Examples with TreeTargetNominalColumnMetaData org.knime.base.node.mine.treeensemble2.data.TreeTargetNominalColumnMetaData used on opensource projects

Example 1 with TreeTargetNominalColumnMetaData

use of org.knime.base.node.mine.treeensemble2.data.TreeTargetNominalColumnMetaData in project knime-core by knime.

the class TreeEnsembleClassificationPredictorCellFactory method getCells.

/**
 * {@inheritDoc}
 */
@Override
public DataCell[] getCells(final DataRow row) {
    TreeEnsembleModelPortObject modelObject = m_predictor.getModelObject();
    TreeEnsemblePredictorConfiguration cfg = m_predictor.getConfiguration();
    final TreeEnsembleModel ensembleModel = modelObject.getEnsembleModel();
    int size = 1;
    final boolean appendConfidence = cfg.isAppendPredictionConfidence();
    if (appendConfidence) {
        size += 1;
    }
    final boolean appendClassConfidences = cfg.isAppendClassConfidences();
    if (appendClassConfidences) {
        size += m_targetValueMap.size();
    }
    final boolean appendModelCount = cfg.isAppendModelCount();
    if (appendModelCount) {
        size += 1;
    }
    final boolean hasOutOfBagFilter = m_predictor.hasOutOfBagFilter();
    DataCell[] result = new DataCell[size];
    DataRow filterRow = new FilterColumnRow(row, m_learnColumnInRealDataIndices);
    PredictorRecord record = ensembleModel.createPredictorRecord(filterRow, m_learnSpec);
    if (record == null) {
        // missing value
        Arrays.fill(result, DataType.getMissingCell());
        return result;
    }
    final Voting voting = m_votingFactory.createVoting();
    final int nrModels = ensembleModel.getNrModels();
    int nrValidModels = 0;
    for (int i = 0; i < nrModels; i++) {
        if (hasOutOfBagFilter && m_predictor.isRowPartOfTrainingData(row.getKey(), i)) {
        // ignore, row was used to train the model
        } else {
            TreeModelClassification m = ensembleModel.getTreeModelClassification(i);
            TreeNodeClassification match = m.findMatchingNode(record);
            voting.addVote(match);
            nrValidModels += 1;
        }
    }
    final NominalValueRepresentation[] targetVals = ((TreeTargetNominalColumnMetaData) ensembleModel.getMetaData().getTargetMetaData()).getValues();
    String majorityClass = voting.getMajorityClass();
    int index = 0;
    if (majorityClass == null) {
        assert nrValidModels == 0;
        Arrays.fill(result, DataType.getMissingCell());
        index = size - 1;
    } else {
        result[index++] = m_targetValueMap.get(majorityClass);
        // final float[] distribution = voting.getClassProbabilities();
        if (appendConfidence) {
            result[index++] = new DoubleCell(voting.getClassProbabilityForClass(majorityClass));
        }
        if (appendClassConfidences) {
            for (String targetValue : m_targetValueMap.keySet()) {
                result[index++] = new DoubleCell(voting.getClassProbabilityForClass(targetValue));
            }
        }
    }
    if (appendModelCount) {
        result[index++] = new IntCell(voting.getNrVotes());
    }
    return result;
}

Example 2 with TreeTargetNominalColumnMetaData

use of org.knime.base.node.mine.treeensemble2.data.TreeTargetNominalColumnMetaData in project knime-core by knime.

the class TreeEnsembleClassificationPredictorCellFactory2 method getCells.

/**
 * {@inheritDoc}
 */
@Override
public DataCell[] getCells(final DataRow row) {
    TreeEnsembleModelPortObject modelObject = m_predictor.getModelObject();
    TreeEnsemblePredictorConfiguration cfg = m_predictor.getConfiguration();
    final TreeEnsembleModel ensembleModel = modelObject.getEnsembleModel();
    int size = 1;
    final boolean appendConfidence = cfg.isAppendPredictionConfidence();
    if (appendConfidence) {
        size += 1;
    }
    final boolean appendClassConfidences = cfg.isAppendClassConfidences();
    if (appendClassConfidences) {
        size += m_targetValueMap.size();
    }
    final boolean appendModelCount = cfg.isAppendModelCount();
    if (appendModelCount) {
        size += 1;
    }
    final boolean hasOutOfBagFilter = m_predictor.hasOutOfBagFilter();
    DataCell[] result = new DataCell[size];
    DataRow filterRow = new FilterColumnRow(row, m_learnColumnInRealDataIndices);
    PredictorRecord record = ensembleModel.createPredictorRecord(filterRow, m_learnSpec);
    if (record == null) {
        // missing value
        Arrays.fill(result, DataType.getMissingCell());
        return result;
    }
    OccurrenceCounter<String> counter = new OccurrenceCounter<String>();
    final int nrModels = ensembleModel.getNrModels();
    TreeTargetNominalColumnMetaData targetMeta = (TreeTargetNominalColumnMetaData) ensembleModel.getMetaData().getTargetMetaData();
    final double[] classProbabilities = new double[targetMeta.getValues().length];
    int nrValidModels = 0;
    for (int i = 0; i < nrModels; i++) {
        if (hasOutOfBagFilter && m_predictor.isRowPartOfTrainingData(row.getKey(), i)) {
        // ignore, row was used to train the model
        } else {
            TreeModelClassification m = ensembleModel.getTreeModelClassification(i);
            TreeNodeClassification match = m.findMatchingNode(record);
            String majorityClassName = match.getMajorityClassName();
            final float[] nodeClassProbs = match.getTargetDistribution();
            double instancesInNode = 0;
            for (int c = 0; c < nodeClassProbs.length; c++) {
                instancesInNode += nodeClassProbs[c];
            }
            for (int c = 0; c < classProbabilities.length; c++) {
                classProbabilities[c] += nodeClassProbs[c] / instancesInNode;
            }
            counter.add(majorityClassName);
            nrValidModels += 1;
        }
    }
    String bestValue = counter.getMostFrequent();
    int index = 0;
    if (bestValue == null) {
        assert nrValidModels == 0;
        Arrays.fill(result, DataType.getMissingCell());
        index = size - 1;
    } else {
        // result[index++] = m_targetValueMap.get(bestValue);
        int indexBest = -1;
        double probBest = -1;
        for (int c = 0; c < classProbabilities.length; c++) {
            double prob = classProbabilities[c];
            if (prob > probBest) {
                probBest = prob;
                indexBest = c;
            }
        }
        result[index++] = new StringCell(targetMeta.getValues()[indexBest].getNominalValue());
        if (appendConfidence) {
            // final int freqValue = counter.getFrequency(bestValue);
            // result[index++] = new DoubleCell(freqValue / (double)nrValidModels);
            result[index++] = new DoubleCell(probBest);
        }
        if (appendClassConfidences) {
            for (NominalValueRepresentation nomVal : targetMeta.getValues()) {
                double prob = classProbabilities[nomVal.getAssignedInteger()] / nrValidModels;
                result[index++] = new DoubleCell(prob);
            }
        }
    }
    if (appendModelCount) {
        result[index++] = new IntCell(nrValidModels);
    }
    return result;
}

Example 3 with TreeTargetNominalColumnMetaData

use of org.knime.base.node.mine.treeensemble2.data.TreeTargetNominalColumnMetaData in project knime-core by knime.

the class NominalTargetColumnHelper method createMetaData.

/**
 * {@inheritDoc}
 */
@Override
protected TreeTargetNominalColumnMetaData createMetaData(final DataColumnSpec nominalColSpec) {
    DataColumnDomain domain = nominalColSpec.getDomain();
    CheckUtils.checkArgument(domain.hasValues(), "The target field \"%s\" in the data dictionary has no possible values assigned.", nominalColSpec);
    NominalValueRepresentation[] nomVals = NominalColumnHelperUtil.extractNomValReps(domain.getValues());
    return new TreeTargetNominalColumnMetaData(nominalColSpec.getName(), nomVals);
}