Search in sources :

Example 76 with BufferedDataTable

use of org.knime.core.node.BufferedDataTable 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 };
}
Also used : DataTableSpec(org.knime.core.data.DataTableSpec) TreeEnsembleModel(org.knime.base.node.mine.treeensemble.model.TreeEnsembleModel) TreeEnsembleModelPortObjectSpec(org.knime.base.node.mine.treeensemble.model.TreeEnsembleModelPortObjectSpec) TreeEnsembleLearner(org.knime.base.node.mine.treeensemble.learner.TreeEnsembleLearner) InvalidSettingsException(org.knime.core.node.InvalidSettingsException) CanceledExecutionException(org.knime.core.node.CanceledExecutionException) IOException(java.io.IOException) ExecutionException(java.util.concurrent.ExecutionException) TreeEnsembleModelPortObject(org.knime.base.node.mine.treeensemble.model.TreeEnsembleModelPortObject) FilterLearnColumnRearranger(org.knime.base.node.mine.treeensemble.node.learner.TreeEnsembleLearnerConfiguration.FilterLearnColumnRearranger) ColumnRearranger(org.knime.core.data.container.ColumnRearranger) InvalidSettingsException(org.knime.core.node.InvalidSettingsException) BufferedDataTable(org.knime.core.node.BufferedDataTable) FilterLearnColumnRearranger(org.knime.base.node.mine.treeensemble.node.learner.TreeEnsembleLearnerConfiguration.FilterLearnColumnRearranger) DataCell(org.knime.core.data.DataCell) TreeData(org.knime.base.node.mine.treeensemble.data.TreeData) ExecutionMonitor(org.knime.core.node.ExecutionMonitor) CanceledExecutionException(org.knime.core.node.CanceledExecutionException) ExecutionException(java.util.concurrent.ExecutionException) TreeEnsemblePredictor(org.knime.base.node.mine.treeensemble.node.predictor.TreeEnsemblePredictor) TreeDataCreator(org.knime.base.node.mine.treeensemble.data.TreeDataCreator) TreeEnsembleModelPortObject(org.knime.base.node.mine.treeensemble.model.TreeEnsembleModelPortObject) PortObject(org.knime.core.node.port.PortObject)

Example 77 with BufferedDataTable

use of org.knime.core.node.BufferedDataTable in project knime-core by knime.

the class RandomForestClassificationPredictorNodeModel method execute.

/**
 * {@inheritDoc}
 */
@Override
protected PortObject[] execute(final PortObject[] inObjects, final ExecutionContext exec) throws Exception {
    TreeEnsembleModelPortObject model = (TreeEnsembleModelPortObject) inObjects[0];
    TreeEnsembleModelPortObjectSpec modelSpec = model.getSpec();
    BufferedDataTable data = (BufferedDataTable) inObjects[1];
    DataTableSpec dataSpec = data.getDataTableSpec();
    final TreeEnsemblePredictor pred = new TreeEnsemblePredictor(modelSpec, model, dataSpec, m_configuration);
    ColumnRearranger rearranger = pred.getPredictionRearranger();
    BufferedDataTable outTable = exec.createColumnRearrangeTable(data, rearranger, exec);
    return new BufferedDataTable[] { outTable };
}
Also used : TreeEnsembleModelPortObject(org.knime.base.node.mine.treeensemble.model.TreeEnsembleModelPortObject) DataTableSpec(org.knime.core.data.DataTableSpec) ColumnRearranger(org.knime.core.data.container.ColumnRearranger) TreeEnsembleModelPortObjectSpec(org.knime.base.node.mine.treeensemble.model.TreeEnsembleModelPortObjectSpec) BufferedDataTable(org.knime.core.node.BufferedDataTable) TreeEnsemblePredictor(org.knime.base.node.mine.treeensemble.node.predictor.TreeEnsemblePredictor)

Example 78 with BufferedDataTable

use of org.knime.core.node.BufferedDataTable in project knime-core by knime.

the class JoinerTest method testSkipPartitionsFullOuterJoin.

@Test
public final void testSkipPartitionsFullOuterJoin() throws Exception {
    Joiner2Settings settingsRef = createReferenceSettings("Data");
    settingsRef.setJoinMode(JoinMode.FullOuterJoin);
    Joiner2Settings settingsTest = createReferenceSettings("Data");
    settingsTest.setJoinMode(JoinMode.FullOuterJoin);
    BufferedDataTable leftTable = m_exec.createBufferedDataTable(new TestData(100, 1), m_exec);
    BufferedDataTable rightTable = m_exec.createBufferedDataTable(new TestData(200, 1), m_exec);
    // run joiner with reference settings
    Joiner joinerRef = new Joiner(leftTable.getDataTableSpec(), rightTable.getDataTableSpec(), settingsRef);
    BufferedDataTable reference = joinerRef.computeJoinTable(leftTable, rightTable, m_exec);
    // run joiner with test settings
    Joiner joinerTest = new Joiner(leftTable.getDataTableSpec(), rightTable.getDataTableSpec(), settingsTest);
    joinerTest.setRowsAddedBeforeOOM(10);
    joinerTest.setNumBitsInitial(8);
    BufferedDataTable test = joinerTest.computeJoinTable(leftTable, rightTable, m_exec);
    compareTables(reference, test);
}
Also used : BufferedDataTable(org.knime.core.node.BufferedDataTable) Test(org.junit.Test)

Example 79 with BufferedDataTable

use of org.knime.core.node.BufferedDataTable in project knime-core by knime.

the class JoinerTest method testSortPartitionsLeftOuterJoin.

@Test
public void testSortPartitionsLeftOuterJoin() throws Exception {
    Joiner2Settings settingsRef = createReferenceSettings(Joiner2Settings.ROW_KEY_IDENTIFIER);
    settingsRef.setJoinMode(JoinMode.LeftOuterJoin);
    Joiner2Settings settingsTest = createReferenceSettings(Joiner2Settings.ROW_KEY_IDENTIFIER);
    settingsTest.setJoinMode(JoinMode.LeftOuterJoin);
    settingsTest.setMaxOpenFiles(3);
    BufferedDataTable leftTable = m_exec.createBufferedDataTable(new TestData(200, 1), m_exec);
    BufferedDataTable rightTable = m_exec.createBufferedDataTable(new TestData(100, 1), m_exec);
    // run joiner with reference settings
    Joiner joinerRef = new Joiner(leftTable.getDataTableSpec(), rightTable.getDataTableSpec(), settingsRef);
    BufferedDataTable reference = joinerRef.computeJoinTable(leftTable, rightTable, m_exec);
    // run joiner with test settings
    Joiner joinerTest = new Joiner(leftTable.getDataTableSpec(), rightTable.getDataTableSpec(), settingsTest);
    joinerTest.setRowsAddedBeforeOOM(10);
    joinerTest.setNumBitsInitial(0);
    joinerTest.setNumBitsMaximal(6);
    BufferedDataTable test = joinerTest.computeJoinTable(leftTable, rightTable, m_exec);
    compareTables(reference, test);
}
Also used : BufferedDataTable(org.knime.core.node.BufferedDataTable) Test(org.junit.Test)

Example 80 with BufferedDataTable

use of org.knime.core.node.BufferedDataTable 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 };
}
Also used : DataTableSpec(org.knime.core.data.DataTableSpec) TreeEnsembleModel(org.knime.base.node.mine.treeensemble.model.TreeEnsembleModel) TreeEnsembleModelPortObjectSpec(org.knime.base.node.mine.treeensemble.model.TreeEnsembleModelPortObjectSpec) TreeEnsembleLearner(org.knime.base.node.mine.treeensemble.learner.TreeEnsembleLearner) InvalidSettingsException(org.knime.core.node.InvalidSettingsException) CanceledExecutionException(org.knime.core.node.CanceledExecutionException) IOException(java.io.IOException) ExecutionException(java.util.concurrent.ExecutionException) TreeEnsembleModelPortObject(org.knime.base.node.mine.treeensemble.model.TreeEnsembleModelPortObject) FilterLearnColumnRearranger(org.knime.base.node.mine.treeensemble.node.learner.TreeEnsembleLearnerConfiguration.FilterLearnColumnRearranger) ColumnRearranger(org.knime.core.data.container.ColumnRearranger) InvalidSettingsException(org.knime.core.node.InvalidSettingsException) BufferedDataTable(org.knime.core.node.BufferedDataTable) FilterLearnColumnRearranger(org.knime.base.node.mine.treeensemble.node.learner.TreeEnsembleLearnerConfiguration.FilterLearnColumnRearranger) DataCell(org.knime.core.data.DataCell) TreeData(org.knime.base.node.mine.treeensemble.data.TreeData) ExecutionMonitor(org.knime.core.node.ExecutionMonitor) CanceledExecutionException(org.knime.core.node.CanceledExecutionException) ExecutionException(java.util.concurrent.ExecutionException) TreeEnsemblePredictor(org.knime.base.node.mine.treeensemble.node.predictor.TreeEnsemblePredictor) TreeDataCreator(org.knime.base.node.mine.treeensemble.data.TreeDataCreator) TreeEnsembleModelPortObject(org.knime.base.node.mine.treeensemble.model.TreeEnsembleModelPortObject) PortObject(org.knime.core.node.port.PortObject)

Aggregations

BufferedDataTable (org.knime.core.node.BufferedDataTable)425 DataTableSpec (org.knime.core.data.DataTableSpec)213 ColumnRearranger (org.knime.core.data.container.ColumnRearranger)148 DataRow (org.knime.core.data.DataRow)118 BufferedDataContainer (org.knime.core.node.BufferedDataContainer)97 PortObject (org.knime.core.node.port.PortObject)96 DataCell (org.knime.core.data.DataCell)85 DataColumnSpec (org.knime.core.data.DataColumnSpec)61 InvalidSettingsException (org.knime.core.node.InvalidSettingsException)60 DefaultRow (org.knime.core.data.def.DefaultRow)56 PMMLPortObject (org.knime.core.node.port.pmml.PMMLPortObject)54 RowKey (org.knime.core.data.RowKey)52 ExecutionMonitor (org.knime.core.node.ExecutionMonitor)50 CanceledExecutionException (org.knime.core.node.CanceledExecutionException)47 SettingsModelString (org.knime.core.node.defaultnodesettings.SettingsModelString)43 IOException (java.io.IOException)41 ExecutionContext (org.knime.core.node.ExecutionContext)40 ArrayList (java.util.ArrayList)33 LinkedHashMap (java.util.LinkedHashMap)31 DoubleValue (org.knime.core.data.DoubleValue)29