use of org.knime.base.node.mine.treeensemble.data.PredictorRecord in project knime-core by knime.
the class RegressionTreeModel method createNominalNumericPredictorRecord.
private PredictorRecord createNominalNumericPredictorRecord(final DataRow filterRow, final DataTableSpec trainSpec) {
final int nrCols = trainSpec.getNumColumns();
Map<String, Object> valueMap = new LinkedHashMap<String, Object>((int) (nrCols / 0.75 + 1.0));
for (int i = 0; i < nrCols; i++) {
DataColumnSpec col = trainSpec.getColumnSpec(i);
String colName = col.getName();
DataType colType = col.getType();
DataCell cell = filterRow.getCell(i);
if (cell.isMissing()) {
valueMap.put(colName, PredictorRecord.NULL);
} else if (colType.isCompatible(NominalValue.class)) {
valueMap.put(colName, cell.toString());
} else if (colType.isCompatible(DoubleValue.class)) {
valueMap.put(colName, ((DoubleValue) cell).getDoubleValue());
} else {
throw new IllegalStateException("Expected nominal or numeric column type for column \"" + colName + "\" but got \"" + colType + "\"");
}
}
return new PredictorRecord(valueMap);
}
use of org.knime.base.node.mine.treeensemble.data.PredictorRecord 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;
}
OccurrenceCounter<String> counter = new OccurrenceCounter<String>();
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);
String majorityClassName = match.getMajorityClassName();
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);
if (appendConfidence) {
final int freqValue = counter.getFrequency(bestValue);
result[index++] = new DoubleCell(freqValue / (double) nrValidModels);
}
if (appendClassConfidences) {
for (String key : m_targetValueMap.keySet()) {
int frequency = counter.getFrequency(key);
double ratio = frequency / (double) nrValidModels;
result[index++] = new DoubleCell(ratio);
}
}
}
if (appendModelCount) {
result[index++] = new IntCell(nrValidModels);
}
return result;
}
use of org.knime.base.node.mine.treeensemble.data.PredictorRecord in project knime-core by knime.
the class RegressionTreePredictorCellFactory method getCells.
/**
* {@inheritDoc}
*/
@Override
public DataCell[] getCells(final DataRow row) {
RegressionTreeModelPortObject modelObject = m_predictor.getModelObject();
final RegressionTreeModel treeModel = modelObject.getModel();
int size = 1;
DataCell[] result = new DataCell[size];
DataRow filterRow = new FilterColumnRow(row, m_learnColumnInRealDataIndices);
PredictorRecord record = treeModel.createPredictorRecord(filterRow, m_learnSpec);
if (record == null) {
// missing value
Arrays.fill(result, DataType.getMissingCell());
return result;
}
TreeModelRegression tree = treeModel.getTreeModel();
TreeNodeRegression match = tree.findMatchingNode(record);
double nodeMean = match.getMean();
result[0] = new DoubleCell(nodeMean);
return result;
}
use of org.knime.base.node.mine.treeensemble.data.PredictorRecord in project knime-core by knime.
the class RegressionTreeModel method createBitVectorPredictorRecord.
private PredictorRecord createBitVectorPredictorRecord(final DataRow filterRow) {
assert filterRow.getNumCells() == 1 : "Expected one cell as bit vector data";
DataCell c = filterRow.getCell(0);
if (c.isMissing()) {
return null;
}
BitVectorValue bv = (BitVectorValue) c;
final long length = bv.length();
if (length != getMetaData().getNrAttributes()) {
throw new IllegalArgumentException("The bit-vector in " + filterRow.getKey().getString() + " has an invalid length (" + length + " instead of " + getMetaData().getNrAttributes() + ").");
}
Map<String, Object> valueMap = new LinkedHashMap<String, Object>((int) (length / 0.75 + 1.0));
for (int i = 0; i < length; i++) {
valueMap.put(TreeBitColumnMetaData.getAttributeName(i), Boolean.valueOf(bv.get(i)));
}
return new PredictorRecord(valueMap);
}
use of org.knime.base.node.mine.treeensemble.data.PredictorRecord in project knime-core by knime.
the class RegressionTreeModel method createByteVectorPredictorRecord.
private PredictorRecord createByteVectorPredictorRecord(final DataRow filterRow) {
assert filterRow.getNumCells() == 1 : "Expected one cell as byte vector data";
DataCell c = filterRow.getCell(0);
if (c.isMissing()) {
return null;
}
ByteVectorValue bv = (ByteVectorValue) c;
final long length = bv.length();
if (length != getMetaData().getNrAttributes()) {
throw new IllegalArgumentException("The byte-vector in " + filterRow.getKey().getString() + " has an invalid length (" + length + " instead of " + getMetaData().getNrAttributes() + ").");
}
Map<String, Object> valueMap = new LinkedHashMap<String, Object>((int) (length / 0.75 + 1.0));
for (int i = 0; i < length; i++) {
valueMap.put(TreeNumericColumnMetaData.getAttributeName(i), Integer.valueOf(bv.get(i)));
}
return new PredictorRecord(valueMap);
}
Aggregations