/**
* Compute relative variable importance for GBM model.
*
* <p>See (45), (35) formulas in Friedman: Greedy Function Approximation: A Gradient boosting
* machine. Algo used here can be used for computation individual importance of features per
* output class.
*/
@Override
protected VarImp doVarImpCalc(
GBMModel model, DTree[] ktrees, int tid, Frame validationFrame, boolean scale) {
assert model.ntrees() - 1 == tid
: "varimp computation expect model with already serialized trees: tid=" + tid;
// Iterates over k-tree
for (DTree t : ktrees) { // Iterate over trees
if (t != null) {
for (int n = 0; n < t.len() - t.leaves; n++)
if (t.node(n) instanceof DecidedNode) { // it is split node
Split split = t.decided(n)._split;
_improvPerVar[split._col] += split.improvement(); // least squares improvement
}
}
}
// Compute variable importance for all trees in model
float[] varimp = new float[model.nfeatures()];
int ntreesTotal = model.ntrees() * model.nclasses();
int maxVar = 0;
for (int var = 0; var < _improvPerVar.length; var++) {
varimp[var] = _improvPerVar[var] / ntreesTotal;
if (varimp[var] > varimp[maxVar]) maxVar = var;
}
// GBM scale varimp to scale 0..100
if (scale) {
float maxVal = varimp[maxVar];
for (int var = 0; var < varimp.length; var++) varimp[var] /= maxVal;
}
return new VarImp(varimp);
}
@Override
protected void initAlgo(GBMModel initialModel) {
// Initialize gbm-specific data structures
if (importance) _improvPerVar = new float[initialModel.nfeatures()];
}
