Examples with TreeNodeClassification org.knime.base.node.mine.treeensemble.model.TreeNodeClassification used on opensource projects

Example 1 with TreeNodeClassification

use of org.knime.base.node.mine.treeensemble.model.TreeNodeClassification in project knime-core by knime.

the class TreeLearnerClassification method learnSingleTree.

/**
 * {@inheritDoc}
 */
@Override
public TreeModelClassification learnSingleTree(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();
    double[] dataMemberships = new double[data.getNrRows()];
    for (int i = 0; i < dataMemberships.length; i++) {
        // dataMemberships[i] = m_rowSampling.getCountFor(i) > 0 ? 1.0 : 0.0;
        dataMemberships[i] = rowSampling.getCountFor(i);
    }
    ClassificationPriors targetPriors = targetColumn.getDistribution(dataMemberships, config);
    BitSet forbiddenColumnSet = new BitSet(data.getNrAttributes());
    // TreeNodeMembershipController rootMembershipController = new TreeNodeMembershipController(data, dataMemberships);
    TreeNodeMembershipController rootMembershipController = null;
    TreeNodeClassification rootNode = buildTreeNode(exec, 0, dataMemberships, TreeNodeSignature.ROOT_SIGNATURE, targetPriors, forbiddenColumnSet, rootMembershipController);
    assert forbiddenColumnSet.cardinality() == 0;
    rootNode.setTreeNodeCondition(TreeNodeTrueCondition.INSTANCE);
    return new TreeModelClassification(rootNode);
}

Example 2 with TreeNodeClassification

use of org.knime.base.node.mine.treeensemble.model.TreeNodeClassification in project knime-core by knime.

the class TreeEnsembleClassificationPredictorCellFactory method getCells.

/**
 * {@inheritDoc}
 */
@Override
public DataCell[] getCells(final DataRow row) {
    TreeEnsembleModelPortObject modelObject = m_predictor.getModelObject();
    TreeEnsemblePredictorConfiguration cfg = m_predictor.getConfiguration();
    final TreeEnsembleModel ensembleModel = modelObject.getEnsembleModel();
    int size = 1;
    final boolean appendConfidence = cfg.isAppendPredictionConfidence();
    if (appendConfidence) {
        size += 1;
    }
    final boolean appendClassConfidences = cfg.isAppendClassConfidences();
    if (appendClassConfidences) {
        size += m_targetValueMap.size();
    }
    final boolean appendModelCount = cfg.isAppendModelCount();
    if (appendModelCount) {
        size += 1;
    }
    final boolean hasOutOfBagFilter = m_predictor.hasOutOfBagFilter();
    DataCell[] result = new DataCell[size];
    DataRow filterRow = new FilterColumnRow(row, m_learnColumnInRealDataIndices);
    PredictorRecord record = ensembleModel.createPredictorRecord(filterRow, m_learnSpec);
    if (record == null) {
        // missing value
        Arrays.fill(result, DataType.getMissingCell());
        return result;
    }
    OccurrenceCounter<String> counter = new OccurrenceCounter<String>();
    final int nrModels = ensembleModel.getNrModels();
    int nrValidModels = 0;
    for (int i = 0; i < nrModels; i++) {
        if (hasOutOfBagFilter && m_predictor.isRowPartOfTrainingData(row.getKey(), i)) {
        // ignore, row was used to train the model
        } else {
            TreeModelClassification m = ensembleModel.getTreeModelClassification(i);
            TreeNodeClassification match = m.findMatchingNode(record);
            String majorityClassName = match.getMajorityClassName();
            counter.add(majorityClassName);
            nrValidModels += 1;
        }
    }
    String bestValue = counter.getMostFrequent();
    int index = 0;
    if (bestValue == null) {
        assert nrValidModels == 0;
        Arrays.fill(result, DataType.getMissingCell());
        index = size - 1;
    } else {
        result[index++] = m_targetValueMap.get(bestValue);
        if (appendConfidence) {
            final int freqValue = counter.getFrequency(bestValue);
            result[index++] = new DoubleCell(freqValue / (double) nrValidModels);
        }
        if (appendClassConfidences) {
            for (String key : m_targetValueMap.keySet()) {
                int frequency = counter.getFrequency(key);
                double ratio = frequency / (double) nrValidModels;
                result[index++] = new DoubleCell(ratio);
            }
        }
    }
    if (appendModelCount) {
        result[index++] = new IntCell(nrValidModels);
    }
    return result;
}

Example 3 with TreeNodeClassification

use of org.knime.base.node.mine.treeensemble.model.TreeNodeClassification in project knime-core by knime.

the class TreeLearnerClassification method buildTreeNode.

private TreeNodeClassification buildTreeNode(final ExecutionMonitor exec, final int currentDepth, final double[] rowSampleWeights, final TreeNodeSignature treeNodeSignature, final ClassificationPriors targetPriors, final BitSet forbiddenColumnSet, final TreeNodeMembershipController membershipController) throws CanceledExecutionException {
    final TreeData data = getData();
    final TreeEnsembleLearnerConfiguration config = getConfig();
    exec.checkCanceled();
    SplitCandidate bestSplit = findBestSplitClassification(currentDepth, rowSampleWeights, treeNodeSignature, targetPriors, forbiddenColumnSet, membershipController);
    if (bestSplit == null) {
        return new TreeNodeClassification(treeNodeSignature, targetPriors, getConfig());
    }
    TreeAttributeColumnData splitColumn = bestSplit.getColumnData();
    final int attributeIndex = splitColumn.getMetaData().getAttributeIndex();
    boolean markAttributeAsForbidden = !bestSplit.canColumnBeSplitFurther();
    forbiddenColumnSet.set(attributeIndex, markAttributeAsForbidden);
    TreeNodeCondition[] childConditions = bestSplit.getChildConditions();
    if (childConditions.length > Short.MAX_VALUE) {
        throw new RuntimeException("Too many children when splitting " + "attribute " + bestSplit.getColumnData() + " (maximum supported: " + Short.MAX_VALUE + "): " + childConditions.length);
    }
    TreeNodeClassification[] childNodes = new TreeNodeClassification[childConditions.length];
    final double[] dataMemberships = rowSampleWeights;
    // final double[] dataMemberships = rowSampleWeights.getMemberships();
    final double[] childMemberships = new double[dataMemberships.length];
    final TreeTargetNominalColumnData targetColumn = (TreeTargetNominalColumnData) data.getTargetColumn();
    for (int i = 0; i < childConditions.length; i++) {
        System.arraycopy(dataMemberships, 0, childMemberships, 0, dataMemberships.length);
        TreeNodeCondition cond = childConditions[i];
        splitColumn.updateChildMemberships(cond, dataMemberships, childMemberships);
        // TreeNodeMembershipController childMembershipController = membershipController.createChildTreeNodeMembershipController(childMemberships);
        TreeNodeMembershipController childMembershipController = null;
        ClassificationPriors childTargetPriors = targetColumn.getDistribution(childMemberships, config);
        TreeNodeSignature childSignature = treeNodeSignature.createChildSignature((short) i);
        childNodes[i] = buildTreeNode(exec, currentDepth + 1, childMemberships, childSignature, childTargetPriors, forbiddenColumnSet, childMembershipController);
        childNodes[i].setTreeNodeCondition(cond);
    }
    if (markAttributeAsForbidden) {
        forbiddenColumnSet.set(attributeIndex, false);
    }
    return new TreeNodeClassification(treeNodeSignature, targetPriors, childNodes, getConfig());
}