/// <summary>Builds a tree.</summary>
/// <param name="x">The Matrix to process.</param>
/// <param name="y">The Vector to process.</param>
/// <param name="depth">The depth.</param>
/// <param name="used">The used.</param>
/// <returns>A Node.</returns>
private Node BuildTree(Matrix x, Vector y, int depth, List<int> used, Tree tree)
{
if (depth < 0)
return BuildLeafNode(y.Mode());
var tuple = GetBestSplit(x, y, used);
var col = tuple.Item1;
var gain = tuple.Item2;
var measure = tuple.Item3;
// uh oh, need to return something?
// a weird node of some sort...
// but just in case...
if (col == -1)
return BuildLeafNode(y.Mode());
used.Add(col);
Node node = new Node
{
Column = col,
Gain = gain,
IsLeaf = false,
Name = Descriptor.ColumnAt(col)
};
// populate edges
List<Edge> edges = new List<Edge>(measure.Segments.Length);
for (int i = 0; i < measure.Segments.Length; i++)
{
// working set
var segment = measure.Segments[i];
var edge = new Edge()
{
ParentId = node.Id,
Discrete = measure.Discrete,
Min = segment.Min,
Max = segment.Max
};
IEnumerable<int> slice;
if (edge.Discrete)
{
// get discrete label
edge.Label = Descriptor.At(col).Convert(segment.Min).ToString();
// do value check for matrix slicing
slice = x.Indices(v => v[col] == segment.Min);
}
else
{
// get range label
edge.Label = string.Format("{0} <= x < {1}", segment.Min, segment.Max);
// do range check for matrix slicing
slice = x.Indices(v => v[col] >= segment.Min && v[col] < segment.Max);
}
// something to look at?
// if this number is 0 then this edge
// leads to a dead end - the edge will
// not be built
if (slice.Count() > 0)
{
Vector ySlice = y.Slice(slice);
// only one answer, set leaf
if (ySlice.Distinct().Count() == 1)
{
var child = BuildLeafNode(ySlice[0]);
tree.AddVertex(child);
edge.ChildId = child.Id;
}
// otherwise continue to build tree
else
{
var child = BuildTree(x.Slice(slice), ySlice, depth - 1, used, tree);
tree.AddVertex(child);
edge.ChildId = child.Id;
}
edges.Add(edge);
}
}
// problem, need to convert
// parent to terminal node
// with mode
if (edges.Count <= 1)
{
var val = y.Mode();
node.IsLeaf = true;
node.Value = val;
}
tree.AddVertex(node);
if(edges.Count > 1)
foreach (var e in edges)
tree.AddEdge(e);
return node;
}