public void Can_split_dataset()
{
var matrix = GetDataSet();
var tree = new DecisionTreeNode(matrix);
var result = tree.Split(0, 1);
// { {1, 1}, {1, 1}, {0, 0} }
Assert.IsNotNull(result);
foreach(var row in result)
{
Assert.AreEqual(2, row.Length);
Assert.AreEqual(row[0], row[1]);
}
result = tree.Split(0, 0);
// { {1, 0}, {1, 0} }
Assert.IsNotNull(result);
foreach (var row in result)
{
Assert.AreEqual(2, row.Length);
Assert.AreNotEqual(row[0], row[1]);
}
}
private static void ReverseNodeOrder(DecisionTreeNode casted)
{
var reversed = casted.Children.Reverse().ToList();
casted.Children.Clear();
foreach(var item in reversed)
{
casted.Children.Add(item);
}
}
public void Can_get_gain_grid_with_classification_error()
{
var matrix = GetDataSet();
var tree = new DecisionTreeNode(matrix);
var grid = tree.GetInformationGain(DisorderType.ClassificationError);
Assert.IsNotNull(grid);
Assert.AreEqual(3, grid.Count);
Assert.AreEqual(1, grid.First().Key);
Assert.AreEqual(2, grid.Last().Key);
}
public void Can_get_gain_grid_with_gini_impurity()
{
var matrix = GetDataSet();
var tree = new DecisionTreeNode(matrix);
var grid = tree.GetInformationGain(DisorderType.GiniImpurity);
Assert.IsNotNull(grid);
Assert.AreEqual(3, grid.Count);
Assert.AreEqual(0, grid.First().Key);
Assert.AreEqual(1, grid.Last().Key);
}
private static ITreeNode CreateTree(Matrix dataSet, IList<string> labels, DisorderType disorderType)
{
var outcomes = dataSet.GetOutcomes();
if(outcomes.Distinct().Count().Equals(1))
{
return new DecisionTreeLeafNode(outcomes[0]);
}
var outcome = dataSet.GetMajorityOutcome();
if(dataSet.Columns == 1)
{
return new DecisionTreeLeafNode(outcome);
}
ITreeNode node = new DecisionTreeNode(dataSet, outcome);
var casted = (DecisionTreeNode) node;
var best = casted.GetInformationGain(disorderType).First();
var label = labels[best.Key];
casted.Label = label;
labels = labels.Where(l => !l.Equals(label)).ToList();
var subset = dataSet.Select(row => row[best.Key]).ToList();
var values = subset.Distinct().ToList();
foreach(var value in values)
{
var copy = new List<string>(labels);
var split = casted.Split(best.Key, value);
var child = CreateTree(split, copy, disorderType);
casted.AddChild(child);
}
ReverseNodeOrder(casted);
return node;
}
