/// <summary>
/// This method implements the main functionality of stochastic gradient boosting
/// </summary>
private void BuildBoostTree(Metrics metrics, BoostTreeLoss boostTreeLoss, DataFeatureSampleRate dataFeatureSampleRate,
int maxTreeSize, int minNumSamples, int numIter,
int cThreads, Random r)
{
float minValidationErr = 100;
float[] funValueGain = new float[this.numSamples];
//(1) compute scores produced by the sub-model
boostTreeLoss.ModelEval(this.subModel, this.labelFeatureDataCoded, this.subModelScore);
//(2) compute the corresponding function values;
boostTreeLoss.ModelScoresToFuncValues();
//(3) compute the metrics of the sub-model
int m = optIter = 0;
metrics.ComputeMetrics(boostTreeLoss.ModelScores, m, false);
#if VERBOSE
Console.WriteLine(metrics.ResultsHeaderStr());
Console.WriteLine(metrics.ResultsStr(m));
#endif
//(4) creat samplers to sub-sampl the features and data during node spliting
RandomSampler featureSampler = new RandomSampler(r);
RandomSampler dataSampler = new RandomSampler(r);
//(5) creat the object that does node splitting
#if SINGLE_THREAD
// single-threaded
this.findSplit = new FindSplitSync();
#else
// multi-threaded
this.findSplit = new FindSplitAsync(cThreads);
#endif //SINGLE_THREAD
//(6) Iteratively building boosted trees
for (m = 0; m < numIter; m++)
{
// selecting a fraction of data groups for each 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 pesuso response
// to compensate the error of the current system
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
this.regressionTrees[m, 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
this.regressionTrees[m, 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
this.regressionTrees[m, k].AdjustResponse(adjFactor);
//update the function value for all data points given the new regression tree
boostTreeLoss.AccFuncValueGain(funValueGain, adjFactor, k);
}
//compute the metrics of the current system
boostTreeLoss.FuncValuesToModelScores();
metrics.ComputeMetrics(boostTreeLoss.ModelScores, m + 1, false);
#if VERBOSE
Console.WriteLine(metrics.ResultsStr(m+1));
#endif
//keep track of the best (minimal Error) iteration on the Validation data set
this.optIter = metrics.GetBest(DataPartitionType.Validation, ref minValidationErr);
if ((m+1) % 5 == 0) // save the tree every 5 iterations
SaveBoostTree();
}
if (this.findSplit != null)
{
this.findSplit.Cleanup();
}
}
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;
}