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

Example 26 with DataColumnDomainCreator

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

the class ConditionalBoxPlotNodeModel method execute.

/**
 * {@inheritDoc}
 */
@Override
protected BufferedDataTable[] execute(final BufferedDataTable[] inData, final ExecutionContext exec) throws Exception {
    m_statistics = new LinkedHashMap<DataColumnSpec, double[]>();
    m_mildOutliers = new LinkedHashMap<String, Map<Double, Set<RowKey>>>();
    m_extremeOutliers = new LinkedHashMap<String, Map<Double, Set<RowKey>>>();
    double nrRows = inData[0].size();
    int rowCount = 0;
    int numericIndex = inData[0].getDataTableSpec().findColumnIndex(m_settings.numericColumn());
    int nominalIndex = inData[0].getDataTableSpec().findColumnIndex(m_settings.nominalColumn());
    Map<String, Map<Double, Set<RowKey>>> data = new LinkedHashMap<String, Map<Double, Set<RowKey>>>();
    // some default values .. if one column only has missing values.
    for (DataCell d : inData[0].getDataTableSpec().getColumnSpec(nominalIndex).getDomain().getValues()) {
        String name = ((StringValue) d).getStringValue();
        m_mildOutliers.put(name, new HashMap<Double, Set<RowKey>>());
        m_extremeOutliers.put(name, new HashMap<Double, Set<RowKey>>());
    }
    for (DataRow r : inData[0]) {
        exec.checkCanceled();
        exec.setProgress(rowCount++ / nrRows, "Separating...");
        if (!m_settings.showMissingValues()) {
            if (r.getCell(nominalIndex).isMissing()) {
                // missing cell in nominal values is unwanted?
                continue;
            }
        }
        String nominal = replaceSpaces(r.getCell(nominalIndex).toString());
        if (r.getCell(numericIndex).isMissing()) {
            // ignore missing cells in numeric column
            continue;
        }
        DoubleValue numeric = (DoubleValue) r.getCell(numericIndex);
        Map<Double, Set<RowKey>> map = data.get(nominal);
        if (map == null) {
            map = new LinkedHashMap<Double, Set<RowKey>>();
        }
        Set<RowKey> set = map.get(numeric.getDoubleValue());
        if (set == null) {
            set = new HashSet<RowKey>();
        }
        set.add(r.getKey());
        map.put(numeric.getDoubleValue(), set);
        data.put(nominal, map);
    }
    List<String> keys = new ArrayList<String>(data.keySet());
    boolean ignoreMissingValues = false;
    if (m_settings.showMissingValues() && !keys.contains(DataType.getMissingCell().toString())) {
        // we promised to create data for missing values..
        // if there aren't any.. we have to create them ourselves
        setWarningMessage("No missing values found.");
        ignoreMissingValues = true;
    }
    Collections.sort(keys);
    DataColumnSpec[] colSpecs = createColumnSpec(inData[0].getDataTableSpec().getColumnSpec(nominalIndex), ignoreMissingValues);
    if (keys.size() == 0) {
        setWarningMessage("All classes are empty.");
    }
    int dataSetNr = 0;
    // for (String d : keys) {
    for (DataColumnSpec dcs : colSpecs) {
        String d = dcs.getName();
        if (data.get(d) == null || keys.size() == 0) {
            dataSetNr++;
            continue;
        }
        exec.checkCanceled();
        exec.setProgress(dataSetNr / (double) keys.size(), "Creating statistics");
        Map<Double, Set<RowKey>> extremeOutliers = new LinkedHashMap<Double, Set<RowKey>>();
        Map<Double, Set<RowKey>> mildOutliers = new LinkedHashMap<Double, Set<RowKey>>();
        double[] stats = calculateStatistic(data.get(d), mildOutliers, extremeOutliers);
        double minimum = stats[BoxPlotNodeModel.MIN];
        double maximum = stats[BoxPlotNodeModel.MAX];
        DataColumnSpecCreator creator = new DataColumnSpecCreator(colSpecs[dataSetNr]);
        creator.setDomain(new DataColumnDomainCreator(new DoubleCell(minimum), new DoubleCell(maximum)).createDomain());
        colSpecs[dataSetNr] = creator.createSpec();
        m_statistics.put(colSpecs[dataSetNr], stats);
        m_mildOutliers.put(d, mildOutliers);
        m_extremeOutliers.put(d, extremeOutliers);
        dataSetNr++;
    }
    DataTableSpec dts = new DataTableSpec("MyTempTable", colSpecs);
    DataContainer cont = new DataContainer(dts);
    cont.close();
    m_dataArray = new DefaultDataArray(cont.getTable(), 1, 2);
    cont.dispose();
    if (ignoreMissingValues) {
        DataColumnSpec[] temp = new DataColumnSpec[colSpecs.length + 1];
        DataColumnSpec missing = new DataColumnSpecCreator(DataType.getMissingCell().toString(), DataType.getMissingCell().getType()).createSpec();
        int i = 0;
        while (missing.getName().compareTo(colSpecs[i].getName()) > 0) {
            temp[i] = colSpecs[i];
            i++;
        }
        temp[i++] = missing;
        while (i < temp.length) {
            temp[i] = colSpecs[i - 1];
            i++;
        }
        colSpecs = temp;
    }
    /* Save inSpec of the numeric column to provide the view a way to
         * consider the input domain for normalization. */
    m_numColSpec = inData[0].getDataTableSpec().getColumnSpec(numericIndex);
    return new BufferedDataTable[] { createOutputTable(inData[0].getDataTableSpec(), colSpecs, exec).getTable() };
}

Example 27 with DataColumnDomainCreator

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

the class Normalizer3NodeModel method calculate.

/**
 * New normalized {@link org.knime.core.data.DataTable} is created depending on the mode.
 */
/**
 * @param inData The input data.
 * @param exec For BufferedDataTable creation and progress.
 * @return the result of the calculation
 * @throws Exception If the node calculation fails for any reason.
 */
protected CalculationResult calculate(final PortObject[] inData, final ExecutionContext exec) throws Exception {
    BufferedDataTable inTable = (BufferedDataTable) inData[0];
    DataTableSpec inSpec = inTable.getSpec();
    // extract selected numeric columns
    String[] includedColumns = getIncludedComlumns(inSpec);
    Normalizer2 ntable = new Normalizer2(inTable, includedColumns);
    long rowcount = inTable.size();
    ExecutionContext prepareExec = exec.createSubExecutionContext(0.3);
    AffineTransTable outTable;
    boolean fixDomainBounds = false;
    switch(m_config.getMode()) {
        case MINMAX:
            fixDomainBounds = true;
            outTable = ntable.doMinMaxNorm(m_config.getMax(), m_config.getMin(), prepareExec);
            break;
        case Z_SCORE:
            outTable = ntable.doZScoreNorm(prepareExec);
            break;
        case DECIMALSCALING:
            outTable = ntable.doDecimalScaling(prepareExec);
            break;
        default:
            throw new InvalidSettingsException("No mode set");
    }
    if (outTable.getErrorMessage() != null) {
        // something went wrong, report and throw an exception
        throw new Exception(outTable.getErrorMessage());
    }
    if (ntable.getErrorMessage() != null) {
        // something went wrong during initialization, report.
        setWarningMessage(ntable.getErrorMessage());
    }
    DataTableSpec modelSpec = FilterColumnTable.createFilterTableSpec(inSpec, includedColumns);
    AffineTransConfiguration configuration = outTable.getConfiguration();
    DataTableSpec spec = outTable.getDataTableSpec();
    // the same transformation, which is not guaranteed to snap to min/max)
    if (fixDomainBounds) {
        DataColumnSpec[] newColSpecs = new DataColumnSpec[spec.getNumColumns()];
        for (int i = 0; i < newColSpecs.length; i++) {
            newColSpecs[i] = spec.getColumnSpec(i);
        }
        for (int i = 0; i < includedColumns.length; i++) {
            int index = spec.findColumnIndex(includedColumns[i]);
            DataColumnSpecCreator creator = new DataColumnSpecCreator(newColSpecs[index]);
            DataColumnDomainCreator domCreator = new DataColumnDomainCreator(newColSpecs[index].getDomain());
            domCreator.setLowerBound(new DoubleCell(m_config.getMin()));
            domCreator.setUpperBound(new DoubleCell(m_config.getMax()));
            creator.setDomain(domCreator.createDomain());
            newColSpecs[index] = creator.createSpec();
        }
        spec = new DataTableSpec(spec.getName(), newColSpecs);
    }
    ExecutionMonitor normExec = exec.createSubProgress(.7);
    BufferedDataContainer container = exec.createDataContainer(spec);
    long count = 1;
    for (DataRow row : outTable) {
        normExec.checkCanceled();
        normExec.setProgress(count / (double) rowcount, "Normalizing row no. " + count + " of " + rowcount + " (\"" + row.getKey() + "\")");
        container.addRowToTable(row);
        count++;
    }
    container.close();
    return new CalculationResult(container.getTable(), modelSpec, configuration);
}

Example 28 with DataColumnDomainCreator

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

the class EditNominalDomainDicNodeModel method mergeTableSpecs.

/**
 * @param orgSpec
 * @param orgIndexToNewDomainValuesMap
 * @return
 */
private static DataTableSpecCreator mergeTableSpecs(final DataTableSpec orgSpec, final Map<Integer, Set<DataCell>> orgIndexToNewDomainValuesMap) {
    DataTableSpecCreator newSpecCreator = new DataTableSpecCreator(orgSpec).dropAllColumns();
    for (int i = 0; i < orgSpec.getNumColumns(); i++) {
        if (orgIndexToNewDomainValuesMap.containsKey(i)) {
            DataColumnSpec orgDataSpec = orgSpec.getColumnSpec(i);
            DataColumnSpecCreator dataColumnSpecCreator = new DataColumnSpecCreator(orgDataSpec);
            DataColumnDomainCreator yetAnotherCreator = new DataColumnDomainCreator(orgDataSpec.getDomain());
            yetAnotherCreator.setValues(orgIndexToNewDomainValuesMap.get(i));
            dataColumnSpecCreator.setDomain(yetAnotherCreator.createDomain());
            newSpecCreator.addColumns(dataColumnSpecCreator.createSpec());
        } else {
            newSpecCreator.addColumns(orgSpec.getColumnSpec(i));
        }
    }
    return newSpecCreator;
}

Example 29 with DataColumnDomainCreator

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

the class EditNumericDomainNodeModel method processDomainSettings.

private DataTableSpec processDomainSettings(final DataTableSpec dataTableSpec) throws InvalidSettingsException {
    if (m_configuration == null) {
        throw new InvalidSettingsException("Missing Configuration.");
    }
    EditNumericDomainConfiguration config = m_configuration;
    FilterResult filterResult = config.getColumnspecFilterConfig().applyTo(dataTableSpec);
    List<DataColumnSpec> newColumnSpecs = new ArrayList<DataColumnSpec>(dataTableSpec.getNumColumns());
    String[] columnNames = dataTableSpec.getColumnNames();
    Set<String> includeSet = new HashSet<String>();
    Collections.addAll(includeSet, filterResult.getIncludes());
    for (int i = 0; i < dataTableSpec.getNumColumns(); i++) {
        DataColumnSpec columnSpec = dataTableSpec.getColumnSpec(i);
        String columnName = columnNames[i];
        if (includeSet.contains(columnName)) {
            DataColumnSpecCreator columnSpecCreator = new DataColumnSpecCreator(columnSpec);
            DataColumnDomainCreator domainCreator = new // 
            DataColumnDomainCreator(// 
            createCell(columnName, columnSpec.getType(), config.getLowerBound()), createCell(columnName, columnSpec.getType(), config.getUpperBound()));
            domainCreator.setValues(columnSpec.getDomain().getValues());
            columnSpecCreator.setDomain(domainCreator.createDomain());
            newColumnSpecs.add(columnSpecCreator.createSpec());
        } else {
            newColumnSpecs.add(columnSpec);
        }
    }
    StringBuilder warnings = new StringBuilder();
    if (includeSet.isEmpty()) {
        warnings.append("No columns are included.");
    }
    if (filterResult.getRemovedFromIncludes().length > 0) {
        warnings.append("\nFollowing columns are configured but no longer exist: " + ConvenienceMethods.getShortStringFrom(Arrays.asList(filterResult.getRemovedFromIncludes()), 5));
    }
    if (warnings.length() > 0) {
        setWarningMessage(warnings.toString());
    }
    return new DataTableSpecCreator(dataTableSpec).dropAllColumns().addColumns(newColumnSpecs.toArray(new DataColumnSpec[newColumnSpecs.size()])).createSpec();
}

Example 30 with DataColumnDomainCreator

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

the class PMCCPortObjectAndSpec method createOutSpec.

/**
 * Creates output spec for correlation table.
 * @param names the column names being analyzed.
 * @return The new output spec.
 * @since 2.6
 */
public static DataTableSpec createOutSpec(final String[] names) {
    DataColumnSpec[] colSpecs = new DataColumnSpec[names.length];
    for (int i = 0; i < colSpecs.length; i++) {
        DataColumnSpecCreator c = new DataColumnSpecCreator(names[i], DoubleCell.TYPE);
        c.setDomain(new DataColumnDomainCreator(MIN_VALUE_CELL, MAX_VALUE_CELL).createDomain());
        colSpecs[i] = c.createSpec();
    }
    return new DataTableSpec("Correlation values", colSpecs);
}