@Override
public void onCompletion(CountedCompleter caller) {
ScoreBuildHistogram sbh = (ScoreBuildHistogram) caller;
// System.out.println(sbh.profString());
final int leafk = _leafs[_k];
int tmax = _tree.len(); // Number of total splits in tree K
for (int leaf = leafk; leaf < tmax; leaf++) { // Visit all the new splits (leaves)
DTree.UndecidedNode udn = _tree.undecided(leaf);
// System.out.println((_st._nclass==1?"Regression":("Class
// "+_fr2.vecs()[_st._ncols].domain()[_k]))+",\n Undecided node:"+udn);
// Replace the Undecided with the Split decision
DTree.DecidedNode dn = _st.makeDecided(udn, sbh._hcs[leaf - leafk]);
// System.out.println(dn +
// " > Split: " + dn._split + " L/R:" + dn._split._n0+" +
// "+dn._split._n1);
if (dn._split._col == -1) udn.do_not_split();
else {
_did_split = true;
DTree.Split s = dn._split; // Accumulate squared error improvements per variable
AtomicUtils.FloatArray.add(_improvPerVar, s.col(), (float) (s.pre_split_se() - s.se()));
}
}
_leafs[_k] = tmax; // Setup leafs for next tree level
int new_leafs = _tree.len() - tmax;
_hcs[_k] = new DHistogram[new_leafs][ /*ncol*/];
for (int nl = tmax; nl < _tree.len(); nl++) _hcs[_k][nl - tmax] = _tree.undecided(nl)._hs;
if (_did_split) _tree._depth++;
}
/**
* Initialize the ModelBuilder, validating all arguments and preparing the training frame. This
* call is expected to be overridden in the subclasses and each subclass will start with
* "super.init();". This call is made by the front-end whenever the GUI is clicked, and needs to
* be fast; heavy-weight prep needs to wait for the trainModel() call.
*/
@Override
public void init(boolean expensive) {
super.init(expensive);
// Initialize local variables
if (!(0.0 < _parms._sample_rate && _parms._sample_rate <= 1.0))
throw new IllegalArgumentException(
"Sample rate should be interval (0,1> but it is " + _parms._sample_rate);
if (_parms._mtries < 1 && _parms._mtries != -1)
error(
"_mtries",
"mtries must be -1 (converted to sqrt(features)), or >= 1 but it is " + _parms._mtries);
if (_train != null) {
int ncols = _train.numCols();
if (_parms._mtries != -1 && !(1 <= _parms._mtries && _parms._mtries < ncols))
error(
"_mtries",
"Computed mtries should be -1 or in interval <1,#cols> but it is " + _parms._mtries);
}
if (_parms._sample_rate == 1f && _valid == null)
error(
"_sample_rate",
"Sample rate is 100% and no validation dataset is specified. There are no OOB data to compute out-of-bag error estimation!");
if (hasOffset()) error("_offset_column", "Offsets are not yet supported for DRF.");
if (hasOffset() && isClassifier()) {
error("_offset_column", "Offset is only supported for regression.");
}
}
/**
* Initialize the ModelBuilder, validating all arguments and preparing the training frame. This
* call is expected to be overridden in the subclasses and each subclass will start with
* "super.init();". This call is made by the front-end whenever the GUI is clicked, and needs to
* be fast; heavy-weight prep needs to wait for the trainModel() call.
*/
@Override
public void init(boolean expensive) {
super.init(expensive);
// Initialize local variables
if (!(0.0 < _parms._sample_rate && _parms._sample_rate <= 1.0))
throw new IllegalArgumentException(
"Sample rate should be interval [0,1] but it is " + _parms._sample_rate);
if (_parms._mtries < 1 && _parms._mtries != -1)
error(
"_mtries",
"mtries must be -1 (converted to sqrt(features)), or >= 1 but it is " + _parms._mtries);
if (_train != null) {
int ncols = _train.numCols();
if (_parms._mtries != -1 && !(1 <= _parms._mtries && _parms._mtries < ncols))
error(
"_mtries",
"Computed mtries should be -1 or in interval [1,"
+ ncols
+ "] but it is "
+ _parms._mtries);
}
if (_parms._distribution == Distribution.Family.AUTO) {
if (_nclass == 1) _parms._distribution = Distribution.Family.gaussian;
if (_nclass >= 2) _parms._distribution = Distribution.Family.multinomial;
}
if (expensive) {
_initialPrediction = isClassifier() ? 0 : getInitialValue();
}
if (_parms._sample_rate == 1f && _valid == null)
error(
"_sample_rate",
"Sample rate is 100% and no validation dataset is specified. There are no OOB data to compute out-of-bag error estimation!");
if (hasOffsetCol()) error("_offset_column", "Offsets are not yet supported for DRF.");
if (hasOffsetCol() && isClassifier()) {
error("_offset_column", "Offset is only supported for regression.");
}
}