/// <summary>
/// Bias variance analysis calculator for constructing learning curves.
/// Learning curves can be used to determine if a model has high bias or high variance.
/// </summary>
/// <param name="trainingValidationIndexSplitter"></param>
/// <param name="shuffler">Type of shuffler to use when splitting data</param>
/// <param name="metric">The error metric used</param>
/// <param name="samplePercentages">A list of sample percentages determining the
/// training data used in each point of the learning curve</param>
/// <param name="numberOfShufflesPrSample">How many times should the data be shuffled pr. calculated point</param>
public LearningCurvesCalculator(ITrainingTestIndexSplitter <double> trainingValidationIndexSplitter,
IIndexSampler <double> shuffler, IMetric <double, TPrediction> metric, double[] samplePercentages, int numberOfShufflesPrSample = 5)
{
if (trainingValidationIndexSplitter == null)
{
throw new ArgumentException("trainingValidationIndexSplitter");
}
if (shuffler == null)
{
throw new ArgumentException("shuffler");
}
if (samplePercentages == null)
{
throw new ArgumentNullException("samplePercentages");
}
if (samplePercentages.Length < 1)
{
throw new ArgumentException("SamplePercentages length must be at least 1");
}
if (metric == null)
{
throw new ArgumentNullException("metric");
}
if (numberOfShufflesPrSample < 1)
{
throw new ArgumentNullException("numberOfShufflesPrSample must be at least 1");
}
m_trainingValidationIndexSplitter = trainingValidationIndexSplitter;
m_indexedSampler = shuffler;
m_samplePercentages = samplePercentages;
m_metric = metric;
m_numberOfShufflesPrSample = numberOfShufflesPrSample;
m_random = new Random(42);
}
/// <summary>
///
/// </summary>
/// <param name="shuffler">the type of shuffler provided</param>
/// <param name="trainingPercentage">What percentage of the indices should go to the training set</param>
public TrainingTestIndexSplitter(IIndexSampler <T> shuffler, double trainingPercentage)
{
m_indexSampler = shuffler ?? throw new ArgumentNullException(nameof(shuffler));
if (trainingPercentage <= 0.0 || trainingPercentage >= 1.0)
{
throw new ArgumentException("Training percentage must be larger than 0.0 and smaller than 1.0");
}
m_trainingPercentage = trainingPercentage;
}
/// <summary>
/// Cross validation for evaluating how learning algorithms perform on unseen observations
/// </summary>
/// <param name="sampler">Sampling strategy for the provided indices
/// before they are divided into the provided folds</param>
/// <param name="crossValidationFolds">Number of folds that should be used for cross validation</param>
public CrossValidation(IIndexSampler <double> sampler, int crossValidationFolds)
{
m_indexedSampler = sampler ?? throw new ArgumentNullException(nameof(sampler));
if (crossValidationFolds < 1)
{
throw new ArgumentException("CrossValidationFolds ");
}
m_crossValidationFolds = crossValidationFolds;
}
/// <summary>
/// Cross validation for evaluating how learning algorithms perform on unseen observations
/// </summary>
/// <param name="sampler">Sampling strategy for the provided indices
/// before they are divided into the provided folds</param>
/// <param name="crossValidationFolds">Number of folds that should be used for cross validation</param>
public CrossValidation(IIndexSampler <double> sampler, int crossValidationFolds)
{
if (sampler == null)
{
throw new ArgumentNullException("shuffler");
}
if (crossValidationFolds < 1)
{
throw new ArgumentException("CrossValidationFolds ");
}
m_indexedSampler = sampler;
m_crossValidationFolds = crossValidationFolds;
}
