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

Example 1 with TreeData

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

the class RandomForestClassificationLearnerNodeModel 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);
    Map<String, DataCell> targetValueMap = ensembleSpec.getTargetColumnPossibleValueMap();
    if (targetValueMap == null) {
        throw new InvalidSettingsException("The target column does not " + "have possible values assigned. Most likely it " + "has too many different distinct values (learning an ID " + "column?) Fix it by preprocessing the table using " + "a \"Domain Calculator\".");
    }
    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 2 with TreeData

use of org.knime.base.node.mine.treeensemble.data.TreeData 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 3 with TreeData

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

the class TreeLearnerClassification method findBestSplitClassification.

private SplitCandidate findBestSplitClassification(final int currentDepth, final double[] rowSampleWeights, final TreeNodeSignature treeNodeSignature, final ClassificationPriors targetPriors, final BitSet forbiddenColumnSet, final TreeNodeMembershipController membershipController) {
    final TreeData data = getData();
    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());
        return rootColumn.calcBestSplitClassification(membershipController, rowSampleWeights, targetPriors, targetColumn);
    } else {
        double bestGainValue = 0.0;
        final ColumnSample columnSample = colSamplingStrategy.getColumnSampleForTreeNode(treeNodeSignature);
        for (TreeAttributeColumnData col : columnSample) {
            if (forbiddenColumnSet.get(col.getMetaData().getAttributeIndex())) {
                continue;
            }
            SplitCandidate currentColSplit = col.calcBestSplitClassification(membershipController, rowSampleWeights, targetPriors, targetColumn);
            if (currentColSplit != null) {
                double gainValue = currentColSplit.getGainValue();
                if (gainValue > bestGainValue) {
                    bestGainValue = gainValue;
                    splitCandidate = currentColSplit;
                }
            }
        }
    }
    return splitCandidate;
}

Example 4 with TreeData

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

the class TreeLearnerRegression method findBestSplitRegression.

private SplitCandidate findBestSplitRegression(final int currentDepth, final double[] rowSampleWeights, final TreeNodeSignature treeNodeSignature, final RegressionPriors targetPriors, final BitSet forbiddenColumnSet, final TreeNodeMembershipController membershipController) {
    final TreeData data = getData();
    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 priorSquaredDeviation = targetPriors.getSumSquaredDeviation();
    if (priorSquaredDeviation < TreeColumnData.EPSILON) {
        return null;
    }
    final TreeTargetNumericColumnData targetColumn = getTargetData();
    SplitCandidate splitCandidate = null;
    if (currentDepth == 0 && config.getHardCodedRootColumn() != null) {
        final TreeAttributeColumnData rootColumn = data.getColumn(config.getHardCodedRootColumn());
        return rootColumn.calcBestSplitRegression(membershipController, rowSampleWeights, targetPriors, targetColumn);
    } else {
        double bestGainValue = 0.0;
        final ColumnSample columnSample = colSamplingStrategy.getColumnSampleForTreeNode(treeNodeSignature);
        for (TreeAttributeColumnData col : columnSample) {
            if (forbiddenColumnSet.get(col.getMetaData().getAttributeIndex())) {
                continue;
            }
            SplitCandidate currentColSplit = col.calcBestSplitRegression(membershipController, rowSampleWeights, targetPriors, targetColumn);
            if (currentColSplit != null) {
                double gainValue = currentColSplit.getGainValue();
                if (gainValue > bestGainValue) {
                    bestGainValue = gainValue;
                    splitCandidate = currentColSplit;
                }
            }
        }
    }
    return splitCandidate;
}

Example 5 with TreeData

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

the class TreeEnsembleClassificationLearnerNodeModel 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);
    Map<String, DataCell> targetValueMap = ensembleSpec.getTargetColumnPossibleValueMap();
    if (targetValueMap == null) {
        throw new InvalidSettingsException("The target column does not " + "have possible values assigned. Most likely it " + "has too many different distinct values (learning an ID " + "column?) Fix it by preprocessing the table using " + "a \"Domain Calculator\".");
    }
    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 };
}