public void Train(Datas.Useable train)
{
var branch_score = train.getLabelCounts();
int max_correct_branch = branch_score.Values.Max();
if (branch_score.Values.Sum() != max_correct_branch) // All children in one levels
{
var tups = new Tuple <float, float> [train._Labels.Count];
int cols = train._CountColumns;
int rows = train._CountRows;
int best_correct = int.MinValue;
for (int c = 0; c < cols; c++)
{
for (int r = 0; r < rows; r++)
{
tups[r] = new Tuple <float, float>(train._Labels[r], train._Data[r, c]);
}
Array.Sort(tups, (Tuple <float, float> a, Tuple <float, float> b) =>
{ return(a.Item2.CompareTo(b.Item2)); });
var branch_less_data = new Dictionary <float, int>();
var branch_more_data = new Dictionary <float, int>();
foreach (var kvp in branch_score)
{
branch_less_data[kvp.Key] = 0;
branch_more_data[kvp.Key] = kvp.Value;
}
for (int split_point = 0; split_point < rows - 1; split_point++)
{
var tup = tups[split_point];
float this_label = tup.Item1;
float this_value = tup.Item2;
branch_less_data[this_label]++;
branch_more_data[this_label]--;
float next_value = tups[split_point + 1].Item2;
// Skip identical values.
float split_value = (this_value + next_value) / 2;
if ((this_value < split_value) == (next_value < split_value))
{
continue;
}
int correct = branch_less_data.Values.Max() + branch_more_data.Values.Max();
if (correct > best_correct)
{
best_correct = correct;
this._BranchSplitValue = split_value;
this._BranchColumn = c;
this._BranchLessClassification = branch_less_data.ArgMax();
this._BranchMoreClassification = branch_more_data.ArgMax();
}
}
}
if (best_correct != int.MinValue)
{
return;
}
}
this._LeafClassification = branch_score.ArgMax();
this._IsLeaf = true;
}
public void Train(Datas.Useable train, int current_depth)
{
var branch_score = train.getLabelCounts();
int max_correct_branch = branch_score.Values.Max();
if ((branch_score.Values.Sum() != max_correct_branch) && // All children are in one cluster.
(this._MaxDepth != current_depth)) // Limit Levels
{
var tups = new Tuple <float, float> [train._Labels.Count];
int cols = train._CountColumns;
int rows = train._CountRows;
double best_entropy = double.MaxValue;
int best_column = -1;
float best_split = -1;
for (int c = 0; c < cols; c++)
{
for (int r = 0; r < rows; r++)
{
tups[r] = new Tuple <float, float>(train._Labels[r], train._Data[r, c]);
}
Array.Sort(tups, (Tuple <float, float> a, Tuple <float, float> b) =>
{ return(a.Item2.CompareTo(b.Item2)); });
var branch_less_data = new Dictionary <float, int>();
var branch_more_data = new Dictionary <float, int>();
foreach (var kvp in branch_score)
{
branch_less_data[kvp.Key] = 0;
branch_more_data[kvp.Key] = kvp.Value;
}
for (int split_point = 0; split_point < rows - 1; split_point++)
{
var tup = tups[split_point];
float this_label = tup.Item1;
float this_value = tup.Item2;
branch_less_data[this_label]++;
branch_more_data[this_label]--;
float next_value = tups[split_point + 1].Item2;
// Skip identical values.
float split_value = (this_value + next_value) / 2;
if ((this_value < split_value) == (next_value < split_value))
{
continue;
}
double p_less = (split_point + 1.0) / rows;
double p_more = 1 - p_less;
double entropy = p_less * branch_less_data.Values.Entropy() +
p_more * branch_more_data.Values.Entropy();
if (entropy < best_entropy)
{
best_entropy = entropy;
best_split = split_value;
best_column = c;
}
}
}
if (best_column != -1)
{
this._BranchSplitValue = best_split;
this._BranchColumn = best_column;
Datas.Useable less, more;
train.Split(
this._BranchColumn,
this._BranchSplitValue,
out less,
out more);
this._BranchLess = new DecisionTree(this._MaxDepth);
this._BranchMore = new DecisionTree(this._MaxDepth);
this._BranchLess.Train(less, current_depth + 1);
this._BranchMore.Train(more, current_depth + 1);
return;
}
}
this._LeafClassification = branch_score.ArgMax();
this._IsLeaf = true;
}