// 构造一个tri-trainer分类器。
public Tritrainer(
String classifier, String trainingIns_File, String testIns_File, double precentage) {
try {
this.classifier1 = (Classifier) Class.forName(classifier).newInstance();
this.classifier2 = (Classifier) Class.forName(classifier).newInstance();
this.classifier3 = (Classifier) Class.forName(classifier).newInstance();
Instances trainingInstances = Util.getInstances(trainingIns_File);
// 将trainIns_File按照precentage和(1-precentage)的比例切割成labeledIns和unlabeledIns;
int length = trainingInstances.numInstances();
int i = new Double(length * precentage).intValue();
labeledIns = new Instances(trainingInstances, 0);
for (int j = 0; j < i; j++) {
labeledIns.add(trainingInstances.firstInstance());
trainingInstances.delete(0);
}
unlabeledIns = trainingInstances;
testIns = Util.getInstances(testIns_File);
Init();
} catch (Exception e) {
}
}
// 计算h1,h2分类器共同的分类错误率；
public double measureBothError(Classifier h1, Classifier h2, Instances test) {
int m = test.numInstances();
double value1, value2, value;
int error = 0, total = 0;
try {
for (int i = 0; i < m; i++) {
value = test.instance(i).classValue();
value1 = h1.classifyInstance(test.instance(i));
value2 = h2.classifyInstance(test.instance(i));
// 两分类器做出相同决策
if (value1 == value2) {
// 两分类器做出相同决策的样本数量
total++;
// 两分类器做出相同错误决策
if (value != value1) {
// 两分类器做出相同错误决策的样本数量
error++;
}
}
}
} catch (Exception e) {
System.out.println(e);
}
// System.out.println("m:=" + m);
// System.out.println("error:=" + error +"; total:=" + total);
// 两个分类器的分类错误率= 两分类器做出相同错误决策的样本数量/两分类器做出相同决策的样本数量
return (error * 1.0) / total;
}
/**
* Generate artificial training examples.
*
* @param artSize size of examples set to create
* @param data training data
* @return the set of unlabeled artificial examples
*/
protected Instances generateArtificialData(int artSize, Instances data) {
int numAttributes = data.numAttributes();
Instances artData = new Instances(data, artSize);
double[] att;
Instance artInstance;
for (int i = 0; i < artSize; i++) {
att = new double[numAttributes];
for (int j = 0; j < numAttributes; j++) {
if (data.attribute(j).isNominal()) {
// Select nominal value based on the frequency of occurence in the training data
double[] stats = (double[]) m_AttributeStats.get(j);
att[j] = (double) selectIndexProbabilistically(stats);
} else if (data.attribute(j).isNumeric()) {
// Generate numeric value from the Guassian distribution
// defined by the mean and std dev of the attribute
double[] stats = (double[]) m_AttributeStats.get(j);
att[j] = (m_Random.nextGaussian() * stats[1]) + stats[0];
} else System.err.println("Decorate can only handle numeric and nominal values.");
}
artInstance = new Instance(1.0, att);
artData.add(artInstance);
}
return artData;
}
// 将样本集中裁剪提取成m个样本组成的集合；
public void SubSample(Instances inst, int m) {
inst.randomize(new Random());
while (inst.numInstances() != m) {
inst.delete(0);
}
// System.out.println("subsample:=" + inst.numInstances() + " m:=" + m );
}
/**
* GetKs - return [K_1,K_2,...,K_L] where each Y_j \in {1,...,K_j}. In the multi-label case, K[j]
* = 2 for all j = 1,...,L.
*
* @param D a dataset
* @return an array of the number of values that each label can take
*/
private static int[] getKs(Instances D) {
int L = D.classIndex();
int K[] = new int[L];
for (int k = 0; k < L; k++) {
K[k] = D.attribute(k).numValues();
}
return K;
}
public int getClusterNumber(String objectID) {
int datasetIndex = -1;
for (int i = 0; i < m_Sequences.numInstances(); i++) {
if (objectID.equals(m_Sequences.instance(i).stringValue(0))) datasetIndex = i;
}
return cluster[datasetIndex];
}
protected void initMinMax(Instances data) {
m_Min = new double[data.numAttributes()];
m_Max = new double[data.numAttributes()];
for (int i = 0; i < data.numAttributes(); i++) {
m_Min[i] = m_Max[i] = Double.NaN;
}
for (int i = 0; i < data.numInstances(); i++) {
updateMinMax(data.instance(i));
}
}
/**
* Labels the artificially generated data.
*
* @param artData the artificially generated instances
* @exception Exception if instances cannot be labeled successfully
*/
protected void labelData(Instances artData) throws Exception {
Instance curr;
double[] probs;
for (int i = 0; i < artData.numInstances(); i++) {
curr = artData.instance(i);
// compute the class membership probs predicted by the current ensemble
probs = distributionForInstance(curr);
// select class label inversely proportional to the ensemble predictions
curr.setClassValue(inverseLabel(probs));
}
}
/**
* Computes the error in classification on the given data.
*
* @param data the instances to be classified
* @return classification error
* @exception Exception if error can not be computed successfully
*/
protected double computeError(Instances data) throws Exception {
double error = 0.0;
int numInstances = data.numInstances();
Instance curr;
for (int i = 0; i < numInstances; i++) {
curr = data.instance(i);
// Check if the instance has been misclassified
if (curr.classValue() != ((int) classifyInstance(curr))) error++;
}
return (error / numInstances);
}
/**
* Inserts an instance into the hash table
*
* @param inst instance to be inserted
* @param instA to create the hash key from
* @throws Exception if the instance can't be inserted
*/
private void insertIntoTable(Instance inst, double[] instA) throws Exception {
double[] tempClassDist2;
double[] newDist;
DecisionTableHashKey thekey;
if (instA != null) {
thekey = new DecisionTableHashKey(instA);
} else {
thekey = new DecisionTableHashKey(inst, inst.numAttributes(), false);
}
// see if this one is already in the table
tempClassDist2 = (double[]) m_entries.get(thekey);
if (tempClassDist2 == null) {
if (m_classIsNominal) {
newDist = new double[m_theInstances.classAttribute().numValues()];
// Leplace estimation
for (int i = 0; i < m_theInstances.classAttribute().numValues(); i++) {
newDist[i] = 1.0;
}
newDist[(int) inst.classValue()] = inst.weight();
// add to the table
m_entries.put(thekey, newDist);
} else {
newDist = new double[2];
newDist[0] = inst.classValue() * inst.weight();
newDist[1] = inst.weight();
// add to the table
m_entries.put(thekey, newDist);
}
} else {
// update the distribution for this instance
if (m_classIsNominal) {
tempClassDist2[(int) inst.classValue()] += inst.weight();
// update the table
m_entries.put(thekey, tempClassDist2);
} else {
tempClassDist2[0] += (inst.classValue() * inst.weight());
tempClassDist2[1] += inst.weight();
// update the table
m_entries.put(thekey, tempClassDist2);
}
}
}
/**
* Generates a clusterer by the mean of spectral clustering algorithm.
*
* @param data set of instances serving as training data
* @exception Exception if the clusterer has not been generated successfully
*/
public void buildClusterer(Instances data) throws java.lang.Exception {
m_Sequences = new Instances(data);
int n = data.numInstances();
int k = data.numAttributes();
DoubleMatrix2D w;
if (useSparseMatrix) w = DoubleFactory2D.sparse.make(n, n);
else w = DoubleFactory2D.dense.make(n, n);
double[][] v1 = new double[n][];
for (int i = 0; i < n; i++) v1[i] = data.instance(i).toDoubleArray();
v = DoubleFactory2D.dense.make(v1);
double sigma_sq = sigma * sigma;
// Sets up similarity matrix
for (int i = 0; i < n; i++)
for (int j = i; j < n; j++) {
/*double dist = distnorm2(v.viewRow(i), v.viewRow(j));
if((r == -1) || (dist < r)) {
double sim = Math.exp(- (dist * dist) / (2 * sigma_sq));
w.set(i, j, sim);
w.set(j, i, sim);
}*/
/* String [] key = {data.instance(i).stringValue(0), data.instance(j).stringValue(0)};
System.out.println(key[0]);
System.out.println(key[1]);
System.out.println(simScoreMap.containsKey(key));
Double simValue = simScoreMap.get(key);*/
double sim = sim_matrix[i][j];
w.set(i, j, sim);
w.set(j, i, sim);
}
// Partitions points
int[][] p = partition(w, alpha_star);
// Deploys results
numOfClusters = p.length;
cluster = new int[n];
for (int i = 0; i < p.length; i++) for (int j = 0; j < p[i].length; j++) cluster[p[i][j]] = i;
// System.out.println("Final partition:");
// UtilsJS.printMatrix(p);
// System.out.println("Cluster:\n");
// UtilsJS.printArray(cluster);
this.numOfClusters = cluster[Utils.maxIndex(cluster)] + 1;
// System.out.println("Num clusters:\t"+this.numOfClusters);
}
protected void updateMinDistance(
double[] minDistance, boolean[] selected, Instances data, Instance center) {
for (int i = 0; i < selected.length; i++)
if (!selected[i]) {
double d = distance(center, data.instance(i));
if (d < minDistance[i]) minDistance[i] = d;
}
}
// 通过h1,h2分类器学习样本集，将h1,h2分类决策相同的样本放入L中，得到标记集合；
public void updateL(Classifier h1, Classifier h2, Instances L, Instances test) {
int length = unlabeledIns.numInstances();
double value1 = 0.0, value2 = 0.0;
try {
for (int i = 0; i < length; i++) {
value1 = h1.classifyInstance(test.instance(i));
value2 = h2.classifyInstance(test.instance(i));
if (value1 == value2) {
// 当两个分类器做出相同决策时重新标记样本的类别；
test.instance(i).setClassValue(value1);
L.add(test.instance(i));
}
}
} catch (Exception e) {
System.out.println(e);
}
// return false;
}
/**
* loads the given dataset and prints the Capabilities necessary to process it.
*
* <p>Valid parameters:
*
* <p>-file filename <br>
* the file to load
*
* <p>-c index the explicit index of the class attribute (default: none)
*
* @param args the commandline arguments
* @throws Exception if something goes wrong
*/
public static void main(String[] args) throws Exception {
String tmpStr;
String filename;
DataSource source;
Instances data;
int classIndex;
Capabilities cap;
Iterator iter;
if (args.length == 0) {
System.out.println(
"\nUsage: " + Capabilities.class.getName() + " -file <dataset> [-c <class index>]\n");
return;
}
// get parameters
tmpStr = Utils.getOption("file", args);
if (tmpStr.length() == 0) throw new Exception("No file provided with option '-file'!");
else filename = tmpStr;
tmpStr = Utils.getOption("c", args);
if (tmpStr.length() != 0) {
if (tmpStr.equals("first")) classIndex = 0;
else if (tmpStr.equals("last")) classIndex = -2; // last
else classIndex = Integer.parseInt(tmpStr) - 1;
} else {
classIndex = -3; // not set
}
// load data
source = new DataSource(filename);
if (classIndex == -3) data = source.getDataSet();
else if (classIndex == -2) data = source.getDataSet(source.getStructure().numAttributes() - 1);
else data = source.getDataSet(classIndex);
// determine and print capabilities
cap = forInstances(data);
System.out.println("File: " + filename);
System.out.println(
"Class index: " + ((data.classIndex() == -1) ? "not set" : "" + (data.classIndex() + 1)));
System.out.println("Capabilities:");
iter = cap.capabilities();
while (iter.hasNext()) System.out.println("- " + iter.next());
}
/**
* Calculates the distance between two instances
*
* @param test the first instance
* @param train the second instance
* @return the distance between the two given instances, between 0 and 1
*/
protected double distance(Instance first, Instance second) {
double distance = 0;
int firstI, secondI;
for (int p1 = 0, p2 = 0; p1 < first.numValues() || p2 < second.numValues(); ) {
if (p1 >= first.numValues()) {
firstI = m_instances.numAttributes();
} else {
firstI = first.index(p1);
}
if (p2 >= second.numValues()) {
secondI = m_instances.numAttributes();
} else {
secondI = second.index(p2);
}
if (firstI == m_instances.classIndex()) {
p1++;
continue;
}
if (secondI == m_instances.classIndex()) {
p2++;
continue;
}
double diff;
if (firstI == secondI) {
diff = difference(firstI, first.valueSparse(p1), second.valueSparse(p2));
p1++;
p2++;
} else if (firstI > secondI) {
diff = difference(secondI, 0, second.valueSparse(p2));
p2++;
} else {
diff = difference(firstI, first.valueSparse(p1), 0);
p1++;
}
distance += diff * diff;
}
return Math.sqrt(distance / m_instances.numAttributes());
}
/**
* clusters an instance that has been through the filters
*
* @param instance the instance to assign a cluster to
* @return a cluster number
*/
protected int clusterProcessedInstance(Instance instance) {
double minDist = Double.MAX_VALUE;
int bestCluster = 0;
for (int i = 0; i < m_NumClusters; i++) {
double dist = distance(instance, m_ClusterCentroids.instance(i));
if (dist < minDist) {
minDist = dist;
bestCluster = i;
}
}
return bestCluster;
}
/**
* Compute and store statistics required for generating artificial data.
*
* @param data training instances
* @exception Exception if statistics could not be calculated successfully
*/
protected void computeStats(Instances data) throws Exception {
int numAttributes = data.numAttributes();
m_AttributeStats = new Vector(numAttributes); // use to map attributes to their stats
for (int j = 0; j < numAttributes; j++) {
if (data.attribute(j).isNominal()) {
// Compute the probability of occurence of each distinct value
int[] nomCounts = (data.attributeStats(j)).nominalCounts;
double[] counts = new double[nomCounts.length];
if (counts.length < 2)
throw new Exception("Nominal attribute has less than two distinct values!");
// Perform Laplace smoothing
for (int i = 0; i < counts.length; i++) counts[i] = nomCounts[i] + 1;
Utils.normalize(counts);
double[] stats = new double[counts.length - 1];
stats[0] = counts[0];
// Calculate cumulative probabilities
for (int i = 1; i < stats.length; i++) stats[i] = stats[i - 1] + counts[i];
m_AttributeStats.add(j, stats);
} else if (data.attribute(j).isNumeric()) {
// Get mean and standard deviation from the training data
double[] stats = new double[2];
stats[0] = data.meanOrMode(j);
stats[1] = Math.sqrt(data.variance(j));
m_AttributeStats.add(j, stats);
} else System.err.println("Decorate can only handle numeric and nominal values.");
}
}
/**
* Buildclassifier selects a classifier from the set of classifiers by minimising error on the
* training data.
*
* @param data the training data to be used for generating the boosted classifier.
* @exception Exception if the classifier could not be built successfully
*/
public void buildClassifier(Instances data) throws Exception {
if (m_Classifiers.length == 0) {
throw new Exception("No base classifiers have been set!");
}
Instances newData = new Instances(data);
newData.deleteWithMissingClass();
newData.randomize(new Random(m_Seed));
if (newData.classAttribute().isNominal() && (m_NumXValFolds > 1))
newData.stratify(m_NumXValFolds);
Instances train = newData; // train on all data by default
Instances test = newData; // test on training data by default
Classifier bestClassifier = null;
int bestIndex = -1;
double bestPerformance = Double.NaN;
int numClassifiers = m_Classifiers.length;
for (int i = 0; i < numClassifiers; i++) {
Classifier currentClassifier = getClassifier(i);
Evaluation evaluation;
if (m_NumXValFolds > 1) {
evaluation = new Evaluation(newData);
for (int j = 0; j < m_NumXValFolds; j++) {
train = newData.trainCV(m_NumXValFolds, j);
test = newData.testCV(m_NumXValFolds, j);
currentClassifier.buildClassifier(train);
evaluation.setPriors(train);
evaluation.evaluateModel(currentClassifier, test);
}
} else {
currentClassifier.buildClassifier(train);
evaluation = new Evaluation(train);
evaluation.evaluateModel(currentClassifier, test);
}
double error = evaluation.errorRate();
if (m_Debug) {
System.err.println(
"Error rate: "
+ Utils.doubleToString(error, 6, 4)
+ " for classifier "
+ currentClassifier.getClass().getName());
}
if ((i == 0) || (error < bestPerformance)) {
bestClassifier = currentClassifier;
bestPerformance = error;
bestIndex = i;
}
}
m_ClassifierIndex = bestIndex;
m_Classifier = bestClassifier;
if (m_NumXValFolds > 1) {
m_Classifier.buildClassifier(newData);
}
}
/**
* Gets the subset of instances that apply to a particluar branch of the split. If the branch
* index is -1, the subset will consist of those instances that don't apply to any branch.
*
* @param branch the index of the branch
* @param sourceInstances the instances from which to find the subset
* @return the set of instances that apply
*/
public ReferenceInstances instancesDownBranch(int branch, Instances instances) {
ReferenceInstances filteredInstances = new ReferenceInstances(instances, 1);
if (branch == -1) {
for (Enumeration e = instances.enumerateInstances(); e.hasMoreElements(); ) {
Instance inst = (Instance) e.nextElement();
if (inst.isMissing(attIndex)) filteredInstances.addReference(inst);
}
} else if (branch == 0) {
for (Enumeration e = instances.enumerateInstances(); e.hasMoreElements(); ) {
Instance inst = (Instance) e.nextElement();
if (!inst.isMissing(attIndex) && inst.value(attIndex) < splitPoint)
filteredInstances.addReference(inst);
}
} else {
for (Enumeration e = instances.enumerateInstances(); e.hasMoreElements(); ) {
Instance inst = (Instance) e.nextElement();
if (!inst.isMissing(attIndex) && inst.value(attIndex) >= splitPoint)
filteredInstances.addReference(inst);
}
}
return filteredInstances;
}
/**
* return a string describing this clusterer
*
* @return a description of the clusterer as a string
*/
public String toString() {
StringBuffer temp = new StringBuffer();
temp.append("\n FarthestFirst\n==============\n");
temp.append("\nCluster centroids:\n");
for (int i = 0; i < m_NumClusters; i++) {
temp.append("\nCluster " + i + "\n\t");
for (int j = 0; j < m_ClusterCentroids.numAttributes(); j++) {
if (m_ClusterCentroids.attribute(j).isNominal()) {
temp.append(
" "
+ m_ClusterCentroids
.attribute(j)
.value((int) m_ClusterCentroids.instance(i).value(j)));
} else {
temp.append(" " + m_ClusterCentroids.instance(i).value(j));
}
}
}
temp.append("\n\n");
return temp.toString();
}
/** @param args */
private void Init() {
testIns.setClassIndex(testIns.numAttributes() - 1);
labeledIns.setClassIndex(labeledIns.numAttributes() - 1);
unlabeledIns.setClassIndex(unlabeledIns.numAttributes() - 1);
class_Array[0] = classifier1;
class_Array[1] = classifier2;
class_Array[2] = classifier3;
}
public void buildClusterer(ArrayList<String> seqDB, double[][] sm) {
seqList = seqDB;
this.setSimMatrix(sm);
Attribute seqString = new Attribute("sequence", (FastVector) null);
FastVector attrInfo = new FastVector();
attrInfo.addElement(seqString);
Instances data = new Instances("data", attrInfo, 0);
for (int i = 0; i < seqList.size(); i++) {
Instance currentInst = new Instance(1);
currentInst.setDataset(data);
currentInst.setValue(0, seqList.get(i));
data.add(currentInst);
}
try {
buildClusterer(data);
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
@Test
public void testSplittable() throws SchedulerException {
List<VM> vms = Arrays.asList(vm1, vm2, vm3);
Collection<Collection<Node>> parts = new ArrayList<>();
parts.add(Arrays.asList(n1, n2));
parts.add(Arrays.asList(n3));
parts.add(Arrays.asList(n4));
Among single = new Among(vms, parts);
/*
N1 v1 v2
N2 v3
---
N3 v4
--
N4 v5
*/
FixedNodeSetsPartitioning partitionner = new FixedNodeSetsPartitioning(parts);
partitionner.setPartitions(parts);
List<Instance> instances =
partitionner.split(
new DefaultParameters(),
new Instance(mo, Collections.<SatConstraint>emptyList(), new MinMTTR()));
TIntIntHashMap vmIndex = Instances.makeVMIndex(instances);
TIntIntHashMap nodeIndex = Instances.makeNodeIndex(instances);
splitter.split(single, new Instance(mo, new MinMTTR()), instances, vmIndex, nodeIndex);
Among a = (Among) instances.get(0).getSatConstraints().iterator().next();
Assert.assertEquals(a.getGroupsOfNodes().size(), 1);
Assert.assertEquals(a.getInvolvedNodes(), Arrays.asList(n1, n2));
for (Instance i : instances) {
System.out.println(i.getSatConstraints());
}
}
/**
* Generates a clusterer. Has to initialize all fields of the clusterer that are not being set via
* options.
*
* @param data set of instances serving as training data
* @exception Exception if the clusterer has not been generated successfully
*/
public void buildClusterer(Instances data) throws Exception {
// long start = System.currentTimeMillis();
if (data.checkForStringAttributes()) {
throw new Exception("Can't handle string attributes!");
}
m_ReplaceMissingFilter = new ReplaceMissingValues();
m_ReplaceMissingFilter.setInputFormat(data);
m_instances = Filter.useFilter(data, m_ReplaceMissingFilter);
initMinMax(m_instances);
m_ClusterCentroids = new Instances(m_instances, m_NumClusters);
int n = m_instances.numInstances();
Random r = new Random(m_Seed);
boolean[] selected = new boolean[n];
double[] minDistance = new double[n];
for (int i = 0; i < n; i++) minDistance[i] = Double.MAX_VALUE;
int firstI = r.nextInt(n);
m_ClusterCentroids.add(m_instances.instance(firstI));
selected[firstI] = true;
updateMinDistance(minDistance, selected, m_instances, m_instances.instance(firstI));
if (m_NumClusters > n) m_NumClusters = n;
for (int i = 1; i < m_NumClusters; i++) {
int nextI = farthestAway(minDistance, selected);
m_ClusterCentroids.add(m_instances.instance(nextI));
selected[nextI] = true;
updateMinDistance(minDistance, selected, m_instances, m_instances.instance(nextI));
}
m_instances = new Instances(m_instances, 0);
// long end = System.currentTimeMillis();
// System.out.println("Clustering Time = " + (end-start));
}
/** Computes the difference between two given attribute values. */
protected double difference(int index, double val1, double val2) {
switch (m_instances.attribute(index).type()) {
case Attribute.NOMINAL:
// If attribute is nominal
if (Instance.isMissingValue(val1)
|| Instance.isMissingValue(val2)
|| ((int) val1 != (int) val2)) {
return 1;
} else {
return 0;
}
case Attribute.NUMERIC:
// If attribute is numeric
if (Instance.isMissingValue(val1) || Instance.isMissingValue(val2)) {
if (Instance.isMissingValue(val1) && Instance.isMissingValue(val2)) {
return 1;
} else {
double diff;
if (Instance.isMissingValue(val2)) {
diff = norm(val1, index);
} else {
diff = norm(val2, index);
}
if (diff < 0.5) {
diff = 1.0 - diff;
}
return diff;
}
} else {
return norm(val1, index) - norm(val2, index);
}
default:
return 0;
}
}
/**
* Add new instances to the given set of instances.
*
* @param data given instances
* @param newData set of instances to add to given instances
*/
protected void addInstances(Instances data, Instances newData) {
for (int i = 0; i < newData.numInstances(); i++) data.add(newData.instance(i));
}
/**
* Removes a specified number of instances from the given set of instances.
*
* @param data given instances
* @param numRemove number of instances to delete from the given instances
*/
protected void removeInstances(Instances data, int numRemove) {
int num = data.numInstances();
for (int i = num - 1; i > num - 1 - numRemove; i--) {
data.delete(i);
}
}
/**
* Tests the given data, whether it can be processed by the handler, given its capabilities.
* Classifiers implementing the <code>MultiInstanceCapabilitiesHandler</code> interface are
* checked automatically for their multi-instance Capabilities (if no bags, then only the
* bag-structure, otherwise only the first bag).
*
* @param data the data to test
* @return true if all the tests succeeded
* @see #test(Instances, int, int)
*/
public boolean test(Instances data) {
return test(data, 0, data.numAttributes() - 1);
}
/**
* Build Decorate classifier
*
* @param data the training data to be used for generating the classifier
* @exception Exception if the classifier could not be built successfully
*/
public void buildClassifier(Instances data) throws Exception {
if (m_Classifier == null) {
throw new Exception("A base classifier has not been specified!");
}
if (data.checkForStringAttributes()) {
throw new UnsupportedAttributeTypeException("Cannot handle string attributes!");
}
if (data.classAttribute().isNumeric()) {
throw new UnsupportedClassTypeException("Decorate can't handle a numeric class!");
}
if (m_NumIterations < m_DesiredSize)
throw new Exception("Max number of iterations must be >= desired ensemble size!");
// initialize random number generator
if (m_Seed == -1) m_Random = new Random();
else m_Random = new Random(m_Seed);
int i = 1; // current committee size
int numTrials = 1; // number of Decorate iterations
Instances divData = new Instances(data); // local copy of data - diversity data
divData.deleteWithMissingClass();
Instances artData = null; // artificial data
// compute number of artficial instances to add at each iteration
int artSize = (int) (Math.abs(m_ArtSize) * divData.numInstances());
if (artSize == 0) artSize = 1; // atleast add one random example
computeStats(data); // Compute training data stats for creating artificial examples
// initialize new committee
m_Committee = new Vector();
Classifier newClassifier = m_Classifier;
newClassifier.buildClassifier(divData);
m_Committee.add(newClassifier);
double eComm = computeError(divData); // compute ensemble error
if (m_Debug)
System.out.println(
"Initialize:\tClassifier " + i + " added to ensemble. Ensemble error = " + eComm);
// repeat till desired committee size is reached OR the max number of iterations is exceeded
while (i < m_DesiredSize && numTrials < m_NumIterations) {
// Generate artificial training examples
artData = generateArtificialData(artSize, data);
// Label artificial examples
labelData(artData);
addInstances(divData, artData); // Add new artificial data
// Build new classifier
Classifier tmp[] = Classifier.makeCopies(m_Classifier, 1);
newClassifier = tmp[0];
newClassifier.buildClassifier(divData);
// Remove all the artificial data
removeInstances(divData, artSize);
// Test if the new classifier should be added to the ensemble
m_Committee.add(newClassifier); // add new classifier to current committee
double currError = computeError(divData);
if (currError <= eComm) { // adding the new member did not increase the error
i++;
eComm = currError;
if (m_Debug)
System.out.println(
"Iteration: "
+ (1 + numTrials)
+ "\tClassifier "
+ i
+ " added to ensemble. Ensemble error = "
+ eComm);
} else { // reject the current classifier because it increased the ensemble error
m_Committee.removeElementAt(m_Committee.size() - 1); // pop the last member
}
numTrials++;
}
}
/**
* Tests a certain range of attributes of the given data, whether it can be processed by the
* handler, given its capabilities. Classifiers implementing the <code>
* MultiInstanceCapabilitiesHandler</code> interface are checked automatically for their
* multi-instance Capabilities (if no bags, then only the bag-structure, otherwise only the first
* bag).
*
* @param data the data to test
* @param fromIndex the range of attributes - start (incl.)
* @param toIndex the range of attributes - end (incl.)
* @return true if all the tests succeeded
* @see MultiInstanceCapabilitiesHandler
* @see #m_InstancesTest
* @see #m_MissingValuesTest
* @see #m_MissingClassValuesTest
* @see #m_MinimumNumberInstancesTest
*/
public boolean test(Instances data, int fromIndex, int toIndex) {
int i;
int n;
int m;
Attribute att;
Instance inst;
boolean testClass;
Capabilities cap;
boolean missing;
Iterator iter;
// shall we test the data?
if (!m_InstancesTest) return true;
// no Capabilities? -> warning
if ((m_Capabilities.size() == 0)
|| ((m_Capabilities.size() == 1) && handles(Capability.NO_CLASS)))
System.err.println(createMessage("No capabilities set!"));
// any attributes?
if (toIndex - fromIndex < 0) {
m_FailReason = new WekaException(createMessage("No attributes!"));
return false;
}
// do wee need to test the class attribute, i.e., is the class attribute
// within the range of attributes?
testClass =
(data.classIndex() > -1)
&& (data.classIndex() >= fromIndex)
&& (data.classIndex() <= toIndex);
// attributes
for (i = fromIndex; i <= toIndex; i++) {
att = data.attribute(i);
// class is handled separately
if (i == data.classIndex()) continue;
// check attribute types
if (!test(att)) return false;
}
// class
if (!handles(Capability.NO_CLASS) && (data.classIndex() == -1)) {
m_FailReason = new UnassignedClassException(createMessage("Class attribute not set!"));
return false;
}
// special case: no class attribute can be handled
if (handles(Capability.NO_CLASS) && (data.classIndex() > -1)) {
cap = getClassCapabilities();
cap.disable(Capability.NO_CLASS);
iter = cap.capabilities();
if (!iter.hasNext()) {
m_FailReason = new WekaException(createMessage("Cannot handle any class attribute!"));
return false;
}
}
if (testClass && !handles(Capability.NO_CLASS)) {
att = data.classAttribute();
if (!test(att, true)) return false;
// special handling of RELATIONAL class
// TODO: store additional Capabilities for this case
// missing class labels
if (m_MissingClassValuesTest) {
if (!handles(Capability.MISSING_CLASS_VALUES)) {
for (i = 0; i < data.numInstances(); i++) {
if (data.instance(i).classIsMissing()) {
m_FailReason =
new WekaException(createMessage("Cannot handle missing class values!"));
return false;
}
}
} else {
if (m_MinimumNumberInstancesTest) {
int hasClass = 0;
for (i = 0; i < data.numInstances(); i++) {
if (!data.instance(i).classIsMissing()) hasClass++;
}
// not enough instances with class labels?
if (hasClass < getMinimumNumberInstances()) {
m_FailReason =
new WekaException(
createMessage(
"Not enough training instances with class labels (required: "
+ getMinimumNumberInstances()
+ ", provided: "
+ hasClass
+ ")!"));
return false;
}
}
}
}
}
// missing values
if (m_MissingValuesTest) {
if (!handles(Capability.MISSING_VALUES)) {
missing = false;
for (i = 0; i < data.numInstances(); i++) {
inst = data.instance(i);
if (inst instanceof SparseInstance) {
for (m = 0; m < inst.numValues(); m++) {
n = inst.index(m);
// out of scope?
if (n < fromIndex) continue;
if (n > toIndex) break;
// skip class
if (n == inst.classIndex()) continue;
if (inst.isMissing(n)) {
missing = true;
break;
}
}
} else {
for (n = fromIndex; n <= toIndex; n++) {
// skip class
if (n == inst.classIndex()) continue;
if (inst.isMissing(n)) {
missing = true;
break;
}
}
}
if (missing) {
m_FailReason =
new NoSupportForMissingValuesException(
createMessage("Cannot handle missing values!"));
return false;
}
}
}
}
// instances
if (m_MinimumNumberInstancesTest) {
if (data.numInstances() < getMinimumNumberInstances()) {
m_FailReason =
new WekaException(
createMessage(
"Not enough training instances (required: "
+ getMinimumNumberInstances()
+ ", provided: "
+ data.numInstances()
+ ")!"));
return false;
}
}
// Multi-Instance? -> check structure (regardless of attribute range!)
if (handles(Capability.ONLY_MULTIINSTANCE)) {
// number of attributes?
if (data.numAttributes() != 3) {
m_FailReason =
new WekaException(
createMessage("Incorrect Multi-Instance format, must be 'bag-id, bag, class'!"));
return false;
}
// type of attributes and position of class?
if (!data.attribute(0).isNominal()
|| !data.attribute(1).isRelationValued()
|| (data.classIndex() != data.numAttributes() - 1)) {
m_FailReason =
new WekaException(
createMessage(
"Incorrect Multi-Instance format, must be 'NOMINAL att, RELATIONAL att, CLASS att'!"));
return false;
}
// check data immediately
if (getOwner() instanceof MultiInstanceCapabilitiesHandler) {
MultiInstanceCapabilitiesHandler handler = (MultiInstanceCapabilitiesHandler) getOwner();
cap = handler.getMultiInstanceCapabilities();
boolean result;
if (data.numInstances() > 0) result = cap.test(data.attribute(1).relation(0));
else result = cap.test(data.attribute(1).relation());
if (!result) {
m_FailReason = cap.m_FailReason;
return false;
}
}
}
// passed all tests!
return true;
}