Examples with FeatureIterator org.knime.base.node.mine.regression.logistic.learner4.data.TrainingRow.FeatureIterator used on opensource projects

Example 6 with FeatureIterator

use of org.knime.base.node.mine.regression.logistic.learner4.data.TrainingRow.FeatureIterator in project knime-core by knime.

the class IrlsLearner method fillXFromRow.

private static void fillXFromRow(final RealMatrix x, final ClassificationTrainingRow row) {
    FeatureIterator iter = row.getFeatureIterator();
    boolean hasNext = iter.next();
    for (int i = 0; i < x.getColumnDimension(); i++) {
        double val = 0.0;
        if (hasNext && iter.getFeatureIndex() == i) {
            val = iter.getFeatureValue();
            hasNext = iter.next();
        }
        x.setEntry(0, i, val);
    }
}

Example 7 with FeatureIterator

use of org.knime.base.node.mine.regression.logistic.learner4.data.TrainingRow.FeatureIterator in project knime-core by knime.

the class IrlsLearner method irlsRls.

/**
 * Do an irls step. The result is stored in beta.
 *
 * @param data over trainings data.
 * @param beta parameter vector
 * @param rC regressors count
 * @param tcC target category count
 * @throws CanceledExecutionException when method is cancelled
 */
private void irlsRls(final TrainingData<ClassificationTrainingRow> data, final RealMatrix beta, final int rC, final int tcC, final ExecutionMonitor exec) throws CanceledExecutionException {
    long rowCount = 0;
    int dim = (rC + 1) * (tcC - 1);
    RealMatrix xTwx = MatrixUtils.createRealMatrix(dim, dim);
    RealMatrix xTyu = MatrixUtils.createRealMatrix(dim, 1);
    double[] eBetaTx = new double[tcC - 1];
    double[] pi = new double[tcC - 1];
    final long totalRowCount = data.getRowCount();
    for (ClassificationTrainingRow row : data) {
        rowCount++;
        exec.checkCanceled();
        exec.setProgress(rowCount / (double) totalRowCount, "Row " + rowCount + "/" + totalRowCount);
        for (int k = 0; k < tcC - 1; k++) {
            double z = 0.0;
            for (FeatureIterator iter = row.getFeatureIterator(); iter.next(); ) {
                double featureVal = iter.getFeatureValue();
                int featureIdx = iter.getFeatureIndex();
                z += featureVal * beta.getEntry(0, k * (rC + 1) + featureIdx);
            }
            eBetaTx[k] = Math.exp(z);
        }
        double sumEBetaTx = 0;
        for (int k = 0; k < tcC - 1; k++) {
            sumEBetaTx += eBetaTx[k];
        }
        for (int k = 0; k < tcC - 1; k++) {
            double pik = eBetaTx[k] / (1 + sumEBetaTx);
            pi[k] = pik;
        }
        // fill xTwx (aka the hessian of the loglikelihood)
        for (FeatureIterator outer = row.getFeatureIterator(); outer.next(); ) {
            int i = outer.getFeatureIndex();
            double outerVal = outer.getFeatureValue();
            for (FeatureIterator inner = outer.spawn(); inner.next(); ) {
                int ii = inner.getFeatureIndex();
                double innerVal = inner.getFeatureValue();
                for (int k = 0; k < tcC - 1; k++) {
                    for (int kk = k; kk < tcC - 1; kk++) {
                        int o1 = k * (rC + 1);
                        int o2 = kk * (rC + 1);
                        double v = xTwx.getEntry(o1 + i, o2 + ii);
                        if (k == kk) {
                            double w = pi[k] * (1 - pi[k]);
                            v += outerVal * w * innerVal;
                            assert o1 == o2;
                        } else {
                            double w = -pi[k] * pi[kk];
                            v += outerVal * w * innerVal;
                        }
                        xTwx.setEntry(o1 + i, o2 + ii, v);
                        xTwx.setEntry(o1 + ii, o2 + i, v);
                        if (k != kk) {
                            xTwx.setEntry(o2 + ii, o1 + i, v);
                            xTwx.setEntry(o2 + i, o1 + ii, v);
                        }
                    }
                }
            }
        }
        int g = row.getCategory();
        // fill matrix xTyu
        for (FeatureIterator iter = row.getFeatureIterator(); iter.next(); ) {
            int idx = iter.getFeatureIndex();
            double val = iter.getFeatureValue();
            for (int k = 0; k < tcC - 1; k++) {
                int o = k * (rC + 1);
                double v = xTyu.getEntry(o + idx, 0);
                double y = k == g ? 1 : 0;
                v += (y - pi[k]) * val;
                xTyu.setEntry(o + idx, 0, v);
            }
        }
    }
    // currently not used but could become interesting in the future
    // if (m_penaltyTerm > 0.0) {
    // RealMatrix stdError = getStdErrorMatrix(xTwx);
    // // do not penalize the constant terms
    // for (int i = 0; i < tcC - 1; i++) {
    // stdError.setEntry(i * (rC + 1), i * (rC + 1), 0);
    // }
    // xTwx = xTwx.add(stdError.scalarMultiply(-0.00001));
    // }
    exec.checkCanceled();
    b = xTwx.multiply(beta.transpose()).add(xTyu);
    A = xTwx;
    if (rowCount < A.getColumnDimension()) {
        // but it's important to ensure this property
        throw new IllegalStateException("The dataset must have at least " + A.getColumnDimension() + " rows, but it has only " + rowCount + " rows. It is recommended to use a " + "larger dataset in order to increase accuracy.");
    }
    DecompositionSolver solver = new SingularValueDecomposition(A).getSolver();
    RealMatrix betaNew = solver.solve(b);
    beta.setSubMatrix(betaNew.transpose().getData(), 0, 0);
}

Example 8 with FeatureIterator

use of org.knime.base.node.mine.regression.logistic.learner4.data.TrainingRow.FeatureIterator in project knime-core by knime.

the class AbstractWeightMatrix method update.

/**
 * {@inheritDoc}
 */
@Override
public void update(final WeightVectorConsumer2 func, final boolean includeIntercept, final TrainingRow row) {
    boolean updateIntercept = m_fitIntercept && includeIntercept;
    // use the feature iterator to efficiently traverse the row
    for (FeatureIterator iter = row.getFeatureIterator(); iter.next(); ) {
        int i = iter.getFeatureIndex();
        double featureValue = iter.getFeatureValue();
        if (!updateIntercept && i == 0) {
            // omit intercept term
            continue;
        }
        for (int c = 0; c < m_data.length; c++) {
            applyFunc(c, i, featureValue, func);
        }
    }
}

Example 9 with FeatureIterator

use of org.knime.base.node.mine.regression.logistic.learner4.data.TrainingRow.FeatureIterator in project knime-core by knime.

the class LazySagUpdater method update.

/**
 * {@inheritDoc}
 */
@Override
public void update(final T x, final double[] sig, final WeightMatrix<T> beta, final double stepSize, final int iteration) {
    int id = x.getId();
    if (!m_seen.get(id)) {
        m_seen.set(id);
        m_covered++;
    }
    // update gradient sum
    for (FeatureIterator iter = x.getFeatureIterator(); iter.next(); ) {
        int idx = iter.getFeatureIndex();
        double val = iter.getFeatureValue();
        for (int c = 0; c < m_nCats; c++) {
            double newD = val * (sig[c] - m_gradientMemory[c][id]);
            assert Double.isFinite(newD);
            m_gradientSum[c][idx] += newD;
        }
    }
    // update gradient memory
    for (int c = 0; c < m_nCats; c++) {
        m_gradientMemory[c][id] = sig[c];
    }
    double prev = iteration == 0 ? 0 : m_cummulativeSum[iteration - 1];
    double scale = beta.getScale();
    m_cummulativeSum[iteration] = prev + stepSize / (scale * m_covered);
    // the intersect is not scaled!
    m_intersectStepSize = stepSize / m_covered;
}

Example 10 with FeatureIterator

use of org.knime.base.node.mine.regression.logistic.learner4.data.TrainingRow.FeatureIterator in project knime-core by knime.

the class LineSearchLearningRateStrategy method calculateSquaredNorm.

private double calculateSquaredNorm(final T row) {
    double norm = 0.0;
    // row.getFeature(0) returns always a 1 for the intercept term
    FeatureIterator iter = row.getFeatureIterator();
    iter.next();
    while (iter.next()) {
        double fet = iter.getFeatureValue();
        norm += fet * fet;
    }
    return norm;
}