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

Example 1 with DomainCreatorColumnSelection

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

the class LogRegLearner method recalcDomainForTargetAndLearningFields.

private BufferedDataTable recalcDomainForTargetAndLearningFields(final BufferedDataTable data, final PMMLPortObjectSpec inPMMLSpec, final ExecutionContext exec) throws InvalidSettingsException, CanceledExecutionException {
    final String targetCol = m_pmmlOutSpec.getTargetFields().get(0);
    DataTableDomainCreator domainCreator = new DataTableDomainCreator(data.getDataTableSpec(), new DomainCreatorColumnSelection() {

        @Override
        public boolean dropDomain(final DataColumnSpec colSpec) {
            return false;
        }

        @Override
        public boolean createDomain(final DataColumnSpec colSpec) {
            return colSpec.getName().equals(targetCol) || (colSpec.getType().isCompatible(NominalValue.class) && m_pmmlOutSpec.getLearningFields().contains(colSpec.getName()));
        }
    }, new DomainCreatorColumnSelection() {

        @Override
        public boolean dropDomain(final DataColumnSpec colSpec) {
            // drop domain of numeric learning fields so that we can check for constant columns
            return colSpec.getType().isCompatible(DoubleValue.class) && m_pmmlOutSpec.getLearningFields().contains(colSpec.getName());
        }

        @Override
        public boolean createDomain(final DataColumnSpec colSpec) {
            return colSpec.getType().isCompatible(DoubleValue.class) && m_pmmlOutSpec.getLearningFields().contains(colSpec.getName());
        }
    });
    domainCreator.updateDomain(data, exec);
    DataTableSpec spec = domainCreator.createSpec();
    CheckUtils.checkSetting(spec.getColumnSpec(targetCol).getDomain().hasValues(), "Target column '%s' has too many" + " unique values - consider to use domain calucator node before to enforce calculation", targetCol);
    BufferedDataTable newDataTable = exec.createSpecReplacerTable(data, spec);
    // bug fix 5580 - ignore columns with too many different values
    Set<String> columnWithTooManyDomainValues = new LinkedHashSet<>();
    for (String learningField : m_pmmlOutSpec.getLearningFields()) {
        DataColumnSpec columnSpec = spec.getColumnSpec(learningField);
        if (columnSpec.getType().isCompatible(NominalValue.class) && !columnSpec.getDomain().hasValues()) {
            columnWithTooManyDomainValues.add(learningField);
        }
    }
    if (!columnWithTooManyDomainValues.isEmpty()) {
        StringBuilder warning = new StringBuilder();
        warning.append(columnWithTooManyDomainValues.size() == 1 ? "Column " : "Columns ");
        warning.append(ConvenienceMethods.getShortStringFrom(columnWithTooManyDomainValues, 5));
        warning.append(columnWithTooManyDomainValues.size() == 1 ? " has " : " have ");
        warning.append("too many different values - will be ignored during training ");
        warning.append("(enforce inclusion by using a domain calculator node before)");
        LOGGER.warn(warning.toString());
        m_warningMessage = (m_warningMessage == null ? "" : m_warningMessage + "\n") + warning.toString();
    }
    // initialize m_learner so that it has the correct DataTableSpec of the input
    init(newDataTable.getDataTableSpec(), inPMMLSpec, columnWithTooManyDomainValues);
    return newDataTable;
}

Example 2 with DomainCreatorColumnSelection

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

the class LogRegLearner method recalcDomainForTargetAndLearningFields.

private BufferedDataTable recalcDomainForTargetAndLearningFields(final BufferedDataTable data, final ExecutionContext exec) throws InvalidSettingsException, CanceledExecutionException {
    final String targetCol = m_pmmlOutSpec.getTargetFields().get(0);
    DataTableDomainCreator domainCreator = new DataTableDomainCreator(data.getDataTableSpec(), new DomainCreatorColumnSelection() {

        @Override
        public boolean dropDomain(final DataColumnSpec colSpec) {
            return false;
        }

        @Override
        public boolean createDomain(final DataColumnSpec colSpec) {
            return colSpec.getName().equals(targetCol) || (colSpec.getType().isCompatible(NominalValue.class) && m_pmmlOutSpec.getLearningFields().contains(colSpec.getName()));
        }
    }, new DomainCreatorColumnSelection() {

        @Override
        public boolean dropDomain(final DataColumnSpec colSpec) {
            // drop domain of numeric learning fields so that we can check for constant columns
            return colSpec.getType().isCompatible(DoubleValue.class) && m_pmmlOutSpec.getLearningFields().contains(colSpec.getName());
        }

        @Override
        public boolean createDomain(final DataColumnSpec colSpec) {
            return colSpec.getType().isCompatible(DoubleValue.class) && m_pmmlOutSpec.getLearningFields().contains(colSpec.getName());
        }
    });
    domainCreator.updateDomain(data, exec);
    DataTableSpec spec = domainCreator.createSpec();
    CheckUtils.checkSetting(spec.getColumnSpec(targetCol).getDomain().hasValues(), "Target column '%s' has too many" + " unique values - consider to use domain calucator node before to enforce calculation", targetCol);
    BufferedDataTable newDataTable = exec.createSpecReplacerTable(data, spec);
    // bug fix 5580 - ignore columns with too many different values
    Set<String> columnWithTooManyDomainValues = new LinkedHashSet<>();
    for (String learningField : m_pmmlOutSpec.getLearningFields()) {
        DataColumnSpec columnSpec = spec.getColumnSpec(learningField);
        if (columnSpec.getType().isCompatible(NominalValue.class) && !columnSpec.getDomain().hasValues()) {
            columnWithTooManyDomainValues.add(learningField);
        }
    }
    if (!columnWithTooManyDomainValues.isEmpty()) {
        StringBuilder warning = new StringBuilder();
        warning.append(columnWithTooManyDomainValues.size() == 1 ? "Column " : "Columns ");
        warning.append(ConvenienceMethods.getShortStringFrom(columnWithTooManyDomainValues, 5));
        warning.append(columnWithTooManyDomainValues.size() == 1 ? " has " : " have ");
        warning.append("too many different values - will be ignored during training ");
        warning.append("(enforce inclusion by using a domain calculator node before)");
        LOGGER.warn(warning.toString());
        m_warningMessage = (m_warningMessage == null ? "" : m_warningMessage + "\n") + warning.toString();
    }
    // initialize m_learner so that it has the correct DataTableSpec of the input
    init(newDataTable.getDataTableSpec(), columnWithTooManyDomainValues);
    return newDataTable;
}

Example 3 with DomainCreatorColumnSelection

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

the class DomainNodeModel method getDomainCreator.

private DataTableDomainCreator getDomainCreator(final DataTableSpec inputSpec) {
    final Set<String> possValCols = new HashSet<String>();
    possValCols.addAll(Arrays.asList(m_possValConfig.applyTo(inputSpec).getIncludes()));
    int maxPoss = m_maxPossValues >= 0 ? m_maxPossValues : Integer.MAX_VALUE;
    final Set<String> minMaxCols = new HashSet<String>();
    minMaxCols.addAll(Arrays.asList(m_minMaxConfig.applyTo(inputSpec).getIncludes()));
    DomainCreatorColumnSelection possValueSelection = new DomainCreatorColumnSelection() {

        @Override
        public boolean createDomain(final DataColumnSpec colSpec) {
            return possValCols.contains(colSpec.getName());
        }

        @Override
        public boolean dropDomain(final DataColumnSpec colSpec) {
            return possValCols.contains(colSpec.getName()) || !m_possValRetainUnselected;
        }
    };
    DomainCreatorColumnSelection minMaxSelection = new DomainCreatorColumnSelection() {

        @Override
        public boolean createDomain(final DataColumnSpec colSpec) {
            return minMaxCols.contains(colSpec.getName());
        }

        @Override
        public boolean dropDomain(final DataColumnSpec colSpec) {
            return minMaxCols.contains(colSpec.getName()) || !m_minMaxRetainUnselected;
        }
    };
    DataTableDomainCreator domainCreator = new DataTableDomainCreator(inputSpec, possValueSelection, minMaxSelection);
    domainCreator.setMaxPossibleValues(maxPoss);
    return domainCreator;
}

Example 4 with DomainCreatorColumnSelection

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

the class DomainNodeModel method getDomainCreator.

private DataTableDomainCreator getDomainCreator(final DataTableSpec inputSpec) {
    final Set<String> possValCols = new HashSet<String>();
    possValCols.addAll(Arrays.asList(m_possValCols));
    int maxPoss = m_maxPossValues >= 0 ? m_maxPossValues : Integer.MAX_VALUE;
    final Set<String> minMaxCols = new HashSet<String>();
    minMaxCols.addAll(Arrays.asList(m_minMaxCols));
    DomainCreatorColumnSelection possValueSelection = new DomainCreatorColumnSelection() {

        @Override
        public boolean createDomain(final DataColumnSpec colSpec) {
            return possValCols.contains(colSpec.getName());
        }

        @Override
        public boolean dropDomain(final DataColumnSpec colSpec) {
            return possValCols.contains(colSpec.getName()) || !m_possValRetainUnselected;
        }
    };
    DomainCreatorColumnSelection minMaxSelection = new DomainCreatorColumnSelection() {

        @Override
        public boolean createDomain(final DataColumnSpec colSpec) {
            return minMaxCols.contains(colSpec.getName());
        }

        @Override
        public boolean dropDomain(final DataColumnSpec colSpec) {
            return minMaxCols.contains(colSpec.getName()) || !m_minMaxRetainUnselected;
        }
    };
    DataTableDomainCreator domainCreator = new DataTableDomainCreator(inputSpec, possValueSelection, minMaxSelection);
    domainCreator.setMaxPossibleValues(maxPoss);
    return domainCreator;
}

Example 5 with DomainCreatorColumnSelection

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

the class LogRegCoordinator method recalcDomainForTargetAndLearningFields.

private BufferedDataTable recalcDomainForTargetAndLearningFields(final BufferedDataTable data, final ExecutionContext exec) throws InvalidSettingsException, CanceledExecutionException {
    final String targetCol = m_pmmlOutSpec.getTargetFields().get(0);
    DataTableDomainCreator domainCreator = new DataTableDomainCreator(data.getDataTableSpec(), new DomainCreatorColumnSelection() {

        @Override
        public boolean dropDomain(final DataColumnSpec colSpec) {
            return false;
        }

        @Override
        public boolean createDomain(final DataColumnSpec colSpec) {
            return colSpec.getName().equals(targetCol) || (colSpec.getType().isCompatible(NominalValue.class) && m_pmmlOutSpec.getLearningFields().contains(colSpec.getName()));
        }
    }, new DomainCreatorColumnSelection() {

        @Override
        public boolean dropDomain(final DataColumnSpec colSpec) {
            // drop domain of numeric learning fields so that we can check for constant columns
            return colSpec.getType().isCompatible(DoubleValue.class) && m_pmmlOutSpec.getLearningFields().contains(colSpec.getName());
        }

        @Override
        public boolean createDomain(final DataColumnSpec colSpec) {
            return colSpec.getType().isCompatible(DoubleValue.class) && m_pmmlOutSpec.getLearningFields().contains(colSpec.getName());
        }
    });
    domainCreator.updateDomain(data, exec);
    DataTableSpec spec = domainCreator.createSpec();
    CheckUtils.checkSetting(spec.getColumnSpec(targetCol).getDomain().hasValues(), "Target column '%s' has too many" + " unique values - consider to use domain calucator node before to enforce calculation", targetCol);
    BufferedDataTable newDataTable = exec.createSpecReplacerTable(data, spec);
    // bug fix 5580 - ignore columns with too many different values
    Set<String> columnWithTooManyDomainValues = new LinkedHashSet<>();
    for (String learningField : m_pmmlOutSpec.getLearningFields()) {
        DataColumnSpec columnSpec = spec.getColumnSpec(learningField);
        if (columnSpec.getType().isCompatible(NominalValue.class) && !columnSpec.getDomain().hasValues()) {
            columnWithTooManyDomainValues.add(learningField);
        }
    }
    if (!columnWithTooManyDomainValues.isEmpty()) {
        StringBuilder warning = new StringBuilder();
        warning.append(columnWithTooManyDomainValues.size() == 1 ? "Column " : "Columns ");
        warning.append(ConvenienceMethods.getShortStringFrom(columnWithTooManyDomainValues, 5));
        warning.append(columnWithTooManyDomainValues.size() == 1 ? " has " : " have ");
        warning.append("too many different values - will be ignored during training ");
        warning.append("(enforce inclusion by using a domain calculator node before)");
        // LOGGER.warn(warning.toString());
        m_warning = (m_warning == null ? "" : m_warning + "\n") + warning.toString();
    }
    // initialize m_learner so that it has the correct DataTableSpec of the input
    init(newDataTable.getDataTableSpec(), columnWithTooManyDomainValues);
    return newDataTable;
}