Examples with FilterLearnColumnRearranger org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration.FilterLearnColumnRearranger used on opensource projects

Example 11 with FilterLearnColumnRearranger

use of org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration.FilterLearnColumnRearranger 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 = 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 12 with FilterLearnColumnRearranger

use of org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration.FilterLearnColumnRearranger 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");
    // Use xgboost missing value handling
    m_configuration.setMissingValueHandling(MissingValueHandling.XGBoost);
    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 13 with FilterLearnColumnRearranger

use of org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration.FilterLearnColumnRearranger in project knime-core by knime.

the class RandomForestRegressionLearnerNodeModel method configure.

/**
 * {@inheritDoc}
 */
@Override
protected PortObjectSpec[] configure(final PortObjectSpec[] inSpecs) throws InvalidSettingsException {
    // guaranteed to not be null (according to API)
    DataTableSpec inSpec = (DataTableSpec) inSpecs[0];
    if (m_configuration == null) {
        throw new InvalidSettingsException("No configuration available");
    }
    final FilterLearnColumnRearranger learnRearranger = m_configuration.filterLearnColumns(inSpec);
    final String warn = learnRearranger.getWarning();
    if (warn != null) {
        setWarningMessage(warn);
    }
    m_configuration.checkColumnSelection(inSpec);
    DataTableSpec learnSpec = learnRearranger.createSpec();
    TreeEnsembleModelPortObjectSpec ensembleSpec = m_configuration.createPortObjectSpec(learnSpec);
    final TreeEnsemblePredictor outOfBagPredictor = createOutOfBagPredictor(ensembleSpec, null, inSpec);
    ColumnRearranger outOfBagRearranger = outOfBagPredictor.getPredictionRearranger();
    DataTableSpec outOfBagSpec = outOfBagRearranger == null ? null : outOfBagRearranger.createSpec();
    DataTableSpec colStatsSpec = TreeEnsembleLearner.getColumnStatisticTableSpec();
    return new PortObjectSpec[] { outOfBagSpec, colStatsSpec, ensembleSpec };
}

Example 14 with FilterLearnColumnRearranger

use of org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration.FilterLearnColumnRearranger in project knime-core by knime.

the class RegressionTreeLearnerNodeModel 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();
    ExecutionMonitor readInExec = exec.createSubProgress(0.1);
    ExecutionMonitor learnExec = exec.createSubProgress(0.9);
    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 tree");
    RandomData rd = m_configuration.createRandomData();
    final IDataIndexManager indexManager;
    if (data.getTreeType() == TreeType.BitVector) {
        indexManager = new BitVectorDataIndexManager(data.getNrRows());
    } else {
        indexManager = new DefaultDataIndexManager(data);
    }
    TreeNodeSignatureFactory signatureFactory = null;
    int maxLevels = m_configuration.getMaxLevels();
    if (maxLevels < TreeEnsembleLearnerConfiguration.MAX_LEVEL_INFINITE) {
        int capacity = IntMath.pow(2, maxLevels - 1);
        signatureFactory = new TreeNodeSignatureFactory(capacity);
    } else {
        signatureFactory = new TreeNodeSignatureFactory();
    }
    final RowSample rowSample = m_configuration.createRowSampler(data).createRowSample(rd);
    TreeLearnerRegression treeLearner = new TreeLearnerRegression(m_configuration, data, indexManager, signatureFactory, rd, rowSample);
    TreeModelRegression regTree = treeLearner.learnSingleTree(learnExec, rd);
    RegressionTreeModel model = new RegressionTreeModel(m_configuration, data.getMetaData(), regTree, data.getTreeType());
    RegressionTreeModelPortObjectSpec treePortObjectSpec = new RegressionTreeModelPortObjectSpec(learnSpec);
    RegressionTreeModelPortObject treePortObject = new RegressionTreeModelPortObject(model, treePortObjectSpec);
    learnExec.setProgress(1.0);
    m_treeModelPortObject = treePortObject;
    if (warn != null) {
        setWarningMessage(warn);
    }
    return new PortObject[] { treePortObject };
}