public DecisionNode(int col, object value, DecisionNode tb, DecisionNode fb)
{
Col = col;
Value = value;
Tb = tb;
Fb = fb;
}
public Dictionary <string, float> MdClassify(object[] observation, DecisionNode tree)
{
if (tree.Results != null)
{
return(tree.Results.ToDictionary(r => r.Key, r => (float)r.Value));
}
var v = observation[tree.Col];
if (v == null)
{
var tr = MdClassify(observation, tree.Tb);
var fr = MdClassify(observation, tree.Fb);
var tcount = tr.Values.Count;
var fcount = fr.Values.Count;
var tw = tcount / (float)(tcount + fcount);
var fw = fcount / (float)(tcount + fcount);
var result = tr.ToDictionary(trKvp => trKvp.Key, trKvp => trKvp.Value * tw);
foreach (var frKvp in fr)
{
if (!result.ContainsKey(frKvp.Key))
{
result.Add(frKvp.Key, 0);
}
result[frKvp.Key] += frKvp.Value * fw;
}
return(result);
}
else
{
DecisionNode branch;
if (v is int || v is float)
{
var val = v is int?Convert.ToInt32(v) : Convert.ToSingle(v);
var treeVal = tree.Value is int?Convert.ToInt32(tree.Value) : Convert.ToSingle(tree.Value);
branch = val >= treeVal ? tree.Tb : tree.Fb;
}
else
{
branch = v.ToString() == tree.Value.ToString() ? tree.Tb : tree.Fb;
}
return(MdClassify(observation, branch));
}
}
public void PrintTree(DecisionNode tree, string indent = "")
{
//是叶节点吗？
if (tree.Results != null)
{
Console.WriteLine(JsonConvert.SerializeObject(tree.Results));
}
else
{
//打印判断条件
Console.WriteLine($"{tree.Col}:{tree.Value}? ");
//打印分支
Console.Write($"{indent}T->");
PrintTree(tree.Tb, indent + " ");
Console.Write($"{indent}F->");
PrintTree(tree.Fb, indent + " ");
}
}
public Dictionary <string, int> Classify(object[] observation, DecisionNode tree)
{
if (tree.Results != null)
{
return(tree.Results);
}
var v = observation[tree.Col];
DecisionNode branch;
if (v is int || v is float)
{
var val = v is int?Convert.ToInt32(v) : Convert.ToSingle(v);
var treeVal = tree.Value is int?Convert.ToInt32(tree.Value) : Convert.ToSingle(tree.Value);
branch = val >= treeVal ? tree.Tb : tree.Fb;
}
else
{
branch = v.ToString() == tree.Value.ToString() ? tree.Tb : tree.Fb;
}
return(Classify(observation, branch));
}
public void Prune(DecisionNode tree, float mingain)
{
//如果分支不是叶节点，则进行剪枝操作
if (tree.Tb.Results == null)
{
Prune(tree.Tb, mingain);
}
if (tree.Fb.Results == null)
{
Prune(tree.Fb, mingain);
}
//如果两个子分支都是叶节点，则判断是否需要合并
if (tree.Tb.Results != null && tree.Fb.Results != null)
{
//构造合并后的数据集
IEnumerable <object[]> tb = new List <object[]>();
IEnumerable <object[]> fb = new List <object[]>();
tb = tree.Tb.Results.Aggregate(tb, (current, tbKvPair)
=> current.Union(ArrayList.Repeat(new object[] { tbKvPair.Key }, (int)tbKvPair.Value).Cast <object[]>()));
fb = tree.Fb.Results.Aggregate(fb, (current, tbKvPair)
=> current.Union(ArrayList.Repeat(new object[] { tbKvPair.Key }, (int)tbKvPair.Value).Cast <object[]>()));
//检查熵增加情况
var mergeNode = tb.Union(fb).ToList();
var delta = Entropy(mergeNode) - (Entropy(tb.ToList()) + Entropy(fb.ToList()) / 2);
Debug.WriteLine(delta);
if (delta < mingain)
{
//合并分支
tree.Tb = null;
tree.Fb = null;
tree.Results = UniqueCounts(mergeNode);
}
}
}
