private static Instances convertToInstances(
final IScope scope,
final IList<String> attributes,
final IAddressableContainer<Integer, IAgent, Integer, IAgent> agents)
throws GamaRuntimeException {
FastVector attribs = new FastVector();
for (String att : attributes) {
attribs.addElement(new Attribute(att));
}
Instances dataset =
new Instances(scope.getAgentScope().getName(), attribs, agents.length(scope));
for (IAgent ag : agents.iterable(scope)) {
int nb = attributes.size();
double vals[] = new double[nb];
for (int i = 0; i < nb; i++) {
String attrib = attributes.get(i);
Double var = Cast.asFloat(scope, ag.getDirectVarValue(scope, attrib));
vals[i] = var;
}
Instance instance = new Instance(1, vals);
dataset.add(instance);
}
return dataset;
}
/**
* Handles the various button clicking type activities.
*
* @param e a value of type 'ActionEvent'
*/
public void actionPerformed(ActionEvent e) {
if (e.getSource() == m_ConfigureBut) {
selectProperty();
} else if (e.getSource() == m_StatusBox) {
// notify any listeners
for (int i = 0; i < m_Listeners.size(); i++) {
ActionListener temp = ((ActionListener) m_Listeners.elementAt(i));
temp.actionPerformed(
new ActionEvent(this, ActionEvent.ACTION_PERFORMED, "Editor status change"));
}
// Toggles whether the custom property is used
if (m_StatusBox.getSelectedIndex() == 0) {
m_Exp.setUsePropertyIterator(false);
m_ConfigureBut.setEnabled(false);
m_ArrayEditor.setEnabled(false);
m_ArrayEditor.setValue(null);
validate();
} else {
if (m_Exp.getPropertyArray() == null) {
selectProperty();
}
if (m_Exp.getPropertyArray() == null) {
m_StatusBox.setSelectedIndex(0);
} else {
m_Exp.setUsePropertyIterator(true);
m_ConfigureBut.setEnabled(true);
m_ArrayEditor.setEnabled(true);
}
validate();
}
}
}
/**
* Gets the scheme paramter with the given index.
*
* @param index the index for the parameter
* @return the scheme parameter
*/
public String getCVParameter(int index) {
if (m_CVParams.size() <= index) {
return "";
}
return ((CVParameter) m_CVParams.elementAt(index)).toString();
}
/**
* Tests the ThresholdCurve generation from the command line. The classifier is currently
* hardcoded. Pipe in an arff file.
*
* @param args currently ignored
*/
public static void main(String[] args) {
try {
Instances inst = new Instances(new java.io.InputStreamReader(System.in));
if (false) {
System.out.println(ThresholdCurve.getNPointPrecision(inst, 11));
} else {
inst.setClassIndex(inst.numAttributes() - 1);
ThresholdCurve tc = new ThresholdCurve();
EvaluationUtils eu = new EvaluationUtils();
Classifier classifier = new weka.classifiers.functions.Logistic();
FastVector predictions = new FastVector();
for (int i = 0; i < 2; i++) { // Do two runs.
eu.setSeed(i);
predictions.appendElements(eu.getCVPredictions(classifier, inst, 10));
// System.out.println("\n\n\n");
}
Instances result = tc.getCurve(predictions);
System.out.println(result);
}
} catch (Exception ex) {
ex.printStackTrace();
}
}
/**
* Produces a shallow copy of this vector.
*
* @return the new vector
*/
public final Object copy() {
FastVector copy = new FastVector(m_Objects.length, m_CapacityIncrement, m_CapacityMultiplier);
copy.m_Size = m_Size;
System.arraycopy(m_Objects, 0, copy.m_Objects, 0, m_Size);
return copy;
}
/**
* Create the options array to pass to the classifier. The parameter values and positions are
* taken from m_ClassifierOptions and m_CVParams.
*
* @return the options array
*/
protected String[] createOptions() {
String[] options = new String[m_ClassifierOptions.length + 2 * m_CVParams.size()];
int start = 0, end = options.length;
// Add the cross-validation parameters and their values
for (int i = 0; i < m_CVParams.size(); i++) {
CVParameter cvParam = (CVParameter) m_CVParams.elementAt(i);
double paramValue = cvParam.m_ParamValue;
if (cvParam.m_RoundParam) {
// paramValue = (double)((int) (paramValue + 0.5));
paramValue = Math.rint(paramValue);
}
if (cvParam.m_AddAtEnd) {
options[--end] = "" + Utils.doubleToString(paramValue, 4);
options[--end] = "-" + cvParam.m_ParamChar;
} else {
options[start++] = "-" + cvParam.m_ParamChar;
options[start++] = "" + Utils.doubleToString(paramValue, 4);
}
}
// Add the static parameters
System.arraycopy(m_ClassifierOptions, 0, options, start, m_ClassifierOptions.length);
return options;
}
/**
* Get the data after filtering the given rule
*
* @param index the index of the rule
* @return the data covered and uncovered by the rule
*/
public Instances[] getFiltered(int index) {
if ((m_Filtered != null) && (index < m_Filtered.size()))
return (Instances[]) m_Filtered.elementAt(index);
return null;
}
/**
* Gets the current settings of the Classifier.
*
* @return an array of strings suitable for passing to setOptions
*/
public String[] getOptions() {
String[] superOptions;
if (m_InitOptions != null) {
try {
((OptionHandler) m_Classifier).setOptions((String[]) m_InitOptions.clone());
superOptions = super.getOptions();
((OptionHandler) m_Classifier).setOptions((String[]) m_BestClassifierOptions.clone());
} catch (Exception e) {
throw new RuntimeException(
"CVParameterSelection: could not set options " + "in getOptions().");
}
} else {
superOptions = super.getOptions();
}
String[] options = new String[superOptions.length + m_CVParams.size() * 2 + 2];
int current = 0;
for (int i = 0; i < m_CVParams.size(); i++) {
options[current++] = "-P";
options[current++] = "" + getCVParameter(i);
}
options[current++] = "-X";
options[current++] = "" + getNumFolds();
System.arraycopy(superOptions, 0, options, current, superOptions.length);
return options;
}
/**
* Get the class distribution predicted by the rule in given position
*
* @param index the position index of the rule
* @return the class distributions
*/
public double[] getDistributions(int index) {
if ((m_Distributions != null) && (index < m_Distributions.size()))
return (double[]) m_Distributions.elementAt(index);
return null;
}
/**
* Sets up the structure for the plot instances. Sets m_PlotInstances to null if instances are not
* saved for visualization.
*
* @see #getSaveForVisualization()
*/
protected void determineFormat() {
FastVector hv;
Attribute predictedClass;
Attribute classAt;
FastVector attVals;
int i;
if (!m_SaveForVisualization) {
m_PlotInstances = null;
return;
}
hv = new FastVector();
classAt = m_Instances.attribute(m_ClassIndex);
if (classAt.isNominal()) {
attVals = new FastVector();
for (i = 0; i < classAt.numValues(); i++) attVals.addElement(classAt.value(i));
predictedClass = new Attribute("predicted" + classAt.name(), attVals);
} else {
predictedClass = new Attribute("predicted" + classAt.name());
}
for (i = 0; i < m_Instances.numAttributes(); i++) {
if (i == m_Instances.classIndex()) hv.addElement(predictedClass);
hv.addElement(m_Instances.attribute(i).copy());
}
m_PlotInstances =
new Instances(m_Instances.relationName() + "_predicted", hv, m_Instances.numInstances());
m_PlotInstances.setClassIndex(m_ClassIndex + 1);
}
/**
* Set the output format. Takes the current average class values and m_InputFormat and calls
* setOutputFormat(Instances) appropriately.
*/
private void setOutputFormat() {
Instances newData;
FastVector newAtts, newVals;
// Compute new attributes
newAtts = new FastVector(getInputFormat().numAttributes());
for (int j = 0; j < getInputFormat().numAttributes(); j++) {
Attribute att = getInputFormat().attribute(j);
if (!m_AttIndices.isInRange(j) || !att.isString()) {
// We don't have to copy the attribute because the
// attribute index remains unchanged.
newAtts.addElement(att);
} else {
// Compute list of attribute values
newVals = new FastVector(att.numValues());
for (int i = 0; i < att.numValues(); i++) {
newVals.addElement(att.value(i));
}
newAtts.addElement(new Attribute(att.name(), newVals));
}
}
// Construct new header
newData = new Instances(getInputFormat().relationName(), newAtts, 0);
newData.setClassIndex(getInputFormat().classIndex());
setOutputFormat(newData);
}
public weka.core.Instances toWekaInstances() {
// attributes
FastVector wattrs = new FastVector();
Iterator itr = attributes.iterator();
while (itr.hasNext()) {
Attribute attr = (Attribute) itr.next();
wattrs.addElement(attr.toWekaAttribute());
}
// data instances
weka.core.Instances winsts = new weka.core.Instances(name, wattrs, instances.size());
itr = instances.iterator();
while (itr.hasNext()) {
Instance inst = (Instance) itr.next();
Iterator itrval = inst.getValues().iterator();
Iterator itrmis = inst.getMissing().iterator();
double[] vals = new double[wattrs.size()];
for (int i = 0; i < wattrs.size(); i++) {
double val = (Double) itrval.next();
if ((Boolean) itrmis.next()) {
vals[i] = weka.core.Instance.missingValue();
} else {
vals[i] = val;
}
}
weka.core.Instance winst = new weka.core.Instance(1, vals);
winst.setDataset(winsts);
winsts.add(winst);
}
winsts.setClassIndex(this.class_index);
return winsts;
}
/**
* Remove the last rule in the ruleset as well as it's stats. It might be useful when the last
* rule was added for testing purpose and then the test failed
*/
public void removeLast() {
int last = m_Ruleset.size() - 1;
m_Ruleset.removeElementAt(last);
m_Filtered.removeElementAt(last);
m_SimpleStats.removeElementAt(last);
if (m_Distributions != null) m_Distributions.removeElementAt(last);
}
/**
* Set the labels for nominal attribute creation.
*
* @param labelList a comma separated list of labels
* @throws IllegalArgumentException if the labelList was invalid
*/
public void setNominalLabels(String labelList) {
FastVector labels = new FastVector(10);
// Split the labelList up into the vector
int commaLoc;
while ((commaLoc = labelList.indexOf(',')) >= 0) {
String label = labelList.substring(0, commaLoc).trim();
if (!label.equals("")) {
labels.addElement(label);
} else {
throw new IllegalArgumentException(
"Invalid label list at " + labelList.substring(commaLoc));
}
labelList = labelList.substring(commaLoc + 1);
}
String label = labelList.trim();
if (!label.equals("")) {
labels.addElement(label);
}
// If everything is OK, make the type change
m_Labels = labels;
if (labels.size() == 0) {
m_AttributeType = Attribute.NUMERIC;
} else {
m_AttributeType = Attribute.NOMINAL;
}
}
/**
* Finds the best parameter combination. (recursive for each parameter being optimised).
*
* @param depth the index of the parameter to be optimised at this level
* @param trainData the data the search is based on
* @param random a random number generator
* @throws Exception if an error occurs
*/
protected void findParamsByCrossValidation(int depth, Instances trainData, Random random)
throws Exception {
if (depth < m_CVParams.size()) {
CVParameter cvParam = (CVParameter) m_CVParams.elementAt(depth);
double upper;
switch ((int) (cvParam.m_Lower - cvParam.m_Upper + 0.5)) {
case 1:
upper = m_NumAttributes;
break;
case 2:
upper = m_TrainFoldSize;
break;
default:
upper = cvParam.m_Upper;
break;
}
double increment = (upper - cvParam.m_Lower) / (cvParam.m_Steps - 1);
for (cvParam.m_ParamValue = cvParam.m_Lower;
cvParam.m_ParamValue <= upper;
cvParam.m_ParamValue += increment) {
findParamsByCrossValidation(depth + 1, trainData, random);
}
} else {
Evaluation evaluation = new Evaluation(trainData);
// Set the classifier options
String[] options = createOptions();
if (m_Debug) {
System.err.print("Setting options for " + m_Classifier.getClass().getName() + ":");
for (int i = 0; i < options.length; i++) {
System.err.print(" " + options[i]);
}
System.err.println("");
}
((OptionHandler) m_Classifier).setOptions(options);
for (int j = 0; j < m_NumFolds; j++) {
// We want to randomize the data the same way for every
// learning scheme.
Instances train = trainData.trainCV(m_NumFolds, j, new Random(1));
Instances test = trainData.testCV(m_NumFolds, j);
m_Classifier.buildClassifier(train);
evaluation.setPriors(train);
evaluation.evaluateModel(m_Classifier, test);
}
double error = evaluation.errorRate();
if (m_Debug) {
System.err.println("Cross-validated error rate: " + Utils.doubleToString(error, 6, 4));
}
if ((m_BestPerformance == -99) || (error < m_BestPerformance)) {
m_BestPerformance = error;
m_BestClassifierOptions = createOptions();
}
}
}
/**
* Calculates the performance stats for the default class and return results as a set of
* Instances. The structure of these Instances is as follows:
*
* <p>
*
* <ul>
* <li><b>True Positives </b>
* <li><b>False Negatives</b>
* <li><b>False Positives</b>
* <li><b>True Negatives</b>
* <li><b>False Positive Rate</b>
* <li><b>True Positive Rate</b>
* <li><b>Precision</b>
* <li><b>Recall</b>
* <li><b>Fallout</b>
* <li><b>Threshold</b> contains the probability threshold that gives rise to the previous
* performance values.
* </ul>
*
* <p>For the definitions of these measures, see TwoClassStats
*
* <p>
*
* @see TwoClassStats
* @param predictions the predictions to base the curve on
* @return datapoints as a set of instances, null if no predictions have been made.
*/
public Instances getCurve(FastVector predictions) {
if (predictions.size() == 0) {
return null;
}
return getCurve(
predictions, ((NominalPrediction) predictions.elementAt(0)).distribution().length - 1);
}
private FastVector attFromStream(StreamElement data) {
FastVector fv = new FastVector();
for (int i = 0; i < data.getFieldNames().length; i++) {
Attribute a = new Attribute(data.getFieldNames()[i]);
fv.addElement(a);
}
return fv;
}
/**
* Returns an enumeration describing the available options.
*
* @return an enumeration of all the available options.
*/
public Enumeration listOptions() {
String string1 = "\tThe required number of rules. (default = " + (m_numRules - 5) + ")";
FastVector newVector = new FastVector(1);
newVector.addElement(new Option(string1, "N", 1, "-N <required number of rules output>"));
return newVector.elements();
}
private List<Instance> myExtractKeyphrases(String document, int numOfPhrases) throws Exception {
// Check whether there is actually any data
//
if (document.length() == 0 || document.equals("")) {
throw new Exception("Couldn't find any data!");
}
FastVector atts = new FastVector(3);
atts.addElement(new Attribute("doc", (FastVector) null));
atts.addElement(new Attribute("keyphrases", (FastVector) null));
Instances data = new Instances("keyphrase_training_data", atts, 0);
List<Instance> myInstances = new ArrayList<Instance>();
double[] newInst = new double[2];
newInst[0] = (double) data.attribute(0).addStringValue(document);
newInst[1] = Instance.missingValue();
data.add(new Instance(1.0, newInst));
m_KEAFilter.input(data.instance(0));
data = data.stringFreeStructure();
ke.setNumPhrases(numOfPhrases);
int numPhrases = numOfPhrases; // ke.getNumPhrases();
Instance[] topRankedInstances = new Instance[numPhrases];
Instance inst;
// Iterating over all extracted keyphrases (inst)
while ((inst = m_KEAFilter.output()) != null) {
int index = (int) inst.value(m_KEAFilter.getRankIndex()) - 1;
if (index < numPhrases) {
topRankedInstances[index] = inst;
}
}
double numExtracted = 0, numCorrect = 0;
for (int i = 0; i < numPhrases; i++) {
if (topRankedInstances[i] != null) {
if (!topRankedInstances[i].isMissing(topRankedInstances[i].numAttributes() - 1)) {
numExtracted += 1.0;
}
if ((int) topRankedInstances[i].value(topRankedInstances[i].numAttributes() - 1) == 1) {
numCorrect += 1.0;
}
myInstances.add(topRankedInstances[i]);
}
}
return myInstances;
}
/**
* Adds the statistics encapsulated in the supplied Evaluation object into this one. Does not
* perform any checks for compatibility between the supplied Evaluation object and this one.
*
* @param evaluation the evaluation object to aggregate
*/
public void aggregate(Evaluation evaluation) {
m_Incorrect += evaluation.incorrect();
m_Correct += evaluation.correct();
m_Unclassified += evaluation.unclassified();
m_MissingClass += evaluation.m_MissingClass;
m_WithClass += evaluation.m_WithClass;
if (evaluation.m_ConfusionMatrix != null) {
double[][] newMatrix = evaluation.confusionMatrix();
if (newMatrix != null) {
for (int i = 0; i < m_ConfusionMatrix.length; i++) {
for (int j = 0; j < m_ConfusionMatrix[i].length; j++) {
m_ConfusionMatrix[i][j] += newMatrix[i][j];
}
}
}
}
double[] newClassPriors = evaluation.m_ClassPriors;
if (newClassPriors != null) {
for (int i = 0; i < this.m_ClassPriors.length; i++) {
m_ClassPriors[i] = newClassPriors[i];
}
}
m_ClassPriorsSum = evaluation.m_ClassPriorsSum;
m_TotalCost += evaluation.totalCost();
m_SumErr += evaluation.m_SumErr;
m_SumAbsErr += evaluation.m_SumAbsErr;
m_SumSqrErr += evaluation.m_SumSqrErr;
m_SumClass += evaluation.m_SumClass;
m_SumSqrClass += evaluation.m_SumSqrClass;
m_SumPredicted += evaluation.m_SumPredicted;
m_SumSqrPredicted += evaluation.m_SumSqrPredicted;
m_SumClassPredicted += evaluation.m_SumClassPredicted;
m_SumPriorAbsErr += evaluation.m_SumPriorAbsErr;
m_SumPriorSqrErr += evaluation.m_SumPriorSqrErr;
m_SumKBInfo += evaluation.m_SumKBInfo;
double[] newMarginCounts = evaluation.m_MarginCounts;
if (newMarginCounts != null) {
for (int i = 0; i < m_MarginCounts.length; i++) {
m_MarginCounts[i] += newMarginCounts[i];
}
}
m_SumPriorEntropy += evaluation.m_SumPriorEntropy;
m_SumSchemeEntropy += evaluation.m_SumSchemeEntropy;
m_TotalSizeOfRegions += evaluation.m_TotalSizeOfRegions;
m_TotalCoverage += evaluation.m_TotalCoverage;
FastVector predsToAdd = evaluation.m_Predictions;
if (predsToAdd != null) {
if (m_Predictions == null) {
m_Predictions = new FastVector();
}
for (int i = 0; i < predsToAdd.size(); i++) {
m_Predictions.addElement(predsToAdd.elementAt(i));
}
}
}
/**
* Clones the vector and shallow copies all its elements. The elements have to implement the
* Copyable interface.
*
* @return the new vector
*/
public final Object copyElements() {
FastVector copy = new FastVector(m_Objects.length, m_CapacityIncrement, m_CapacityMultiplier);
copy.m_Size = m_Size;
for (int i = 0; i < m_Size; i++) {
copy.m_Objects[i] = ((Copyable) m_Objects[i]).copy();
}
return copy;
}
/**
* Trains the classifier on the array of Signal objects. Implementations of this method should
* also produce an ordered list of the class names which can be returned with the <code>
* getClassNames</code> method.
*
* @param inputData the Signal array that the model should be trained on.
* @throws noMetadataException Thrown if there is no class metadata to train the Gaussian model
* with
*/
public void train(Signal[] inputData) {
List classNamesList = new ArrayList();
for (int i = 0; i < inputData.length; i++) {
try {
String className = inputData[i].getStringMetadata(Signal.PROP_CLASS);
if ((className != null) && (!classNamesList.contains(className))) {
classNamesList.add(className);
}
} catch (noMetadataException ex) {
throw new RuntimeException("No class metadata found to train model on!", ex);
}
}
Collections.sort(classNamesList);
classnames = (String[]) classNamesList.toArray(new String[classNamesList.size()]);
FastVector classValues = new FastVector(classnames.length);
for (int i = 0; i < classnames.length; i++) {
classValues.addElement(classnames[i]);
}
classAttribute = new Attribute(Signal.PROP_CLASS, classValues);
Instances trainingDataSet =
new Instances(Signal2Instance.convert(inputData[0], classAttribute));
if (inputData.length > 1) {
for (int i = 1; i < inputData.length; i++) {
Instances aSignalInstance = Signal2Instance.convert(inputData[i], classAttribute);
for (int j = 0; j < aSignalInstance.numInstances(); j++)
trainingDataSet.add(aSignalInstance.instance(j));
}
}
trainingDataSet.setClass(classAttribute);
inputData = null;
theRule = new MISMO();
// parse options
StringTokenizer stOption = new StringTokenizer(this.MISMOOptions, " ");
String[] options = new String[stOption.countTokens()];
for (int i = 0; i < options.length; i++) {
options[i] = stOption.nextToken();
}
try {
theRule.setOptions(options);
} catch (Exception ex) {
throw new RuntimeException("Failed to set MISMO classifier options!", ex);
}
try {
theRule.buildClassifier(trainingDataSet);
System.out.println("WEKA: outputting MISMO classifier; " + theRule.globalInfo());
} catch (Exception ex) {
throw new RuntimeException("Failed to train classifier!", ex);
}
}
public FastVector buildCosineAttributes() {
FastVector attributes = new FastVector(2);
attributes.addElement(new Attribute("cosine"));
FastVector classVal = new FastVector();
classVal.addElement("1");
classVal.addElement("0");
Attribute label = new Attribute("label", classVal);
attributes.addElement(label);
return attributes;
}
public Instances initializeInstances() {
FastVector wekaAttributes = buildCosineAttributes();
Attribute label = (Attribute) wekaAttributes.lastElement();
Instances data = new Instances("semantic-space", wekaAttributes, 1000);
data.setClass(label);
return data;
}
/**
* @param predictions the predictions to use
* @param classIndex the class index
* @return the probabilities
*/
private double[] getProbabilities(FastVector predictions, int classIndex) {
// sort by predicted probability of the desired class.
double[] probs = new double[predictions.size()];
for (int i = 0; i < probs.length; i++) {
NominalPrediction pred = (NominalPrediction) predictions.elementAt(i);
probs[i] = pred.distribution()[classIndex];
}
return probs;
}
/** 构造分类器，主要及时对数据格式，类标，类别数目等进行说明 */
public MessageClassify() throws Exception {
String nameOfDataset = "MessageClassification";
FastVector attributes = new FastVector(2);
attributes.addElement(new Attribute("Message", (FastVector) null));
FastVector classValues = new FastVector(2); // 类标向量，共有两类
classValues.addElement("0");
classValues.addElement("1");
attributes.addElement(new Attribute("Class", classValues));
instances = new Instances(nameOfDataset, attributes, 100); // 可以把instance认为是行，attribute认为是列
instances.setClassIndex(instances.numAttributes() - 1); // 类表在instance中的那列
}
public void testEvaluationMode() throws Exception {
int cind = 0;
for (int i = 0; i < ThresholdSelector.TAGS_EVAL.length; i++) {
((ThresholdSelector) m_Classifier)
.setEvaluationMode(
new SelectedTag(ThresholdSelector.TAGS_EVAL[i].getID(), ThresholdSelector.TAGS_EVAL));
m_Instances.setClassIndex(1);
FastVector result = useClassifier();
assertTrue(result.size() != 0);
}
}
/**
* Get the list of labels for nominal attribute creation.
*
* @return the list of labels for nominal attribute creation
*/
public String getNominalLabels() {
String labelList = "";
for (int i = 0; i < m_Labels.size(); i++) {
if (i == 0) {
labelList = (String) m_Labels.elementAt(i);
} else {
labelList += "," + (String) m_Labels.elementAt(i);
}
}
return labelList;
}
public void testDesignatedClass() throws Exception {
int cind = 0;
for (int i = 0; i < ThresholdSelector.TAGS_OPTIMIZE.length; i++) {
((ThresholdSelector) m_Classifier)
.setDesignatedClass(
new SelectedTag(
ThresholdSelector.TAGS_OPTIMIZE[i].getID(), ThresholdSelector.TAGS_OPTIMIZE));
m_Instances.setClassIndex(1);
FastVector result = useClassifier();
assertTrue(result.size() != 0);
}
}
/**
* Determines the output format based on the input format and returns this. In case the output
* format cannot be returned immediately, i.e., hasImmediateOutputFormat() returns false, then
* this method will called from batchFinished() after the call of preprocess(Instances), in which,
* e.g., statistics for the actual processing step can be gathered.
*
* @param inputFormat the input format to base the output format on
* @return the output format
* @throws Exception in case the determination goes wrong
*/
protected Instances determineOutputFormat(Instances inputFormat) throws Exception {
Instances result;
FastVector atts;
int i;
int numAtts;
Vector<Integer> indices;
Vector<Integer> subset;
Random rand;
int index;
// determine the number of attributes
numAtts = inputFormat.numAttributes();
if (inputFormat.classIndex() > -1) numAtts--;
if (m_NumAttributes < 1) {
numAtts = (int) Math.round((double) numAtts * m_NumAttributes);
} else {
if (m_NumAttributes < numAtts) numAtts = (int) m_NumAttributes;
}
if (getDebug()) System.out.println("# of atts: " + numAtts);
// determine random indices
indices = new Vector<Integer>();
for (i = 0; i < inputFormat.numAttributes(); i++) {
if (i == inputFormat.classIndex()) continue;
indices.add(i);
}
subset = new Vector<Integer>();
rand = new Random(m_Seed);
for (i = 0; i < numAtts; i++) {
index = rand.nextInt(indices.size());
subset.add(indices.get(index));
indices.remove(index);
}
Collections.sort(subset);
if (inputFormat.classIndex() > -1) subset.add(inputFormat.classIndex());
if (getDebug()) System.out.println("indices: " + subset);
// generate output format
atts = new FastVector();
m_Indices = new int[subset.size()];
for (i = 0; i < subset.size(); i++) {
atts.addElement(inputFormat.attribute(subset.get(i)));
m_Indices[i] = subset.get(i);
}
result = new Instances(inputFormat.relationName(), atts, 0);
if (inputFormat.classIndex() > -1) result.setClassIndex(result.numAttributes() - 1);
return result;
}
