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

Example 46 with DataRow

use of org.knime.core.data.DataRow 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 47 with DataRow

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

the class VariableFileReaderNodeModel method execute.

/**
 * {@inheritDoc}
 */
@Override
protected PortObject[] execute(final PortObject[] inData, final ExecutionContext exec) throws Exception {
    Map<String, FlowVariable> stack = createStack(m_frSettings.getVariableName());
    VariableFileReaderNodeSettings settings = m_frSettings.createSettingsFrom(stack);
    LOGGER.info("Preparing to read from '" + m_frSettings.getDataFileLocation().toString() + "'.");
    // check again the settings - especially file existence (under Linux
    // files could be deleted/renamed since last config-call...
    SettingsStatus status = settings.getStatusOfSettings(true, null);
    if (status.getNumOfErrors() > 0) {
        throw new InvalidSettingsException(status.getAllErrorMessages(10));
    }
    DataTableSpec tSpec = settings.createDataTableSpec();
    FileTable fTable = new FileTable(tSpec, settings, settings.getSkippedColumns(), exec);
    // create a DataContainer and fill it with the rows read. It is faster
    // then reading the file every time (for each row iterator), and it
    // collects the domain for each column for us. Also, if things fail,
    // the error message is printed during file reader execution (were it
    // belongs to) and not some time later when a node uses the row
    // iterator from the file table.
    BufferedDataContainer c = exec.createDataContainer(fTable.getDataTableSpec(), /* initDomain= */
    true);
    int row = 0;
    FileRowIterator it = fTable.iterator();
    try {
        if (it.getZipEntryName() != null) {
            // seems we are reading a ZIP archive.
            LOGGER.info("Reading entry '" + it.getZipEntryName() + "' from the specified ZIP archive.");
        }
        while (it.hasNext()) {
            row++;
            DataRow next = it.next();
            String message = "Caching row #" + row + " (\"" + next.getKey() + "\")";
            exec.setMessage(message);
            exec.checkCanceled();
            c.addRowToTable(next);
        }
        if (it.zippedSourceHasMoreEntries()) {
            // after reading til the end of the file this returns a valid
            // result
            setWarningMessage("Source is a ZIP archive with multiple " + "entries. Only reading first entry!");
        }
    } catch (DuplicateKeyException dke) {
        String msg = dke.getMessage();
        if (msg == null) {
            msg = "Duplicate row IDs";
        }
        msg += ". Consider making IDs unique in the advanced settings.";
        DuplicateKeyException newDKE = new DuplicateKeyException(msg);
        newDKE.initCause(dke);
        throw newDKE;
    } finally {
        c.close();
    }
    // user settings allow for truncating the table
    if (it.iteratorEndedEarly()) {
        setWarningMessage("Data was truncated due to user settings.");
    }
    BufferedDataTable out = c.getTable();
    // closes all sources.
    fTable.dispose();
    return new BufferedDataTable[] { out };
}

Example 48 with DataRow

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

the class DecTreePredictorNodeModel method execute.

/**
 * {@inheritDoc}
 */
@Override
public PortObject[] execute(final PortObject[] inPorts, final ExecutionContext exec) throws CanceledExecutionException, Exception {
    exec.setMessage("Decision Tree Predictor: Loading predictor...");
    PMMLPortObject port = (PMMLPortObject) inPorts[INMODELPORT];
    List<Node> models = port.getPMMLValue().getModels(PMMLModelType.TreeModel);
    if (models.isEmpty()) {
        String msg = "Decision Tree evaluation failed: " + "No tree model found.";
        LOGGER.error(msg);
        throw new RuntimeException(msg);
    }
    PMMLDecisionTreeTranslator trans = new PMMLDecisionTreeTranslator();
    port.initializeModelTranslator(trans);
    DecisionTree decTree = trans.getDecisionTree();
    decTree.resetColorInformation();
    BufferedDataTable inData = (BufferedDataTable) inPorts[INDATAPORT];
    // get column with color information
    String colorColumn = null;
    for (DataColumnSpec s : inData.getDataTableSpec()) {
        if (s.getColorHandler() != null) {
            colorColumn = s.getName();
            break;
        }
    }
    decTree.setColorColumn(colorColumn);
    exec.setMessage("Decision Tree Predictor: start execution.");
    PortObjectSpec[] inSpecs = new PortObjectSpec[] { inPorts[0].getSpec(), inPorts[1].getSpec() };
    DataTableSpec outSpec = createOutTableSpec(inSpecs);
    BufferedDataContainer outData = exec.createDataContainer(outSpec);
    long coveredPattern = 0;
    long nrPattern = 0;
    long rowCount = 0;
    long numberRows = inData.size();
    exec.setMessage("Classifying...");
    for (DataRow thisRow : inData) {
        DataCell cl = null;
        LinkedHashMap<String, Double> classDistrib = null;
        try {
            Pair<DataCell, LinkedHashMap<DataCell, Double>> pair = decTree.getWinnerAndClasscounts(thisRow, inData.getDataTableSpec());
            cl = pair.getFirst();
            LinkedHashMap<DataCell, Double> classCounts = pair.getSecond();
            classDistrib = getDistribution(classCounts);
            if (coveredPattern < m_maxNumCoveredPattern.getIntValue()) {
                // remember this one for HiLite support
                decTree.addCoveredPattern(thisRow, inData.getDataTableSpec());
                coveredPattern++;
            } else {
                // too many patterns for HiLite - at least remember color
                decTree.addCoveredColor(thisRow, inData.getDataTableSpec());
            }
            nrPattern++;
        } catch (Exception e) {
            LOGGER.error("Decision Tree evaluation failed: " + e.getMessage());
            throw e;
        }
        if (cl == null) {
            LOGGER.error("Decision Tree evaluation failed: result empty");
            throw new Exception("Decision Tree evaluation failed.");
        }
        DataCell[] newCells = new DataCell[outSpec.getNumColumns()];
        int numInCells = thisRow.getNumCells();
        for (int i = 0; i < numInCells; i++) {
            newCells[i] = thisRow.getCell(i);
        }
        if (m_showDistribution.getBooleanValue()) {
            for (int i = numInCells; i < newCells.length - 1; i++) {
                String predClass = outSpec.getColumnSpec(i).getName();
                if (classDistrib != null && classDistrib.get(predClass) != null) {
                    newCells[i] = new DoubleCell(classDistrib.get(predClass));
                } else {
                    newCells[i] = new DoubleCell(0.0);
                }
            }
        }
        newCells[newCells.length - 1] = cl;
        outData.addRowToTable(new DefaultRow(thisRow.getKey(), newCells));
        rowCount++;
        if (rowCount % 100 == 0) {
            exec.setProgress(rowCount / (double) numberRows, "Classifying... Row " + rowCount + " of " + numberRows);
        }
        exec.checkCanceled();
    }
    if (coveredPattern < nrPattern) {
        // let the user know that we did not store all available pattern
        // for HiLiting.
        this.setWarningMessage("Tree only stored first " + m_maxNumCoveredPattern.getIntValue() + " (of " + nrPattern + ") rows for HiLiting!");
    }
    outData.close();
    m_decTree = decTree;
    exec.setMessage("Decision Tree Predictor: end execution.");
    return new BufferedDataTable[] { outData.getTable() };
}

Example 49 with DataRow

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

the class RegressionPredictorNodeModel method configure.

/**
 * {@inheritDoc}
 */
@Override
protected PortObjectSpec[] configure(final PortObjectSpec[] inSpecs) throws InvalidSettingsException {
    PMMLPortObjectSpec regModelSpec = (PMMLPortObjectSpec) inSpecs[0];
    DataTableSpec dataSpec = (DataTableSpec) inSpecs[1];
    if (dataSpec == null || regModelSpec == null) {
        throw new InvalidSettingsException("No input specification available");
    }
    if (regModelSpec.getTargetCols().get(0).getType().isCompatible(DoubleValue.class) && m_settings.getIncludeProbabilities()) {
        setWarningMessage("The option \"Append columns with predicted probabilities\"" + " has only an effect for nominal targets");
    }
    if (null != RegressionPredictorCellFactory.createColumnSpec(regModelSpec, dataSpec, m_settings)) {
        ColumnRearranger c = new ColumnRearranger(dataSpec);
        c.append(new RegressionPredictorCellFactory(regModelSpec, dataSpec, m_settings) {

            @Override
            public DataCell[] getCells(final DataRow row) {
                // not called during configure
                return null;
            }
        });
        DataTableSpec outSpec = c.createSpec();
        return new DataTableSpec[] { outSpec };
    } else {
        return null;
    }
}

Example 50 with DataRow

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

the class BitVectorGeneratorNodeModel method calculateMeanValues.

private double[] calculateMeanValues(final DataTable input) {
    double[] meanValues = new double[input.getDataTableSpec().getNumColumns()];
    int nrOfRows = 0;
    for (DataRow row : input) {
        for (int i = 0; i < row.getNumCells(); i++) {
            if (row.getCell(i).isMissing() || !row.getCell(i).getType().isCompatible(DoubleValue.class)) {
                continue;
            }
            meanValues[i] += ((DoubleValue) row.getCell(i)).getDoubleValue();
        }
        nrOfRows++;
    }
    for (int i = 0; i < meanValues.length; i++) {
        meanValues[i] = meanValues[i] / nrOfRows;
    }
    return meanValues;
}