DecisionStump<MatType>::DecisionStump(const MatType& data,
const arma::Row<size_t>& labels,
const size_t classes,
size_t inpBucketSize)
{
numClass = classes;
bucketSize = inpBucketSize;
// If classLabels are not all identical, proceed with training.
int bestAtt = 0;
double entropy;
const double rootEntropy = CalculateEntropy<size_t>(
labels.subvec(0, labels.n_elem - 1));
double gain, bestGain = 0.0;
for (int i = 0; i < data.n_rows; i++)
{
// Go through each attribute of the data.
if (IsDistinct<double>(data.row(i)))
{
// For each attribute with non-identical values, treat it as a potential
// splitting attribute and calculate entropy if split on it.
entropy = SetupSplitAttribute(data.row(i), labels);
// Rcpp::Rcout << "Entropy for attribute " << i << " is " << entropy << ".\n";
gain = rootEntropy - entropy;
// Find the attribute with the best entropy so that the gain is
// maximized.
// if (entropy < bestEntropy)
// Instead of the above rule, we are maximizing gain, which was
// what is returned from SetupSplitAttribute.
if (gain < bestGain)
{
bestAtt = i;
bestGain = gain;
}
}
}
splitAttribute = bestAtt;
// Once the splitting column/attribute has been decided, train on it.
TrainOnAtt<double>(data.row(splitAttribute), labels);
}
void DecisionStump<MatType>::Train(const MatType& data,
const arma::Row<size_t>& labels,
const arma::rowvec& weights)
{
this->classes = classes;
this->bucketSize = bucketSize;
// If classLabels are not all identical, proceed with training.
size_t bestDim = 0;
double entropy;
const double rootEntropy = CalculateEntropy<UseWeights>(labels, weights);
double gain, bestGain = 0.0;
for (size_t i = 0; i < data.n_rows; i++)
{
// Go through each dimension of the data.
if (IsDistinct(data.row(i)))
{
// For each dimension with non-identical values, treat it as a potential
// splitting dimension and calculate entropy if split on it.
entropy = SetupSplitDimension<UseWeights>(data.row(i), labels, weights);
gain = rootEntropy - entropy;
// Find the dimension with the best entropy so that the gain is
// maximized.
// We are maximizing gain, which is what is returned from
// SetupSplitDimension().
if (gain < bestGain)
{
bestDim = i;
bestGain = gain;
}
}
}
splitDimension = bestDim;
// Once the splitting column/dimension has been decided, train on it.
TrainOnDim(data.row(splitDimension), labels);
}
RegularizedSVDFunction<MatType>::RegularizedSVDFunction(const MatType& data,
const size_t rank,
const double lambda) :
data(math::MakeAlias(const_cast<MatType&>(data), false)),
rank(rank),
lambda(lambda)
{
// Number of users and items in the data.
numUsers = max(data.row(0)) + 1;
numItems = max(data.row(1)) + 1;
// Initialize the parameters.
initialPoint.randu(rank, numUsers + numItems);
}
