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

Example 61 with DataCell

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

the class DateShiftConfigure method getColumnbasedCellFactory.

/**
 * @param spec the  output column spec
 * @param col1Idx the column index of the numerical column to add
 * @param g the time field to modify (as defined by calendar constants)
 * @param conf the configuration object
 * @param col2Idx the time column
 * @return the cell factory
 */
public static SingleCellFactory getColumnbasedCellFactory(final DataColumnSpec spec, final int col1Idx, final int col2Idx, final int g, final DateShiftConfigure conf) {
    return new SingleCellFactory(spec) {

        /**
         * Value for the new column is based on the values of two column of the row (first and second date column),
         * the selected granularity, and the fraction digits for rounding.
         *
         * @param row the current row
         * @return the difference between the two date values with the given granularity and rounding
         */
        @Override
        public DataCell getCell(final DataRow row) {
            final int value;
            DataCell cell2 = row.getCell(col2Idx);
            if (cell2.isMissing()) {
                return DataType.getMissingCell();
            }
            String typeofshift = conf.gettypeofshift().getStringValue();
            if (typeofshift.equals(DateShiftNodeDialog.CFG_COLUMN_SHIFT)) {
                DataCell cell1 = row.getCell(col1Idx);
                if ((cell1.isMissing())) {
                    return DataType.getMissingCell();
                }
                value = ((IntValue) cell1).getIntValue();
            } else {
                value = conf.getvalueofshift().getIntValue();
            }
            Calendar c = ((DateAndTimeValue) cell2).getUTCCalendarClone();
            c.add(g, value);
            return new DateAndTimeCell(c.getTimeInMillis(), conf.getHasDate().getBooleanValue(), conf.getHasTime().getBooleanValue(), conf.getHasMiliSeconds().getBooleanValue());
        }
    };
}

Example 62 with DataCell

use of org.knime.core.data.DataCell 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 63 with DataCell

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

the class Statistics2Table method createNominalValueTable.

/**
 * Create nominal value table containing all possible values together with
 * their occurrences.
 * @param nominal value output table
 * @return data table with nominal values for each column
 */
public DataTable createNominalValueTable(final List<String> nominal) {
    DataTableSpec outSpec = createOutSpecNominal(m_spec, nominal);
    Iterator[] it = new Iterator[outSpec.getNumColumns() / 2];
    int idx = 0;
    for (int i = 0; i < m_nominalValues.length; i++) {
        if (m_nominalValues[i] != null) {
            it[idx++] = m_nominalValues[i].entrySet().iterator();
        }
    }
    DataContainer cont = new DataContainer(outSpec);
    int rowIndex = 0;
    do {
        boolean addEnd = true;
        DataCell[] cells = new DataCell[2 * it.length];
        for (int i = 0; i < it.length; i++) {
            if (it[i] != null && it[i].hasNext()) {
                Map.Entry<DataCell, Integer> e = (Map.Entry<DataCell, Integer>) it[i].next();
                cells[2 * i] = e.getKey();
                cells[2 * i + 1] = new IntCell(e.getValue());
                addEnd = false;
            } else {
                cells[2 * i] = DataType.getMissingCell();
                cells[2 * i + 1] = DataType.getMissingCell();
            }
        }
        if (addEnd) {
            break;
        }
        cont.addRowToTable(new DefaultRow(RowKey.createRowKey(rowIndex++), cells));
    } while (true);
    cont.close();
    return cont.getTable();
}

Example 64 with DataCell

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

the class Statistics2Table method load.

/**
 * Load a new statistic table by the given settings object.
 * @param sett to load this table from
 * @return a new statistic table
 * @throws InvalidSettingsException if the settings are corrupt
 */
public static Statistics2Table load(final NodeSettingsRO sett) throws InvalidSettingsException {
    DataTableSpec spec = DataTableSpec.load(sett.getConfig("spec"));
    Map<DataCell, Integer>[] nominalValues = new Map[spec.getNumColumns()];
    for (int c = 0; c < nominalValues.length; c++) {
        String name = spec.getColumnSpec(c).getName();
        if (!sett.containsKey(name)) {
            nominalValues[c] = null;
        } else {
            nominalValues[c] = new LinkedHashMap<DataCell, Integer>();
            NodeSettingsRO subSett = sett.getNodeSettings(name);
            for (String key : subSett.keySet()) {
                NodeSettingsRO nomSett = subSett.getNodeSettings(key);
                nominalValues[c].put(nomSett.getDataCell("key"), nomSett.getInt("value"));
            }
        }
    }
    double[] min = sett.getDoubleArray("minimum");
    double[] max = sett.getDoubleArray("maximum");
    double[] mean = sett.getDoubleArray("mean");
    double[] var = sett.getDoubleArray("variance");
    double[] median = sett.getDoubleArray("median");
    double[] missings = sett.getDoubleArray("missings");
    double[] sums = sett.getDoubleArray("sums");
    // added with 2.7, fallback -1
    int rowCount = sett.getInt("row_count", -1);
    return new Statistics2Table(spec, min, max, mean, median, var, sums, missings, nominalValues, rowCount);
}

Example 65 with DataCell

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

the class ReadPNGFromURLNodeModel method createColumnRearranger.

private ColumnRearranger createColumnRearranger(final DataTableSpec in, final AtomicLong failCounter) throws InvalidSettingsException {
    String colName = m_config.getUrlColName();
    if (colName == null) {
        // throws ISE
        m_config.guessDefaults(in);
        colName = m_config.getUrlColName();
        setWarningMessage("Auto-configuration: Guessing column \"" + colName + "\" to contain locations");
    }
    final int colIndex = in.findColumnIndex(colName);
    if (colIndex < 0) {
        throw new InvalidSettingsException("No such column in input: " + colName);
    }
    DataColumnSpec colSpec = in.getColumnSpec(colIndex);
    if (!colSpec.getType().isCompatible(StringValue.class)) {
        throw new InvalidSettingsException("Selected column \"" + colName + "\" is not string-compatible");
    }
    final String newColName = m_config.getNewColumnName();
    DataColumnSpecCreator colSpecCreator;
    if (newColName != null) {
        String newName = DataTableSpec.getUniqueColumnName(in, newColName);
        colSpecCreator = new DataColumnSpecCreator(newName, PNGImageContent.TYPE);
    } else {
        colSpecCreator = new DataColumnSpecCreator(colSpec);
        colSpecCreator.setType(PNGImageContent.TYPE);
        colSpecCreator.removeAllHandlers();
        colSpecCreator.setDomain(null);
    }
    DataColumnSpec outColumnSpec = colSpecCreator.createSpec();
    ColumnRearranger rearranger = new ColumnRearranger(in);
    CellFactory fac = new SingleCellFactory(outColumnSpec) {

        @Override
        public DataCell getCell(final DataRow row) {
            DataCell cell = row.getCell(colIndex);
            if (cell.isMissing()) {
                return DataType.getMissingCell();
            } else {
                String url = ((StringValue) cell).getStringValue();
                try {
                    return toPNGCell(url);
                } catch (Exception e) {
                    if (m_config.isFailOnInvalid()) {
                        if (e instanceof RuntimeException) {
                            throw (RuntimeException) e;
                        } else {
                            throw new RuntimeException(e.getMessage(), e);
                        }
                    } else {
                        String message = "Failed to read png content from " + "\"" + url + "\": " + e.getMessage();
                        LOGGER.warn(message, e);
                        failCounter.incrementAndGet();
                        return DataType.getMissingCell();
                    }
                }
            }
        }
    };
    if (newColName == null) {
        rearranger.replace(fac, colIndex);
    } else {
        rearranger.append(fac);
    }
    return rearranger;
}