public final Vec[] vecs() {
if (_vecs != null) return _vecs;
// Load all Vec headers; load them all in parallel by spawning F/J tasks.
final Vec[] vecs = new Vec[_keys.length];
Futures fs = new Futures();
for (int i = 0; i < _keys.length; i++) {
final int ii = i;
final Key k = _keys[i];
H2OCountedCompleter t =
new H2OCountedCompleter() {
// We need higher priority here as there is a danger of deadlock in
// case of many calls from MRTask2 at once (e.g. frame with many
// vectors invokes rollup tasks for all vectors in parallel). Should
// probably be done in CPS style in the future
@Override
public byte priority() {
return H2O.MIN_HI_PRIORITY;
}
@Override
public void compute2() {
vecs[ii] = DKV.get(k).get();
tryComplete();
}
};
H2O.submitTask(t);
fs.add(t);
}
fs.blockForPending();
return _vecs = vecs;
}
static void invalidate(H2ONode h2o, Key key, Value newval, Futures fs) {
assert newval._key != null && key.home();
// Prevent the new Value from being overwritten by Yet Another PUT by
// read-locking it. It's safe to read, but not to over-write, until this
// invalidate completes on the *prior* value.
newval.read_lock(); // block further writes until all invalidates complete
fs.add(RPC.call(h2o, new TaskInvalidateKey(key, newval)));
}
/**
* On-the-fly version for varimp. After generation a new tree, its tree votes are collected on
* shuffled OOB rows and variable importance is recomputed.
*
* <p>The <a
* href="http://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm#varimp">page</a> says:
* <cite> "In every tree grown in the forest, put down the oob cases and count the number of votes
* cast for the correct class. Now randomly permute the values of variable m in the oob cases and
* put these cases down the tree. Subtract the number of votes for the correct class in the
* variable-m-permuted oob data from the number of votes for the correct class in the untouched
* oob data. The average of this number over all trees in the forest is the raw importance score
* for variable m." </cite>
*/
@Override
protected VarImp doVarImpCalc(
final DRFModel model, DTree[] ktrees, final int tid, final Frame fTrain, boolean scale) {
// Check if we have already serialized 'ktrees'-trees in the model
assert model.ntrees() - 1 == tid
: "Cannot compute DRF varimp since 'ktrees' are not serialized in the model! tid=" + tid;
assert _treeMeasuresOnOOB.npredictors() - 1 == tid
: "Tree votes over OOB rows for this tree (var ktrees) were not found!";
// Compute tree votes over shuffled data
final CompressedTree[ /*nclass*/] theTree =
model.ctree(tid); // get the last tree FIXME we should pass only keys
final int nclasses = model.nclasses();
Futures fs = new Futures();
for (int var = 0; var < _ncols; var++) {
final int variable = var;
H2OCountedCompleter task4var =
classification
? new H2OCountedCompleter() {
@Override
public void compute2() {
// Compute this tree votes over all data over given variable
TreeVotes cd =
TreeMeasuresCollector.collectVotes(
theTree, nclasses, fTrain, _ncols, sample_rate, variable);
assert cd.npredictors() == 1;
asVotes(_treeMeasuresOnSOOB[variable]).append(cd);
tryComplete();
}
}
: /* regression */ new H2OCountedCompleter() {
@Override
public void compute2() {
// Compute this tree votes over all data over given variable
TreeSSE cd =
TreeMeasuresCollector.collectSSE(
theTree, nclasses, fTrain, _ncols, sample_rate, variable);
assert cd.npredictors() == 1;
asSSE(_treeMeasuresOnSOOB[variable]).append(cd);
tryComplete();
}
};
H2O.submitTask(task4var); // Fork computation
fs.add(task4var);
}
fs.blockForPending(); // Wait for results
// Compute varimp for individual features (_ncols)
final float[] varimp = new float[_ncols]; // output variable importance
final float[] varimpSD = new float[_ncols]; // output variable importance sd
for (int var = 0; var < _ncols; var++) {
double[ /*2*/] imp =
classification
? asVotes(_treeMeasuresOnSOOB[var]).imp(asVotes(_treeMeasuresOnOOB))
: asSSE(_treeMeasuresOnSOOB[var]).imp(asSSE(_treeMeasuresOnOOB));
varimp[var] = (float) imp[0];
varimpSD[var] = (float) imp[1];
}
return new VarImp.VarImpMDA(varimp, varimpSD, model.ntrees());
}
static void put(H2ONode h2o, Key key, Value val, Futures fs, boolean dontCache) {
fs.add(RPC.call(h2o, new TaskPutKey(key, val, dontCache)));
}
