Examples with TreeData org.knime.base.node.mine.treeensemble.data.TreeData used on opensource projects

Example 6 with TreeData

use of org.knime.base.node.mine.treeensemble.data.TreeData in project knime-core by knime.

the class RandomForestRegressionLearnerNodeModel method execute.

/**
 * {@inheritDoc}
 */
@Override
protected PortObject[] execute(final PortObject[] inObjects, final ExecutionContext exec) throws Exception {
    BufferedDataTable t = (BufferedDataTable) inObjects[0];
    DataTableSpec spec = t.getDataTableSpec();
    final FilterLearnColumnRearranger learnRearranger = m_configuration.filterLearnColumns(spec);
    String warn = learnRearranger.getWarning();
    BufferedDataTable learnTable = exec.createColumnRearrangeTable(t, learnRearranger, exec.createSubProgress(0.0));
    DataTableSpec learnSpec = learnTable.getDataTableSpec();
    TreeEnsembleModelPortObjectSpec ensembleSpec = m_configuration.createPortObjectSpec(learnSpec);
    ExecutionMonitor readInExec = exec.createSubProgress(0.1);
    ExecutionMonitor learnExec = exec.createSubProgress(0.8);
    ExecutionMonitor outOfBagExec = exec.createSubProgress(0.1);
    TreeDataCreator dataCreator = new TreeDataCreator(m_configuration, learnSpec, learnTable.getRowCount());
    exec.setProgress("Reading data into memory");
    TreeData data = dataCreator.readData(learnTable, m_configuration, readInExec);
    m_hiliteRowSample = dataCreator.getDataRowsForHilite();
    m_viewMessage = dataCreator.getViewMessage();
    String dataCreationWarning = dataCreator.getAndClearWarningMessage();
    if (dataCreationWarning != null) {
        if (warn == null) {
            warn = dataCreationWarning;
        } else {
            warn = warn + "\n" + dataCreationWarning;
        }
    }
    readInExec.setProgress(1.0);
    exec.setMessage("Learning trees");
    TreeEnsembleLearner learner = new TreeEnsembleLearner(m_configuration, data);
    TreeEnsembleModel model;
    try {
        model = learner.learnEnsemble(learnExec);
    } catch (ExecutionException e) {
        Throwable cause = e.getCause();
        if (cause instanceof Exception) {
            throw (Exception) cause;
        }
        throw e;
    }
    TreeEnsembleModelPortObject modelPortObject = new TreeEnsembleModelPortObject(ensembleSpec, model);
    learnExec.setProgress(1.0);
    exec.setMessage("Out of bag prediction");
    TreeEnsemblePredictor outOfBagPredictor = createOutOfBagPredictor(ensembleSpec, modelPortObject, spec);
    outOfBagPredictor.setOutofBagFilter(learner.getRowSamples(), data.getTargetColumn());
    ColumnRearranger outOfBagRearranger = outOfBagPredictor.getPredictionRearranger();
    BufferedDataTable outOfBagTable = exec.createColumnRearrangeTable(t, outOfBagRearranger, outOfBagExec);
    BufferedDataTable colStatsTable = learner.createColumnStatisticTable(exec.createSubExecutionContext(0.0));
    m_ensembleModelPortObject = modelPortObject;
    if (warn != null) {
        setWarningMessage(warn);
    }
    return new PortObject[] { outOfBagTable, colStatsTable, modelPortObject };
}

Example 7 with TreeData

use of org.knime.base.node.mine.treeensemble.data.TreeData 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());
}

Example 8 with TreeData

use of org.knime.base.node.mine.treeensemble.data.TreeData in project knime-core by knime.

the class TreeLearnerRegression method learnSingleTree.

/**
 * {@inheritDoc}
 */
@Override
public TreeModelRegression learnSingleTree(final ExecutionMonitor exec, final RandomData rd) throws CanceledExecutionException {
    final TreeTargetNumericColumnData targetColumn = getTargetData();
    final TreeData data = getData();
    final RowSample rowSampling = getRowSampling();
    final TreeEnsembleLearnerConfiguration config = getConfig();
    double[] dataMemberships = new double[data.getNrRows()];
    for (int i = 0; i < dataMemberships.length; i++) {
        dataMemberships[i] = rowSampling.getCountFor(i);
    }
    RegressionPriors targetPriors = targetColumn.getPriors(dataMemberships, config);
    BitSet forbiddenColumnSet = new BitSet(data.getNrAttributes());
    // TreeNodeMembershipController rootMembershipController = new TreeNodeMembershipController(data, dataMemberships);
    TreeNodeMembershipController rootMembershipController = null;
    TreeNodeRegression rootNode = buildTreeNode(exec, 0, dataMemberships, TreeNodeSignature.ROOT_SIGNATURE, targetPriors, forbiddenColumnSet, rootMembershipController);
    assert forbiddenColumnSet.cardinality() == 0;
    rootNode.setTreeNodeCondition(TreeNodeTrueCondition.INSTANCE);
    return new TreeModelRegression(rootNode);
}

Example 9 with TreeData

use of org.knime.base.node.mine.treeensemble.data.TreeData in project knime-core by knime.

the class TreeLearnerRegression method buildTreeNode.

private TreeNodeRegression buildTreeNode(final ExecutionMonitor exec, final int currentDepth, final double[] rowSampleWeights, final TreeNodeSignature treeNodeSignature, final RegressionPriors targetPriors, final BitSet forbiddenColumnSet, final TreeNodeMembershipController membershipController) throws CanceledExecutionException {
    final TreeData data = getData();
    final TreeEnsembleLearnerConfiguration config = getConfig();
    exec.checkCanceled();
    SplitCandidate bestSplit = findBestSplitRegression(currentDepth, rowSampleWeights, treeNodeSignature, targetPriors, forbiddenColumnSet, membershipController);
    if (bestSplit == null) {
        return new TreeNodeRegression(treeNodeSignature, targetPriors);
    }
    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);
    }
    TreeNodeRegression[] childNodes = new TreeNodeRegression[childConditions.length];
    final double[] dataMemberships = rowSampleWeights;
    final double[] childMemberships = new double[dataMemberships.length];
    final TreeTargetNumericColumnData targetColumn = (TreeTargetNumericColumnData) 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);
        RegressionPriors childTargetPriors = targetColumn.getPriors(childMemberships, config);
        TreeNodeSignature childSignature = treeNodeSignature.createChildSignature((short) i);
        TreeNodeMembershipController childMembershipController = splitColumn.getChildNodeMembershipController(cond, membershipController);
        childNodes[i] = buildTreeNode(exec, currentDepth + 1, childMemberships, childSignature, childTargetPriors, forbiddenColumnSet, childMembershipController);
        childNodes[i].setTreeNodeCondition(cond);
    }
    if (markAttributeAsForbidden) {
        forbiddenColumnSet.set(attributeIndex, false);
    }
    return new TreeNodeRegression(treeNodeSignature, targetPriors, childNodes);
}

Example 10 with TreeData

use of org.knime.base.node.mine.treeensemble.data.TreeData in project knime-core by knime.

the class TreeEnsembleRegressionLearnerNodeModel method execute.

/**
 * {@inheritDoc}
 */
@Override
protected PortObject[] execute(final PortObject[] inObjects, final ExecutionContext exec) throws Exception {
    BufferedDataTable t = (BufferedDataTable) inObjects[0];
    DataTableSpec spec = t.getDataTableSpec();
    final FilterLearnColumnRearranger learnRearranger = m_configuration.filterLearnColumns(spec);
    String warn = learnRearranger.getWarning();
    BufferedDataTable learnTable = exec.createColumnRearrangeTable(t, learnRearranger, exec.createSubProgress(0.0));
    DataTableSpec learnSpec = learnTable.getDataTableSpec();
    TreeEnsembleModelPortObjectSpec ensembleSpec = m_configuration.createPortObjectSpec(learnSpec);
    ExecutionMonitor readInExec = exec.createSubProgress(0.1);
    ExecutionMonitor learnExec = exec.createSubProgress(0.8);
    ExecutionMonitor outOfBagExec = exec.createSubProgress(0.1);
    TreeDataCreator dataCreator = new TreeDataCreator(m_configuration, learnSpec, learnTable.getRowCount());
    exec.setProgress("Reading data into memory");
    TreeData data = dataCreator.readData(learnTable, m_configuration, readInExec);
    m_hiliteRowSample = dataCreator.getDataRowsForHilite();
    m_viewMessage = dataCreator.getViewMessage();
    String dataCreationWarning = dataCreator.getAndClearWarningMessage();
    if (dataCreationWarning != null) {
        if (warn == null) {
            warn = dataCreationWarning;
        } else {
            warn = warn + "\n" + dataCreationWarning;
        }
    }
    readInExec.setProgress(1.0);
    exec.setMessage("Learning trees");
    TreeEnsembleLearner learner = new TreeEnsembleLearner(m_configuration, data);
    TreeEnsembleModel model;
    try {
        model = learner.learnEnsemble(learnExec);
    } catch (ExecutionException e) {
        Throwable cause = e.getCause();
        if (cause instanceof Exception) {
            throw (Exception) cause;
        }
        throw e;
    }
    TreeEnsembleModelPortObject modelPortObject = new TreeEnsembleModelPortObject(ensembleSpec, model);
    learnExec.setProgress(1.0);
    exec.setMessage("Out of bag prediction");
    TreeEnsemblePredictor outOfBagPredictor = createOutOfBagPredictor(ensembleSpec, modelPortObject, spec);
    outOfBagPredictor.setOutofBagFilter(learner.getRowSamples(), data.getTargetColumn());
    ColumnRearranger outOfBagRearranger = outOfBagPredictor.getPredictionRearranger();
    BufferedDataTable outOfBagTable = exec.createColumnRearrangeTable(t, outOfBagRearranger, outOfBagExec);
    BufferedDataTable colStatsTable = learner.createColumnStatisticTable(exec.createSubExecutionContext(0.0));
    m_ensembleModelPortObject = modelPortObject;
    if (warn != null) {
        setWarningMessage(warn);
    }
    return new PortObject[] { outOfBagTable, colStatsTable, modelPortObject };
}