/// <summary>
/// Fites a regression decision tree using a set presorted indices for each feature.
/// </summary>
/// <param name="maximumTreeDepth">The maximal tree depth before a leaf is generated</param>
/// <param name="minimumSplitSize">The minimum size </param>
/// <param name="minimumInformationGain">The minimum improvement in information gain before a split is made</param>
/// <param name="featuresPrSplit">Number of features used at each split in the tree. 0 means all will be used</param>
/// <param name="loss">loss function used</param>
/// <param name="runParallel">Use multi threading to speed up execution</param>
public GBMDecisionTreeLearner(int maximumTreeDepth, int minimumSplitSize, double minimumInformationGain, int featuresPrSplit, IGradientBoostLoss loss, bool runParallel)
{
if (maximumTreeDepth <= 0)
{
throw new ArgumentException("maximum tree depth must be larger than 0");
}
if (minimumInformationGain <= 0)
{
throw new ArgumentException("minimum information gain must be larger than 0");
}
if (minimumSplitSize <= 0)
{
throw new ArgumentException("minimum split size must be larger than 0");
}
if (featuresPrSplit < 0)
{
throw new ArgumentException("featuresPrSplit must be at least 0");
}
if (loss == null)
{
throw new ArgumentNullException("loss");
}
m_maximumTreeDepth = maximumTreeDepth;
m_minimumSplitSize = minimumSplitSize;
m_minimumInformationGain = minimumInformationGain;
m_featuresPrSplit = featuresPrSplit;
m_runParallel = runParallel;
m_loss = loss;
}
/// <summary>
/// Base regression gradient boost learner.
/// A series of regression trees are fitted stage wise on the residuals of the previous stage
/// </summary>
/// <param name="iterations">The number of iterations or stages</param>
/// <param name="learningRate">How much each iteration should contribute with</param>
/// <param name="maximumTreeDepth">The maximum depth of the tree models</param>
/// <param name="minimumSplitSize">minimum node split size in the trees 1 is default</param>
/// <param name="minimumInformationGain">The minimum improvement in information gain before a split is made</param>
/// <param name="subSampleRatio">ratio of observations sampled at each iteration. Default is 1.0.
/// If below 1.0 the algorithm changes to stochastic gradient boosting.
/// This reduces variance in the ensemble and can help outer overfitting</param>
/// <param name="featuresPrSplit">Number of features used at each split in the tree. 0 means all will be used</param>
/// <param name="loss">loss function used</param>
/// <param name="runParallel">Use multi threading to speed up execution</param>
public RegressionGradientBoostLearner(
int iterations,
double learningRate,
int maximumTreeDepth,
int minimumSplitSize,
double minimumInformationGain,
double subSampleRatio,
int featuresPrSplit,
IGradientBoostLoss loss,
bool runParallel)
{
if (iterations < 1)
{
throw new ArgumentException("Iterations must be at least 1");
}
if (learningRate <= 0.0)
{
throw new ArgumentException("learning rate must be larger than 0");
}
if (minimumSplitSize <= 0)
{
throw new ArgumentException("minimum split size must be larger than 0");
}
if (maximumTreeDepth < 0)
{
throw new ArgumentException("maximum tree depth must be larger than 0");
}
if (minimumInformationGain <= 0)
{
throw new ArgumentException("minimum information gain must be larger than 0");
}
if ((subSampleRatio <= 0.0) || (subSampleRatio > 1.0))
{
throw new ArgumentException("subSampleRatio must be larger than 0.0 and at max 1.0");
}
if (featuresPrSplit < 0)
{
throw new ArgumentException("featuresPrSplit must be at least 0");
}
m_loss = loss ?? throw new ArgumentNullException(nameof(loss));
m_iterations = iterations;
m_learningRate = learningRate;
m_subSampleRatio = subSampleRatio;
m_learner = new GBMDecisionTreeLearner(maximumTreeDepth, minimumSplitSize,
minimumInformationGain, featuresPrSplit, m_loss, runParallel);
}
