public void AdjustTreeOutputs(IChannel ch, RegressionTree tree, DocumentPartitioning partitioning, ScoreTracker trainingScores) { const double epsilon = 1.4e-45; double multiplier = LearningRate * Shrinkage; double[] means = null; if (!BestStepRankingRegressionTrees) { means = _parallelTraining.GlobalMean(Dataset, tree, partitioning, Weights, false); } for (int l = 0; l < tree.NumLeaves; ++l) { double output = tree.GetOutput(l); if (BestStepRankingRegressionTrees) { output *= multiplier; } else { output = multiplier * (output + epsilon) / (means[l] + epsilon); } if (output > MaxTreeOutput) { output = MaxTreeOutput; } else if (output < -MaxTreeOutput) { output = -MaxTreeOutput; } tree.SetOutput(l, output); } }
public double[] GlobalMean(Dataset dataset, RegressionTree tree, DocumentPartitioning partitioning, double[] weights, bool filterZeroLambdas) { double[] means = new double[tree.NumLeaves]; for (int l = 0; l < tree.NumLeaves; ++l) { means[l] = partitioning.Mean(weights, dataset.SampleWeights, l, filterZeroLambdas); } return(means); }
public void AdjustTreeOutputs(IChannel ch, RegressionTree tree, DocumentPartitioning partitioning, ScoreTracker trainingScores) { double shrinkage = LearningRate * Shrinkage; for (int l = 0; l < tree.NumLeaves; ++l) { double output = tree.GetOutput(l) * shrinkage; tree.SetOutput(l, output); } }
public void AdjustTreeOutputs(IChannel ch, RegressionTree tree, DocumentPartitioning partitioning, ScoreTracker trainingScores) { double shrinkage = LearningRate * Shrinkage; var scores = trainingScores.Scores; var weights = trainingScores.Dataset.SampleWeights; // Following equation 18, and line 2c of algorithm 1 in the source paper. for (int l = 0; l < tree.NumLeaves; ++l) { Double num = 0; Double denom = 0; if (_index1 == 0) { // The index == 1 Poisson case. foreach (int i in partitioning.DocumentsInLeaf(l)) { var s = scores[i]; var w = weights == null ? 1 : weights[i]; num += w * _labels[i]; denom += w * Math.Exp(s); } } else { // The index in (1,2] case. foreach (int i in partitioning.DocumentsInLeaf(l)) { var s = scores[i]; var w = weights == null ? 1 : weights[i]; num += w * _labels[i] * Math.Exp(_index1 * s); denom += w * Math.Exp(_index2 * s); } } var step = shrinkage * (Math.Log(num) - Math.Log(denom)); if (num == 0 && denom == 0) { step = 0; } // If we do not clamp, it is entirely possible for num to be 0 (with 0 labels), which // means that we will have negative infinities in the leaf nodes. This has a number of // bad negative effects we'd prefer to avoid. Nonetheless, we do give up a substantial // amount of "gain" for those examples. if (step < -_maxClamp) { step = -_maxClamp; } else if (step > _maxClamp) { step = _maxClamp; } tree.SetOutput(l, step); } }
public double[] GlobalMean(Dataset dataset, RegressionTree tree, DocumentPartitioning partitioning, double[] weights, bool filterZeroLambdas) { Assert.True(_isInitEnv); Assert.True(_isInitTreeLearner); Assert.NotNull(dataset); Assert.NotNull(tree); Assert.NotNull(partitioning); double[] means = new double[tree.NumLeaves]; for (int l = 0; l < tree.NumLeaves; ++l) { means[l] = partitioning.Mean(weights, dataset.SampleWeights, l, filterZeroLambdas); } return(means); }
public void AdjustTreeOutputs(IChannel ch, RegressionTree tree, DocumentPartitioning partitioning, ScoreTracker trainingScores) { }