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

Example 46 with DataColumnDomainCreator

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

the class SubgroupMinerModel2 method createItemsetOutputSpec.

private DataTableSpec createItemsetOutputSpec(final DataTableSpec spec) {
    /*
         * creating the output spec with (maxDepth + 1) String columns and the
         * first column as an int column (the support)
         */
    DataColumnSpec[] colSpecs = new DataColumnSpec[2];
    DataColumnSpecCreator colspeccreator = new DataColumnSpecCreator("Support(0-1):", DoubleCell.TYPE);
    colspeccreator.setDomain(new DataColumnDomainCreator(new DoubleCell(0), new DoubleCell(1)).createDomain());
    colSpecs[0] = colspeccreator.createSpec();
    DataType transType = spec.getColumnSpec(m_transactionColumn.getStringValue()).getType();
    DataType transCollType = transType.getCollectionElementType();
    colSpecs[1] = new DataColumnSpecCreator("Items", transCollType == null ? SetCell.getCollectionType(StringCell.TYPE) : SetCell.getCollectionType(transCollType)).createSpec();
    return new DataTableSpec(colSpecs);
}

Example 47 with DataColumnDomainCreator

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

the class BinningCellFactory method getColumnSpecs.

/**
 * {@inheritDoc}
 */
public DataColumnSpec[] getColumnSpecs() {
    DataColumnSpecCreator creator = new DataColumnSpecCreator(m_name, StringCell.TYPE);
    DataCell[] values = new DataCell[m_bins.size()];
    for (int i = 0; i < values.length; i++) {
        values[i] = m_bins.get(i).getValue();
    }
    DataColumnDomainCreator domainCreator = new DataColumnDomainCreator(values);
    creator.setDomain(domainCreator.createDomain());
    return new DataColumnSpec[] { creator.createSpec() };
}

Example 48 with DataColumnDomainCreator

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

the class AutoBinner method calcDomainBoundsIfNeccessary.

/**
 * Determines the per column min/max values of the given data if not already present in the domain.
 *
 * @param data the data
 * @param exec the execution context
 * @param recalcValuesFor The columns
 * @return The data with extended domain information
 * @throws InvalidSettingsException ...
 * @throws CanceledExecutionException ...
 */
public BufferedDataTable calcDomainBoundsIfNeccessary(final BufferedDataTable data, final ExecutionContext exec, final List<String> recalcValuesFor) throws InvalidSettingsException, CanceledExecutionException {
    if (null == recalcValuesFor || recalcValuesFor.isEmpty()) {
        return data;
    }
    List<Integer> valuesI = new ArrayList<Integer>();
    for (String colName : recalcValuesFor) {
        DataColumnSpec colSpec = data.getDataTableSpec().getColumnSpec(colName);
        if (!colSpec.getType().isCompatible(DoubleValue.class)) {
            throw new InvalidSettingsException("Can only process numeric " + "data. The column \"" + colSpec.getName() + "\" is not numeric.");
        }
        if (recalcValuesFor.contains(colName) && !colSpec.getDomain().hasBounds()) {
            valuesI.add(data.getDataTableSpec().findColumnIndex(colName));
        }
    }
    if (valuesI.isEmpty()) {
        return data;
    }
    Map<Integer, Double> min = new HashMap<Integer, Double>();
    Map<Integer, Double> max = new HashMap<Integer, Double>();
    for (int col : valuesI) {
        min.put(col, Double.MAX_VALUE);
        max.put(col, Double.MIN_VALUE);
    }
    int c = 0;
    for (DataRow row : data) {
        c++;
        exec.checkCanceled();
        exec.setProgress(c / (double) data.size());
        for (int col : valuesI) {
            double val = ((DoubleValue) row.getCell(col)).getDoubleValue();
            if (min.get(col) > val) {
                min.put(col, val);
            }
            if (max.get(col) < val) {
                min.put(col, val);
            }
        }
    }
    List<DataColumnSpec> newColSpecList = new ArrayList<DataColumnSpec>();
    int cc = 0;
    for (DataColumnSpec columnSpec : data.getDataTableSpec()) {
        if (recalcValuesFor.contains(columnSpec.getName())) {
            DataColumnSpecCreator specCreator = new DataColumnSpecCreator(columnSpec);
            DataColumnDomainCreator domainCreator = new DataColumnDomainCreator(new DoubleCell(min.get(cc)), new DoubleCell(max.get(cc)));
            specCreator.setDomain(domainCreator.createDomain());
            DataColumnSpec newColSpec = specCreator.createSpec();
            newColSpecList.add(newColSpec);
        } else {
            newColSpecList.add(columnSpec);
        }
        cc++;
    }
    DataTableSpec spec = new DataTableSpec(newColSpecList.toArray(new DataColumnSpec[0]));
    BufferedDataTable newDataTable = exec.createSpecReplacerTable(data, spec);
    return newDataTable;
}

Example 49 with DataColumnDomainCreator

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

the class ClusterMembershipFactory method getColumnSpecs.

/**
 * {@inheritDoc}
 */
public DataColumnSpec[] getColumnSpecs() {
    int nrclusters = m_nrClusters;
    DataColumnSpec[] newSpec = new DataColumnSpec[nrclusters + 1];
    int cluster = 0;
    DataColumnSpecCreator colspecCreator = null;
    for (int j = 0; j < nrclusters; j++) {
        if (m_noise && j == (newSpec.length - 2)) {
            colspecCreator = new DataColumnSpecCreator(FuzzyClusterNodeModel.NOISESPEC_KEY, DoubleCell.TYPE);
            colspecCreator.setProperties(new DataColumnProperties(Collections.singletonMap(DataValueRenderer.PROPERTY_PREFERRED_RENDERER, DoubleBarRenderer.DESCRIPTION)));
            colspecCreator.setDomain(new DataColumnDomainCreator(new DoubleCell(0.0), new DoubleCell(1.0)).createDomain());
            newSpec[j] = colspecCreator.createSpec();
            break;
        }
        colspecCreator = new DataColumnSpecCreator(FuzzyClusterNodeModel.CLUSTER_KEY + cluster, DoubleCell.TYPE);
        colspecCreator.setProperties(new DataColumnProperties(Collections.singletonMap(DataValueRenderer.PROPERTY_PREFERRED_RENDERER, DoubleBarRenderer.DESCRIPTION)));
        colspecCreator.setDomain(new DataColumnDomainCreator(new DoubleCell(0.0), new DoubleCell(1.0)).createDomain());
        newSpec[j] = colspecCreator.createSpec();
        cluster++;
    }
    newSpec[newSpec.length - 1] = new DataColumnSpecCreator("Winner Cluster", StringCell.TYPE).createSpec();
    return newSpec;
}

Example 50 with DataColumnDomainCreator

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

the class DecTreePredictorNodeModel method createOutTableSpec.

private DataTableSpec createOutTableSpec(final PortObjectSpec[] inSpecs) throws InvalidSettingsException {
    List<DataCell> predValues = null;
    if (m_showDistribution.getBooleanValue()) {
        predValues = getPredictionValues((PMMLPortObjectSpec) inSpecs[INMODELPORT]);
        if (predValues == null) {
            // no out spec can be determined
            return null;
        }
    }
    int numCols = (predValues == null ? 0 : predValues.size()) + 1;
    DataTableSpec inSpec = (DataTableSpec) inSpecs[INDATAPORT];
    DataColumnSpec[] newCols = new DataColumnSpec[numCols];
    /* Set bar renderer and domain [0,1] as default for the double cells
         * containing the distribution */
    // DataColumnProperties propsRendering = new DataColumnProperties(
    // Collections.singletonMap(
    // DataValueRenderer.PROPERTY_PREFERRED_RENDERER,
    // DoubleBarRenderer.DESCRIPTION));
    DataColumnDomain domain = new DataColumnDomainCreator(new DoubleCell(0.0), new DoubleCell(1.0)).createDomain();
    PredictorHelper predictorHelper = PredictorHelper.getInstance();
    String trainingColumnName = ((PMMLPortObjectSpec) inSpecs[INMODELPORT]).getTargetFields().iterator().next();
    // add all distribution columns
    for (int i = 0; i < numCols - 1; i++) {
        assert predValues != null;
        DataColumnSpecCreator colSpecCreator = new DataColumnSpecCreator(predictorHelper.probabilityColumnName(trainingColumnName, predValues.get(i).toString(), m_probabilitySuffix.getStringValue()), DoubleCell.TYPE);
        // colSpecCreator.setProperties(propsRendering);
        colSpecCreator.setDomain(domain);
        newCols[i] = colSpecCreator.createSpec();
    }
    // add the prediction column
    String predictionColumnName = predictorHelper.computePredictionColumnName(m_predictionColumn.getStringValue(), m_overridePrediction.getBooleanValue(), trainingColumnName);
    newCols[numCols - 1] = new DataColumnSpecCreator(predictionColumnName, StringCell.TYPE).createSpec();
    DataTableSpec newColSpec = new DataTableSpec(newCols);
    return new DataTableSpec(inSpec, newColSpec);
}