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

Example 26 with DataType

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

the class ModifyTimeNodeModel method createColumnRearranger.

/**
 * {@inheritDoc}
 */
@Override
protected ColumnRearranger createColumnRearranger(final DataTableSpec inSpec) {
    final ColumnRearranger rearranger = new ColumnRearranger(inSpec);
    final String[] includeList = m_colSelect.applyTo(inSpec).getIncludes();
    final int[] includeIndices = Arrays.stream(m_colSelect.applyTo(inSpec).getIncludes()).mapToInt(s -> inSpec.findColumnIndex(s)).toArray();
    // determine the data type of output
    DataType dataType;
    if (m_modifyAction.getStringValue().equals(MODIFY_OPTION_REMOVE)) {
        dataType = LocalDateCellFactory.TYPE;
    } else {
        if (m_modifyAction.getStringValue().equals(MODIFY_OPTION_CHANGE)) {
            dataType = LocalDateTimeCellFactory.TYPE;
        } else {
            if (m_timeZone.useZone()) {
                dataType = ZonedDateTimeCellFactory.TYPE;
            } else {
                dataType = LocalDateTimeCellFactory.TYPE;
            }
        }
    }
    int i = 0;
    for (final String includedCol : includeList) {
        if (inSpec.getColumnSpec(includedCol).getType().equals(ZonedDateTimeCellFactory.TYPE) && m_modifyAction.getStringValue().equals(MODIFY_OPTION_CHANGE)) {
            dataType = ZonedDateTimeCellFactory.TYPE;
        }
        if (m_isReplaceOrAppend.getStringValue().equals(OPTION_REPLACE)) {
            final DataColumnSpecCreator dataColumnSpecCreator = new DataColumnSpecCreator(includedCol, dataType);
            final SingleCellFactory cellFac = createCellFactory(dataColumnSpecCreator.createSpec(), includeIndices[i++], m_timeZone.getZone());
            rearranger.replace(cellFac, includedCol);
        } else {
            final DataColumnSpec dataColSpec = new UniqueNameGenerator(inSpec).newColumn(includedCol + m_suffix.getStringValue(), dataType);
            final SingleCellFactory cellFac = createCellFactory(dataColSpec, includeIndices[i++], m_timeZone.getZone());
            rearranger.append(cellFac);
        }
    }
    return rearranger;
}

Example 27 with DataType

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

the class ModifyDateNodeModel method createColumnRearranger.

/**
 * @param inSpec table input spec
 * @return the CR describing the output
 */
@Override
protected ColumnRearranger createColumnRearranger(final DataTableSpec inSpec) {
    final ColumnRearranger rearranger = new ColumnRearranger(inSpec);
    final String[] includeList = m_colSelect.applyTo(inSpec).getIncludes();
    final int[] includeIndices = Arrays.stream(m_colSelect.applyTo(inSpec).getIncludes()).mapToInt(s -> inSpec.findColumnIndex(s)).toArray();
    // determine the data type of output
    DataType dataType;
    if (m_modifyAction.getStringValue().equals(MODIFY_OPTION_REMOVE)) {
        dataType = LocalTimeCellFactory.TYPE;
    } else {
        if (m_modifyAction.getStringValue().equals(MODIFY_OPTION_CHANGE)) {
            dataType = LocalDateTimeCellFactory.TYPE;
        } else {
            if (m_timeZone.useZone()) {
                dataType = ZonedDateTimeCellFactory.TYPE;
            } else {
                dataType = LocalDateTimeCellFactory.TYPE;
            }
        }
    }
    final ZoneId zone = m_timeZone.getZone();
    int i = 0;
    for (final String includedCol : includeList) {
        if (inSpec.getColumnSpec(includedCol).getType().equals(ZonedDateTimeCellFactory.TYPE) && m_modifyAction.getStringValue().equals(MODIFY_OPTION_CHANGE)) {
            dataType = ZonedDateTimeCellFactory.TYPE;
        }
        if (m_isReplaceOrAppend.getStringValue().equals(OPTION_REPLACE)) {
            final DataColumnSpecCreator dataColumnSpecCreator = new DataColumnSpecCreator(includedCol, dataType);
            final SingleCellFactory cellFac = createCellFactory(dataColumnSpecCreator.createSpec(), includeIndices[i++], zone);
            rearranger.replace(cellFac, includedCol);
        } else {
            final DataColumnSpec dataColSpec = new UniqueNameGenerator(inSpec).newColumn(includedCol + m_suffix.getStringValue(), dataType);
            final SingleCellFactory cellFac = createCellFactory(dataColSpec, includeIndices[i++], zone);
            rearranger.append(cellFac);
        }
    }
    return rearranger;
}

Example 28 with DataType

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

the class StatisticsTable method calculateAllMoments.

/**
 * Calculates <b>all the statistical moments in one pass </b>. After the
 * call of this operation, the statistical moments can be obtained very fast
 * from all the other methods.
 *
 * @param rowCount Row count of table for progress, may be NaN if unknown.
 * @param exec object to check with if user canceled the operation
 * @throws CanceledExecutionException if user canceled
 * @throws IllegalArgumentException if rowCount argument < 0
 */
protected void calculateAllMoments(final double rowCount, final ExecutionMonitor exec) throws CanceledExecutionException {
    if (rowCount < 0.0) {
        throw new IllegalArgumentException("rowCount argument must not < 0: " + rowCount);
    }
    DataTableSpec origSpec = m_table.getDataTableSpec();
    int numOfCols = origSpec.getNumColumns();
    // the number of non-missing cells in each column
    int[] validCount = new int[numOfCols];
    double[] sumsquare = new double[numOfCols];
    final DataValueComparator[] comp = new DataValueComparator[numOfCols];
    for (int i = 0; i < numOfCols; i++) {
        sumsquare[i] = 0.0;
        validCount[i] = 0;
        comp[i] = origSpec.getColumnSpec(i).getType().getComparator();
        assert comp[i] != null;
    }
    int nrRows = 0;
    for (RowIterator rowIt = m_table.iterator(); rowIt.hasNext(); nrRows++) {
        DataRow row = rowIt.next();
        if (exec != null) {
            double prog = Double.isNaN(rowCount) ? 0.0 : nrRows / rowCount;
            exec.setProgress(prog, "Calculating statistics, processing row " + (nrRows + 1) + " (\"" + row.getKey() + "\")");
            // throws exception if user canceled
            exec.checkCanceled();
        }
        for (int c = 0; c < numOfCols; c++) {
            final DataCell cell = row.getCell(c);
            if (!(cell.isMissing())) {
                // keep the min and max for each column
                if ((m_minValues[c] == null) || (comp[c].compare(cell, m_minValues[c]) < 0)) {
                    m_minValues[c] = cell;
                }
                if ((m_maxValues[c] == null) || (comp[c].compare(m_maxValues[c], cell) < 0)) {
                    m_maxValues[c] = cell;
                }
                // for double columns we calc the sum (for the mean calc)
                DataType type = origSpec.getColumnSpec(c).getType();
                if (type.isCompatible(DoubleValue.class)) {
                    double d = ((DoubleValue) cell).getDoubleValue();
                    if (Double.isNaN(m_sum[c])) {
                        m_sum[c] = d;
                    } else {
                        m_sum[c] += d;
                    }
                    sumsquare[c] += d * d;
                    validCount[c]++;
                }
            } else {
                m_missingValueCnt[c]++;
            }
        }
        calculateMomentInSubClass(row);
    }
    m_nrRows = nrRows;
    for (int j = 0; j < numOfCols; j++) {
        // missing values
        if (validCount[j] == 0 || m_minValues[j] == null) {
            DataCell mc = DataType.getMissingCell();
            m_minValues[j] = mc;
            m_maxValues[j] = mc;
            m_meanValues[j] = Double.NaN;
            m_varianceValues[j] = Double.NaN;
        } else {
            m_meanValues[j] = m_sum[j] / validCount[j];
            if (validCount[j] > 1) {
                m_varianceValues[j] = (sumsquare[j] - ((m_sum[j] * m_sum[j]) / validCount[j])) / (validCount[j] - 1);
            } else {
                m_varianceValues[j] = 0.0;
            }
            // round-off errors resulting in negative variance values
            if (m_varianceValues[j] < 0.0 && m_varianceValues[j] > -1.0E8) {
                m_varianceValues[j] = 0.0;
            }
            assert m_varianceValues[j] >= 0.0 : "Variance cannot be negative (column \"" + origSpec.getColumnSpec(j).getName() + "\": " + m_varianceValues[j];
        }
    }
    // compute resulting table spec
    int nrCols = m_table.getDataTableSpec().getNumColumns();
    DataColumnSpec[] cSpec = new DataColumnSpec[nrCols];
    for (int c = 0; c < nrCols; c++) {
        DataColumnSpec s = m_table.getDataTableSpec().getColumnSpec(c);
        // we create domains with our bounds.
        Set<DataCell> values = (s.getDomain() == null ? null : s.getDomain().getValues());
        DataColumnDomain newDomain = new DataColumnDomainCreator(values, (m_minValues[c] == null || m_minValues[c].isMissing()) ? null : m_minValues[c], (m_maxValues[c] == null || m_maxValues[c].isMissing()) ? null : m_maxValues[c]).createDomain();
        DataColumnSpecCreator creator = new DataColumnSpecCreator(s);
        creator.setDomain(newDomain);
        cSpec[c] = creator.createSpec();
    }
    m_tSpec = new DataTableSpec(cSpec);
}

Example 29 with DataType

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

the class AppendVariableToTableNodeModel method createColumnRearranger.

private ColumnRearranger createColumnRearranger(final DataTableSpec spec) throws InvalidSettingsException {
    ColumnRearranger arranger = new ColumnRearranger(spec);
    Set<String> nameHash = new HashSet<String>();
    for (DataColumnSpec c : spec) {
        nameHash.add(c.getName());
    }
    List<Pair<String, FlowVariable.Type>> vars;
    if (m_settings.getIncludeAll()) {
        vars = getAllVariables();
    } else {
        vars = m_settings.getVariablesOfInterest();
    }
    if (vars.isEmpty()) {
        throw new InvalidSettingsException("No variables selected");
    }
    DataColumnSpec[] specs = new DataColumnSpec[vars.size()];
    final DataCell[] values = new DataCell[vars.size()];
    for (int i = 0; i < vars.size(); i++) {
        Pair<String, FlowVariable.Type> c = vars.get(i);
        String name = c.getFirst();
        DataType type;
        switch(c.getSecond()) {
            case DOUBLE:
                type = DoubleCell.TYPE;
                try {
                    double dValue = peekFlowVariableDouble(name);
                    values[i] = new DoubleCell(dValue);
                } catch (NoSuchElementException e) {
                    throw new InvalidSettingsException("No such flow variable (of type double): " + name);
                }
                break;
            case INTEGER:
                type = IntCell.TYPE;
                try {
                    int iValue = peekFlowVariableInt(name);
                    values[i] = new IntCell(iValue);
                } catch (NoSuchElementException e) {
                    throw new InvalidSettingsException("No such flow variable (of type int): " + name);
                }
                break;
            case STRING:
                type = StringCell.TYPE;
                try {
                    String sValue = peekFlowVariableString(name);
                    sValue = sValue == null ? "" : sValue;
                    values[i] = new StringCell(sValue);
                } catch (NoSuchElementException e) {
                    throw new InvalidSettingsException("No such flow variable (of type String): " + name);
                }
                break;
            default:
                throw new InvalidSettingsException("Unsupported variable type: " + c.getSecond());
        }
        if (nameHash.contains(name) && !name.toLowerCase().endsWith("(variable)")) {
            name = name.concat(" (variable)");
        }
        String newName = name;
        int uniquifier = 1;
        while (!nameHash.add(newName)) {
            newName = name + " (#" + (uniquifier++) + ")";
        }
        specs[i] = new DataColumnSpecCreator(newName, type).createSpec();
    }
    arranger.append(new AbstractCellFactory(specs) {

        /**
         * {@inheritDoc}
         */
        @Override
        public DataCell[] getCells(final DataRow row) {
            return values;
        }
    });
    return arranger;
}

Example 30 with DataType

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

the class VariableToTableNodeModel method createOutSpec.

private DataTableSpec createOutSpec() throws InvalidSettingsException {
    List<Pair<String, FlowVariable.Type>> vars;
    if (m_settings.getIncludeAll()) {
        vars = getAllVariables();
    } else {
        vars = m_settings.getVariablesOfInterest();
    }
    if (vars.isEmpty()) {
        throw new InvalidSettingsException("No variables selected");
    }
    DataColumnSpec[] specs = new DataColumnSpec[vars.size()];
    for (int i = 0; i < vars.size(); i++) {
        Pair<String, FlowVariable.Type> c = vars.get(i);
        DataType type;
        switch(c.getSecond()) {
            case DOUBLE:
                type = DoubleCell.TYPE;
                break;
            case INTEGER:
                type = IntCell.TYPE;
                break;
            case STRING:
                type = StringCell.TYPE;
                break;
            default:
                throw new InvalidSettingsException("Unsupported variable type: " + c.getSecond());
        }
        specs[i] = new DataColumnSpecCreator(c.getFirst(), type).createSpec();
    }
    return new DataTableSpec(specs);
}