/// <summary>
/// Learns a decision tree from the provided observations and targets but limited to the observation indices provided by indices.
/// Indices can contain the same index multiple times. Weights can be provided in order to weight each sample individually
/// </summary>
/// <param name="observations"></param>
/// <param name="targets"></param>
/// <param name="indices"></param>
/// <param name="weights">Provide weights inorder to weigh each sample separetely</param>
/// <returns></returns>
public BinaryTree Learn(F64Matrix observations, double[] targets, int[] indices, double[] weights)
{
using (var pinnedFeatures = observations.GetPinnedPointer())
{
return(Learn(pinnedFeatures.View(), targets, indices, weights));
}
}
public void ArrayExtensions_IndexedCopy_ColumnView_Interval()
{
var values = new double[] { 0, 10, 20, 30, 40, 50 };
var matrix = new F64Matrix(values, 6, 1);
var indices = new int[] { 1, 1, 2, 2, 2, 5 };
var destination = new double[values.Length];
var interval = Interval1D.Create(1, 5);
using (var ptr = matrix.GetPinnedPointer())
{
var view = ptr.View().ColumnView(0);
indices.IndexedCopy(view, interval, destination);
var expected = new double[] { 0, 10, 20, 20, 20, 0 };
CollectionAssert.AreEqual(expected, destination);
}
}
