// --------------------------------------------------------------------------
// Build the next random k-trees represeint tid-th tree
private DTree[] buildNextKTrees(Frame fr, int mtrys, float sample_rate, Random rand, int tid) {
// We're going to build K (nclass) trees - each focused on correcting
// errors for a single class.
final DTree[] ktrees = new DTree[_nclass];
// Initial set of histograms. All trees; one leaf per tree (the root
// leaf); all columns
DHistogram hcs[][][] = new DHistogram[_nclass][1 /*just root leaf*/][_ncols];
// Use for all k-trees the same seed. NOTE: this is only to make a fair
// view for all k-trees
long rseed = rand.nextLong();
// Initially setup as-if an empty-split had just happened
for (int k = 0; k < _nclass; k++) {
assert (_distribution != null && classification)
|| (_distribution == null && !classification);
if (_distribution == null || _distribution[k] != 0) { // Ignore missing classes
// The Boolean Optimization
// This optimization assumes the 2nd tree of a 2-class system is the
// inverse of the first. This is false for DRF (and true for GBM) -
// DRF picks a random different set of columns for the 2nd tree.
// if( k==1 && _nclass==2 ) continue;
ktrees[k] = new DRFTree(fr, _ncols, (char) nbins, (char) _nclass, min_rows, mtrys, rseed);
boolean isBinom = classification;
new DRFUndecidedNode(
ktrees[k],
-1,
DHistogram.initialHist(fr, _ncols, nbins, hcs[k][0], isBinom)); // The "root" node
}
}
// Sample - mark the lines by putting 'OUT_OF_BAG' into nid(<klass>) vector
Timer t_1 = new Timer();
Sample ss[] = new Sample[_nclass];
for (int k = 0; k < _nclass; k++)
if (ktrees[k] != null)
ss[k] =
new Sample((DRFTree) ktrees[k], sample_rate)
.dfork(0, new Frame(vec_nids(fr, k), vec_resp(fr, k)), build_tree_one_node);
for (int k = 0; k < _nclass; k++) if (ss[k] != null) ss[k].getResult();
Log.debug(Sys.DRF__, "Sampling took: + " + t_1);
int[] leafs =
new int
[_nclass]; // Define a "working set" of leaf splits, from leafs[i] to tree._len for each
// tree i
// ----
// One Big Loop till the ktrees are of proper depth.
// Adds a layer to the trees each pass.
Timer t_2 = new Timer();
int depth = 0;
for (; depth < max_depth; depth++) {
if (!Job.isRunning(self())) return null;
hcs = buildLayer(fr, ktrees, leafs, hcs, true, build_tree_one_node);
// If we did not make any new splits, then the tree is split-to-death
if (hcs == null) break;
}
Log.debug(Sys.DRF__, "Tree build took: " + t_2);
// Each tree bottomed-out in a DecidedNode; go 1 more level and insert
// LeafNodes to hold predictions.
Timer t_3 = new Timer();
for (int k = 0; k < _nclass; k++) {
DTree tree = ktrees[k];
if (tree == null) continue;
int leaf = leafs[k] = tree.len();
for (int nid = 0; nid < leaf; nid++) {
if (tree.node(nid) instanceof DecidedNode) {
DecidedNode dn = tree.decided(nid);
for (int i = 0; i < dn._nids.length; i++) {
int cnid = dn._nids[i];
if (cnid == -1
|| // Bottomed out (predictors or responses known constant)
tree.node(cnid) instanceof UndecidedNode
|| // Or chopped off for depth
(tree.node(cnid) instanceof DecidedNode
&& // Or not possible to split
((DecidedNode) tree.node(cnid))._split.col() == -1)) {
LeafNode ln = new DRFLeafNode(tree, nid);
ln._pred = dn.pred(i); // Set prediction into the leaf
dn._nids[i] = ln.nid(); // Mark a leaf here
}
}
// Handle the trivial non-splitting tree
if (nid == 0 && dn._split.col() == -1) new DRFLeafNode(tree, -1, 0);
}
}
} // -- k-trees are done
Log.debug(Sys.DRF__, "Nodes propagation: " + t_3);
// ----
// Move rows into the final leaf rows
Timer t_4 = new Timer();
CollectPreds cp = new CollectPreds(ktrees, leafs).doAll(fr, build_tree_one_node);
if (importance) {
if (classification)
asVotes(_treeMeasuresOnOOB)
.append(cp.rightVotes, cp.allRows); // Track right votes over OOB rows for this tree
else /* regression */ asSSE(_treeMeasuresOnOOB).append(cp.sse, cp.allRows);
}
Log.debug(Sys.DRF__, "CollectPreds done: " + t_4);
// Collect leaves stats
for (int i = 0; i < ktrees.length; i++)
if (ktrees[i] != null) ktrees[i].leaves = ktrees[i].len() - leafs[i];
// DEBUG: Print the generated K trees
// printGenerateTrees(ktrees);
return ktrees;
}
