@Override
public Model learn(ExampleSet exampleSet) throws OperatorException {
Tools.onlyNonMissingValues(exampleSet, getOperatorClassName(), this, new String[0]);
ImprovedNeuralNetModel model = new ImprovedNeuralNetModel(exampleSet);
List<String[]> hiddenLayers = getParameterList(PARAMETER_HIDDEN_LAYERS);
int maxCycles = getParameterAsInt(PARAMETER_TRAINING_CYCLES);
double maxError = getParameterAsDouble(PARAMETER_ERROR_EPSILON);
double learningRate = getParameterAsDouble(PARAMETER_LEARNING_RATE);
double momentum = getParameterAsDouble(PARAMETER_MOMENTUM);
boolean decay = getParameterAsBoolean(PARAMETER_DECAY);
boolean shuffle = getParameterAsBoolean(PARAMETER_SHUFFLE);
boolean normalize = getParameterAsBoolean(PARAMETER_NORMALIZE);
RandomGenerator randomGenerator = RandomGenerator.getRandomGenerator(this);
model.train(
exampleSet,
hiddenLayers,
maxCycles,
maxError,
learningRate,
momentum,
decay,
shuffle,
normalize,
randomGenerator,
this);
return model;
}
@Override
public void doWork() throws OperatorException {
ExampleSet exampleSet = exampleSetInput.getData(ExampleSet.class);
// only use numeric attributes
Tools.onlyNumericalAttributes(exampleSet, "KernelPCA");
Tools.onlyNonMissingValues(exampleSet, getOperatorClassName(), this);
Attributes attributes = exampleSet.getAttributes();
int numberOfExamples = exampleSet.size();
// calculating means for later zero centering
exampleSet.recalculateAllAttributeStatistics();
double[] means = new double[exampleSet.getAttributes().size()];
int i = 0;
for (Attribute attribute : exampleSet.getAttributes()) {
means[i] = exampleSet.getStatistics(attribute, Statistics.AVERAGE);
i++;
}
// kernel
Kernel kernel = Kernel.createKernel(this);
// copying zero centered exampleValues
ArrayList<double[]> exampleValues = new ArrayList<double[]>(numberOfExamples);
i = 0;
for (Example columnExample : exampleSet) {
double[] columnValues = getAttributeValues(columnExample, attributes, means);
exampleValues.add(columnValues);
i++;
}
// filling kernel matrix
Matrix kernelMatrix = new Matrix(numberOfExamples, numberOfExamples);
for (i = 0; i < numberOfExamples; i++) {
for (int j = 0; j < numberOfExamples; j++) {
kernelMatrix.set(
i, j, kernel.calculateDistance(exampleValues.get(i), exampleValues.get(j)));
}
}
// calculating eigenVectors
EigenvalueDecomposition eig = kernelMatrix.eig();
Model model = new KernelPCAModel(exampleSet, means, eig.getV(), exampleValues, kernel);
if (exampleSetOutput.isConnected()) {
exampleSetOutput.deliver(model.apply(exampleSet));
}
originalOutput.deliver(exampleSet);
modelOutput.deliver(model);
}
@Override
public ClusterModel generateClusterModel(ExampleSet exampleSet) throws OperatorException {
int k = getParameterAsInt(PARAMETER_K);
int maxOptimizationSteps = getParameterAsInt(PARAMETER_MAX_OPTIMIZATION_STEPS);
boolean useExampleWeights = getParameterAsBoolean(PARAMETER_USE_WEIGHTS);
Kernel kernel = Kernel.createKernel(this);
// init operator progress
getProgress().setTotal(maxOptimizationSteps);
// checking and creating ids if necessary
Tools.checkAndCreateIds(exampleSet);
// additional checks
Tools.onlyNonMissingValues(exampleSet, getOperatorClassName(), this, new String[0]);
if (exampleSet.size() < k) {
throw new UserError(this, 142, k);
}
// extracting attribute names
Attributes attributes = exampleSet.getAttributes();
ArrayList<String> attributeNames = new ArrayList<String>(attributes.size());
for (Attribute attribute : attributes) {
attributeNames.add(attribute.getName());
}
Attribute weightAttribute = attributes.getWeight();
RandomGenerator generator = RandomGenerator.getRandomGenerator(this);
ClusterModel model =
new ClusterModel(
exampleSet,
k,
getParameterAsBoolean(RMAbstractClusterer.PARAMETER_ADD_AS_LABEL),
getParameterAsBoolean(RMAbstractClusterer.PARAMETER_REMOVE_UNLABELED));
// init centroids
int[] clusterAssignments = new int[exampleSet.size()];
for (int i = 0; i < exampleSet.size(); i++) {
clusterAssignments[i] = generator.nextIntInRange(0, k);
}
// run optimization steps
boolean stable = false;
for (int step = 0; step < maxOptimizationSteps && !stable; step++) {
// calculating cluster kernel properties
double[] clusterWeights = new double[k];
double[] clusterKernelCorrection = new double[k];
int i = 0;
for (Example firstExample : exampleSet) {
double firstExampleWeight = useExampleWeights ? firstExample.getValue(weightAttribute) : 1d;
double[] firstExampleValues = getAsDoubleArray(firstExample, attributes);
clusterWeights[clusterAssignments[i]] += firstExampleWeight;
int j = 0;
for (Example secondExample : exampleSet) {
if (clusterAssignments[i] == clusterAssignments[j]) {
double secondExampleWeight =
useExampleWeights ? secondExample.getValue(weightAttribute) : 1d;
clusterKernelCorrection[clusterAssignments[i]] +=
firstExampleWeight
* secondExampleWeight
* kernel.calculateDistance(
firstExampleValues, getAsDoubleArray(secondExample, attributes));
}
j++;
}
i++;
}
for (int z = 0; z < k; z++) {
clusterKernelCorrection[z] /= clusterWeights[z] * clusterWeights[z];
}
// assign examples to new centroids
int[] newClusterAssignments = new int[exampleSet.size()];
i = 0;
for (Example example : exampleSet) {
double[] exampleValues = getAsDoubleArray(example, attributes);
double exampleKernelValue = kernel.calculateDistance(exampleValues, exampleValues);
double nearestDistance = Double.POSITIVE_INFINITY;
int nearestIndex = 0;
for (int clusterIndex = 0; clusterIndex < k; clusterIndex++) {
double distance = 0;
// iterating over all examples in cluster to get kernel distance
int j = 0;
for (Example clusterExample : exampleSet) {
if (clusterAssignments[j] == clusterIndex) {
distance +=
(useExampleWeights ? clusterExample.getValue(weightAttribute) : 1d)
* kernel.calculateDistance(
getAsDoubleArray(clusterExample, attributes), exampleValues);
}
j++;
}
distance *= -2d / clusterWeights[clusterIndex];
// copy in outer loop
distance += exampleKernelValue;
distance += clusterKernelCorrection[clusterIndex];
if (distance < nearestDistance) {
nearestDistance = distance;
nearestIndex = clusterIndex;
}
}
newClusterAssignments[i] = nearestIndex;
i++;
}
// finishing assignment
stable = true;
for (int j = 0; j < exampleSet.size() && stable; j++) {
stable &= newClusterAssignments[j] == clusterAssignments[j];
}
clusterAssignments = newClusterAssignments;
// trigger operator progress
getProgress().step();
}
// setting last clustering into model
model.setClusterAssignments(clusterAssignments, exampleSet);
getProgress().complete();
if (addsClusterAttribute()) {
Attribute cluster = AttributeFactory.createAttribute("cluster", Ontology.NOMINAL);
exampleSet.getExampleTable().addAttribute(cluster);
exampleSet.getAttributes().setCluster(cluster);
int i = 0;
for (Example example : exampleSet) {
example.setValue(cluster, "cluster_" + clusterAssignments[i]);
i++;
}
}
return model;
}
@Override
public void doWork() throws OperatorException {
ExampleSet exampleSet = exampleSetInput.getData(ExampleSet.class);
DistanceMeasure measure = measureHelper.getInitializedMeasure(exampleSet);
// additional checks
Tools.onlyNonMissingValues(exampleSet, getOperatorClassName(), this, new String[0]);
Tools.checkAndCreateIds(exampleSet);
Attribute idAttribute = exampleSet.getAttributes().getId();
boolean idAttributeIsNominal = idAttribute.isNominal();
DistanceMatrix matrix = new DistanceMatrix(exampleSet.size());
Map<Integer, HierarchicalClusterNode> clusterMap =
new HashMap<Integer, HierarchicalClusterNode>(exampleSet.size());
int[] clusterIds = new int[exampleSet.size()];
// filling the distance matrix
int nextClusterId = 0;
for (Example example1 : exampleSet) {
checkForStop();
clusterIds[nextClusterId] = nextClusterId;
int y = 0;
for (Example example2 : exampleSet) {
if (y > nextClusterId) {
matrix.set(nextClusterId, y, measure.calculateDistance(example1, example2));
}
y++;
}
if (idAttributeIsNominal) {
clusterMap.put(
nextClusterId,
new HierarchicalClusterLeafNode(nextClusterId, example1.getValueAsString(idAttribute)));
} else {
clusterMap.put(
nextClusterId,
new HierarchicalClusterLeafNode(nextClusterId, example1.getValue(idAttribute)));
}
nextClusterId++;
}
// creating linkage method
AbstractLinkageMethod linkage = new SingleLinkageMethod(matrix, clusterIds);
if (getParameterAsString(PARAMETER_MODE).equals(modes[1])) {
linkage = new CompleteLinkageMethod(matrix, clusterIds);
} else if (getParameterAsString(PARAMETER_MODE).equals(modes[2])) {
linkage = new AverageLinkageMethod(matrix, clusterIds);
}
// now building agglomerative tree bottom up
while (clusterMap.size() > 1) {
Agglomeration agglomeration = linkage.getNextAgglomeration(nextClusterId, clusterMap);
HierarchicalClusterNode newNode =
new HierarchicalClusterNode(nextClusterId, agglomeration.getDistance());
newNode.addSubNode(clusterMap.get(agglomeration.getClusterId1()));
newNode.addSubNode(clusterMap.get(agglomeration.getClusterId2()));
clusterMap.remove(agglomeration.getClusterId1());
clusterMap.remove(agglomeration.getClusterId2());
clusterMap.put(nextClusterId, newNode);
nextClusterId++;
}
// creating model
HierarchicalClusterModel model =
new DendogramHierarchicalClusterModel(clusterMap.entrySet().iterator().next().getValue());
// registering visualizer
ObjectVisualizerService.addObjectVisualizer(
model, new ExampleVisualizer((ExampleSet) exampleSet.clone()));
modelOutput.deliver(model);
exampleSetOutput.deliver(exampleSet);
}
