/// <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;
}
public void TreeNotEqualTest()
{
Vertex.Reset();
Tree g1 = new Tree();
var r1 = new Vertex();
g1.Root = r1;
g1.AddVertex(r1); // 1
g1.AddVertex(new Vertex()); // 2
g1.AddVertex(new Vertex()); // 3
g1.AddVertex(new Vertex()); // 4
g1.AddVertex(new Vertex()); // 5
g1.AddVertex(new Vertex()); // 6
g1.AddVertex(new Vertex()); // 7
g1.AddEdge(new Edge { ParentId = 1, ChildId = 2 });
g1.AddEdge(new Edge { ParentId = 1, ChildId = 3 });
g1.AddEdge(new Edge { ParentId = 2, ChildId = 4 });
g1.AddEdge(new Edge { ParentId = 2, ChildId = 5 });
g1.AddEdge(new Edge { ParentId = 3, ChildId = 6 });
g1.AddEdge(new Edge { ParentId = 3, ChildId = 7 });
Vertex.Reset();
Tree g2 = new Tree();
var r2 = new Vertex();
g2.Root = r2;
g2.AddVertex(r2); // 1
g2.AddVertex(new Vertex()); // 2
g2.AddVertex(new Vertex()); // 3
g2.AddVertex(new Vertex()); // 4
g2.AddVertex(new Vertex()); // 5
g2.AddVertex(new Vertex()); // 6
g2.AddVertex(new Vertex()); // 7
g2.AddEdge(new Edge { ParentId = 1, ChildId = 2 });
g2.AddEdge(new Edge { ParentId = 1, ChildId = 3 });
g2.AddEdge(new Edge { ParentId = 2, ChildId = 4 });
g2.AddEdge(new Edge { ParentId = 2, ChildId = 5 });
g2.AddEdge(new Edge { ParentId = 1, ChildId = 6 });
g2.AddEdge(new Edge { ParentId = 3, ChildId = 7 });
Assert.False(g1.Equals(g2));
}
/// <summary>Generates.</summary>
/// <exception cref="InvalidOperationException">Thrown when the requested operation is invalid.</exception>
/// <param name="X">The Matrix to process.</param>
/// <param name="y">The Vector to process.</param>
/// <returns>An IModel.</returns>
public override IModel Generate(Matrix X, Vector y)
{
if (Descriptor == null)
throw new InvalidOperationException("Cannot build decision tree without type knowledge!");
this.Preprocess(X);
var tree = new Tree();
//var n = BuildUglyTree(x, y, Depth, new List<int>(x.Cols));
tree.Root = BuildTree(X, y, Depth, new List<int>(X.Cols), tree);
// have to guess something....
// especially when automating
// the thing in a Learner
// this only happens if it is something
// it has never seen.
if (Hint == double.Epsilon)
Hint = y.GetRandom(); // flip a coin...
return new DecisionTreeModel
{
Descriptor = Descriptor,
NormalizeFeatures = NormalizeFeatures,
FeatureNormalizer = FeatureNormalizer,
FeatureProperties = FeatureProperties,
Tree = tree,
Hint = Hint
};
}
