")) {
// try to load file as PMML first
boolean success = false;
try {
PMMLModel pmmlModel = PMMLFactory.getPMMLModel(tmpO);
if (pmmlModel instanceof PMMLClassifier) {
classifier = ((PMMLClassifier)pmmlModel);
success = true;
}
} catch (IllegalArgumentException ex) {
success = false;
}
if (!success) {
// load options from serialized data ('-l' is automatically erased!)
XMLClassifier xmlserial = new XMLClassifier();
OptionHandler cl = (OptionHandler) 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) {
if (objectInputFileName.endsWith(".xml")) {
// if this is the case then it means that a PMML classifier was
// successfully loaded earlier in the code
objectInputStream = null;
xmlInputStream = null;
} else {
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 = Double.parseDouble(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 =
(int) Math.round(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 (!(classifier instanceof weka.classifiers.misc.InputMappedClassifier)) {
if ((testSetPresent) && !test.equalHeaders(train)) {
throw new IllegalArgumentException("Train and test file not compatible!\n" + test.equalHeadersMsg(train));
}
}
}
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);
thresholdFile = Utils.getOption("threshold-file", options);
thresholdLabel = Utils.getOption("threshold-label", options);
String classifications = Utils.getOption("classifications", options);
String classificationsOld = Utils.getOption("p", options);
if (classifications.length() > 0) {
noOutput = true;
classificationOutput = AbstractOutput.fromCommandline(classifications);
classificationOutput.setHeader(template);
}
// backwards compatible with old "-p range" and "-distribution" options
else if (classificationsOld.length() > 0) {
noOutput = true;
classificationOutput = new PlainText();
classificationOutput.setHeader(template);
if (!classificationsOld.equals("0"))
classificationOutput.setAttributes(classificationsOld);
classificationOutput.setOutputDistribution(Utils.getFlag("distribution", options));
}
// -distribution flag needs -p option
else {
if (Utils.getFlag("distribution", options))
throw new Exception("Cannot print distribution without '-p' option!");
}
// if no training file given, we don't have any priors
if ( (!trainSetPresent) && (printComplexityStatistics) )
throw new Exception("Cannot print complexity statistics ('-k') without training file ('-t')!");
// If a model file is given, we can't process
// scheme-specific options
if (objectInputFileName.length() != 0) {
Utils.checkForRemainingOptions(options);
} else {
// Set options for classifier
if (classifier instanceof OptionHandler) {
for (int i = 0; i < options.length; i++) {
if (options[i].length() != 0) {
if (schemeOptionsText == null) {
schemeOptionsText = new StringBuffer();
}
if (options[i].indexOf(' ') != -1) {
schemeOptionsText.append('"' + options[i] + "\" ");
} else {
schemeOptionsText.append(options[i] + " ");
}
}
}
((OptionHandler)classifier).setOptions(options);
}
}
Utils.checkForRemainingOptions(options);
} catch (Exception e) {
throw new Exception("\nWeka exception: " + e.getMessage()
+ makeOptionString(classifier, false));
}
if (objectInputFileName.length() != 0) {
// Load classifier from file
if (objectInputStream != null) {
classifier = (Classifier) objectInputStream.readObject();
// try and read a header (if present)
Instances savedStructure = null;
try {
savedStructure = (Instances) objectInputStream.readObject();
} catch (Exception ex) {
// don't make a fuss
}
if (savedStructure != null) {
// test for compatibility with template
if (!template.equalHeaders(savedStructure)) {
throw new Exception("training and test set are not compatible\n" + template.equalHeadersMsg(savedStructure));
}
}
objectInputStream.close();
}
else if (xmlInputStream != null) {
// whether KOML is available has already been checked (objectInputStream would null otherwise)!
classifier = (Classifier) KOML.read(xmlInputStream);
xmlInputStream.close();
}
}
// Setup up evaluation objects
Evaluation trainingEvaluation = new Evaluation(new Instances(template, 0), costMatrix);