public KeyValuePair <string, Dictionary <string, DecisionTreeNode <T> > > Prune()
{
Dictionary <string, DecisionTreeNode <T> > children = mChildren;
KeyValuePair <string, Dictionary <string, DecisionTreeNode <T> > > tree_info = new KeyValuePair <string, Dictionary <string, DecisionTreeNode <T> > >(
mSplitVariableName,
children);
DecisionTreePartition <T> partition = DecisionTreePartition <T> .Create(this);
Dictionary <string, DecisionTreePartition <T> > sub_partitions_by_class_variable = DecisionTreeMethods.SplitPartitionByClassVariable <T>(partition, (gain, feature_name) =>
{
if (HandleCost != null)
{
return(HandleCost(gain, feature_name));
}
return(gain);
});
partition.UpdateSubPartitions(sub_partitions_by_class_variable, DecisionTree <T> .ClassVariableName);
return(tree_info);
}
public static void Split <T>(DecisionTreePartition <T> partition, HashSet <string> feature_variable_names, DoAttributeCostGainHandle handle_cost)
where T : DDataRecord
{
if (feature_variable_names.Count == 0)
{
Dictionary <string, DecisionTreePartition <T> > sub_partitions_by_class_variable = SplitPartitionByClassVariable(partition, handle_cost);
partition.UpdateSubPartitions(sub_partitions_by_class_variable, DecisionTree <T> .ClassVariableName);
return;
}
double max_information_gain = 0;
string selected_feature_name = null;
HashSet <string> temp_feature_variable_names = null;
if (partition.Forest == null)
{
temp_feature_variable_names = feature_variable_names.Clone();
}
else // if in random forest, select a random subset of features to split
{
int subset_featire_variable_count = partition.Forest.FeatureSubsetSize;
List <string> temp_names = feature_variable_names.ToList();
temp_names.Shuffle();
temp_feature_variable_names = new HashSet <string>();
for (int i = 0; i < subset_featire_variable_count; ++i)
{
temp_feature_variable_names.Add(temp_names[i]);
}
}
foreach (string variable_name in temp_feature_variable_names)
{
double g = CalcInformationGain(partition, variable_name, handle_cost);
if (max_information_gain < g)
{
max_information_gain = g;
selected_feature_name = variable_name;
}
}
partition.SplitInformationGain = max_information_gain;
if (selected_feature_name == null) // this suggest the children of the nodes are leave nodes
{
Dictionary <string, DecisionTreePartition <T> > sub_partitions_by_class_variable = SplitPartitionByClassVariable(partition, handle_cost);
partition.UpdateSubPartitions(sub_partitions_by_class_variable, DecisionTree <T> .ClassVariableName);
}
else
{
if (partition.Forest == null) // if not in random forest, remove the used feature variable; otherwise, keep all and in subsequent split, select random subset
{
feature_variable_names.Remove(selected_feature_name);
}
Dictionary <string, DecisionTreePartition <T> > sub_partitions_by_feature_name = SplitPartitionByFeatureVariable(partition, selected_feature_name, handle_cost);
partition.UpdateSubPartitions(sub_partitions_by_feature_name, selected_feature_name);
if (feature_variable_names.Count > 0)
{
foreach (DecisionTreePartition <T> sub_partition_by_feature_name in sub_partitions_by_feature_name.Values)
{
Split(sub_partition_by_feature_name, feature_variable_names.Clone(), handle_cost);
}
}
}
}
