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

Example 6 with ClassificationPriors

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

the class TreeBitVectorColumnData method calcBestSplitClassification.

/**
 * {@inheritDoc}
 */
@Override
public SplitCandidate calcBestSplitClassification(final DataMemberships dataMemberships, final ClassificationPriors targetPriors, final TreeTargetNominalColumnData targetColumn, final RandomData rd) {
    final NominalValueRepresentation[] targetVals = targetColumn.getMetaData().getValues();
    final IImpurity impurityCriterion = targetPriors.getImpurityCriterion();
    final int minChildSize = getConfiguration().getMinChildSize();
    // distribution of target for On ('1') and Off ('0') bits
    final double[] onTargetWeights = new double[targetVals.length];
    final double[] offTargetWeights = new double[targetVals.length];
    double onWeights = 0.0;
    double offWeights = 0.0;
    final ColumnMemberships columnMemberships = dataMemberships.getColumnMemberships(getMetaData().getAttributeIndex());
    while (columnMemberships.next()) {
        final double weight = columnMemberships.getRowWeight();
        if (weight < EPSILON) {
            // ignore record: not in current branch or not in sample
            assert false : "This code should never be reached!";
        } else {
            final int target = targetColumn.getValueFor(columnMemberships.getOriginalIndex());
            if (m_columnBitSet.get(columnMemberships.getIndexInColumn())) {
                onWeights += weight;
                onTargetWeights[target] += weight;
            } else {
                offWeights += weight;
                offTargetWeights[target] += weight;
            }
        }
    }
    if (onWeights < minChildSize || offWeights < minChildSize) {
        return null;
    }
    final double weightSum = onWeights + offWeights;
    final double onImpurity = impurityCriterion.getPartitionImpurity(onTargetWeights, onWeights);
    final double offImpurity = impurityCriterion.getPartitionImpurity(offTargetWeights, offWeights);
    final double[] partitionWeights = new double[] { onWeights, offWeights };
    final double postSplitImpurity = impurityCriterion.getPostSplitImpurity(new double[] { onImpurity, offImpurity }, partitionWeights, weightSum);
    final double gainValue = impurityCriterion.getGain(targetPriors.getPriorImpurity(), postSplitImpurity, partitionWeights, weightSum);
    return new BitSplitCandidate(this, gainValue);
}

Example 7 with ClassificationPriors

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

the class TreeLearnerClassification method findBestSplitClassification.

private SplitCandidate findBestSplitClassification(final int currentDepth, final DataMemberships dataMemberships, final ColumnSample columnSample, final TreeNodeSignature treeNodeSignature, final ClassificationPriors targetPriors, final BitSet forbiddenColumnSet) {
    final TreeData data = getData();
    final RandomData rd = getRandomData();
    // final ColumnSampleStrategy colSamplingStrategy = getColSamplingStrategy();
    final TreeEnsembleLearnerConfiguration config = getConfig();
    final int maxLevels = config.getMaxLevels();
    if (maxLevels != TreeEnsembleLearnerConfiguration.MAX_LEVEL_INFINITE && currentDepth >= maxLevels) {
        return null;
    }
    final int minNodeSize = config.getMinNodeSize();
    if (minNodeSize != TreeEnsembleLearnerConfiguration.MIN_NODE_SIZE_UNDEFINED) {
        if (targetPriors.getNrRecords() < minNodeSize) {
            return null;
        }
    }
    final double priorImpurity = targetPriors.getPriorImpurity();
    if (priorImpurity < TreeColumnData.EPSILON) {
        return null;
    }
    final TreeTargetNominalColumnData targetColumn = (TreeTargetNominalColumnData) data.getTargetColumn();
    SplitCandidate splitCandidate = null;
    if (currentDepth == 0 && config.getHardCodedRootColumn() != null) {
        final TreeAttributeColumnData rootColumn = data.getColumn(config.getHardCodedRootColumn());
        // TODO discuss whether this option makes sense with surrogates
        return rootColumn.calcBestSplitClassification(dataMemberships, targetPriors, targetColumn, rd);
    }
    double bestGainValue = 0.0;
    for (TreeAttributeColumnData col : columnSample) {
        if (forbiddenColumnSet.get(col.getMetaData().getAttributeIndex())) {
            continue;
        }
        final SplitCandidate currentColSplit = col.calcBestSplitClassification(dataMemberships, targetPriors, targetColumn, rd);
        if (currentColSplit != null) {
            final double currentGain = currentColSplit.getGainValue();
            final boolean tiebreaker = currentGain == bestGainValue ? (rd.nextInt(0, 1) == 0) : false;
            if (currentColSplit.getGainValue() > bestGainValue || tiebreaker) {
                splitCandidate = currentColSplit;
                bestGainValue = currentGain;
            }
        }
    }
    return splitCandidate;
}

Example 8 with ClassificationPriors

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

the class TreeLearnerClassification method findBestSplitsClassification.

/**
 * Returns a list of SplitCandidates sorted (descending) by their gain
 *
 * @param currentDepth
 * @param rowSampleWeights
 * @param treeNodeSignature
 * @param targetPriors
 * @param forbiddenColumnSet
 * @param membershipController
 * @return
 */
private SplitCandidate[] findBestSplitsClassification(final int currentDepth, final DataMemberships dataMemberships, final ColumnSample columnSample, final TreeNodeSignature treeNodeSignature, final ClassificationPriors targetPriors, final BitSet forbiddenColumnSet) {
    final TreeData data = getData();
    final RandomData rd = getRandomData();
    // final ColumnSampleStrategy colSamplingStrategy = getColSamplingStrategy();
    final TreeEnsembleLearnerConfiguration config = getConfig();
    final int maxLevels = config.getMaxLevels();
    if (maxLevels != TreeEnsembleLearnerConfiguration.MAX_LEVEL_INFINITE && currentDepth >= maxLevels) {
        return null;
    }
    final int minNodeSize = config.getMinNodeSize();
    if (minNodeSize != TreeEnsembleLearnerConfiguration.MIN_NODE_SIZE_UNDEFINED) {
        if (targetPriors.getNrRecords() < minNodeSize) {
            return null;
        }
    }
    final double priorImpurity = targetPriors.getPriorImpurity();
    if (priorImpurity < TreeColumnData.EPSILON) {
        return null;
    }
    final TreeTargetNominalColumnData targetColumn = (TreeTargetNominalColumnData) data.getTargetColumn();
    SplitCandidate splitCandidate = null;
    if (currentDepth == 0 && config.getHardCodedRootColumn() != null) {
        final TreeAttributeColumnData rootColumn = data.getColumn(config.getHardCodedRootColumn());
        // TODO discuss whether this option makes sense with surrogates
        return new SplitCandidate[] { rootColumn.calcBestSplitClassification(dataMemberships, targetPriors, targetColumn, rd) };
    }
    double bestGainValue = 0.0;
    final Comparator<SplitCandidate> comp = new Comparator<SplitCandidate>() {

        @Override
        public int compare(final SplitCandidate o1, final SplitCandidate o2) {
            int compareDouble = -Double.compare(o1.getGainValue(), o2.getGainValue());
            return compareDouble;
        }
    };
    ArrayList<SplitCandidate> candidates = new ArrayList<SplitCandidate>(columnSample.getNumCols());
    for (TreeAttributeColumnData col : columnSample) {
        if (forbiddenColumnSet.get(col.getMetaData().getAttributeIndex())) {
            continue;
        }
        SplitCandidate currentColSplit = col.calcBestSplitClassification(dataMemberships, targetPriors, targetColumn, rd);
        if (currentColSplit != null) {
            candidates.add(currentColSplit);
        }
    }
    if (candidates.isEmpty()) {
        return null;
    }
    candidates.sort(comp);
    return candidates.toArray(new SplitCandidate[candidates.size()]);
}

Example 9 with ClassificationPriors

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

the class TreeLearnerClassification method learnSingleTreeRecursive.

private TreeModelClassification learnSingleTreeRecursive(final ExecutionMonitor exec, final RandomData rd) throws CanceledExecutionException {
    final TreeData data = getData();
    final RowSample rowSampling = getRowSampling();
    final TreeEnsembleLearnerConfiguration config = getConfig();
    final TreeTargetNominalColumnData targetColumn = (TreeTargetNominalColumnData) data.getTargetColumn();
    final // new RootDataMem(rowSampling, getIndexManager());
    DataMemberships rootDataMemberships = new RootDataMemberships(rowSampling, data, getIndexManager());
    ClassificationPriors targetPriors = targetColumn.getDistribution(rootDataMemberships, config);
    BitSet forbiddenColumnSet = new BitSet(data.getNrAttributes());
    // final DataMemberships rootDataMemberships = new IntArrayDataMemberships(sampleWeights, data);
    final TreeNodeSignature rootSignature = TreeNodeSignature.ROOT_SIGNATURE;
    final ColumnSample rootColumnSample = getColSamplingStrategy().getColumnSampleForTreeNode(rootSignature);
    TreeNodeClassification rootNode = null;
    rootNode = buildTreeNode(exec, 0, rootDataMemberships, rootColumnSample, rootSignature, targetPriors, forbiddenColumnSet);
    assert forbiddenColumnSet.cardinality() == 0;
    rootNode.setTreeNodeCondition(TreeNodeTrueCondition.INSTANCE);
    return new TreeModelClassification(rootNode);
}

Example 10 with ClassificationPriors

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

the class TreeNumericColumnDataTest method testCalcBestSplitClassification.

@Test
public void testCalcBestSplitClassification() throws Exception {
    TreeEnsembleLearnerConfiguration config = createConfig();
    /* data from J. Fuernkranz, Uni Darmstadt:
         * http://www.ke.tu-darmstadt.de/lehre/archiv/ws0809/mldm/dt.pdf */
    final double[] data = asDataArray("60,70,75,85, 90, 95, 100,120,125,220");
    final String[] target = asStringArray("No,No,No,Yes,Yes,Yes,No, No, No, No");
    Pair<TreeOrdinaryNumericColumnData, TreeTargetNominalColumnData> exampleData = exampleData(config, data, target);
    RandomData rd = config.createRandomData();
    TreeNumericColumnData columnData = exampleData.getFirst();
    TreeTargetNominalColumnData targetData = exampleData.getSecond();
    assertEquals(SplitCriterion.Gini, config.getSplitCriterion());
    double[] rowWeights = new double[data.length];
    Arrays.fill(rowWeights, 1.0);
    TreeData treeData = createTreeDataClassification(exampleData);
    IDataIndexManager indexManager = new DefaultDataIndexManager(treeData);
    DataMemberships dataMemberships = new RootDataMemberships(rowWeights, treeData, indexManager);
    ClassificationPriors priors = targetData.getDistribution(rowWeights, config);
    SplitCandidate splitCandidate = columnData.calcBestSplitClassification(dataMemberships, priors, targetData, rd);
    assertNotNull(splitCandidate);
    assertThat(splitCandidate, instanceOf(NumericSplitCandidate.class));
    assertTrue(splitCandidate.canColumnBeSplitFurther());
    // libre office calc
    assertEquals(/*0.42 - 0.300 */
    0.12, splitCandidate.getGainValue(), 0.00001);
    NumericSplitCandidate numSplitCandidate = (NumericSplitCandidate) splitCandidate;
    TreeNodeNumericCondition[] childConditions = numSplitCandidate.getChildConditions();
    assertEquals(2, childConditions.length);
    assertEquals((95.0 + 100.0) / 2.0, childConditions[0].getSplitValue(), 0.0);
    assertEquals((95.0 + 100.0) / 2.0, childConditions[1].getSplitValue(), 0.0);
    assertEquals(NumericOperator.LessThanOrEqual, childConditions[0].getNumericOperator());
    assertEquals(NumericOperator.LargerThan, childConditions[1].getNumericOperator());
    double[] childRowWeights = new double[data.length];
    System.arraycopy(rowWeights, 0, childRowWeights, 0, rowWeights.length);
    BitSet inChild = columnData.updateChildMemberships(childConditions[0], dataMemberships);
    DataMemberships childMemberships = dataMemberships.createChildMemberships(inChild);
    ClassificationPriors childTargetPriors = targetData.getDistribution(childMemberships, config);
    SplitCandidate splitCandidateChild = columnData.calcBestSplitClassification(childMemberships, childTargetPriors, targetData, rd);
    assertNotNull(splitCandidateChild);
    assertThat(splitCandidateChild, instanceOf(NumericSplitCandidate.class));
    // manually via libre office calc
    assertEquals(0.5, splitCandidateChild.getGainValue(), 0.00001);
    TreeNodeNumericCondition[] childConditions2 = ((NumericSplitCandidate) splitCandidateChild).getChildConditions();
    assertEquals(2, childConditions2.length);
    assertEquals((75.0 + 85.0) / 2.0, childConditions2[0].getSplitValue(), 0.0);
    System.arraycopy(rowWeights, 0, childRowWeights, 0, rowWeights.length);
    inChild = columnData.updateChildMemberships(childConditions[1], dataMemberships);
    childMemberships = dataMemberships.createChildMemberships(inChild);
    childTargetPriors = targetData.getDistribution(childMemberships, config);
    splitCandidateChild = columnData.calcBestSplitClassification(childMemberships, childTargetPriors, targetData, rd);
    assertNull(splitCandidateChild);
}