public static bool isTrivial(DTNode node)
{
for (int i = 0; i < node.getTrainingSet().Count - 1; i++)
{
if (node.getTrainingSet()[i].getResult().Equals
(node.getTrainingSet()[i + 1].getResult()) == false)
{
return(false);
}
}
return(true);
}
public static void buildTree(DTNode root)
{
if (isTrivial(root) == true)
{
root.setResult(root.getTrainingSet()[0].getResult());
}
else if (root.getAttrNames().Count == 0)
{
// set as a result the most frequent class in training set
Dictionary <String, int> classCount = new Dictionary <String, int>();
foreach (String className in root.getClasses())
{
classCount.Add(className, 0);
}
// get entropy of all training set
foreach (Example example in root.getTrainingSet())
{
int value;
if (classCount.TryGetValue(example.getResult(), out value))
{
classCount[example.getResult()] = value + 1;
}
}
int maxCount = 0;
String classResult = "";
foreach (KeyValuePair <String, int> entry in classCount)
{
if (maxCount < entry.Value)
{
maxCount = entry.Value;
classResult = entry.Key;
}
}
root.setResult(classResult);
}
else
{
// find attribute with maximum gain
GainResult gainResult = new GainResult();
GainResult gainResultMax = new GainResult();
gainResultMax.setGain(0.0);
int resultIndex = 0;
for (int i = 0; i < root.getAttrNames().Count; i++)
{
gainResult = getGain(root.getTrainingSet(), root.getAttrNames()[i], root.getClasses());
gainResult.setGain(getEntropy(root.getTrainingSet(), root.getClasses(), root.getAttrNames()[i], -1) -
gainResult.getGain());
if (gainResultMax.getGain() < gainResult.getGain())
{
gainResultMax.setGain(gainResult.getGain());
gainResultMax.setPartitionIndex(gainResult.getPartitionIndex());
resultIndex = i;
}
}
String attributeNode = root.getAttrNames()[resultIndex];
root.getAttrNames().RemoveAt(resultIndex);
// sort training list by the attribute with maximum gain
root.getTrainingSet().Sort(new ExampleComparator(attributeNode));
// form children
for (int i = 0; i < 2; i++)
{
List <String> newAttrNames = new List <String>();
foreach (String str in root.getAttrNames())
{
newAttrNames.Add(str);
}
List <String> newClassNames = new List <String>();
foreach (String str in root.getClasses())
{
newClassNames.Add(str);
}
DTNode child = new DTNode(new List <Example>(), newAttrNames, newClassNames);
List <Example> newTrainingSet = new List <Example>();
Condition condition = new Condition();
if (i == 0)
{
for (int p = 0; p <= gainResultMax.getPartitionIndex(); p++)
{
Example example = root.getTrainingSet()[p];
Example newExample = new Example();
// copy result
newExample.setResult(example.getResult());
// copy attribute values
Dictionary <String, Double> newAttributes = new Dictionary <String, Double>();
foreach (KeyValuePair <String, Double> entry in example.getAttributes())
{
newAttributes.Add(entry.Key, entry.Value);
}
newExample.setAttributes(newAttributes);
newTrainingSet.Add(newExample);
}
condition.setOperator(Constants.conditionType.LT);
}
else
{
for (int p = gainResultMax.getPartitionIndex() + 1; p < root.getTrainingSet().Count; p++)
{
Example example = root.getTrainingSet()[p];
Example newExample = new Example();
// copy result
newExample.setResult(example.getResult());
// copy attribute values
Dictionary <String, Double> newAttributes = new Dictionary <String, Double>();
foreach (KeyValuePair <String, Double> entry in example.getAttributes())
{
newAttributes.Add(entry.Key, entry.Value);
}
newExample.setAttributes(newAttributes);
newTrainingSet.Add(newExample);
}
condition.setOperator(Constants.conditionType.GEQT);
}
condition.setMember1(attributeNode);
double leftValue = root.getTrainingSet()[gainResultMax.getPartitionIndex()].getValue(attributeNode);
double rightValue = root.getTrainingSet()[gainResultMax.getPartitionIndex() + 1].getValue(attributeNode);
condition.setMember2((leftValue + rightValue) / 2);
child.setTrainingSet(newTrainingSet);
root.getChildren().Add(child, condition);
buildTree(child);
}
}
}
public static void buildTree(DTNode root) {
if (isTrivial(root) == true) {
root.setResult(root.getTrainingSet()[0].getResult());
}
else if (root.getAttrNames().Count == 0) {
// set as a result the most frequent class in training set
Dictionary<String, int> classCount = new Dictionary<String, int>();
foreach (String className in root.getClasses()) {
classCount.Add(className, 0);
}
// get entropy of all training set
foreach (Example example in root.getTrainingSet()) {
int value;
if (classCount.TryGetValue(example.getResult(), out value))
{
classCount[example.getResult()] = value+1;
}
}
int maxCount = 0;
String classResult = "";
foreach(KeyValuePair<String, int> entry in classCount)
{
if (maxCount < entry.Value) {
maxCount = entry.Value;
classResult = entry.Key;
}
}
root.setResult(classResult);
}
else {
// find attribute with maximum gain
GainResult gainResult = new GainResult();
GainResult gainResultMax = new GainResult();
gainResultMax.setGain(0.0);
int resultIndex = 0;
for (int i=0; i<root.getAttrNames().Count; i++) {
gainResult = getGain(root.getTrainingSet(), root.getAttrNames()[i], root.getClasses());
gainResult.setGain(getEntropy(root.getTrainingSet(), root.getClasses(), root.getAttrNames()[i], -1) -
gainResult.getGain());
if (gainResultMax.getGain() < gainResult.getGain()) {
gainResultMax.setGain(gainResult.getGain());
gainResultMax.setPartitionIndex(gainResult.getPartitionIndex());
resultIndex = i;
}
}
String attributeNode = root.getAttrNames()[resultIndex];
root.getAttrNames().RemoveAt(resultIndex);
// sort training list by the attribute with maximum gain
root.getTrainingSet().Sort(new ExampleComparator(attributeNode));
// form children
for (int i=0; i<2; i++)
{
List<String> newAttrNames = new List<String>();
foreach (String str in root.getAttrNames()) {
newAttrNames.Add(str);
}
List<String> newClassNames = new List<String>();
foreach (String str in root.getClasses()) {
newClassNames.Add(str);
}
DTNode child = new DTNode(new List<Example>(), newAttrNames, newClassNames);
List<Example> newTrainingSet = new List<Example>();
Condition condition = new Condition();
if (i == 0) {
for (int p=0; p <= gainResultMax.getPartitionIndex(); p++) {
Example example = root.getTrainingSet()[p];
Example newExample = new Example();
// copy result
newExample.setResult(example.getResult());
// copy attribute values
Dictionary<String, Double> newAttributes = new Dictionary<String, Double>();
foreach (KeyValuePair<String, Double> entry in example.getAttributes())
{
newAttributes.Add(entry.Key, entry.Value);
}
newExample.setAttributes(newAttributes);
newTrainingSet.Add(newExample);
}
condition.setOperator(Constants.conditionType.LT);
}
else {
for (int p=gainResultMax.getPartitionIndex()+1; p<root.getTrainingSet().Count; p++) {
Example example = root.getTrainingSet()[p];
Example newExample = new Example();
// copy result
newExample.setResult(example.getResult());
// copy attribute values
Dictionary<String, Double> newAttributes = new Dictionary<String, Double>();
foreach (KeyValuePair<String, Double> entry in example.getAttributes())
{
newAttributes.Add(entry.Key, entry.Value);
}
newExample.setAttributes(newAttributes);
newTrainingSet.Add(newExample);
}
condition.setOperator(Constants.conditionType.GEQT);
}
condition.setMember1(attributeNode);
double leftValue = root.getTrainingSet()[gainResultMax.getPartitionIndex()].getValue(attributeNode);
double rightValue = root.getTrainingSet()[gainResultMax.getPartitionIndex()+1].getValue(attributeNode);
condition.setMember2((leftValue+rightValue)/2);
child.setTrainingSet(newTrainingSet);
root.getChildren().Add(child, condition);
buildTree(child);
}
}
}
public static bool isTrivial(DTNode node)
{
for (int i = 0; i < node.getTrainingSet().Count - 1; i++)
{
if (node.getTrainingSet()[i].getResult().Equals
(node.getTrainingSet()[i+1].getResult()) == false)
return false;
}
return true;
}