public Classifier(BuildDecisionTree tree, Hashtable item)
{
while (true)
{
if (tree.Category != null)
{
result = tree.Category;
return;
}
double itemValue = (double)item[tree.SplitAttribute];
if (itemValue >= tree.SplitPivot)
{
tree = tree.MatchSubTree;
}
else
{
tree = tree.NotMatchSubTree;
}
}
}
public BuildDecisionTree(Hashtable[] trainingSet, int maxTreeDepth)
{
{
// Checking if maxTreeDepth/minItemsCount is reached
if (maxTreeDepth == 0 || trainingSet.Length <= minItemsCount)
{
category = MostFrequentValue(trainingSet, categoryAttribute);
return;
}
double initialEntropy = Entropy(trainingSet, categoryAttribute);
// Checking if entropyThreshold is reached
if (initialEntropy <= entropyThreshold)
{
category = MostFrequentValue(trainingSet, categoryAttribute);
return;
}
Hashtable bestSplit = new Hashtable();
bestSplit.Add("gain", 0);
List <string> alreadyChecked = new List <string>();
for (int i = 0; i < trainingSet.Length; i++)
{
Hashtable instance = trainingSet[i];
ICollection keys = instance.Keys;
// Iterating over all attributes of instance
foreach (object attribute in keys)
{
if (Convert.ToString(attribute) == categoryAttribute)
{
continue;
}
// Let the value of current attribute be the pivot
double pivot = (Convert.ToDouble(instance[attribute]));
string attributePivot = attribute + Convert.ToString(pivot);
if (alreadyChecked.Contains(attributePivot))
{
continue;
}
alreadyChecked.Add(attributePivot);
// Splitting training set
Hashtable currentSplit = Split(trainingSet, attribute, pivot);
// Calculating entropy of subsets
double matchEntropy = Entropy((Hashtable[])currentSplit["match"], categoryAttribute);
double notMatchEntropy = Entropy((Hashtable[])currentSplit["notMatch"], categoryAttribute);
// Calculating informational gain
double newEntropy = 0;
newEntropy += matchEntropy * ((Hashtable[])currentSplit["match"]).Length;
newEntropy += notMatchEntropy * ((Hashtable[])currentSplit["notMatch"]).Length;
newEntropy /= trainingSet.Length;
double currentGain = initialEntropy - newEntropy;
if (currentGain > Convert.ToDouble(bestSplit["gain"]))
{
bestSplit = currentSplit;
bestSplit.Add("splitAttribute", attribute);
bestSplit.Add("splitPivot", pivot);
bestSplit.Add("gain", currentGain);
}
}
}
if (Convert.ToDouble(bestSplit["gain"]) == 0)
{
category = MostFrequentValue(trainingSet, categoryAttribute);
}
// Building subtrees
maxTreeDepth--;
matchSubTree = new BuildDecisionTree((Hashtable[])bestSplit["match"], maxTreeDepth);
notMatchSubTree = new BuildDecisionTree((Hashtable[])bestSplit["notMatch"], maxTreeDepth);
splitAttribute = Convert.ToString(bestSplit["splitAttribute"]);
splitPivot = Convert.ToDouble(bestSplit["splitPivot"]);
matchedLength = ((Hashtable[])bestSplit["match"]).Length;
notMatchedLength = ((Hashtable[])bestSplit["notMatch"]).Length;
}
}
