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

Example 56 with DataColumnSpec

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

the class NaiveBayesCellFactory method createResultColSpecs.

/**
 * Creates the column specification of the result columns and returns
 * them in the order they should be appended to the original table
 * specification.
 * @param classColumn the class column spec
 * @param inSpec the <code>DataTableSpec</code> of the input data to check
 * if the winner column name already exists
 * @param inclClassProbVals if the probability values should be displayed
 * @return <code>DataColumnSpec[]</code> with the column specifications
 * of the result columns
 */
public static DataColumnSpec createResultColSpecs(final DataColumnSpec classColumn, final DataTableSpec inSpec, final boolean inclClassProbVals) {
    if (inclClassProbVals) {
        return null;
    }
    final String colName = DataTableSpec.getUniqueColumnName(inSpec, WINNER_COLUMN_NAME);
    final DataColumnSpecCreator colSpecCreator = new DataColumnSpecCreator(colName, classColumn.getType());
    final DataColumnSpec classColSpec = colSpecCreator.createSpec();
    return classColSpec;
}

Example 57 with DataColumnSpec

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

the class DecTreePredictorNodeModel method getPredictionValues.

private LinkedList<DataCell> getPredictionValues(final PMMLPortObjectSpec treeSpec) {
    String targetCol = treeSpec.getTargetFields().get(0);
    DataColumnSpec colSpec = treeSpec.getDataTableSpec().getColumnSpec(targetCol);
    if (colSpec.getDomain().hasValues()) {
        LinkedList<DataCell> predValues = new LinkedList<DataCell>();
        predValues.addAll(colSpec.getDomain().getValues());
        return predValues;
    } else {
        return null;
    }
}

Example 58 with DataColumnSpec

use of org.knime.core.data.DataColumnSpec 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 59 with DataColumnSpec

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

the class DecTreePredictorNodeModel method createOutTableSpec.

private DataTableSpec createOutTableSpec(final PortObjectSpec[] inSpecs) {
    LinkedList<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];
    UniqueNameGenerator nameGenerator = new UniqueNameGenerator(inSpec);
    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();
    // add all distribution columns
    for (int i = 0; i < numCols - 1; i++) {
        DataColumnSpecCreator colSpecCreator = nameGenerator.newCreator(predValues.get(i).toString(), DoubleCell.TYPE);
        // colSpecCreator.setProperties(propsRendering);
        colSpecCreator.setDomain(domain);
        newCols[i] = colSpecCreator.createSpec();
    }
    // add the prediction column
    newCols[numCols - 1] = nameGenerator.newColumn("Prediction (DecTree)", StringCell.TYPE);
    DataTableSpec newColSpec = new DataTableSpec(newCols);
    return new DataTableSpec(inSpec, newColSpec);
}

Example 60 with DataColumnSpec

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

the class MLPPredictorNodeModel method configure.

/**
 * The additional columns are created based on the model which is loaded in
 * the execute-method. Therefore, new DataTableSpecs are not available until
 * execute has been called.
 *
 * {@inheritDoc}
 */
@Override
protected PortObjectSpec[] configure(final PortObjectSpec[] inSpecs) throws InvalidSettingsException {
    PMMLPortObjectSpec modelspec = (PMMLPortObjectSpec) inSpecs[0];
    DataTableSpec testSpec = (DataTableSpec) inSpecs[1];
    List<DataColumnSpec> targetCols = modelspec.getTargetCols();
    if (targetCols.isEmpty()) {
        throw new InvalidSettingsException("The PMML model" + " does not specify a target column for the prediction.");
    }
    DataColumnSpec targetCol = targetCols.iterator().next();
    /*
         * Check consistency between model and inputs, find columns to work on.
         */
    for (String incol : modelspec.getLearningFields()) {
        if (!testSpec.containsName(incol)) {
            throw new InvalidSettingsException("Could not find " + incol + " in inputspec");
        }
    }
    m_columns = getLearningColumnIndices(testSpec, modelspec);
    MLPClassificationFactory mymlp;
    // Regression
    if (targetCol.getType().isCompatible(DoubleValue.class)) {
        mymlp = new MLPClassificationFactory(true, m_columns, targetCol);
    } else {
        // Classification
        mymlp = new MLPClassificationFactory(false, m_columns, targetCol);
    }
    ColumnRearranger colre = new ColumnRearranger(testSpec);
    colre.append(mymlp);
    return new DataTableSpec[] { colre.createSpec() };
}