@Override
public Model learn(ExampleSet exampleSet) throws OperatorException {
DistanceMeasure measure = DistanceMeasures.createMeasure(this);
measure.init(exampleSet);
GeometricDataCollection<RegressionData> data = new LinearList<RegressionData>(measure);
// check if weights should be used
boolean useWeights = getParameterAsBoolean(PARAMETER_USE_EXAMPLE_WEIGHTS);
// check if robust estimate should be performed: Then calculate weights and use it anyway
if (getParameterAsBoolean(PARAMETER_USE_ROBUST_ESTIMATION)) {
useWeights = true;
LocalPolynomialExampleWeightingOperator weightingOperator;
try {
weightingOperator =
OperatorService.createOperator(LocalPolynomialExampleWeightingOperator.class);
exampleSet = weightingOperator.doWork((ExampleSet) exampleSet.clone(), this);
} catch (OperatorCreationException e) {
throw new UserError(this, 904, "LocalPolynomialExampleWeighting", e.getMessage());
}
}
Attributes attributes = exampleSet.getAttributes();
Attribute label = attributes.getLabel();
Attribute weightAttribute = attributes.getWeight();
for (Example example : exampleSet) {
double[] values = new double[attributes.size()];
double labelValue = example.getValue(label);
double weight = 1d;
if (weightAttribute != null && useWeights) {
weight = example.getValue(weightAttribute);
}
// filter out examples without influence
if (weight > 0d) {
// copying example values
int i = 0;
for (Attribute attribute : attributes) {
values[i] = example.getValue(attribute);
i++;
}
// inserting into geometric data collection
data.add(values, new RegressionData(values, labelValue, weight));
}
}
return new LocalPolynomialRegressionModel(
exampleSet,
data,
Neighborhoods.createNeighborhood(this),
SmoothingKernels.createKernel(this),
getParameterAsInt(PARAMETER_DEGREE),
getParameterAsDouble(PARAMETER_RIDGE));
}
@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;
}
