/**
* Initializes the ranges using all instances of the dataset. Sets m_Ranges.
*
* @return the ranges
*/
public double[][] initializeRanges() {
if (m_Data == null) {
m_Ranges = null;
return m_Ranges;
}
int numAtt = m_Data.numAttributes();
double[][] ranges = new double[numAtt][3];
if (m_Data.numInstances() <= 0) {
initializeRangesEmpty(numAtt, ranges);
m_Ranges = ranges;
return m_Ranges;
} else {
// initialize ranges using the first instance
updateRangesFirst(m_Data.instance(0), numAtt, ranges);
}
// update ranges, starting from the second
for (int i = 1; i < m_Data.numInstances(); i++) {
updateRanges(m_Data.instance(i), numAtt, ranges);
}
m_Ranges = ranges;
return m_Ranges;
}
/**
* initializes the algorithm
*
* @param data the data to work with
* @throws Exception if m_SVM is null
*/
protected void init(Instances data) throws Exception {
if (m_SVM == null) {
throw new Exception("SVM not initialized in optimizer. Use RegOptimizer.setSVMReg()");
}
m_C = m_SVM.getC();
m_data = data;
m_classIndex = data.classIndex();
m_nInstances = data.numInstances();
// Initialize kernel
m_kernel = Kernel.makeCopy(m_SVM.getKernel());
m_kernel.buildKernel(data);
// init m_target
m_target = new double[m_nInstances];
for (int i = 0; i < m_nInstances; i++) {
m_target[i] = data.instance(i).classValue();
}
m_random = new Random(m_nSeed);
// initialize alpha and alpha* array to all zero
m_alpha = new double[m_target.length];
m_alphaStar = new double[m_target.length];
m_supportVectors = new SMOset(m_nInstances);
m_b = 0.0;
m_nEvals = 0;
m_nCacheHits = -1;
}
/**
* Generates the classifier.
*
* @param instances set of instances serving as training data
* @throws Exception if the classifier has not been generated successfully
*/
public void buildClassifier(Instances instances) throws Exception {
if (!(m_Classifier instanceof WeightedInstancesHandler)) {
throw new IllegalArgumentException("Classifier must be a " + "WeightedInstancesHandler!");
}
// can classifier handle the data?
getCapabilities().testWithFail(instances);
// remove instances with missing class
instances = new Instances(instances);
instances.deleteWithMissingClass();
// only class? -> build ZeroR model
if (instances.numAttributes() == 1) {
System.err.println(
"Cannot build model (only class attribute present in data!), "
+ "using ZeroR model instead!");
m_ZeroR = new weka.classifiers.rules.ZeroR();
m_ZeroR.buildClassifier(instances);
return;
} else {
m_ZeroR = null;
}
m_Train = new Instances(instances, 0, instances.numInstances());
m_NNSearch.setInstances(m_Train);
}
// 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) {
}
}
// 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 );
}
// 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;
}
private static IList<IList<IAgent>> clusteringUsingWeka(
final IScope scope,
final Clusterer clusterer,
final IList<String> attributes,
final IAddressableContainer<Integer, IAgent, Integer, IAgent> agents)
throws GamaRuntimeException {
Instances dataset = convertToInstances(scope, attributes, agents);
try {
clusterer.buildClusterer(dataset);
IList<IList<IAgent>> groupes = GamaListFactory.create(Types.LIST.of(Types.AGENT));
for (int i = 0; i < clusterer.numberOfClusters(); i++) {
groupes.add(GamaListFactory.<IAgent>create(Types.AGENT));
}
for (int i = 0; i < dataset.numInstances(); i++) {
Instance inst = dataset.instance(i);
int clusterIndex = -1;
clusterIndex = clusterer.clusterInstance(inst);
IList<IAgent> groupe = groupes.get(clusterIndex);
groupe.add(agents.get(scope, i));
}
return groupes;
} catch (Exception e) {
return null;
}
}
/**
* Private function to compute default number of accurate instances in the specified data for the
* consequent of the rule
*
* @param data the data in question
* @return the default accuracy number
*/
private double computeDefAccu(Instances data) {
double defAccu = 0;
for (int i = 0; i < data.numInstances(); i++) {
Instance inst = data.instance(i);
if ((int) inst.classValue() == (int) m_Consequent) defAccu += inst.weight();
}
return defAccu;
}
/**
* Computes the entropy of a dataset.
*
* @param data the data for which entropy is to be computed
* @return the entropy of the data's class distribution
* @throws Exception if computation fails
*/
private double computeEntropy(Instances data) throws Exception {
double[] classCounts = new double[data.numClasses()];
Enumeration instEnum = data.enumerateInstances();
while (instEnum.hasMoreElements()) {
Instance inst = (Instance) instEnum.nextElement();
classCounts[(int) inst.classValue()]++;
}
double entropy = 0;
for (int j = 0; j < data.numClasses(); j++) {
if (classCounts[j] > 0) {
entropy -= classCounts[j] * Utils.log2(classCounts[j]);
}
}
entropy /= (double) data.numInstances();
return entropy + Utils.log2(data.numInstances());
}
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];
}
/**
* Determines the output format based on the input format and returns this. In case the output
* format cannot be returned immediately, i.e., immediateOutputFormat() returns false, then this
* method will be called from batchFinished().
*
* @param inputFormat the input format to base the output format on
* @return the output format
* @throws Exception in case the determination goes wrong
* @see #hasImmediateOutputFormat()
* @see #batchFinished()
*/
protected Instances determineOutputFormat(Instances inputFormat) throws Exception {
Instances data;
Instances result;
FastVector atts;
FastVector values;
HashSet hash;
int i;
int n;
boolean isDate;
Instance inst;
Vector sorted;
m_Cols.setUpper(inputFormat.numAttributes() - 1);
data = new Instances(inputFormat);
atts = new FastVector();
for (i = 0; i < data.numAttributes(); i++) {
if (!m_Cols.isInRange(i) || !data.attribute(i).isNumeric()) {
atts.addElement(data.attribute(i));
continue;
}
// date attribute?
isDate = (data.attribute(i).type() == Attribute.DATE);
// determine all available attribtues in dataset
hash = new HashSet();
for (n = 0; n < data.numInstances(); n++) {
inst = data.instance(n);
if (inst.isMissing(i)) continue;
if (isDate) hash.add(inst.stringValue(i));
else hash.add(new Double(inst.value(i)));
}
// sort values
sorted = new Vector();
for (Object o : hash) sorted.add(o);
Collections.sort(sorted);
// create attribute from sorted values
values = new FastVector();
for (Object o : sorted) {
if (isDate) values.addElement(o.toString());
else values.addElement(Utils.doubleToString(((Double) o).doubleValue(), MAX_DECIMALS));
}
atts.addElement(new Attribute(data.attribute(i).name(), values));
}
result = new Instances(inputFormat.relationName(), atts, 0);
result.setClassIndex(inputFormat.classIndex());
return result;
}
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);
}
/**
* Computes information gain for an attribute.
*
* @param data the data for which info gain is to be computed
* @param att the attribute
* @return the information gain for the given attribute and data
* @throws Exception if computation fails
*/
private double computeInfoGain(Instances data, Attribute att) throws Exception {
double infoGain = computeEntropy(data);
Instances[] splitData = splitData(data, att);
for (int j = 0; j < att.numValues(); j++) {
if (splitData[j].numInstances() > 0) {
infoGain -=
((double) splitData[j].numInstances() / (double) data.numInstances())
* computeEntropy(splitData[j]);
}
}
return infoGain;
}
/**
* Implements the splitData function. This procedure is to split the data into bags according to
* the nominal attribute value The infoGain for each bag is also calculated.
*
* @param data the data to be split
* @param defAcRt the default accuracy rate for data
* @param cl the class label to be predicted
* @return the array of data after split
*/
public Instances[] splitData(Instances data, double defAcRt, double cl) {
int bag = att.numValues();
Instances[] splitData = new Instances[bag];
for (int x = 0; x < bag; x++) {
splitData[x] = new Instances(data, data.numInstances());
accurate[x] = 0;
coverage[x] = 0;
}
for (int x = 0; x < data.numInstances(); x++) {
Instance inst = data.instance(x);
if (!inst.isMissing(att)) {
int v = (int) inst.value(att);
splitData[v].add(inst);
coverage[v] += inst.weight();
if ((int) inst.classValue() == (int) cl) accurate[v] += inst.weight();
}
}
for (int x = 0; x < bag; x++) {
double t = coverage[x] + 1.0;
double p = accurate[x] + 1.0;
double infoGain =
// Utils.eq(defAcRt, 1.0) ?
// accurate[x]/(double)numConds :
accurate[x] * (Utils.log2(p / t) - Utils.log2(defAcRt));
if (infoGain > maxInfoGain) {
maxInfoGain = infoGain;
cover = coverage[x];
accu = accurate[x];
accuRate = p / t;
value = (double) x;
}
}
return splitData;
}
/**
* Initializes a gain ratio attribute evaluator. Discretizes all attributes that are numeric.
*
* @param data set of instances serving as training data
* @throws Exception if the evaluator has not been generated successfully
*/
public void buildEvaluator(Instances data) throws Exception {
// can evaluator handle data?
getCapabilities().testWithFail(data);
m_trainInstances = data;
m_classIndex = m_trainInstances.classIndex();
m_numAttribs = m_trainInstances.numAttributes();
m_numInstances = m_trainInstances.numInstances();
Discretize disTransform = new Discretize();
disTransform.setUseBetterEncoding(true);
disTransform.setInputFormat(m_trainInstances);
m_trainInstances = Filter.useFilter(m_trainInstances, disTransform);
m_numClasses = m_trainInstances.attribute(m_classIndex).numValues();
}
/**
* Splits a dataset according to the values of a nominal attribute.
*
* @param data the data which is to be split
* @param att the attribute to be used for splitting
* @return the sets of instances produced by the split
*/
private Instances[] splitData(Instances data, Attribute att) {
Instances[] splitData = new Instances[att.numValues()];
for (int j = 0; j < att.numValues(); j++) {
splitData[j] = new Instances(data, data.numInstances());
}
Enumeration instEnum = data.enumerateInstances();
while (instEnum.hasMoreElements()) {
Instance inst = (Instance) instEnum.nextElement();
splitData[(int) inst.value(att)].add(inst);
}
for (int i = 0; i < splitData.length; i++) {
splitData[i].compactify();
}
return splitData;
}
/**
* 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);
}
// 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;
}
/**
* Processes the given data (may change the provided dataset) and returns the modified version.
* This method is called in batchFinished().
*
* @param instances the data to process
* @return the modified data
* @throws Exception in case the processing goes wrong
* @see #batchFinished()
*/
protected Instances process(Instances instances) throws Exception {
Instances result;
int i;
int n;
double[] values;
String value;
Instance inst;
Instance newInst;
// we need the complete input data!
if (!isFirstBatchDone()) setOutputFormat(determineOutputFormat(getInputFormat()));
result = new Instances(getOutputFormat());
for (i = 0; i < instances.numInstances(); i++) {
inst = instances.instance(i);
values = inst.toDoubleArray();
for (n = 0; n < values.length; n++) {
if (!m_Cols.isInRange(n) || !instances.attribute(n).isNumeric() || inst.isMissing(n))
continue;
// get index of value
if (instances.attribute(n).type() == Attribute.DATE) value = inst.stringValue(n);
else value = Utils.doubleToString(inst.value(n), MAX_DECIMALS);
values[n] = result.attribute(n).indexOfValue(value);
}
// generate new instance
if (inst instanceof SparseInstance) newInst = new SparseInstance(inst.weight(), values);
else newInst = new DenseInstance(inst.weight(), values);
// copy possible string, relational values
newInst.setDataset(getOutputFormat());
copyValues(newInst, false, inst.dataset(), getOutputFormat());
result.add(newInst);
}
return result;
}
/**
* Method for building an Id3 tree.
*
* @param data the training data
* @exception Exception if decision tree can't be built successfully
*/
private void makeTree(Instances data) throws Exception {
// Check if no instances have reached this node.
if (data.numInstances() == 0) {
m_Attribute = null;
m_ClassValue = Utils.missingValue();
m_Distribution = new double[data.numClasses()];
return;
}
// Compute attribute with maximum information gain.
double[] infoGains = new double[data.numAttributes()];
Enumeration attEnum = data.enumerateAttributes();
while (attEnum.hasMoreElements()) {
Attribute att = (Attribute) attEnum.nextElement();
infoGains[att.index()] = computeInfoGain(data, att);
}
m_Attribute = data.attribute(Utils.maxIndex(infoGains));
// Make leaf if information gain is zero.
// Otherwise create successors.
if (Utils.eq(infoGains[m_Attribute.index()], 0)) {
m_Attribute = null;
m_Distribution = new double[data.numClasses()];
Enumeration instEnum = data.enumerateInstances();
while (instEnum.hasMoreElements()) {
Instance inst = (Instance) instEnum.nextElement();
m_Distribution[(int) inst.classValue()]++;
}
Utils.normalize(m_Distribution);
m_ClassValue = Utils.maxIndex(m_Distribution);
m_ClassAttribute = data.classAttribute();
} else {
Instances[] splitData = splitData(data, m_Attribute);
m_Successors = new Id3[m_Attribute.numValues()];
for (int j = 0; j < m_Attribute.numValues(); j++) {
m_Successors[j] = new Id3();
m_Successors[j].makeTree(splitData[j]);
}
}
}
/**
* 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));
}
/**
* Initializes the ranges of a subset of the instances of this dataset. Therefore m_Ranges is not
* set.
*
* @param instList list of indexes of the subset
* @return the ranges
* @throws Exception if something goes wrong
*/
public double[][] initializeRanges(int[] instList) throws Exception {
if (m_Data == null) {
throw new Exception("No instances supplied.");
}
int numAtt = m_Data.numAttributes();
double[][] ranges = new double[numAtt][3];
if (m_Data.numInstances() <= 0) {
initializeRangesEmpty(numAtt, ranges);
return ranges;
} else {
// initialize ranges using the first instance
updateRangesFirst(m_Data.instance(instList[0]), numAtt, ranges);
// update ranges, starting from the second
for (int i = 1; i < instList.length; i++) {
updateRanges(m_Data.instance(instList[i]), numAtt, ranges);
}
}
return ranges;
}
/**
* Generates an attribute evaluator. Has to initialise all fields of the evaluator that are not
* being set via options.
*
* @param data set of instances serving as training data
* @throws Exception if the evaluator has not been generated successfully
*/
public void buildEvaluator(Instances data) throws Exception {
// can evaluator handle data?
getCapabilities().testWithFail(data);
m_trainInstances = new Instances(data);
m_trainInstances.deleteWithMissingClass();
m_numAttribs = m_trainInstances.numAttributes();
m_numInstances = m_trainInstances.numInstances();
// if the data has no decision feature, m_classIndex is negative
m_classIndex = m_trainInstances.classIndex();
// supervised
if (m_classIndex >= 0) {
m_isNumeric = m_trainInstances.attribute(m_classIndex).isNumeric();
if (m_isNumeric) {
m_DecisionSimilarity = m_Similarity;
} else m_DecisionSimilarity = m_SimilarityEq;
}
m_Similarity.setInstances(m_trainInstances);
m_DecisionSimilarity.setInstances(m_trainInstances);
m_SimilarityEq.setInstances(m_trainInstances);
m_composition = m_Similarity.getTNorm();
m_FuzzyMeasure.set(
m_Similarity,
m_DecisionSimilarity,
m_TNorm,
m_composition,
m_Implicator,
m_SNorm,
m_numInstances,
m_numAttribs,
m_classIndex,
m_trainInstances);
}
public void calculateConfidences(Instances data) throws Exception {
RipperRule tempRule = (RipperRule) this.copy();
while (tempRule.hasAntds()) {
double acc = 0;
double cov = 0;
for (int i = 0; i < data.numInstances(); i++) {
double membershipValue = tempRule.coverageDegree(data.instance(i));
cov += membershipValue;
if (m_Consequent == data.instance(i).classValue()) {
acc += membershipValue;
}
}
// m-estimate
double m = 2.0;
((Antd) this.m_Antds.elementAt((int) tempRule.size() - 1)).m_confidence =
(acc + m * (aprioriDistribution[(int) m_Consequent] / Utils.sum(aprioriDistribution)))
/ (cov + m);
tempRule.m_Antds.removeElementAt(tempRule.m_Antds.size() - 1);
}
}
/**
* 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);
}
}
/**
* 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++;
}
}
public static void main(String args[]) {
Timers timer = new Timers();
try {
// Get the data set path.
String referenceFile = Utils.getOption('r', args);
String queryFile = Utils.getOption('q', args);
if (referenceFile.length() == 0)
throw new IllegalArgumentException(
"Required option: File containing" + "the reference dataset.");
// Load input dataset.
DataSource source = new DataSource(referenceFile);
Instances referenceData = source.getDataSet();
Instances queryData = null;
if (queryFile.length() != 0) {
source = new DataSource(queryFile);
queryData = source.getDataSet();
}
timer.StartTimer("total_time");
// Get all the parameters.
String leafSize = Utils.getOption('l', args);
String neighbors = Utils.getOption('k', args);
// Validate options.
int k = 0;
if (neighbors.length() == 0) {
throw new IllegalArgumentException(
"Required option: Number of " + "furthest neighbors to find.");
} else {
k = Integer.parseInt(neighbors);
if (k < 1 || k > referenceData.numInstances())
throw new IllegalArgumentException("[Fatal] Invalid k");
}
int l = 20;
if (leafSize.length() != 0) l = Integer.parseInt(leafSize);
// Create KDTree.
KDTree tree = new KDTree();
tree.setMaxInstInLeaf(l);
tree.setInstances(referenceData);
// Perform All K-Nearest-Neighbors.
if (queryFile.length() != 0) {
for (int i = 0; i < queryData.numInstances(); i++) {
Instances out = tree.kNearestNeighbours(queryData.instance(i), k);
}
} else {
for (int i = 0; i < referenceData.numInstances(); i++) {
Instances out = tree.kNearestNeighbours(referenceData.instance(i), k);
}
}
timer.StopTimer("total_time");
timer.PrintTimer("total_time");
} catch (IOException e) {
System.err.println(USAGE);
} catch (Exception e) {
e.printStackTrace();
}
}
