use of org.knime.base.node.mine.treeensemble2.model.TreeNodeSignature in project knime-core by knime.
the class LKGradientBoostedTreesLearner method adaptPreviousFunction.
private void adaptPreviousFunction(final double[] previousFunction, final TreeModelRegression tree, final Map<TreeNodeSignature, Double> coefficientMap) {
final TreeData data = getData();
final IDataIndexManager indexManager = getIndexManager();
for (int i = 0; i < previousFunction.length; i++) {
final PredictorRecord record = createPredictorRecord(data, indexManager, i);
final TreeNodeSignature signature = tree.findMatchingNode(record).getSignature();
previousFunction[i] += coefficientMap.get(signature);
}
}
use of org.knime.base.node.mine.treeensemble2.model.TreeNodeSignature in project knime-core by knime.
the class LKGradientBoostedTreesLearner method learn.
/**
* {@inheritDoc}
*
* @throws ExecutionException
* @throws InterruptedException
*/
@Override
public MultiClassGradientBoostedTreesModel learn(final ExecutionMonitor exec) throws CanceledExecutionException, InterruptedException, ExecutionException {
final TreeData data = getData();
final TreeTargetNominalColumnData target = (TreeTargetNominalColumnData) data.getTargetColumn();
final NominalValueRepresentation[] classNomVals = target.getMetaData().getValues();
final int numClasses = classNomVals.length;
final String[] classLabels = new String[numClasses];
final int nrModels = getConfig().getNrModels();
final int nrRows = target.getNrRows();
final TreeModelRegression[][] models = new TreeModelRegression[nrModels][numClasses];
final ArrayList<ArrayList<Map<TreeNodeSignature, Double>>> coefficientMaps = new ArrayList<ArrayList<Map<TreeNodeSignature, Double>>>(nrModels);
// variables for parallelization
final ThreadPool tp = KNIMEConstants.GLOBAL_THREAD_POOL;
final AtomicReference<Throwable> learnThrowableRef = new AtomicReference<Throwable>();
final int procCount = 3 * Runtime.getRuntime().availableProcessors() / 2;
exec.setMessage("Transforming problem");
// transform the original k class classification problem into k regression problems
final TreeData[] actual = new TreeData[numClasses];
for (int i = 0; i < numClasses; i++) {
final double[] newTarget = calculateNewTarget(target, i);
actual[i] = createNumericDataFromArray(newTarget);
classLabels[i] = classNomVals[i].getNominalValue();
}
final RandomData rd = getConfig().createRandomData();
final double[][] previousFunctions = new double[numClasses][nrRows];
TreeNodeSignatureFactory signatureFactory = null;
final int maxLevels = getConfig().getMaxLevels();
if (maxLevels < TreeEnsembleLearnerConfiguration.MAX_LEVEL_INFINITE) {
int capacity = IntMath.pow(2, maxLevels - 1);
signatureFactory = new TreeNodeSignatureFactory(capacity);
} else {
signatureFactory = new TreeNodeSignatureFactory();
}
exec.setMessage("Learn trees");
for (int i = 0; i < nrModels; i++) {
final Semaphore semaphore = new Semaphore(procCount);
final ArrayList<Map<TreeNodeSignature, Double>> classCoefficientMaps = new ArrayList<Map<TreeNodeSignature, Double>>(numClasses);
// prepare calculation of pseudoResiduals
final double[][] probs = new double[numClasses][nrRows];
for (int r = 0; r < nrRows; r++) {
double sumExpF = 0;
for (int j = 0; j < numClasses; j++) {
sumExpF += Math.exp(previousFunctions[j][r]);
}
for (int j = 0; j < numClasses; j++) {
probs[j][r] = Math.exp(previousFunctions[j][r]) / sumExpF;
}
}
final Future<?>[] treeCoefficientMapPairs = new Future<?>[numClasses];
for (int j = 0; j < numClasses; j++) {
checkThrowable(learnThrowableRef);
final RandomData rdSingle = TreeEnsembleLearnerConfiguration.createRandomData(rd.nextLong(Long.MIN_VALUE, Long.MAX_VALUE));
final ExecutionMonitor subExec = exec.createSubProgress(0.0);
semaphore.acquire();
treeCoefficientMapPairs[j] = tp.enqueue(new TreeLearnerCallable(rdSingle, probs[j], actual[j], subExec, numClasses, previousFunctions[j], semaphore, learnThrowableRef, signatureFactory));
}
for (int j = 0; j < numClasses; j++) {
checkThrowable(learnThrowableRef);
semaphore.acquire();
final Pair<TreeModelRegression, Map<TreeNodeSignature, Double>> pair = (Pair<TreeModelRegression, Map<TreeNodeSignature, Double>>) treeCoefficientMapPairs[j].get();
models[i][j] = pair.getFirst();
classCoefficientMaps.add(pair.getSecond());
semaphore.release();
}
checkThrowable(learnThrowableRef);
coefficientMaps.add(classCoefficientMaps);
exec.setProgress((double) i / nrModels, "Finished level " + i + "/" + nrModels);
}
return MultiClassGradientBoostedTreesModel.createMultiClassGradientBoostedTreesModel(getConfig(), data.getMetaData(), models, data.getTreeType(), 0, numClasses, coefficientMaps, classLabels);
}
use of org.knime.base.node.mine.treeensemble2.model.TreeNodeSignature in project knime-core by knime.
the class TreeLearnerClassification method findBestSplitClassification.
private SplitCandidate findBestSplitClassification(final int currentDepth, final DataMemberships dataMemberships, final ColumnSample columnSample, final TreeNodeSignature treeNodeSignature, final ClassificationPriors targetPriors, final BitSet forbiddenColumnSet) {
final TreeData data = getData();
final RandomData rd = getRandomData();
// final ColumnSampleStrategy colSamplingStrategy = getColSamplingStrategy();
final TreeEnsembleLearnerConfiguration config = getConfig();
final int maxLevels = config.getMaxLevels();
if (maxLevels != TreeEnsembleLearnerConfiguration.MAX_LEVEL_INFINITE && currentDepth >= maxLevels) {
return null;
}
final int minNodeSize = config.getMinNodeSize();
if (minNodeSize != TreeEnsembleLearnerConfiguration.MIN_NODE_SIZE_UNDEFINED) {
if (targetPriors.getNrRecords() < minNodeSize) {
return null;
}
}
final double priorImpurity = targetPriors.getPriorImpurity();
if (priorImpurity < TreeColumnData.EPSILON) {
return null;
}
final TreeTargetNominalColumnData targetColumn = (TreeTargetNominalColumnData) data.getTargetColumn();
SplitCandidate splitCandidate = null;
if (currentDepth == 0 && config.getHardCodedRootColumn() != null) {
final TreeAttributeColumnData rootColumn = data.getColumn(config.getHardCodedRootColumn());
// TODO discuss whether this option makes sense with surrogates
return rootColumn.calcBestSplitClassification(dataMemberships, targetPriors, targetColumn, rd);
}
double bestGainValue = 0.0;
for (TreeAttributeColumnData col : columnSample) {
if (forbiddenColumnSet.get(col.getMetaData().getAttributeIndex())) {
continue;
}
final SplitCandidate currentColSplit = col.calcBestSplitClassification(dataMemberships, targetPriors, targetColumn, rd);
if (currentColSplit != null) {
final double currentGain = currentColSplit.getGainValue();
final boolean tiebreaker = currentGain == bestGainValue ? (rd.nextInt(0, 1) == 0) : false;
if (currentColSplit.getGainValue() > bestGainValue || tiebreaker) {
splitCandidate = currentColSplit;
bestGainValue = currentGain;
}
}
}
return splitCandidate;
}
use of org.knime.base.node.mine.treeensemble2.model.TreeNodeSignature in project knime-core by knime.
the class TreeLearnerClassification method findBestSplitsClassification.
/**
* Returns a list of SplitCandidates sorted (descending) by their gain
*
* @param currentDepth
* @param rowSampleWeights
* @param treeNodeSignature
* @param targetPriors
* @param forbiddenColumnSet
* @param membershipController
* @return
*/
private SplitCandidate[] findBestSplitsClassification(final int currentDepth, final DataMemberships dataMemberships, final ColumnSample columnSample, final TreeNodeSignature treeNodeSignature, final ClassificationPriors targetPriors, final BitSet forbiddenColumnSet) {
final TreeData data = getData();
final RandomData rd = getRandomData();
// final ColumnSampleStrategy colSamplingStrategy = getColSamplingStrategy();
final TreeEnsembleLearnerConfiguration config = getConfig();
final int maxLevels = config.getMaxLevels();
if (maxLevels != TreeEnsembleLearnerConfiguration.MAX_LEVEL_INFINITE && currentDepth >= maxLevels) {
return null;
}
final int minNodeSize = config.getMinNodeSize();
if (minNodeSize != TreeEnsembleLearnerConfiguration.MIN_NODE_SIZE_UNDEFINED) {
if (targetPriors.getNrRecords() < minNodeSize) {
return null;
}
}
final double priorImpurity = targetPriors.getPriorImpurity();
if (priorImpurity < TreeColumnData.EPSILON) {
return null;
}
final TreeTargetNominalColumnData targetColumn = (TreeTargetNominalColumnData) data.getTargetColumn();
SplitCandidate splitCandidate = null;
if (currentDepth == 0 && config.getHardCodedRootColumn() != null) {
final TreeAttributeColumnData rootColumn = data.getColumn(config.getHardCodedRootColumn());
// TODO discuss whether this option makes sense with surrogates
return new SplitCandidate[] { rootColumn.calcBestSplitClassification(dataMemberships, targetPriors, targetColumn, rd) };
}
double bestGainValue = 0.0;
final Comparator<SplitCandidate> comp = new Comparator<SplitCandidate>() {
@Override
public int compare(final SplitCandidate o1, final SplitCandidate o2) {
int compareDouble = -Double.compare(o1.getGainValue(), o2.getGainValue());
return compareDouble;
}
};
ArrayList<SplitCandidate> candidates = new ArrayList<SplitCandidate>(columnSample.getNumCols());
for (TreeAttributeColumnData col : columnSample) {
if (forbiddenColumnSet.get(col.getMetaData().getAttributeIndex())) {
continue;
}
SplitCandidate currentColSplit = col.calcBestSplitClassification(dataMemberships, targetPriors, targetColumn, rd);
if (currentColSplit != null) {
candidates.add(currentColSplit);
}
}
if (candidates.isEmpty()) {
return null;
}
candidates.sort(comp);
return candidates.toArray(new SplitCandidate[candidates.size()]);
}
use of org.knime.base.node.mine.treeensemble2.model.TreeNodeSignature in project knime-core by knime.
the class TreeLearnerClassification method learnSingleTreeRecursive.
private TreeModelClassification learnSingleTreeRecursive(final ExecutionMonitor exec, final RandomData rd) throws CanceledExecutionException {
final TreeData data = getData();
final RowSample rowSampling = getRowSampling();
final TreeEnsembleLearnerConfiguration config = getConfig();
final TreeTargetNominalColumnData targetColumn = (TreeTargetNominalColumnData) data.getTargetColumn();
final // new RootDataMem(rowSampling, getIndexManager());
DataMemberships rootDataMemberships = new RootDataMemberships(rowSampling, data, getIndexManager());
ClassificationPriors targetPriors = targetColumn.getDistribution(rootDataMemberships, config);
BitSet forbiddenColumnSet = new BitSet(data.getNrAttributes());
// final DataMemberships rootDataMemberships = new IntArrayDataMemberships(sampleWeights, data);
final TreeNodeSignature rootSignature = TreeNodeSignature.ROOT_SIGNATURE;
final ColumnSample rootColumnSample = getColSamplingStrategy().getColumnSampleForTreeNode(rootSignature);
TreeNodeClassification rootNode = null;
rootNode = buildTreeNode(exec, 0, rootDataMemberships, rootColumnSample, rootSignature, targetPriors, forbiddenColumnSet);
assert forbiddenColumnSet.cardinality() == 0;
rootNode.setTreeNodeCondition(TreeNodeTrueCondition.INSTANCE);
return new TreeModelClassification(rootNode);
}
Aggregations