public class ScoreBuildHistogram extends water.MRTask<ScoreBuildHistogram>
Fuse 2 conceptual passes into one:
The result is a set of DHistogram arrays; one DHistogram array for each unique 'leaf' in the tree being histogramed in parallel. These have node ID's (nids) from 'leaf' to 'tree._len'. Each DHistogram array is for all the columns in that 'leaf'.
The other result is a prediction "score" for the whole dataset, based on the previous passes' DHistograms.
Modifier and Type | Field and Description |
---|---|
static int |
DECIDED_ROW
Marker for already decided row.
|
static int |
FRESH |
static int |
MISSING_RESPONSE
Marker for rows without a response
|
static int |
OUT_OF_BAG
Marker for sampled out rows
|
static int |
UNDECIDED_CHILD_NODE_ID
Marker for a fresh tree
|
Constructor and Description |
---|
ScoreBuildHistogram(water.H2O.H2OCountedCompleter cc,
int k,
int ncols,
int nbins,
int nbins_cats,
DTree tree,
int leaf,
DHistogram[][] hcs,
hex.genmodel.utils.DistributionFamily family,
int weightIdx,
int workIdx,
int nidIdx) |
Modifier and Type | Method and Description |
---|---|
ScoreBuildHistogram |
dfork2(byte[] types,
water.fvec.Frame fr,
boolean run_local) |
static boolean |
isDecidedRow(int nid) |
static boolean |
isOOBRow(int nid) |
void |
map(water.fvec.Chunk[] chks) |
static int |
nid2Oob(int nid) |
static int |
oob2Nid(int oobNid) |
void |
reduce(ScoreBuildHistogram sbh) |
protected void |
score_decide(water.fvec.Chunk[] chks,
water.fvec.Chunk nids,
int[] nnids) |
void |
setupLocal() |
appendables, asyncExecOnAllNodes, block, closeLocal, compute2, dfork, dfork, dfork, dfork, dfork, dinvoke, doAll, doAll, doAll, doAll, doAll, doAll, doAll, doAll, doAll, doAll, doAll, doAll, doAllNodes, getResult, getResult, isReleasable, map, map, map, map, map, map, map, map, map, map, modifiesVolatileVecs, onCompletion, onExceptionalCompletion, outputFrame, outputFrame, outputFrame, postGlobal, profile, profString, self
copyOver, getDException, hasException, logVerbose, onAck, onAckAck, setException
asBytes, clone, compute, compute1, currThrPriority, frozenType, icer, priority, read, readJSON, reloadFromBytes, write, writeJSON
__tryComplete, addToPendingCount, compareAndSetPendingCount, complete, exec, getCompleter, getPendingCount, getRawResult, setCompleter, setPendingCount, setRawResult, tryComplete
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
public static final int DECIDED_ROW
public static final int OUT_OF_BAG
public static final int MISSING_RESPONSE
public static final int UNDECIDED_CHILD_NODE_ID
public static final int FRESH
public ScoreBuildHistogram(water.H2O.H2OCountedCompleter cc, int k, int ncols, int nbins, int nbins_cats, DTree tree, int leaf, DHistogram[][] hcs, hex.genmodel.utils.DistributionFamily family, int weightIdx, int workIdx, int nidIdx)
public ScoreBuildHistogram dfork2(byte[] types, water.fvec.Frame fr, boolean run_local)
public static boolean isOOBRow(int nid)
public static boolean isDecidedRow(int nid)
public static int oob2Nid(int oobNid)
public static int nid2Oob(int nid)
public void setupLocal()
setupLocal
in class water.MRTask<ScoreBuildHistogram>
public void map(water.fvec.Chunk[] chks)
map
in class water.MRTask<ScoreBuildHistogram>
public void reduce(ScoreBuildHistogram sbh)
reduce
in class water.MRTask<ScoreBuildHistogram>
protected void score_decide(water.fvec.Chunk[] chks, water.fvec.Chunk nids, int[] nnids)