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

Example 21 with DataColumnDomainCreator

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

the class RegressionPredictorCellFactory method createColumnSpec.

/**
 * Creates the spec of the output if possible.
 *
 * @param portSpec the spec of the pmml input port
 * @param tableSpec the spec of the data input port
 * @param settings settings for the predictor node
 * @return The spec of the output or null
 * @throws InvalidSettingsException when tableSpec and portSpec do not match
 */
public static DataColumnSpec[] createColumnSpec(final PMMLPortObjectSpec portSpec, final DataTableSpec tableSpec, final RegressionPredictorSettings settings) throws InvalidSettingsException {
    // Assertions
    if (portSpec.getTargetCols().isEmpty()) {
        throw new InvalidSettingsException("The general regression model" + " does not specify a target column.");
    }
    for (DataColumnSpec learningColSpec : portSpec.getLearningCols()) {
        String learningCol = learningColSpec.getName();
        if (tableSpec.containsName(learningCol)) {
            DataColumnSpec colSpec = tableSpec.getColumnSpec(learningCol);
            if (learningColSpec.getType().isCompatible(NominalValue.class)) {
                if (!colSpec.getType().isCompatible(BitVectorValue.class) && !colSpec.getType().isCompatible(ByteVectorValue.class) && !colSpec.getType().isCompatible(NominalValue.class)) {
                    throw new InvalidSettingsException("The column \"" + learningCol + "\" in the table of prediction " + "is expected to be  compatible with " + "\"NominalValue\".");
                }
            } else if (learningColSpec.getType().isCompatible(DoubleValue.class) && !colSpec.getType().isCompatible(DoubleValue.class)) {
                throw new InvalidSettingsException("The column \"" + learningCol + "\" in the table of prediction " + "is expected to be numeric.");
            }
        } else {
            throw new InvalidSettingsException("The table for prediction " + "does not contain the column \"" + learningCol + "\".");
        }
    }
    // The list of added columns
    List<DataColumnSpec> newColsSpec = new ArrayList<DataColumnSpec>();
    String targetCol = portSpec.getTargetFields().get(0);
    DataColumnSpec targetColSpec = portSpec.getDataTableSpec().getColumnSpec(targetCol);
    if (settings.getIncludeProbabilities() && targetColSpec.getType().isCompatible(NominalValue.class)) {
        if (!targetColSpec.getDomain().hasValues()) {
            return null;
        }
        List<DataCell> targetCategories = new ArrayList<DataCell>();
        targetCategories.addAll(targetColSpec.getDomain().getValues());
        for (DataCell value : targetCategories) {
            String name = "P (" + targetCol + "=" + value.toString() + ")" + settings.getPropColumnSuffix();
            String newColName = DataTableSpec.getUniqueColumnName(tableSpec, name);
            DataColumnSpecCreator colSpecCreator = new DataColumnSpecCreator(newColName, DoubleCell.TYPE);
            DataColumnDomainCreator domainCreator = new DataColumnDomainCreator(new DoubleCell(0.0), new DoubleCell(1.0));
            colSpecCreator.setDomain(domainCreator.createDomain());
            newColsSpec.add(colSpecCreator.createSpec());
        }
    }
    String targetColName = settings.getHasCustomPredictionName() ? settings.getCustomPredictionName() : "Prediction (" + targetCol + ")";
    String uniqueTargetColName = DataTableSpec.getUniqueColumnName(tableSpec, targetColName);
    DataType targetType = targetColSpec.getType().isCompatible(NominalValue.class) ? targetColSpec.getType() : DoubleCell.TYPE;
    DataColumnSpecCreator targetColSpecCreator = new DataColumnSpecCreator(uniqueTargetColName, targetType);
    if (targetColSpec.getType().isCompatible(NominalValue.class)) {
        DataColumnDomainCreator targetDomainCreator = new DataColumnDomainCreator(targetColSpec.getDomain());
        targetColSpecCreator.setDomain(targetDomainCreator.createDomain());
    }
    newColsSpec.add(targetColSpecCreator.createSpec());
    return newColsSpec.toArray(new DataColumnSpec[0]);
}

Example 22 with DataColumnDomainCreator

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

the class ClusterNodeModel method createAppendedSpec.

private DataTableSpec createAppendedSpec(final DataTableSpec originalSpec) {
    // determine the possible values of the appended column
    DataCell[] possibleValues = new DataCell[m_nrOfClusters.getIntValue()];
    for (int i = 0; i < m_nrOfClusters.getIntValue(); i++) {
        DataCell key = new StringCell(CLUSTER + i);
        possibleValues[i] = key;
    }
    // create the domain
    // 1) guess an unused name for the new column (fixes bug #1022)
    String colNameGuess = "Cluster";
    int uniqueNr = 0;
    while (originalSpec.getColumnSpec(colNameGuess) != null) {
        uniqueNr++;
        colNameGuess = "Cluster_" + uniqueNr;
    }
    // 2) create spec
    DataColumnDomainCreator domainCreator = new DataColumnDomainCreator(possibleValues);
    DataColumnSpecCreator creator = new DataColumnSpecCreator(colNameGuess, StringCell.TYPE);
    creator.setDomain(domainCreator.createDomain());
    // create the appended column spec
    DataColumnSpec labelColSpec = creator.createSpec();
    return new DataTableSpec(originalSpec, new DataTableSpec(labelColSpec));
}

Example 23 with DataColumnDomainCreator

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

the class AbstractMany2OneCellFactory method getColumnSpecs.

/**
 * {@inheritDoc}
 */
@Override
public DataColumnSpec[] getColumnSpecs() {
    // new column
    DataColumnSpecCreator appendedColumnCreator = new DataColumnSpecCreator(m_appendedColumnName, StringCell.TYPE);
    // possible values depend on allow multi occurrences
    DataColumnDomainCreator possibleValuesCreator = new DataColumnDomainCreator(m_columnNames);
    appendedColumnCreator.setDomain(possibleValuesCreator.createDomain());
    return new DataColumnSpec[] { appendedColumnCreator.createSpec() };
}

Example 24 with DataColumnDomainCreator

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

the class BinModelPlotter method updatePaintModel.

/**
 * {@inheritDoc}
 */
@Override
public synchronized void updatePaintModel() {
    if (m_discretizationModel == null) {
        return;
    }
    // clear the drawing pane
    ((BinModelDrawingPane) getDrawingPane()).setBinningSchemes(null);
    // get the first columns
    if (m_selectedColumns == null) {
        m_selectedColumns = new LinkedHashSet<String>();
        String[] binnedColumnNames = m_discretizationModel.getIncludedColumnNames();
        for (int i = 0; i < binnedColumnNames.length; i++) {
            // add them to the selected columns
            m_selectedColumns.add(binnedColumnNames[i]);
        }
        ((MultiColumnPlotterProperties) getProperties()).updateColumnSelection(m_binnedColumnsSpec, m_selectedColumns);
    }
    if (m_selectedColumns.size() == 0) {
        getDrawingPane().repaint();
        return;
    }
    Set<DataCell> selectedColumnCells = new LinkedHashSet<DataCell>();
    m_coordinates = new ArrayList<Coordinate>();
    List<Integer> columnIndices = new ArrayList<Integer>();
    for (String name : m_selectedColumns) {
        int idx = m_binnedColumnsSpec.findColumnIndex(name);
        if (idx >= 0) {
            selectedColumnCells.add(new StringCell(name));
            DataColumnSpec colSpec = m_binnedColumnsSpec.getColumnSpec(idx);
            columnIndices.add(idx);
            Coordinate coordinate = Coordinate.createCoordinate(colSpec);
            m_coordinates.add(coordinate);
        }
    }
    // get the binning schemes for the selected columns
    DiscretizationScheme[] selectedSchemes = getSelectedSchemes();
    String[] selectedColumnNames = getSelectedColumnNames();
    // calculate the display coordinates for the drawing pane
    BinRuler[] binRulers = new BinRuler[selectedSchemes.length];
    // determine the width available for a bin ruler
    int rulerWidth = getDrawingPaneDimension().width - 2 * m_hMargin;
    for (int i = 0; i < selectedSchemes.length; i++) {
        double[] bounds = selectedSchemes[i].getBounds();
        double min = bounds[0];
        double max = bounds[bounds.length - 1];
        // first create a colum spec from the schemes
        DataColumnSpecCreator columnSpecCreator = new DataColumnSpecCreator("", DoubleCell.TYPE);
        columnSpecCreator.setDomain(new DataColumnDomainCreator(new DoubleCell(min), new DoubleCell(max)).createDomain());
        DoubleCoordinate coordinate = (DoubleCoordinate) Coordinate.createCoordinate(columnSpecCreator.createSpec());
        Point leftStart = new Point(m_hMargin, m_vMargin + (i + 1) * m_columnDisplayHeight);
        int[] binPositions = new int[bounds.length];
        String[] binLabels = new String[bounds.length];
        int count = 0;
        for (double bound : bounds) {
            binPositions[count] = (int) coordinate.calculateMappedValue(new DoubleCell(bound), rulerWidth, true);
            binLabels[count] = coordinate.formatNumber(bounds[count]);
            count++;
        }
        binRulers[i] = new BinRuler(leftStart, rulerWidth, binPositions, binLabels, selectedColumnNames[i]);
    }
    ((BinModelDrawingPane) getDrawingPane()).setBinningSchemes(binRulers);
    m_hMargin = 10;
    m_vMargin = 10;
    ((BinModelDrawingPane) getDrawingPane()).setHorizontalMargin(m_hMargin);
    setHeight(binRulers[binRulers.length - 1].getLeftStartPoint().y + 40);
}

Example 25 with DataColumnDomainCreator

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

the class EditNominalDomainNodeModel method sortPossibleValues.

private DataTableSpec sortPossibleValues(final DataTableSpec orgSpec) throws InvalidSettingsException {
    if (m_configuration == null) {
        throw new InvalidSettingsException("Missing Configuration.");
    }
    Set<String> configuredColumns = new HashSet<String>(m_configuration.getConfiguredColumns());
    String[] columnNames = orgSpec.getColumnNames();
    DataTableSpecCreator creator = new DataTableSpecCreator(orgSpec).dropAllColumns();
    for (int i = 0; i < orgSpec.getNumColumns(); i++) {
        String name = columnNames[i];
        if (configuredColumns.remove(name)) {
            DataColumnSpec orgDataSpec = orgSpec.getColumnSpec(i);
            if (!StringCell.TYPE.equals(orgDataSpec.getType())) {
                CheckUtils.checkSetting(m_configuration.isIgnoreWrongTypes(), "Column '%s' must be of type '%s' \nbut was of type: '%s'", name, StringCell.TYPE, orgDataSpec.getType());
                creator.addColumns(orgDataSpec);
            } else {
                DataColumnDomain domain = orgDataSpec.getDomain();
                DataColumnSpecCreator dataColumnSpecCreator = new DataColumnSpecCreator(orgDataSpec);
                DataColumnDomainCreator yetAnotherCreator = new DataColumnDomainCreator(domain.getLowerBound(), domain.getUpperBound());
                List<DataCell> sorting = new ArrayList<DataCell>(m_configuration.getSorting(name));
                Set<DataCell> difference = diff(domain.getValues(), sorting);
                yetAnotherCreator.setValues(resolveNewValues(sorting, difference));
                dataColumnSpecCreator.setDomain(yetAnotherCreator.createDomain());
                creator.addColumns(dataColumnSpecCreator.createSpec());
            }
        } else {
            creator.addColumns(orgSpec.getColumnSpec(i));
        }
    }
    if (!configuredColumns.isEmpty()) {
        String missingColumnsString = "Following columns are configured but no longer exist: \n" + ConvenienceMethods.getShortStringFrom(configuredColumns, 5);
        CheckUtils.checkSetting(m_configuration.isIgnoreNotExistingColumns(), missingColumnsString);
        setWarningMessage(missingColumnsString);
    }
    return creator.createSpec();
}