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

Example 1 with DataMemberships

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

the class TreeNominalColumnData method calcBestSplitClassificationBinary.

NominalBinarySplitCandidate calcBestSplitClassificationBinary(final ColumnMemberships columnMemberships, final ClassificationPriors targetPriors, final TreeTargetNominalColumnData targetColumn, final IImpurity impCriterion, final NominalValueRepresentation[] nomVals, final NominalValueRepresentation[] targetVals, final RandomData rd) {
    if (nomVals.length <= 1) {
        return null;
    }
    final int minChildSize = getConfiguration().getMinChildSize();
    final int lengthNonMissing = containsMissingValues() ? nomVals.length - 1 : nomVals.length;
    // distribution of target for each attribute value
    final double[][] targetCountsSplitPerAttribute = new double[lengthNonMissing][targetVals.length];
    // number of valid records for each attribute value
    final double[] attWeights = new double[lengthNonMissing];
    // number (sum) of total valid values
    double totalWeight = 0.0;
    int start = 0;
    columnMemberships.next();
    for (int att = 0; att < lengthNonMissing; att++) {
        final int end = start + m_nominalValueCounts[att];
        double currentAttValWeight = 0.0;
        for (int index = columnMemberships.getIndexInColumn(); index < end; columnMemberships.next(), index = columnMemberships.getIndexInColumn()) {
            final double weight = columnMemberships.getRowWeight();
            assert weight > EPSILON : "The usage of datamemberships should ensure that no rows with zero weight are encountered";
            int target = targetColumn.getValueFor(columnMemberships.getOriginalIndex());
            targetCountsSplitPerAttribute[att][target] += weight;
            currentAttValWeight += weight;
        }
        totalWeight += currentAttValWeight;
        attWeights[att] = currentAttValWeight;
        start = end;
    }
    BinarySplitEnumeration splitEnumeration;
    if (nomVals.length <= 10) {
        splitEnumeration = new FullBinarySplitEnumeration(nomVals.length);
    } else {
        int maxSearch = (1 << 10 - 2);
        splitEnumeration = new RandomBinarySplitEnumeration(nomVals.length, maxSearch, rd);
    }
    BigInteger bestPartitionMask = null;
    boolean isBestSplitValid = false;
    double bestPartitionGain = Double.NEGATIVE_INFINITY;
    final double[] targetCountsSplitLeft = new double[targetVals.length];
    final double[] targetCountsSplitRight = new double[targetVals.length];
    final double[] binaryImpurityValues = new double[2];
    final double[] binaryPartitionWeights = new double[2];
    do {
        Arrays.fill(targetCountsSplitLeft, 0.0);
        Arrays.fill(targetCountsSplitRight, 0.0);
        double weightLeft = 0.0;
        double weightRight = 0.0;
        for (int i = 0; i < nomVals.length; i++) {
            final boolean isAttributeInRightBranch = splitEnumeration.isInRightBranch(i);
            double[] targetCountsCurrentAttribute = targetCountsSplitPerAttribute[i];
            for (int targetVal = 0; targetVal < targetVals.length; targetVal++) {
                if (isAttributeInRightBranch) {
                    targetCountsSplitRight[targetVal] += targetCountsCurrentAttribute[targetVal];
                } else {
                    targetCountsSplitLeft[targetVal] += targetCountsCurrentAttribute[targetVal];
                }
            }
            if (isAttributeInRightBranch) {
                weightRight += attWeights[i];
            } else {
                weightLeft += attWeights[i];
            }
        }
        binaryPartitionWeights[0] = weightRight;
        binaryPartitionWeights[1] = weightLeft;
        boolean isValidSplit = weightRight >= minChildSize && weightLeft >= minChildSize;
        binaryImpurityValues[0] = impCriterion.getPartitionImpurity(targetCountsSplitRight, weightRight);
        binaryImpurityValues[1] = impCriterion.getPartitionImpurity(targetCountsSplitLeft, weightLeft);
        double postSplitImpurity = impCriterion.getPostSplitImpurity(binaryImpurityValues, binaryPartitionWeights, totalWeight);
        double gain = impCriterion.getGain(targetPriors.getPriorImpurity(), postSplitImpurity, binaryPartitionWeights, totalWeight);
        // use random tie breaker if gains are equal
        boolean randomTieBreaker = gain == bestPartitionGain ? rd.nextInt(0, 1) == 1 : false;
        // store if better than before or first valid split
        if (gain > bestPartitionGain || (!isBestSplitValid && isValidSplit) || randomTieBreaker) {
            if (isValidSplit || !isBestSplitValid) {
                bestPartitionGain = gain;
                bestPartitionMask = splitEnumeration.getValueMask();
                isBestSplitValid = isValidSplit;
            }
        }
    } while (splitEnumeration.next());
    if (bestPartitionGain > 0.0) {
        return new NominalBinarySplitCandidate(this, bestPartitionGain, bestPartitionMask, getMissedRows(columnMemberships), NominalBinarySplitCandidate.NO_MISSINGS);
    }
    return null;
}

Example 2 with DataMemberships

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

the class TreeNominalColumnData method updateChildMembershipsMultiway.

private BitSet updateChildMembershipsMultiway(final TreeNodeNominalCondition nomCondition, final DataMemberships parentMemberships) {
    String value = nomCondition.getValue();
    int att = -1;
    final NominalValueRepresentation[] reps = getMetaData().getValues();
    for (final NominalValueRepresentation rep : reps) {
        if (rep.getNominalValue().equals(value)) {
            att = rep.getAssignedInteger();
            break;
        }
    }
    if (att == -1) {
        throw new IllegalStateException("Unknown value: " + value);
    }
    ColumnMemberships columnMemberships = parentMemberships.getColumnMemberships(getMetaData().getAttributeIndex());
    BitSet inChild = new BitSet(columnMemberships.size());
    columnMemberships.reset();
    int start = 0;
    for (int a = 0; a < att; a++) {
        start += m_nominalValueCounts[a];
    }
    // Make sure that we are using an index >= start
    if (!columnMemberships.nextIndexFrom(start)) {
        return inChild;
    }
    boolean reachedEnd = false;
    int end = start + m_nominalValueCounts[att];
    for (int index = columnMemberships.getIndexInColumn(); index < end; index = columnMemberships.getIndexInColumn()) {
        inChild.set(columnMemberships.getIndexInDataMemberships());
        if (!columnMemberships.next()) {
            reachedEnd = true;
            break;
        }
    }
    if (!reachedEnd && containsMissingValues() && nomCondition.acceptsMissings()) {
        // move to missing values
        for (int i = att; i < reps.length - 1; i++) {
            start += m_nominalValueCounts[i];
        }
        if (columnMemberships.nextIndexFrom(start)) {
            do {
                inChild.set(columnMemberships.getIndexInDataMemberships());
            } while (columnMemberships.next());
        }
    }
    return inChild;
}

Example 3 with DataMemberships

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

the class TreeNominalColumnData method calcBestSplitRegression.

/**
 * {@inheritDoc}
 */
@Override
public SplitCandidate calcBestSplitRegression(final DataMemberships dataMemberships, final RegressionPriors targetPriors, final TreeTargetNumericColumnData targetColumn, final RandomData rd) {
    final NominalValueRepresentation[] nomVals = getMetaData().getValues();
    final ColumnMemberships columnMemberships = dataMemberships.getColumnMemberships(getMetaData().getAttributeIndex());
    final boolean useBinaryNominalSplits = getConfiguration().isUseBinaryNominalSplits();
    if (useBinaryNominalSplits) {
        return calcBestSplitRegressionBinaryBreiman(columnMemberships, targetPriors, targetColumn, nomVals, rd);
    } else {
        return calcBestSplitRegressionMultiway(columnMemberships, targetPriors, targetColumn, nomVals, rd);
    }
}

Example 4 with DataMemberships

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

the class TreeNominalColumnData method updateChildMembershipsBinary.

private BitSet updateChildMembershipsBinary(final TreeNodeNominalBinaryCondition childBinaryCondition, final DataMemberships parentMemberships) {
    ColumnMemberships columnMemberships = parentMemberships.getColumnMemberships(getMetaData().getAttributeIndex());
    columnMemberships.reset();
    BitSet inChild = new BitSet(columnMemberships.size());
    // TODO Check if this can be done more efficiently
    NominalValueRepresentation[] reps = getMetaData().getValues();
    int start = 0;
    boolean reachedEnd = false;
    final int lengthNonMissing = containsMissingValues() ? reps.length - 1 : reps.length;
    for (int att = 0; att < lengthNonMissing; att++) {
        if (childBinaryCondition.testCondition(att)) {
            // move columnMemberships to correct position
            if (!columnMemberships.nextIndexFrom(start)) {
                // reached end of columnMemberships
                break;
            }
            int end = start + m_nominalValueCounts[att];
            for (int index = columnMemberships.getIndexInColumn(); index < end; index = columnMemberships.getIndexInColumn()) {
                inChild.set(columnMemberships.getIndexInDataMemberships());
                if (!columnMemberships.next()) {
                    reachedEnd = true;
                    break;
                }
            }
        }
        start += m_nominalValueCounts[att];
    }
    if (!reachedEnd && containsMissingValues() && childBinaryCondition.acceptsMissings()) {
        if (columnMemberships.nextIndexFrom(start)) {
            do {
                inChild.set(columnMemberships.getIndexInDataMemberships());
            } while (columnMemberships.next());
        }
    }
    return inChild;
}

Example 5 with DataMemberships

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

the class TreeNominalColumnData 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();
    IImpurity impCriterion = targetPriors.getImpurityCriterion();
    // distribution of target for each attribute value
    final NominalValueRepresentation[] nomVals = getMetaData().getValues();
    final boolean useBinaryNominalSplits = getConfiguration().isUseBinaryNominalSplits();
    final ColumnMemberships columnMemberships = dataMemberships.getColumnMemberships(getMetaData().getAttributeIndex());
    if (useBinaryNominalSplits) {
        if (targetVals.length == 2) {
            return calcBestSplitClassificationBinaryTwoClass(columnMemberships, targetPriors, targetColumn, impCriterion, nomVals, targetVals, rd);
        } else {
            return calcBestSplitClassificationBinaryPCA(columnMemberships, targetPriors, targetColumn, impCriterion, nomVals, targetVals, rd);
        // return calcBestSplitClassificationBinary(membershipController, rowWeights, targetPriors, targetColumn,
        // impCriterion, nomVals, targetVals, originalIndexInColumnList, rd);
        }
    } else {
        return calcBestSplitClassificationMultiway(columnMemberships, targetPriors, targetColumn, impCriterion, nomVals, targetVals, rd);
    }
}