hex.drf

Class TreeVotesCollector

java.lang.Object

jsr166y.ForkJoinTask<java.lang.Void>

jsr166y.CountedCompleter

water.H2O.H2OCountedCompleter

water.DTask

water.MRTask2<TreeVotesCollector>

hex.drf.TreeVotesCollector

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, java.util.concurrent.Future<java.lang.Void>, jsr166y.ForkJoinPool.ManagedBlocker, Freezable

public class TreeVotesCollector
extends MRTask2<TreeVotesCollector>

Score given tree model and preserve errors per tree. This is different from Model.score() function since the MR task uses inverse loop: first over all trees and over all rows in chunk.

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	TreeVotesCollector.TreeVotes

Field Summary

Fields inherited from class water.MRTask2

_appendables, _fr, _fs, _hi, _left, _lo, _nleft, _nodes, _nrite, _rite, _topLocal

Fields inherited from class water.DTask

_cls, _eFromNode, _exception, _fname, _lineNum, _msg, _mth

Method Summary

Methods

Modifier and Type	Method and Description
static TreeVotesCollector.TreeVotes	collect(DTree.TreeModel.CompressedTree[] tree, int nclasses, Frame f, int ncols, float rate, int variable)
static TreeVotesCollector.TreeVotes	collect(DTree.TreeModel tmodel, Frame f, int ncols, float rate, int variable)
void	map(Chunk[] chks) Override with your map implementation.
void	reduce(TreeVotesCollector t) Override to combine results from 'mrt' into 'this' MRTask2.
TreeVotesCollector.TreeVotes	result()

Methods inherited from class water.MRTask2

block, clone, closeLocal, compute2, dfork, dfork, dfork, dfork, dinvoke, doAll, doAll, doAll, doAll, doAll, doAll, getResult, isReleasable, map, map, map, map, map, map, map, map, map, map, map, onCompletion, onExceptionalCompletion, outputFrame, outputFrame, outputFrame, postGlobal, profString, reduce4, setupLocal, vecs

Methods inherited from class water.DTask

copyOver, frozenType, getDException, hasException, logVerbose, newInstance, onAck, onAckAck, read, setException, toDocField, write, writeJSONFields

Methods inherited from class water.H2O.H2OCountedCompleter

compute, priority

Methods inherited from class jsr166y.CountedCompleter

addToPendingCount, compareAndSetPendingCount, complete, exec, getCompleter, getPendingCount, getRawResult, setCompleter, setPendingCount, setRawResult, tryComplete

Methods inherited from class jsr166y.ForkJoinTask

adapt, adapt, adapt, cancel, compareAndSetForkJoinTaskTag, completeExceptionally, fork, get, get, getException, getForkJoinTaskTag, getPool, getQueuedTaskCount, getSurplusQueuedTaskCount, helpQuiesce, inForkJoinPool, invoke, invokeAll, invokeAll, invokeAll, isCancelled, isCompletedAbnormally, isCompletedNormally, isDone, join, peekNextLocalTask, pollNextLocalTask, pollTask, quietlyComplete, quietlyInvoke, quietlyJoin, reinitialize, setForkJoinTaskTag, tryUnfork

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Detail

map

public void map(Chunk[] chks)

Description copied from class: MRTask2

Override with your map implementation. This overload is given an array of local input Chunks, for Frames with arbitrary column numbers. All map variants are called, but only one is expected to be overridden.

Overrides:

map in class MRTask2<TreeVotesCollector>

reduce

public void reduce(TreeVotesCollector t)

Description copied from class: MRTask2

Override to combine results from 'mrt' into 'this' MRTask2. Both 'this' and 'mrt' are guaranteed to either have map() run on them, or be the results of a prior reduce(). Reduce is optional if, e.g., the result is some output vector.

Overrides:

reduce in class MRTask2<TreeVotesCollector>

result

public TreeVotesCollector.TreeVotes result()

collect

public static TreeVotesCollector.TreeVotes collect(DTree.TreeModel tmodel,
                                   Frame f,
                                   int ncols,
                                   float rate,
                                   int variable)

Parameters:

tmodel -

f - input frame (should be already adapted to a model) - ncols-features + response

ncols - number of features

rate -

variable -

Returns:

collect

public static TreeVotesCollector.TreeVotes collect(DTree.TreeModel.CompressedTree[] tree,
                                   int nclasses,
                                   Frame f,
                                   int ncols,
                                   float rate,
                                   int variable)