Examples with PMMLPortObjectSpecCreator org.knime.core.node.port.pmml.PMMLPortObjectSpecCreator used on opensource projects

Example 6 with PMMLPortObjectSpecCreator

use of org.knime.core.node.port.pmml.PMMLPortObjectSpecCreator in project knime-core by knime.

the class LogRegLearner method init.

/**
 * Initialize instance and check if settings are consistent.
 */
private void init(final DataTableSpec inSpec, final PMMLPortObjectSpec pmmlSpec, final Set<String> exclude) throws InvalidSettingsException {
    List<String> inputCols = new ArrayList<String>();
    for (DataColumnSpec column : inSpec) {
        inputCols.add(column.getName());
    }
    if (!m_settings.getIncludeAll()) {
        List<String> included = Arrays.asList(m_settings.getIncludedColumns());
        if (!inputCols.containsAll(included)) {
            LOGGER.warn("Input does not contain all learning columns. " + "Proceed with the remaining learning columns.");
        }
        inputCols.retainAll(included);
    }
    inputCols.remove(m_settings.getTargetColumn());
    if (inputCols.isEmpty()) {
        throw new InvalidSettingsException("At least one column must " + "be included.");
    }
    DataColumnSpec targetColSpec = null;
    List<DataColumnSpec> regressorColSpecs = new ArrayList<DataColumnSpec>();
    // Auto configuration when target is not set
    if (null == m_settings.getTargetColumn() && m_settings.getIncludeAll()) {
        for (int i = 0; i < inSpec.getNumColumns(); i++) {
            DataColumnSpec colSpec = inSpec.getColumnSpec(i);
            String colName = colSpec.getName();
            inputCols.remove(colName);
            if (colSpec.getType().isCompatible(NominalValue.class)) {
                m_settings.setTargetColumn(colName);
            }
        }
        // when there is no column with nominal data
        if (null == m_settings.getTargetColumn()) {
            throw new InvalidSettingsException("No column in " + "spec compatible to \"NominalValue\".");
        }
    }
    // remove all columns that should not be used
    inputCols.removeAll(exclude);
    for (int i = 0; i < inSpec.getNumColumns(); i++) {
        DataColumnSpec colSpec = inSpec.getColumnSpec(i);
        String colName = colSpec.getName();
        if (m_settings.getTargetColumn().equals(colName)) {
            if (colSpec.getType().isCompatible(NominalValue.class)) {
                targetColSpec = colSpec;
            } else {
                throw new InvalidSettingsException("Type of column \"" + colName + "\" is not nominal.");
            }
        } else if (inputCols.contains(colName)) {
            if (colSpec.getType().isCompatible(DoubleValue.class) || colSpec.getType().isCompatible(NominalValue.class)) {
                regressorColSpecs.add(colSpec);
            } else {
                throw new InvalidSettingsException("Type of column \"" + colName + "\" is not one of the allowed types, " + "which are numeric or nomial.");
            }
        }
    }
    if (null != targetColSpec) {
        // Check if target has at least two categories.
        final Set<DataCell> targetValues = targetColSpec.getDomain().getValues();
        if (targetValues != null && targetValues.size() < 2) {
            throw new InvalidSettingsException("The target column \"" + targetColSpec.getName() + "\" has one value, only. " + "At least two target categories are expected.");
        }
        String[] learnerCols = new String[regressorColSpecs.size() + 1];
        for (int i = 0; i < regressorColSpecs.size(); i++) {
            learnerCols[i] = regressorColSpecs.get(i).getName();
        }
        learnerCols[learnerCols.length - 1] = targetColSpec.getName();
        PMMLPortObjectSpecCreator creator = new PMMLPortObjectSpecCreator(pmmlSpec, inSpec);
        creator.setTargetCols(Arrays.asList(targetColSpec));
        creator.setLearningCols(regressorColSpecs);
        m_pmmlOutSpec = creator.createSpec();
        m_learner = new Learner(m_pmmlOutSpec, m_settings.getTargetReferenceCategory(), m_settings.getSortTargetCategories(), m_settings.getSortIncludesCategories());
    } else {
        throw new InvalidSettingsException("The target is " + "not in the input.");
    }
}

Example 7 with PMMLPortObjectSpecCreator

use of org.knime.core.node.port.pmml.PMMLPortObjectSpecCreator in project knime-core by knime.

the class LogRegLearnerNodeModel method execute.

/**
 * {@inheritDoc}
 */
@Override
protected PortObject[] execute(final PortObject[] inObjects, final ExecutionContext exec) throws Exception {
    final BufferedDataTable data = (BufferedDataTable) inObjects[0];
    DataTableSpec tableSpec = data.getDataTableSpec();
    // handle the optional PMML input
    PMMLPortObject inPMMLPort = m_pmmlInEnabled ? (PMMLPortObject) inObjects[1] : null;
    PMMLPortObjectSpec inPMMLSpec = null;
    if (inPMMLPort != null) {
        inPMMLSpec = inPMMLPort.getSpec();
    } else {
        PMMLPortObjectSpecCreator creator = new PMMLPortObjectSpecCreator(tableSpec);
        inPMMLSpec = creator.createSpec();
        inPMMLPort = new PMMLPortObject(inPMMLSpec);
    }
    LogRegLearner learner = new LogRegLearner(new PortObjectSpec[] { tableSpec, inPMMLSpec }, m_pmmlInEnabled, m_settings);
    m_content = learner.execute(new PortObject[] { data, inPMMLPort }, exec);
    String warn = learner.getWarningMessage();
    if (warn != null) {
        setWarningMessage(warn);
    }
    // third argument is ignored since we provide a port
    PMMLPortObject outPMMLPort = new PMMLPortObject((PMMLPortObjectSpec) learner.getOutputSpec()[0], inPMMLPort, null);
    PMMLGeneralRegressionTranslator trans = new PMMLGeneralRegressionTranslator(m_content.createGeneralRegressionContent());
    outPMMLPort.addModelTranslater(trans);
    return new PortObject[] { outPMMLPort, m_content.createTablePortObject(exec) };
}

Example 8 with PMMLPortObjectSpecCreator

use of org.knime.core.node.port.pmml.PMMLPortObjectSpecCreator in project knime-core by knime.

the class LogisticRegressionContent method createSpec.

private static PMMLPortObjectSpec createSpec(final DataTableSpec spec, final String target, final String[] learningCols) {
    PMMLPortObjectSpecCreator c = new PMMLPortObjectSpecCreator(spec);
    c.setTargetColName(target);
    c.setLearningColsNames(Arrays.asList(learningCols));
    return c.createSpec();
}

Example 9 with PMMLPortObjectSpecCreator

use of org.knime.core.node.port.pmml.PMMLPortObjectSpecCreator in project knime-core by knime.

the class PolyRegLearnerNodeModel method createModelSpec.

private PMMLPortObjectSpec createModelSpec(final PMMLPortObjectSpec inModelSpec, final DataTableSpec inDataSpec) throws InvalidSettingsException {
    String[] selectedCols = computeSelectedColumns(inDataSpec);
    DataColumnSpec[] usedColumns = new DataColumnSpec[selectedCols.length + 1];
    int k = 0;
    Set<String> hash = new HashSet<String>(Arrays.asList(selectedCols));
    for (DataColumnSpec dcs : inDataSpec) {
        if (hash.contains(dcs.getName())) {
            usedColumns[k++] = dcs;
        }
    }
    usedColumns[k++] = inDataSpec.getColumnSpec(m_settings.getTargetColumn());
    DataTableSpec tableSpec = new DataTableSpec(usedColumns);
    PMMLPortObjectSpecCreator crea = new PMMLPortObjectSpecCreator(inModelSpec, inDataSpec);
    crea.setLearningCols(tableSpec);
    crea.setTargetCol(usedColumns[k - 1]);
    return crea.createSpec();
}

Example 10 with PMMLPortObjectSpecCreator

use of org.knime.core.node.port.pmml.PMMLPortObjectSpecCreator in project knime-core by knime.

the class AbstractTreeModelExporter method reduceSpec.

/**
 * Recursively goes through the tree and only keeps those learning cols that are actually used
 * by the model.
 * The target is always retained since we currently need to be able to set a target in segmentations
 * (this could change if we update to PMML 4.3).
 *
 * @param pmmlSpec the full spec
 * @return a spec that only contains those learn columns that actually appear in the model
 */
private PMMLPortObjectSpec reduceSpec(final PMMLPortObjectSpec pmmlSpec) {
    assert m_treeModel != null;
    PMMLPortObjectSpecCreator creator = new PMMLPortObjectSpecCreator(pmmlSpec);
    Set<String> usedFields = new HashSet<>();
    recursivelyCheckUsedFields(m_treeModel.getRootNode(), pmmlSpec.getLearningFields().size(), usedFields);
    creator.setLearningCols(pmmlSpec.getLearningCols().stream().filter(s -> usedFields.contains(s.getName())).collect(Collectors.toList()));
    return creator.createSpec();
}