@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 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;
}
/**
* Checks if the arguments are compatible with the attributes specified by getInputAttributes().
*/
private boolean argumentsOk(ExampleTable input) {
Attribute[] inputA = getInputAttributes();
for (int i = 0; i < inputA.length; i++) {
if (!Tools.compatible(arguments[i], inputA[i])) return false;
}
return true;
}
@Override
public ClusterModel generateClusterModel(ExampleSet exampleSet) throws OperatorException {
// checking and creating ids if necessary
Tools.checkAndCreateIds(exampleSet);
// generating assignment
RandomGenerator random = RandomGenerator.getRandomGenerator(this);
int clusterAssignments[] = new int[exampleSet.size()];
int k = getParameterAsInt(PARAMETER_NUMBER_OF_CLUSTERS);
for (int i = 0; i < exampleSet.size(); i++) {
clusterAssignments[i] = random.nextInt(k);
}
ClusterModel model =
new ClusterModel(
exampleSet,
k,
getParameterAsBoolean(RMAbstractClusterer.PARAMETER_ADD_AS_LABEL),
getParameterAsBoolean(RMAbstractClusterer.PARAMETER_REMOVE_UNLABELED));
model.setClusterAssignments(clusterAssignments, exampleSet);
// generating cluster attribute
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;
}
/**
* Creates a fresh example set of the given size from the RapidMiner example reader. The alpha
* values and b are zero, the label will be set if it is known.
*/
public SVMExamples(
com.rapidminer.example.ExampleSet exampleSet,
Attribute labelAttribute,
Map<Integer, MeanVariance> meanVariances) {
this(exampleSet.size(), 0.0d);
this.meanVarianceMap = meanVariances;
Iterator<com.rapidminer.example.Example> reader = exampleSet.iterator();
Attribute idAttribute = exampleSet.getAttributes().getId();
int exampleCounter = 0;
while (reader.hasNext()) {
com.rapidminer.example.Example current = reader.next();
Map<Integer, Double> attributeMap = new LinkedHashMap<Integer, Double>();
int a = 0;
for (Attribute attribute : exampleSet.getAttributes()) {
double value = current.getValue(attribute);
if (!com.rapidminer.example.Tools.isDefault(attribute.getDefault(), value)) {
attributeMap.put(a, value);
}
if ((a + 1) > dim) {
dim = (a + 1);
}
a++;
}
atts[exampleCounter] = new double[attributeMap.size()];
index[exampleCounter] = new int[attributeMap.size()];
Iterator<Map.Entry<Integer, Double>> i = attributeMap.entrySet().iterator();
int attributeCounter = 0;
while (i.hasNext()) {
Map.Entry<Integer, Double> e = i.next();
Integer indexValue = e.getKey();
Double attributeValue = e.getValue();
index[exampleCounter][attributeCounter] = indexValue.intValue();
double value = attributeValue.doubleValue();
MeanVariance meanVariance = meanVarianceMap.get(indexValue);
if (meanVariance != null) {
if (meanVariance.getVariance() == 0.0d) {
value = 0.0d;
} else {
value = (value - meanVariance.getMean()) / Math.sqrt(meanVariance.getVariance());
}
}
atts[exampleCounter][attributeCounter] = value;
attributeCounter++;
}
if (labelAttribute != null) {
double label = current.getValue(labelAttribute);
if (labelAttribute.isNominal()) {
ys[exampleCounter] = (label == labelAttribute.getMapping().getPositiveIndex() ? 1 : -1);
} else {
ys[exampleCounter] = label;
}
}
if (idAttribute != null) {
ids[exampleCounter] = current.getValueAsString(idAttribute);
}
exampleCounter++;
}
}
public HyperplaneModel(
ExampleSet exampleSet, String classNegative, String classPositive, Kernel kernel) {
super(exampleSet);
this.coefficientNames = com.rapidminer.example.Tools.getRegularAttributeNames(exampleSet);
this.classNegative = classNegative;
this.classPositive = classPositive;
this.kernel = kernel;
}
/**
* Iterates over all models and returns the class with maximum likelihood.
*
* @param origExampleSet the set of examples to be classified
*/
@Override
public ExampleSet performPrediction(ExampleSet origExampleSet, Attribute predictedLabel)
throws OperatorException {
final String attributePrefix = "AdaBoostModelPrediction";
final int numLabels = predictedLabel.getMapping().size();
final Attribute[] specialAttributes = new Attribute[numLabels];
OperatorProgress progress = null;
if (getShowProgress() && getOperator() != null && getOperator().getProgress() != null) {
progress = getOperator().getProgress();
progress.setTotal(100);
}
for (int i = 0; i < numLabels; i++) {
specialAttributes[i] =
com.rapidminer.example.Tools.createSpecialAttribute(
origExampleSet, attributePrefix + i, Ontology.NUMERICAL);
if (progress != null) {
progress.setCompleted((int) (25.0 * (i + 1) / numLabels));
}
}
Iterator<Example> reader = origExampleSet.iterator();
int progressCounter = 0;
while (reader.hasNext()) {
Example example = reader.next();
for (int i = 0; i < specialAttributes.length; i++) {
example.setValue(specialAttributes[i], 0);
}
if (progress != null && ++progressCounter % OPERATOR_PROGRESS_STEPS == 0) {
progress.setCompleted((int) (25.0 * progressCounter / origExampleSet.size()) + 25);
}
}
reader = origExampleSet.iterator();
for (int modelNr = 0; modelNr < this.getNumberOfModels(); modelNr++) {
Model model = this.getModel(modelNr);
ExampleSet exampleSet = (ExampleSet) origExampleSet.clone();
exampleSet = model.apply(exampleSet);
this.updateEstimates(exampleSet, modelNr, specialAttributes);
PredictionModel.removePredictedLabel(exampleSet);
if (progress != null) {
progress.setCompleted((int) (25.0 * (modelNr + 1) / this.getNumberOfModels()) + 50);
}
}
// Turn prediction weights into confidences and a crisp predcition:
this.evaluateSpecialAttributes(origExampleSet, specialAttributes);
// Clean up attributes:
for (int i = 0; i < numLabels; i++) {
origExampleSet.getAttributes().remove(specialAttributes[i]);
origExampleSet.getExampleTable().removeAttribute(specialAttributes[i]);
if (progress != null) {
progress.setCompleted((int) (25.0 * (i + 1) / numLabels) + 75);
}
}
return origExampleSet;
}
protected boolean checkCompatibility(
Attribute attribute, Attribute compatible, String[] functions) {
if (Tools.compatible(attribute, compatible)) {
for (int f = 0; f < functions.length; f++) {
if (attribute.getConstruction().indexOf(functions[f]) != -1) return false;
}
return true;
} else {
return false;
}
}
// checking for example set and valid attributes
@Override
public void init(ExampleSet exampleSet) throws OperatorException {
super.init(exampleSet);
Tools.onlyNominalAttributes(exampleSet, "nominal similarities");
this.useAttribute = new boolean[exampleSet.getAttributes().size()];
int i = 0;
for (Attribute attribute : exampleSet.getAttributes()) {
if (attribute.isNominal()) {
useAttribute[i] = true;
}
i++;
}
}
@Override
public void doWork() throws OperatorException {
ExampleSet exampleSet = exampleSetInput.getData(ExampleSet.class);
// needed for some measures
Tools.checkAndCreateIds(exampleSet);
DistanceMeasure measure = measureHelper.getInitializedMeasure(exampleSet);
SimilarityMeasureObject measureObject = new SimilarityMeasureObject(measure, exampleSet);
ObjectVisualizerService.addObjectVisualizer(measureObject, new ExampleVisualizer(exampleSet));
similarityOutput.deliver(measureObject);
exampleSetOutput.deliver(exampleSet);
}
@Override
public void init(ExampleSet exampleSet) throws OperatorException {
super.init(exampleSet);
Tools.onlyNumericalAttributes(exampleSet, "value based similarities");
Attributes attributes = exampleSet.getAttributes();
if (attributes.size() != 1)
throw new OperatorException(
"The bregman divergence you've choosen is not applicable for the dataset! Proceeding with the 'Squared Euclidean distance' bregman divergence.");
for (Example example : exampleSet) {
for (Attribute attribute : attributes) {
if (example.getValue(attribute) <= 0)
throw new OperatorException(
"The bregman divergence you've choosen is not applicable for the dataset! Proceeding with the 'Squared Euclidean distance' bregman divergence.");
;
}
}
}
protected void prepareWeights(ExampleSet exampleSet) {
Attribute weightAttr = exampleSet.getAttributes().getWeight();
if (weightAttr == null) {
this.oldWeights = null;
com.rapidminer.example.Tools.createWeightAttribute(exampleSet);
} else { // Back up old weights
this.oldWeights = new double[exampleSet.size()];
Iterator<Example> reader = exampleSet.iterator();
for (int i = 0; (reader.hasNext() && i < oldWeights.length); i++) {
Example example = reader.next();
if (example != null) {
this.oldWeights[i] = example.getWeight();
example.setWeight(1);
}
}
}
}
public IOObject[] apply() throws OperatorException {
ExampleSet eSet = getInput(ExampleSet.class);
// only warning, removing is done by createSpecialAttribute(...)
Attribute idAttribute = eSet.getAttributes().getId();
if (idAttribute != null) {
logWarning("Overwriting old id attribute!");
}
// create new id attribute
boolean nominalIds = getParameterAsBoolean(PARAMETER_CREATE_NOMINAL_IDS);
idAttribute =
Tools.createSpecialAttribute(
eSet, Attributes.ID_NAME, nominalIds ? Ontology.NOMINAL : Ontology.INTEGER);
// set IDs
int currentId = 1;
Iterator<Example> r = eSet.iterator();
while (r.hasNext()) {
Example example = r.next();
example.setValue(
idAttribute,
nominalIds ? idAttribute.getMapping().mapString("id_" + currentId) : currentId);
currentId++;
checkForStop();
}
// initialize example visualizer
Operator visualizer = null;
try {
visualizer = OperatorService.createOperator(ExampleVisualizationOperator.class);
} catch (OperatorCreationException e) {
logNote("Cannot initialize example visualizer, skipping...");
}
if (visualizer != null) visualizer.apply(new IOContainer(eSet));
return new IOObject[] {eSet};
}
@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;
}
/**
* Constructs a <code>Model</code> repeatedly running a weak learner, reweighting the training
* example set accordingly, and combining the hypothesis using the available weighted performance
* values.
*/
public Model learn(ExampleSet exampleSet) throws OperatorException {
this.runVector = new RunVector();
BayBoostModel ensembleNewBatch = null;
BayBoostModel ensembleExtBatch = null;
final Vector<BayBoostBaseModelInfo> modelInfo = new Vector<BayBoostBaseModelInfo>(); // for
// models
// and
// their
// probability
// estimates
Vector<BayBoostBaseModelInfo> modelInfo2 = new Vector<BayBoostBaseModelInfo>();
this.currentIteration = 0;
int firstOpenBatch = 1;
// prepare the stream control attribute
final Attribute streamControlAttribute;
{
Attribute attr = null;
if ((attr = exampleSet.getAttributes().get(STREAM_CONTROL_ATTRIB_NAME)) == null)
streamControlAttribute =
com.rapidminer.example.Tools.createSpecialAttribute(
exampleSet, STREAM_CONTROL_ATTRIB_NAME, Ontology.INTEGER);
else {
streamControlAttribute = attr;
logWarning(
"Attribute with the (reserved) name of the stream control attribute exists. It is probably an old version created by this operator. Trying to recycle it... ");
// Resetting the stream control attribute values by overwriting
// them with 0 avoids (unlikely)
// problems in case the same ExampleSet is passed to this
// operator over and over again:
Iterator<Example> e = exampleSet.iterator();
while (e.hasNext()) {
e.next().setValue(streamControlAttribute, 0);
}
}
}
// and the weight attribute
if (exampleSet.getAttributes().getWeight() == null) {
this.prepareWeights(exampleSet);
}
boolean estimateFavoursExtBatch = true;
// *** The main loop, one iteration per batch: ***
Iterator<Example> reader = exampleSet.iterator();
while (reader.hasNext()) {
// increment batch number, collect batch and evaluate performance of
// current model on batch
double[] classPriors =
this.prepareBatch(++this.currentIteration, reader, streamControlAttribute);
ConditionedExampleSet trainingSet =
new ConditionedExampleSet(
exampleSet, new BatchFilterCondition(streamControlAttribute, this.currentIteration));
final EstimatedPerformance estPerf;
// Step 1: apply the ensemble model to the current batch (prediction
// phase), evaluate and store result
if (ensembleExtBatch != null) {
// apply extended batch model first:
trainingSet = (ConditionedExampleSet) ensembleExtBatch.apply(trainingSet);
this.performance = evaluatePredictions(trainingSet); // unweighted
// performance;
// then apply new batch model:
trainingSet = (ConditionedExampleSet) ensembleNewBatch.apply(trainingSet);
double newBatchPerformance = evaluatePredictions(trainingSet);
// heuristic: use extended batch model for predicting
// unclassified instances
if (estimateFavoursExtBatch == true)
estPerf =
new EstimatedPerformance("accuracy", this.performance, trainingSet.size(), false);
else
estPerf =
new EstimatedPerformance("accuracy", newBatchPerformance, trainingSet.size(), false);
// final double[] ensembleWeights;
// continue with the better model:
if (newBatchPerformance > this.performance) {
this.performance = newBatchPerformance;
firstOpenBatch = Math.max(1, this.currentIteration - 1);
// ensembleWeights = ensembleNewBatch.getModelWeights();
} else {
modelInfo.clear();
modelInfo.addAll(modelInfo2);
// ensembleWeights = ensembleExtBatch.getModelWeights();
}
} else if (ensembleNewBatch != null) {
trainingSet = (ConditionedExampleSet) ensembleNewBatch.apply(trainingSet);
this.performance = evaluatePredictions(trainingSet);
firstOpenBatch = Math.max(1, this.currentIteration - 1);
estPerf = new EstimatedPerformance("accuracy", this.performance, trainingSet.size(), false);
} else estPerf = null; // no model ==> no prediction performance
if (estPerf != null) {
PerformanceVector perf = new PerformanceVector();
perf.addAveragable(estPerf);
this.runVector.addVector(perf);
}
// *** retraining phase ***
// Step 2: First reconstruct the initial weighting, if necessary.
if (this.getParameterAsBoolean(PARAMETER_RESCALE_LABEL_PRIORS) == true) {
this.rescalePriors(trainingSet, classPriors);
}
estimateFavoursExtBatch = true;
// Step 3: Find better weights for existing models and continue
// training
if (modelInfo.size() > 0) {
modelInfo2 = new Vector<BayBoostBaseModelInfo>();
for (BayBoostBaseModelInfo bbbmi : modelInfo) {
modelInfo2.add(bbbmi); // BayBoostBaseModelInfo objects
// cannot be changed, no deep copy
// required
}
// separate hold out set
final double holdOutRatio = this.getParameterAsDouble(PARAMETER_FRACTION_HOLD_OUT_SET);
Vector<Example> holdOutExamples = new Vector<Example>();
if (holdOutRatio > 0) {
RandomGenerator random = RandomGenerator.getRandomGenerator(this);
Iterator<Example> randBatchReader = trainingSet.iterator();
while (randBatchReader.hasNext()) {
Example example = randBatchReader.next();
if (random.nextDoubleInRange(0, 1) <= holdOutRatio) {
example.setValue(streamControlAttribute, 0);
holdOutExamples.add(example);
}
}
// TODO: create new example set
// trainingSet.updateCondition();
}
// model 1: train one more base classifier
boolean trainingExamplesLeft = this.adjustBaseModelWeights(trainingSet, modelInfo);
if (trainingExamplesLeft) {
// "trainingExamplesLeft" needs to be checked to avoid
// exceptions.
// Anyway, learning does not make sense, otherwise.
if (!this.trainAdditionalModel(trainingSet, modelInfo)) {}
}
ensembleNewBatch = new BayBoostModel(exampleSet, modelInfo, classPriors);
// model 2: remove last classifier, extend batch, train on
// extended batch
ExampleSet extendedBatch = // because of the ">=" condition it
// is sufficient to remember the
// opening batch
new ConditionedExampleSet(
exampleSet, new BatchFilterCondition(streamControlAttribute, firstOpenBatch));
classPriors = this.prepareExtendedBatch(extendedBatch);
if (this.getParameterAsBoolean(PARAMETER_RESCALE_LABEL_PRIORS) == true) {
this.rescalePriors(extendedBatch, classPriors);
}
modelInfo2.remove(modelInfo2.size() - 1);
trainingExamplesLeft = this.adjustBaseModelWeights(extendedBatch, modelInfo2);
// If no training examples are left: no need and chance to
// continue training.
if (trainingExamplesLeft == false) {
ensembleExtBatch = new BayBoostModel(exampleSet, modelInfo2, classPriors);
} else {
boolean success = this.trainAdditionalModel(extendedBatch, modelInfo2);
if (success) {
ensembleExtBatch = new BayBoostModel(exampleSet, modelInfo2, classPriors);
} else {
ensembleExtBatch = null;
estimateFavoursExtBatch = false;
}
}
if (holdOutRatio > 0) {
Iterator hoEit = holdOutExamples.iterator();
while (hoEit.hasNext()) {
((Example) hoEit.next()).setValue(streamControlAttribute, this.currentIteration);
}
// TODO: create new example set
// trainingSet.updateCondition();
if (ensembleExtBatch != null) {
trainingSet = (ConditionedExampleSet) ensembleNewBatch.apply(trainingSet);
hoEit = holdOutExamples.iterator();
int errors = 0;
while (hoEit.hasNext()) {
Example example = (Example) hoEit.next();
if (example.getPredictedLabel() != example.getLabel()) errors++;
}
double newBatchErr = ((double) errors) / holdOutExamples.size();
trainingSet = (ConditionedExampleSet) ensembleExtBatch.apply(trainingSet);
hoEit = holdOutExamples.iterator();
errors = 0;
while (hoEit.hasNext()) {
Example example = (Example) hoEit.next();
if (example.getPredictedLabel() != example.getLabel()) errors++;
}
double extBatchErr = ((double) errors) / holdOutExamples.size();
estimateFavoursExtBatch = (extBatchErr <= newBatchErr);
if (estimateFavoursExtBatch) {
ensembleExtBatch =
this.retrainLastWeight(ensembleExtBatch, trainingSet, holdOutExamples);
} else
ensembleNewBatch =
this.retrainLastWeight(ensembleNewBatch, trainingSet, holdOutExamples);
} else
ensembleNewBatch =
this.retrainLastWeight(ensembleNewBatch, trainingSet, holdOutExamples);
}
} else {
this.trainAdditionalModel(trainingSet, modelInfo);
ensembleNewBatch = new BayBoostModel(exampleSet, modelInfo, classPriors);
ensembleExtBatch = null;
estimateFavoursExtBatch = false;
}
}
this.restoreOldWeights(exampleSet);
return (ensembleExtBatch == null ? ensembleNewBatch : ensembleExtBatch);
}
/** Sets the given data for the given index. */
@Override
protected void set(int index, double value, double defaultValue) {
if (Tools.isDefault(defaultValue, value)) data.remove(index);
else data.put(index, value);
}
@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);
}
@Override
public void init(ExampleSet exampleSet) throws OperatorException {
super.init(exampleSet);
Tools.onlyNumericalAttributes(exampleSet, "value based similarities");
}