Examples with DataCell org.knime.core.data.DataCell used on opensource projects

Example 81 with DataCell

use of org.knime.core.data.DataCell in project knime-core by knime.

the class ProximityMatrix method createTable.

public BufferedDataTable createTable(final ExecutionContext exec) throws CanceledExecutionException {
    int numCols = getNumCols();
    int numRows = getNumRows();
    DataColumnSpec[] colSpecs = new DataColumnSpec[numCols];
    for (int i = 0; i < colSpecs.length; i++) {
        colSpecs[i] = new DataColumnSpecCreator(getRowKeyForTable(1, i).getString(), DoubleCell.TYPE).createSpec();
    }
    DataTableSpec tableSpec = new DataTableSpec(colSpecs);
    BufferedDataContainer container = exec.createDataContainer(tableSpec);
    for (int i = 0; i < numRows; i++) {
        exec.checkCanceled();
        exec.setProgress(((double) i) / numRows, "Row " + i + "/" + numRows);
        DataCell[] cells = new DataCell[numCols];
        for (int j = 0; j < numCols; j++) {
            cells[j] = new DoubleCell(getEntryAt(i, j));
        }
        container.addRowToTable(new DefaultRow(getRowKeyForTable(0, i), cells));
    }
    container.close();
    return container.getTable();
}

Example 82 with DataCell

use of org.knime.core.data.DataCell in project knime-core by knime.

the class TreeEnsembleStatisticsNodeModel method execute.

@Override
protected PortObject[] execute(final PortObject[] inObjects, final ExecutionContext exec) throws Exception {
    TreeEnsembleModel treeEnsemble = ((TreeEnsembleModelPortObject) inObjects[0]).getEnsembleModel();
    EnsembleStatistic ensembleStats = new EnsembleStatistic(treeEnsemble);
    DataContainer containerEnsembleStats = exec.createDataContainer(createEnsembleStatsSpec());
    DataCell[] cells = new DataCell[7];
    cells[0] = new IntCell(treeEnsemble.getNrModels());
    cells[1] = new IntCell(ensembleStats.getMinLevel());
    cells[2] = new IntCell(ensembleStats.getMaxLevel());
    cells[3] = new DoubleCell(ensembleStats.getAvgLevel());
    cells[4] = new IntCell(ensembleStats.getMinNumNodes());
    cells[5] = new IntCell(ensembleStats.getMaxNumNodes());
    cells[6] = new DoubleCell(ensembleStats.getAvgNumNodes());
    containerEnsembleStats.addRowToTable(new DefaultRow(RowKey.createRowKey(0L), cells));
    containerEnsembleStats.close();
    DataContainer containerTreeStats = exec.createDataContainer(createTreeStatsSpec());
    for (int i = 0; i < treeEnsemble.getNrModels(); i++) {
        DataCell[] treeCells = new DataCell[2];
        TreeStatistic treeStat = ensembleStats.getTreeStatistic(i);
        treeCells[0] = new IntCell(treeStat.getNumLevels());
        treeCells[1] = new IntCell(treeStat.getNumNodes());
        containerTreeStats.addRowToTable(new DefaultRow(RowKey.createRowKey((long) i), treeCells));
    }
    containerTreeStats.close();
    return new PortObject[] { (PortObject) containerEnsembleStats.getTable(), (PortObject) containerTreeStats.getTable() };
}

Example 83 with DataCell

use of org.knime.core.data.DataCell 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 84 with DataCell

use of org.knime.core.data.DataCell in project knime-core by knime.

the class TreeEnsembleModelExtractorNodeModel method execute.

/**
 * {@inheritDoc}
 */
@Override
protected PortObject[] execute(final PortObject[] inObjects, final ExecutionContext exec) throws Exception {
    TreeEnsembleModelPortObject treeEnsembleModel = (TreeEnsembleModelPortObject) inObjects[0];
    DataTableSpec outSpec = createOutSpec();
    BufferedDataContainer container = exec.createDataContainer(outSpec, false, 0);
    int nrModels = treeEnsembleModel.getEnsembleModel().getNrModels();
    for (int i = 0; i < nrModels; i++) {
        PMMLPortObject pmmlObject = treeEnsembleModel.createDecisionTreePMMLPortObject(i);
        DataCell cell = PMMLCellFactory.create(pmmlObject.getPMMLValue().toString());
        RowKey key = RowKey.createRowKey(i);
        container.addRowToTable(new DefaultRow(key, cell));
        exec.checkCanceled();
        exec.setProgress(i / (double) nrModels, "Exported model " + (i + 1) + "/" + nrModels);
    }
    container.close();
    return new BufferedDataTable[] { container.getTable() };
}

Example 85 with DataCell

use of org.knime.core.data.DataCell in project knime-core by knime.

the class TreeEnsembleClassificationPredictorCellFactory2 method getCells.

/**
 * {@inheritDoc}
 */
@Override
public DataCell[] getCells(final DataRow row) {
    TreeEnsembleModelPortObject modelObject = m_predictor.getModelObject();
    TreeEnsemblePredictorConfiguration cfg = m_predictor.getConfiguration();
    final TreeEnsembleModel ensembleModel = modelObject.getEnsembleModel();
    int size = 1;
    final boolean appendConfidence = cfg.isAppendPredictionConfidence();
    if (appendConfidence) {
        size += 1;
    }
    final boolean appendClassConfidences = cfg.isAppendClassConfidences();
    if (appendClassConfidences) {
        size += m_targetValueMap.size();
    }
    final boolean appendModelCount = cfg.isAppendModelCount();
    if (appendModelCount) {
        size += 1;
    }
    final boolean hasOutOfBagFilter = m_predictor.hasOutOfBagFilter();
    DataCell[] result = new DataCell[size];
    DataRow filterRow = new FilterColumnRow(row, m_learnColumnInRealDataIndices);
    PredictorRecord record = ensembleModel.createPredictorRecord(filterRow, m_learnSpec);
    if (record == null) {
        // missing value
        Arrays.fill(result, DataType.getMissingCell());
        return result;
    }
    OccurrenceCounter<String> counter = new OccurrenceCounter<String>();
    final int nrModels = ensembleModel.getNrModels();
    TreeTargetNominalColumnMetaData targetMeta = (TreeTargetNominalColumnMetaData) ensembleModel.getMetaData().getTargetMetaData();
    final double[] classProbabilities = new double[targetMeta.getValues().length];
    int nrValidModels = 0;
    for (int i = 0; i < nrModels; i++) {
        if (hasOutOfBagFilter && m_predictor.isRowPartOfTrainingData(row.getKey(), i)) {
        // ignore, row was used to train the model
        } else {
            TreeModelClassification m = ensembleModel.getTreeModelClassification(i);
            TreeNodeClassification match = m.findMatchingNode(record);
            String majorityClassName = match.getMajorityClassName();
            final float[] nodeClassProbs = match.getTargetDistribution();
            double instancesInNode = 0;
            for (int c = 0; c < nodeClassProbs.length; c++) {
                instancesInNode += nodeClassProbs[c];
            }
            for (int c = 0; c < classProbabilities.length; c++) {
                classProbabilities[c] += nodeClassProbs[c] / instancesInNode;
            }
            counter.add(majorityClassName);
            nrValidModels += 1;
        }
    }
    String bestValue = counter.getMostFrequent();
    int index = 0;
    if (bestValue == null) {
        assert nrValidModels == 0;
        Arrays.fill(result, DataType.getMissingCell());
        index = size - 1;
    } else {
        // result[index++] = m_targetValueMap.get(bestValue);
        int indexBest = -1;
        double probBest = -1;
        for (int c = 0; c < classProbabilities.length; c++) {
            double prob = classProbabilities[c];
            if (prob > probBest) {
                probBest = prob;
                indexBest = c;
            }
        }
        result[index++] = new StringCell(targetMeta.getValues()[indexBest].getNominalValue());
        if (appendConfidence) {
            // final int freqValue = counter.getFrequency(bestValue);
            // result[index++] = new DoubleCell(freqValue / (double)nrValidModels);
            result[index++] = new DoubleCell(probBest);
        }
        if (appendClassConfidences) {
            for (NominalValueRepresentation nomVal : targetMeta.getValues()) {
                double prob = classProbabilities[nomVal.getAssignedInteger()] / nrValidModels;
                result[index++] = new DoubleCell(prob);
            }
        }
    }
    if (appendModelCount) {
        result[index++] = new IntCell(nrValidModels);
    }
    return result;
}