hex.glm

Class GLMTask.GLMIterationTask

java.lang.Object

jsr166y.ForkJoinTask<java.lang.Void>

jsr166y.CountedCompleter

water.H2O.H2OCountedCompleter

water.DTask

water.MRTask2<T>

hex.FrameTask<T>

hex.glm.GLMTask<GLMTask.GLMIterationTask>

hex.glm.GLMTask.GLMIterationTask

All Implemented Interfaces:

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

Enclosing class:

GLMTask<T extends GLMTask<T>>

public static class GLMTask.GLMIterationTask
extends GLMTask<GLMTask.GLMIterationTask>

One iteration of glm, computes weighted gram matrix and t(x)*y vector and t(y)*y scalar.

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class hex.glm.GLMTask

GLMTask.GLMIterationTask, GLMTask.GLMLineSearchTask

Nested classes/interfaces inherited from class hex.FrameTask

FrameTask.DataInfo

Nested classes/interfaces inherited from class water.DTask

DTask.DKeyTask<T extends DTask.DKeyTask,V extends Iced>

Field Summary

Fields

Modifier and Type	Field and Description
protected double[]	_grad
protected Gram	_gram
protected double	_reg
static int	N_THRESHOLDS

Fields inherited from class hex.glm.GLMTask

_glm

Fields inherited from class hex.FrameTask

_dinfo, _jobKey, _shuffle, _useFraction

Fields inherited from class water.MRTask2

_appendables, _fr, _fs, _hi, _left, _lo, _nhi, _nleft, _nrite, _nxx, _rite, _t0, _topLocal

Fields inherited from class water.DTask

_ex

Constructor Summary

Constructors

Constructor and Description
GLMTask.GLMIterationTask(Key jobKey, FrameTask.DataInfo dinfo, GLMParams glm, boolean computeGram, boolean validate, boolean computeGradient, double[] beta, double ymu, double reg, float[] thresholds, H2O.H2OCountedCompleter cmp)

Method Summary

Methods

Modifier and Type	Method and Description
protected void	chunkDone(long n) Override this to do post-chunk processing work.
protected void	chunkInit() Override this to initialize at the beginning of chunk processing.
double[]	gradient(double alpha, double lambda)
void	postGlobal()
void	processRow(long gid, double[] nums, int ncats, int[] cats, double[] responses) Method to process one row of the data for GLM functions.
void	reduce(GLMTask.GLMIterationTask git) Override to combine results from 'mrt' into 'this' MRTask2.

Methods inherited from class hex.glm.GLMTask

computeEta

Methods inherited from class hex.FrameTask

dfork, map, normMul, normRespMul, normRespSub, normSub, processRow, skipMissing

Methods inherited from class water.MRTask2

asyncExec, asyncExec, asyncExec, block, clone, closeLocal, compute2, dfork, dfork, dfork, dinvoke, doAll, doAll, doAll, doAll, doAll, doAll, exec, exec, exec, getResult, isReleasable, map, map, map, map, map, map, map, map, map, map, map, onCompletion, onExceptionalCompletion, outputFrame, outputFrame, outputFrame, priority, 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

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

Field Detail

_gram

protected Gram _gram

_grad

protected double[] _grad

_reg

protected final double _reg

N_THRESHOLDS

public static final int N_THRESHOLDS

See Also:

Constant Field Values

Constructor Detail

GLMTask.GLMIterationTask

public GLMTask.GLMIterationTask(Key jobKey,
                        FrameTask.DataInfo dinfo,
                        GLMParams glm,
                        boolean computeGram,
                        boolean validate,
                        boolean computeGradient,
                        double[] beta,
                        double ymu,
                        double reg,
                        float[] thresholds,
                        H2O.H2OCountedCompleter cmp)

Method Detail

processRow

public void processRow(long gid,
              double[] nums,
              int ncats,
              int[] cats,
              double[] responses)

Description copied from class: FrameTask

Method to process one row of the data for GLM functions. Numeric and categorical values are passed separately, as is response. Categoricals are passed as absolute indexes into the expanded beta vector, 0-levels are skipped (so the number of passed categoricals will not be the same for every row). Categorical expansion/indexing: Categoricals are placed in the beginning of the beta vector. Each cat variable with n levels is expanded into n-1 independent binary variables. Indexes in cats[] will point to the appropriate coefficient in the beta vector, so e.g. assume we have 2 categorical columns both with values A,B,C, then the following rows will have following indexes: A,A - ncats = 0, we do not pass any categorical here A,B - ncats = 1, indexes = [2] B,B - ncats = 2, indexes = [0,2] and so on

Overrides:

processRow in class FrameTask<GLMTask.GLMIterationTask>

Parameters:

gid - - global id of this row, in [0,_adaptedFrame.numRows())

nums - - numeric values of this row

ncats - - number of passed (non-zero) categoricals

cats - - indexes of categoricals into the expanded beta-vector.

responses - - numeric value for the response

chunkInit

protected void chunkInit()

Description copied from class: FrameTask

Override this to initialize at the beginning of chunk processing.

Overrides:

chunkInit in class FrameTask<GLMTask.GLMIterationTask>

chunkDone

protected void chunkDone(long n)

Description copied from class: FrameTask

Override this to do post-chunk processing work.

Overrides:

chunkDone in class FrameTask<GLMTask.GLMIterationTask>

Parameters:

n - Number of processed rows

reduce

public void reduce(GLMTask.GLMIterationTask git)

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<GLMTask.GLMIterationTask>

postGlobal

public void postGlobal()

Overrides:

postGlobal in class MRTask2<GLMTask.GLMIterationTask>

gradient

public double[] gradient(double alpha,
                double lambda)