/// <summary>
/// A series of regression trees are fitted stage wise on the residuals of the previous tree
/// </summary>
/// <param name="observations"></param>
/// <param name="targets"></param>
/// <param name="indices"></param>
/// <returns></returns>
public RegressionGradientBoostModel Learn(F64Matrix observations, double[] targets,
int[] indices)
{
Checks.VerifyObservationsAndTargets(observations, targets);
Checks.VerifyIndices(indices, observations, targets);
var rows = observations.RowCount;
var orderedElements = CreateOrderedElements(observations, rows);
var inSample = targets.Select(t => false).ToArray();
indices.ForEach(i => inSample[i] = true);
var workIndices = indices.ToArray();
var trees = new GBMTree[m_iterations];
var initialLoss = m_loss.InitialLoss(targets, inSample);
var predictions = targets.Select(t => initialLoss).ToArray();
var residuals = new double[targets.Length];
var predictWork = new double[observations.RowCount];
for (int iteration = 0; iteration < m_iterations; iteration++)
{
m_loss.UpdateResiduals(targets, predictions, residuals, inSample);
var sampleSize = targets.Length;
if (m_subSampleRatio != 1.0)
{
sampleSize = (int)Math.Round(m_subSampleRatio * workIndices.Length);
var currentInSample = Sample(sampleSize, workIndices, targets.Length);
trees[iteration] = m_learner.Learn(observations, targets, residuals,
predictions, orderedElements, currentInSample);
}
else
{
trees[iteration] = m_learner.Learn(observations, targets, residuals,
predictions, orderedElements, inSample);
}
trees[iteration].Predict(observations, predictWork);
for (int i = 0; i < predictWork.Length; i++)
{
predictions[i] += m_learningRate * predictWork[i];
}
}
return(new RegressionGradientBoostModel(trees, m_learningRate, initialLoss,
observations.ColumnCount));
}
/// <summary>
/// A series of regression trees are fitted stage wise on the residuals of the previous stage
/// </summary>
/// <param name="observations"></param>
/// <param name="targets"></param>
/// <param name="indices"></param>
/// <returns></returns>
public ClassificationGradientBoostModel Learn(F64Matrix observations, double[] targets,
int[] indices)
{
Checks.VerifyObservationsAndTargets(observations, targets);
Checks.VerifyIndices(indices, observations, targets);
var rows = observations.RowCount;
var orderedElements = CreateOrderedElements(observations, rows);
var inSample = targets.Select(t => false).ToArray();
indices.ForEach(i => inSample[i] = true);
var workIndices = indices.ToArray();
var uniqueTargets = targets.Distinct().OrderBy(v => v).ToArray();
var initialLoss = m_loss.InitialLoss(targets, inSample);
double[][] oneVsAllTargets = null;
double[][] predictions = null;
double[][] residuals = null;
GBMTree[][] trees = null;
if (uniqueTargets.Length == 2) // Binary case - only need to fit to one class and use (1.0 - probability)
{
trees = new GBMTree[][] { new GBMTree[m_iterations] };
predictions = new double[][] { targets.Select(_ => initialLoss).ToArray() };
residuals = new double[][] { new double[targets.Length] };
oneVsAllTargets = new double[1][];
var target = uniqueTargets[0];
oneVsAllTargets[0] = targets.Select(t => t == target ? 1.0 : 0.0).ToArray();
}
else // multi-class case - use oneVsAll strategy and fit probability for each class
{
trees = new GBMTree[uniqueTargets.Length][];
predictions = uniqueTargets.Select(_ => targets.Select(t => initialLoss).ToArray())
.ToArray();
residuals = uniqueTargets.Select(_ => new double[targets.Length])
.ToArray();
oneVsAllTargets = new double[uniqueTargets.Length][];
for (int i = 0; i < uniqueTargets.Length; i++)
{
var target = uniqueTargets[i];
oneVsAllTargets[i] = targets.Select(t => t == target ? 1.0 : 0.0).ToArray();
trees[i] = new GBMTree[m_iterations];
}
}
var predictWork = new double[observations.RowCount];
for (int iteration = 0; iteration < m_iterations; iteration++)
{
for (int itarget = 0; itarget < trees.Length; itarget++)
{
m_loss.UpdateResiduals(oneVsAllTargets[itarget], predictions[itarget],
residuals[itarget], inSample);
var sampleSize = targets.Length;
if (m_subSampleRatio != 1.0)
{
sampleSize = (int)Math.Round(m_subSampleRatio * workIndices.Length);
var currentInSample = Sample(sampleSize, workIndices, targets.Length);
trees[itarget][iteration] = m_learner.Learn(observations, oneVsAllTargets[itarget],
residuals[itarget], predictions[itarget], orderedElements, currentInSample);
}
else
{
trees[itarget][iteration] = m_learner.Learn(observations, oneVsAllTargets[itarget],
residuals[itarget], predictions[itarget], orderedElements, inSample);
}
trees[itarget][iteration].Predict(observations, predictWork);
for (int i = 0; i < predictWork.Length; i++)
{
predictions[itarget][i] += m_learningRate * predictWork[i];
}
}
}
return(new ClassificationGradientBoostModel(trees, uniqueTargets, m_learningRate,
initialLoss, observations.ColumnCount));
}
