/**
* Parses a given list of options. Valid options are:
*
* <p>-I num <br>
* The number of iterations to be performed. (default 1)
*
* <p>-E num <br>
* The exponent for the polynomial kernel. (default 1)
*
* <p>-S num <br>
* The seed for the random number generator. (default 1)
*
* <p>-M num <br>
* The maximum number of alterations allowed. (default 10000)
*
* <p>
*
* @param options the list of options as an array of strings
* @exception Exception if an option is not supported
*/
public void setOptions(String[] options) throws Exception {
String iterationsString = Utils.getOption('I', options);
if (iterationsString.length() != 0) {
m_NumIterations = Integer.parseInt(iterationsString);
} else {
m_NumIterations = 1;
}
String exponentsString = Utils.getOption('E', options);
if (exponentsString.length() != 0) {
m_Exponent = (new Double(exponentsString)).doubleValue();
} else {
m_Exponent = 1.0;
}
String seedString = Utils.getOption('S', options);
if (seedString.length() != 0) {
m_Seed = Integer.parseInt(seedString);
} else {
m_Seed = 1;
}
String alterationsString = Utils.getOption('M', options);
if (alterationsString.length() != 0) {
m_MaxK = Integer.parseInt(alterationsString);
} else {
m_MaxK = 10000;
}
}
/**
* Parses a given list of options. Valid options are:
*
* <p>-W classname <br>
* Specify the full class name of a weak classifier as the basis for bagging (required).
*
* <p>-I num <br>
* Set the number of bagging iterations (default 10).
*
* <p>-S seed <br>
* Random number seed for resampling (default 1).
*
* <p>-P num <br>
* Size of each bag, as a percentage of the training size (default 100).
*
* <p>-O <br>
* Compute out of bag error.
*
* <p>Options after -- are passed to the designated classifier.
*
* <p>
*
* @param options the list of options as an array of strings
* @exception Exception if an option is not supported
*/
@Override
public void setOptions(String[] options) throws Exception {
String bagSize = Utils.getOption('P', options);
if (bagSize.length() != 0) {
setBagSizePercent(Integer.parseInt(bagSize));
} else {
setBagSizePercent(100);
}
setCalcOutOfBag(Utils.getFlag('O', options));
super.setOptions(options);
}
/**
* Evaluates a clusterer with the options given in an array of strings. It takes the string
* indicated by "-t" as training file, the string indicated by "-T" as test file. If the test file
* is missing, a stratified ten-fold cross-validation is performed (distribution clusterers only).
* Using "-x" you can change the number of folds to be used, and using "-s" the random seed. If
* the "-p" option is present it outputs the classification for each test instance. If you provide
* the name of an object file using "-l", a clusterer will be loaded from the given file. If you
* provide the name of an object file using "-d", the clusterer built from the training data will
* be saved to the given file.
*
* @param clusterer machine learning clusterer
* @param options the array of string containing the options
* @exception Exception if model could not be evaluated successfully
* @return a string describing the results
*/
public static String evaluateClusterer(Clusterer clusterer, String[] options) throws Exception {
int seed = 1, folds = 10;
boolean doXval = false;
Instances train = null;
Instances test = null;
Random random;
String trainFileName,
testFileName,
seedString,
foldsString,
objectInputFileName,
objectOutputFileName,
attributeRangeString;
String[] savedOptions = null;
boolean printClusterAssignments = false;
Range attributesToOutput = null;
ObjectInputStream objectInputStream = null;
ObjectOutputStream objectOutputStream = null;
StringBuffer text = new StringBuffer();
int theClass = -1; // class based evaluation of clustering
try {
if (Utils.getFlag('h', options)) {
throw new Exception("Help requested.");
}
// Get basic options (options the same for all clusterers
// printClusterAssignments = Utils.getFlag('p', options);
objectInputFileName = Utils.getOption('l', options);
objectOutputFileName = Utils.getOption('d', options);
trainFileName = Utils.getOption('t', options);
testFileName = Utils.getOption('T', 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) {
printClusterAssignments = true;
if (!attributeRangeString.equals("0")) attributesToOutput = new Range(attributeRangeString);
}
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) && (printClusterAssignments == false)) {
throw new Exception("Can't use both train and model file " + "unless -p specified.");
}
}
seedString = Utils.getOption('s', options);
if (seedString.length() != 0) {
seed = Integer.parseInt(seedString);
}
foldsString = Utils.getOption('x', options);
if (foldsString.length() != 0) {
folds = Integer.parseInt(foldsString);
doXval = true;
}
} catch (Exception e) {
throw new Exception('\n' + e.getMessage() + makeOptionString(clusterer));
}
try {
if (trainFileName.length() != 0) {
train = new Instances(new BufferedReader(new FileReader(trainFileName)));
String classString = Utils.getOption('c', options);
if (classString.length() != 0) {
if (classString.compareTo("last") == 0) {
theClass = train.numAttributes();
} else if (classString.compareTo("first") == 0) {
theClass = 1;
} else {
theClass = Integer.parseInt(classString);
}
if (doXval || testFileName.length() != 0) {
throw new Exception("Can only do class based evaluation on the " + "training data");
}
if (objectInputFileName.length() != 0) {
throw new Exception("Can't load a clusterer and do class based " + "evaluation");
}
}
if (theClass != -1) {
if (theClass < 1 || theClass > train.numAttributes()) {
throw new Exception("Class is out of range!");
}
if (!train.attribute(theClass - 1).isNominal()) {
throw new Exception("Class must be nominal!");
}
train.setClassIndex(theClass - 1);
}
}
if (objectInputFileName.length() != 0) {
objectInputStream = new ObjectInputStream(new FileInputStream(objectInputFileName));
}
if (objectOutputFileName.length() != 0) {
objectOutputStream = new ObjectOutputStream(new FileOutputStream(objectOutputFileName));
}
} catch (Exception e) {
throw new Exception("ClusterEvaluation: " + e.getMessage() + '.');
}
// Save options
if (options != null) {
savedOptions = new String[options.length];
System.arraycopy(options, 0, savedOptions, 0, options.length);
}
if (objectInputFileName.length() != 0) {
Utils.checkForRemainingOptions(options);
}
// Set options for clusterer
if (clusterer instanceof OptionHandler) {
((OptionHandler) clusterer).setOptions(options);
}
Utils.checkForRemainingOptions(options);
if (objectInputFileName.length() != 0) {
// Load the clusterer from file
clusterer = (Clusterer) objectInputStream.readObject();
objectInputStream.close();
} else {
// Build the clusterer if no object file provided
if (theClass == -1) {
clusterer.buildClusterer(train);
} else {
Remove removeClass = new Remove();
removeClass.setAttributeIndices("" + theClass);
removeClass.setInvertSelection(false);
removeClass.setInputFormat(train);
Instances clusterTrain = Filter.useFilter(train, removeClass);
clusterer.buildClusterer(clusterTrain);
ClusterEvaluation ce = new ClusterEvaluation();
ce.setClusterer(clusterer);
ce.evaluateClusterer(train);
return "\n\n=== Clustering stats for training data ===\n\n" + ce.clusterResultsToString();
}
}
/* Output cluster predictions only (for the test data if specified,
otherwise for the training data */
if (printClusterAssignments) {
return printClusterings(clusterer, train, testFileName, attributesToOutput);
}
text.append(clusterer.toString());
text.append(
"\n\n=== Clustering stats for training data ===\n\n"
+ printClusterStats(clusterer, trainFileName));
if (testFileName.length() != 0) {
text.append(
"\n\n=== Clustering stats for testing data ===\n\n"
+ printClusterStats(clusterer, testFileName));
}
if ((clusterer instanceof DensityBasedClusterer)
&& (doXval == true)
&& (testFileName.length() == 0)
&& (objectInputFileName.length() == 0)) {
// cross validate the log likelihood on the training data
random = new Random(seed);
random.setSeed(seed);
train.randomize(random);
text.append(
crossValidateModel(clusterer.getClass().getName(), train, folds, savedOptions, random));
}
// Save the clusterer if an object output file is provided
if (objectOutputFileName.length() != 0) {
objectOutputStream.writeObject(clusterer);
objectOutputStream.flush();
objectOutputStream.close();
}
return text.toString();
}
/** Main method. */
public static void main(String[] args) {
try {
String[] options = args;
StRipShort classifier = new StRipShort();
InstancesShort train = null, tempTrain, test = null, template = null;
int seed = 1, folds = 10, classIndex = -1;
String trainFileName,
testFileName,
sourceClass,
classIndexString,
seedString,
foldsString,
objectInputFileName,
objectOutputFileName,
attributeRangeString;
boolean IRstatistics = false,
noOutput = false,
printClassifications = false,
trainStatistics = true,
printMargins = false,
printComplexityStatistics = false,
printGraph = false,
classStatistics = false,
printSource = false;
StringBuffer text = new StringBuffer();
BufferedReader trainReader = null, testReader = null;
ObjectInputStream objectInputStream = null;
CostMatrix costMatrix = null;
StringBuffer schemeOptionsText = null;
Range attributesToOutput = null;
long trainTimeStart = 0, trainTimeElapsed = 0, testTimeStart = 0, testTimeElapsed = 0;
classIndexString = Utils.getOption('c', options);
if (classIndexString.length() != 0) {
classIndex = Integer.parseInt(classIndexString);
}
trainFileName = Utils.getOption('t', options);
objectInputFileName = Utils.getOption('l', options);
objectOutputFileName = Utils.getOption('d', options);
testFileName = Utils.getOption('T', options);
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.");
}
}
try {
if (trainFileName.length() != 0) {
trainReader = new BufferedReader(new FileReader(trainFileName));
}
if (testFileName.length() != 0) {
testReader = new BufferedReader(new FileReader(testFileName));
}
if (objectInputFileName.length() != 0) {
InputStream is = new FileInputStream(objectInputFileName);
if (objectInputFileName.endsWith(".gz")) {
is = new GZIPInputStream(is);
}
objectInputStream = new ObjectInputStream(is);
}
} catch (Exception e) {
throw new Exception("Can't open file " + e.getMessage() + '.');
}
if (testFileName.length() != 0) {
template = test = new InstancesShort(testReader, 1);
if (classIndex != -1) {
test.setClassIndex(classIndex - 1);
} else {
test.setClassIndex(test.numAttributes() - 1);
}
if (classIndex > test.numAttributes()) {
throw new Exception("Index of class attribute too large.");
}
}
seedString = Utils.getOption('s', options);
if (seedString.length() != 0) {
seed = Integer.parseInt(seedString);
}
foldsString = Utils.getOption('x', options);
if (foldsString.length() != 0) {
folds = Integer.parseInt(foldsString);
}
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);
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] + " ");
}
}
}
classifier.setOptions(options);
Utils.checkForRemainingOptions(options);
train = new ModifiedInstancesShort(trainReader);
if (classIndex != -1) {
train.setClassIndex(classIndex - 1);
} else {
train.setClassIndex(train.numAttributes() - 1);
}
train.cleanUpValues();
// System.err.println(train);
classifier.buildClassifier(train);
} catch (Exception e) {
e.printStackTrace();
System.err.println(e.getMessage());
}
}