Examples with TreeData org.knime.base.node.mine.treeensemble2.data.TreeData used on opensource projects

Example 1 with TreeData

use of org.knime.base.node.mine.treeensemble2.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 = TreeEnsembleModelPortObject.createPortObject(ensembleSpec, model, exec.createFileStore("TreeEnsemble"));
    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.treeensemble2.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 = TreeEnsembleModelPortObject.createPortObject(ensembleSpec, model, exec.createFileStore(UUID.randomUUID().toString() + ""));
    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 3 with TreeData

use of org.knime.base.node.mine.treeensemble2.data.TreeData in project knime-core by knime.

the class AbstractColumnSampleTest method createTreeData.

/**
 * @return TreeData object for testing purposes
 */
protected static TreeData createTreeData() {
    final TestDataGenerator dataGen = new TestDataGenerator(new TreeEnsembleLearnerConfiguration(false));
    final TreeAttributeColumnData[] cols = new TreeAttributeColumnData[10];
    for (int i = 0; i < TREE_DATA_SIZE; i++) {
        if (i % 2 == 0) {
            cols[i] = dataGen.createNominalAttributeColumn("a, b", "nom" + i, i);
        } else {
            cols[i] = dataGen.createNumericAttributeColumn("1, 2", "num1", i);
        }
    }
    TreeTargetColumnData target = TestDataGenerator.createNominalTargetColumn("A, B");
    return dataGen.createTreeData(target, cols);
}

Example 4 with TreeData

use of org.knime.base.node.mine.treeensemble2.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();
    final IDataIndexManager indexManager = getIndexManager();
    DataMemberships rootDataMemberships = new RootDataMemberships(rowSampling, data, indexManager);
    RegressionPriors targetPriors = targetColumn.getPriors(rootDataMemberships, config);
    BitSet forbiddenColumnSet = new BitSet(data.getNrAttributes());
    boolean isGradientBoosting = config instanceof GradientBoostingLearnerConfiguration;
    if (isGradientBoosting) {
        m_leafs = new ArrayList<TreeNodeRegression>();
    }
    final TreeNodeSignature rootSignature = TreeNodeSignature.ROOT_SIGNATURE;
    final ColumnSample rootColumnSample = getColSamplingStrategy().getColumnSampleForTreeNode(rootSignature);
    TreeNodeRegression rootNode = buildTreeNode(exec, 0, rootDataMemberships, rootColumnSample, getSignatureFactory().getRootSignature(), targetPriors, forbiddenColumnSet);
    assert forbiddenColumnSet.cardinality() == 0;
    rootNode.setTreeNodeCondition(TreeNodeTrueCondition.INSTANCE);
    if (isGradientBoosting) {
        return new TreeModelRegression(rootNode, m_leafs);
    }
    return new TreeModelRegression(rootNode);
}

Example 5 with TreeData

use of org.knime.base.node.mine.treeensemble2.data.TreeData in project knime-core by knime.

the class TreeLearnerRegression method findBestSplitsRegression.

private SplitCandidate[] findBestSplitsRegression(final int currentDepth, final DataMemberships dataMemberships, final ColumnSample columnSample, final RegressionPriors targetPriors, final BitSet forbiddenColumnSet) {
    final TreeData data = getData();
    final RandomData rd = getRandomData();
    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();
    ArrayList<SplitCandidate> splitCandidates = null;
    if (currentDepth == 0 && config.getHardCodedRootColumn() != null) {
        final TreeAttributeColumnData rootColumn = data.getColumn(config.getHardCodedRootColumn());
        return new SplitCandidate[] { rootColumn.calcBestSplitRegression(dataMemberships, targetPriors, targetColumn, rd) };
    } else {
        splitCandidates = new ArrayList<SplitCandidate>(columnSample.getNumCols());
        for (TreeAttributeColumnData col : columnSample) {
            if (forbiddenColumnSet.get(col.getMetaData().getAttributeIndex())) {
                continue;
            }
            SplitCandidate currentColSplit = col.calcBestSplitRegression(dataMemberships, targetPriors, targetColumn, rd);
            if (currentColSplit != null) {
                splitCandidates.add(currentColSplit);
            }
        }
    }
    Comparator<SplitCandidate> comp = new Comparator<SplitCandidate>() {

        @Override
        public int compare(final SplitCandidate arg0, final SplitCandidate arg1) {
            int compareDouble = -Double.compare(arg0.getGainValue(), arg1.getGainValue());
            return compareDouble;
        }
    };
    if (splitCandidates.isEmpty()) {
        return null;
    }
    splitCandidates.sort(comp);
    return splitCandidates.toArray(new SplitCandidate[splitCandidates.size()]);
}