public void AddWeakLearner(RegressionTree[] candidateTree, float[] funValueGain, int m, Metrics metrics, BoostTreeLoss boostTreeLoss, DataFeatureSampleRate dataFeatureSampleRate, int maxTreeSize, int minNumSamples, int cThreads, Random r)
{
//update the function value for all data points given the new regression tree
for (int i = 0; i < boostTreeLoss.NumTreesPerIteration; i++)
{
candidateTree[i].PredictFunValue(this.labelFeatureDataCoded, true, ref funValueGain);
this.regressionTrees[m, i] = candidateTree[i];
boostTreeLoss.AccFuncValueGain(funValueGain, candidateTree[i].AdjustFactor, i);
}
}
public double EvaluateWeakLearner(RegressionTree[] candidateTree, float[] funValueGain, Metrics metrics, BoostTreeLoss boostTreeLoss, int id)
{
float[][] scores = new float[boostTreeLoss.NumTreesPerIteration][];
for (int k = 0; k < boostTreeLoss.NumTreesPerIteration; k++)
{
scores[k] = new float[funValueGain.GetLength(0)];
for (int i = 0; i < funValueGain.GetLength(0); i++)
{
scores[k][i] = 0.0F;
}
}
double result = 0.0;
for (int k = 0; k < boostTreeLoss.NumTreesPerIteration; k++)
{
candidateTree[k].PredictFunValue(this.labelFeatureDataCoded, true, ref funValueGain);
//we hard code here that k=0 (not performing classification)
//kms: this is a bit of hack...only will really work for non-classification currently
// upgrade to have a per loss function evaluation
for (int i = 0; i < funValueGain.GetLength(0); i++)
{
scores[k][i] = boostTreeLoss.ModelScores[k][i] +(funValueGain[i] * candidateTree[k].AdjustFactor);
}
}
//need to update id so we have unique id. For now, we take M + m + 1;
//assume only want NDCGPairwise for now
metrics.ComputeMetrics(scores, id, false);
//NDCGPairwiseType = 2;
result = metrics.ResultsStrMatrix(id)[(int)DataPartitionType.Train][2];
//Console.WriteLine(result);
return result;
}
public RegressionTree[] GetNextWeakLearner(int m, float[] funValueGain, Metrics metrics, BoostTreeLoss boostTreeLoss, DataFeatureSampleRate dataFeatureSampleRate, RandomSampler dataSampler, RandomSampler featureSampler,
int maxTreeSize, int minNumSamples, int cThreads, Random r)
{
// select a fraction of data groups for this iteration
float sampleRate = dataFeatureSampleRate.SampleDataGroupRate(m);
DataSet workDataSet = this.labelFeatureDataCoded.DataGroups.GetDataPartition(DataPartitionType.Train, sampleRate, r);
workDataSet.Sort(); // sorting gains some noticable speedup.
// compute the pseudo response of the current system
boostTreeLoss.ComputePseudoResponse(workDataSet);
//set the data and feature sampling rate for node spliting in this iteration
featureSampler.SampleRate = dataFeatureSampleRate.SampleFeatureRate(m);
dataSampler.SampleRate = dataFeatureSampleRate.SampleDataRate(m);
// fit a residual model (regression trees) from the pseudo response
// to compensate the error of the current system
RegressionTree[] newTree = new RegressionTree[boostTreeLoss.NumTreesPerIteration];
for (int k = 0; k < boostTreeLoss.NumTreesPerIteration; k++)
{
//only use the important data points if necessary
int[] trimIndex = boostTreeLoss.TrimIndex(workDataSet, k, m);
//build a regression tree according to the pseduo-response
newTree[k] = new RegressionTree(this.labelFeatureDataCoded, boostTreeLoss, k, trimIndex,
dataSampler, featureSampler, maxTreeSize, minNumSamples, this.findSplit, this.tempSpace);
//compute the function value of all data points produced by the newly generated regression tree
newTree[k].PredictFunValue(this.labelFeatureDataCoded, ref funValueGain);
//try to do a more global optimalization - refine the leaf node response of a decision tree
//by looking at all the training data points, instead of only the ones falling into the regaion.
//Here we are estimate and apply a global mutiplication factor for all leaf nodes
float adjFactor = (m > 0) ? boostTreeLoss.ComputeResponseAdjust(funValueGain) : 1.0F;
//apply the multiplication factor to the leaf nodes of the newly generated regression tree
newTree[k].AdjustResponse(adjFactor);
newTree[k].AdjustFactor = adjFactor;
}
//return the k regression trees
return newTree;
}