void RandomTree::findProximity(DataFrame & data, std::vector<unsigned int> & proximity)
{
std::vector<unsigned int> proxVec;
unsigned int dSize = data.getNumDataVectors();
proxVec.resize(dSize);
//Find out which node each vector is classified as
for(unsigned int i = 0; i < dSize; i++)
{
std::string resultClass;
unsigned int nodeId = classifyDataVector(data.getDataVector(i), resultClass);
proxVec[i] = nodeId;
}
for(unsigned int j = 0; j < dSize; j++)
{
unsigned int tempId = proxVec[j];
for(unsigned int k = j; k < dSize;j++)
{
if(proxVec[k] == tempId)
{
proximity[j * dSize + k] += 1;
}
}
}
}
double RandomTree::computeErrorRate(DataFrame & data)
{
unsigned int correct = 0;
unsigned int incorrect = 0;
std::string result;
for(unsigned int i = 0; i < _oobSet.size(); i++)
{
classifyDataVector(data.getDataVector(_oobSet[i]), result);
if(result == data.getTrainingLabel(_oobSet[i]))
{
correct++;
}
else
{
incorrect++;
}
}
return (double)incorrect / (double)(incorrect + correct);
}
