hex.singlenoderf

Class SpeeDRF

java.lang.Object

water.Iced

water.api.Constants

water.api.RequestStatics

water.api.RequestArguments

water.api.RequestQueries

water.api.RequestBuilders

water.api.Request

water.Request2

water.Func

water.Job

water.Job.FrameJob

water.Job.ColumnsJob

water.Job.ColumnsResJob

water.Job.ModelJobWithoutClassificationField

water.Job.ModelJob

water.Job.ValidatedJob

hex.singlenoderf.SpeeDRF

All Implemented Interfaces:

java.lang.Cloneable, Freezable

public class SpeeDRF
extends Job.ValidatedJob

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	SpeeDRF.DRFParams RF execution parameters.
static class	SpeeDRF.DRFTask

Nested classes/interfaces inherited from class water.Job.ValidatedJob

Job.ValidatedJob.Response2CMAdaptor

Nested classes/interfaces inherited from class water.Job

Job.ChunkProgress, Job.ChunkProgressJob, Job.ColumnsJob, Job.ColumnsResJob, Job.Fail, Job.FrameJob, Job.JobCancelledException, Job.JobHandle, Job.JobState, Job.List, Job.ModelJob, Job.ModelJobWithoutClassificationField, Job.Progress, Job.ProgressMonitor, Job.ValidatedJob

Nested classes/interfaces inherited from class water.Request2

Request2.ColumnSelect, Request2.Dependent, Request2.DoClassBoolean, Request2.DRFCopyDataBoolean, Request2.MultiVecSelect, Request2.MultiVecSelectType, Request2.TypeaheadKey, Request2.VecClassSelect, Request2.VecSelect

Nested classes/interfaces inherited from class water.api.Request

Request.API, Request.Default, Request.Filter, Request.Validator<V>

Nested classes/interfaces inherited from class water.api.RequestBuilders

RequestBuilders.ArrayBuilder, RequestBuilders.ArrayHeaderRowBuilder, RequestBuilders.ArrayRowBuilder, RequestBuilders.ArrayRowElementBuilder, RequestBuilders.ArrayRowSingleColBuilder, RequestBuilders.BooleanStringBuilder, RequestBuilders.Builder, RequestBuilders.ElementBuilder, RequestBuilders.HideBuilder, RequestBuilders.KeyCellBuilder, RequestBuilders.KeyElementBuilder, RequestBuilders.KeyLinkElementBuilder, RequestBuilders.KeyMinAvgMaxBuilder, RequestBuilders.NoCaptionObjectBuilder, RequestBuilders.ObjectBuilder, RequestBuilders.PaginatedTable, RequestBuilders.PreFormattedBuilder, RequestBuilders.Response, RequestBuilders.ResponseInfo, RequestBuilders.WarningCellBuilder

Nested classes/interfaces inherited from class water.api.RequestArguments

RequestArguments.Argument<T>, RequestArguments.Bool, RequestArguments.ClassifyBool, RequestArguments.DRFCopyDataBool, RequestArguments.EnumArgument<T extends java.lang.Enum<T>>, RequestArguments.ExistingFile, RequestArguments.FrameClassVec, RequestArguments.FrameKeyMultiVec, RequestArguments.FrameKeyVec, RequestArguments.GeneralFile, RequestArguments.H2OExistingKey, RequestArguments.H2OIllegalArgumentException, RequestArguments.H2OKey, RequestArguments.H2OKey2, RequestArguments.InputCheckBox, RequestArguments.InputSelect<T>, RequestArguments.InputText<T>, RequestArguments.Int, RequestArguments.LongInt, RequestArguments.MultipleSelect<T>, RequestArguments.MultipleText<T>, RequestArguments.NumberSequence, RequestArguments.NumberSequenceFloat, RequestArguments.Real, RequestArguments.Record<T>, RequestArguments.RSeq, RequestArguments.RSeqFloat, RequestArguments.Str, RequestArguments.StringList, RequestArguments.TypeaheadInputText<T>

Nested classes/interfaces inherited from class water.api.RequestStatics

RequestStatics.RequestType

Nested classes/interfaces inherited from class water.api.Constants

Constants.Extensions, Constants.Schemes, Constants.Suffixes

Field Summary

Fields

Modifier and Type	Field and Description
int	_exclusiveSplitLimit
Key	_modelKey
boolean	balance_classes For imbalanced data, balance training data class counts via over/under-sampling.
double[]	class_weights
static DocGen.FieldDoc[]	DOC_FIELDS
static java.lang.String	DOC_GET
SpeeDRF.DRFParams	drfParams
boolean	importance
float	max_after_balance_size When classes are balanced, limit the resulting dataset size to the specified multiple of the original dataset size.
int	max_depth
int	mtries
int	nbins
int	ntrees
boolean	oobee
double	sample_rate
Sampling.Strategy	sampling_strategy
boolean	score_each_iteration
long	seed
Tree.SelectStatType	select_stat_type
boolean	verbose

Fields inherited from class water.Job.ValidatedJob

_cmDomain, _cv_count, _names, _responseName, _sourceResponseDomain, _train, _valid, _validResponse, _validResponseDomain, keep_cross_validation_splits, n_folds, validation, xval_models

Fields inherited from class water.Job.ModelJob

classification

Fields inherited from class water.Job.ColumnsResJob

response

Fields inherited from class water.Job.ColumnsJob

cols, ignored_cols, ignored_cols_by_name

Fields inherited from class water.Job.FrameJob

source

Fields inherited from class water.Job

_cv, _fjtask, description, destination_key, end_time, exception, job_key, LIST, start_time, state

Fields inherited from class water.Request2

_parms, response_info

Fields inherited from class water.api.Request

_requestHelp, SUPPORTS_ONLY_V1, SUPPORTS_ONLY_V2, SUPPORTS_V1_V2

Fields inherited from class water.api.RequestBuilders

ARRAY_BUILDER, ARRAY_HEADER_ROW_BUILDER, ARRAY_ROW_BUILDER, ARRAY_ROW_ELEMENT_BUILDER, ARRAY_ROW_SINGLECOL_BUILDER, ELEMENT_BUILDER, GSON_BUILDER, OBJECT_BUILDER, ROOT_OBJECT

Fields inherited from class water.api.RequestQueries

_queryHtml

Fields inherited from class water.api.RequestArguments

_arguments

Fields inherited from class water.api.Constants

ALPHA, ARGUMENTS, AUC, BASE, BEST_THRESHOLD, BETA_EPS, BIN_LIMIT, BROWSE, BUCKET, BUILT_IN_KEY_JOBS, CANCELLED, CARDINALITY, CASE, CASE_MODE, CHUNK, CLASS, CLOUD_HEALTH, CLOUD_NAME, CLOUD_SIZE, CLOUD_UPTIME_MILLIS, CLUSTERS, COEFFICIENTS, COL_INDEX, COLS, COLUMN_NAME, COLUMNS_DISPLAY, CONSENSUS, CONTENTS, COUNT, DATA_KEY, DEPTH, DESCRIPTION, DEST_KEY, DTHRESHOLDS, ELAPSED, END_TIME, ENUM_DOMAIN_SIZE, ERROR, ESCAPE_NAN, EXCLUSIVE_SPLIT_LIMIT, EXPRESSION, FAILED, FAMILY, FEATURES, FILE, FILES, FILTER, FIRST_CHUNK, FJ_QUEUE_HI, FJ_QUEUE_LO, FJ_THREADS_HI, FJ_THREADS_LO, FREE_DISK, FREE_MEM, GFLOPS, HEADER, HEIGHT, HELP, IGNORE, ITEMS, ITERATIVE_CM, JOB, JOB_KEY, JOBS, JSON_H2O, KEY, KEYS, LAMBDA, LAST_CONTACT, LIMIT, LINK, LOCKED, MAX, MAX_DISK, MAX_ITER, MAX_MEM, MAX_ROWS, MEAN, MEM_BW, MIN, MODEL_KEY, MODELS, MORE, MTRY, MTRY_NODES, NAME, NEG_X, NO_CM, NODE, NODE_HEALTH, NODE_NAME, NODES, NORMALIZE, NUM_COLS, NUM_CPUS, NUM_FAILED, NUM_KEYS, NUM_MISSING_VALUES, NUM_ROWS, NUM_SUCCEEDED, NUM_TREES, OBJECT, OFFSET, OOBEE, PARALLEL, PARSER_TYPE, PATH, PREVIEW, PREVIOUS_MODEL_KEY, PRIOR, PROGRESS, PROGRESS_KEY, PROGRESS_TOTAL, REDIRECT, REDIRECT_ARGS, REPLICATION_FACTOR, REQUEST_TIME, RESPONSE, RHO, ROW, ROW_SIZE, ROWS, RPCS, SAMPLE, SAMPLING_STRATEGY, SCALE, SEED, SENT_ROWS, SEPARATOR, SIZE, SOURCE_KEY, STACK_TRACES, START_TIME, STAT_TYPE, STATUS, STEP, STRATA_SAMPLES, SUCCEEDED, SYSTEM_LOAD, TASK_KEY, TCPS_ACTIVE, TCPS_DUTY, TIME, TO_ENUM, TOT_MEM, TREE_COUNT, TREE_DEPTH, TREE_LEAVES, TREE_NUM, TREES, TWEEDIE_POWER, TYPE, URL, USE_NON_LOCAL_DATA, VALUE, VALUE_SIZE, VALUE_TYPE, VARIANCE, VERSION, VIEW, WARNINGS, WEIGHT, WEIGHTS, WIDTH, X, XVAL, Y

Constructor Summary

Constructors

Constructor and Description
SpeeDRF()

Method Summary

Methods

Modifier and Type	Method and Description
static void	build(Key jobKey, Key modelKey, SpeeDRF.DRFParams drfParams, Data localData, int ntrees, int numSplitFeatures, int[] rowsPerChunks) Build random forest for data stored on this node.
void	crossValidate(Frame[] splits, Frame[] cv_preds, long[] offsets, int i) Cross-Validate a SpeeDRF model by building new models on N train/test holdout splits
protected void	execImpl() The real implementation which should be provided by ancestors.
protected void	init() Invoked before job runs.
SpeeDRFModel	initModel(Frame train, Frame test, float[] priorDist)
static java.lang.String	link(Key k, java.lang.String content) Return the query link to this page
protected SpeeDRFModel	makeModel(SpeeDRFModel model, double err, ConfusionMatrix cm, VarImp varimp, AUCData validAUC)
protected void	queryArgumentValueSet(RequestArguments.Argument arg, java.util.Properties inputArgs) Helper to handle arguments based on existing input values
protected RequestBuilders.Response	redirect()
Frame	score(Frame fr)

Methods inherited from class water.Job.ValidatedJob

cv_progress, genericCrossValidation, getCMDomain, getOrigValidation, getValidAdaptor, getValidation, getVectorDomain, hasValidation, prepareValidationWithModel, registered, toJSON

Methods inherited from class water.Job.ColumnsJob

selectFrame, selectVecs

Methods inherited from class water.Job

all, cancel, cancel, cancel, checkIdx, defaultDestKey, defaultJobKey, dest, findJob, findJobByDest, fork, get, getState, gridParallelism, hygiene, hygiene, invoke, isCancelledOrCrashed, isCrashed, isDone, isEnded, isRunning, isRunning, onCancelled, progress, remove, runTimeMs, self, serve, speedDescription, speedValue, start, waitUntilJobEnded, waitUntilJobEnded

Methods inherited from class water.Func

cleanup, emptyLTrash, exec, gtrash, gtrash, ltrash, ltrash

Methods inherited from class water.Request2

create, fillResponseInfo, filterNaCols, input, logStart, makeJsonBox, serveGrid, servePublic, set, split, superServeGrid, supportedVersions, toJSON, toString

Methods inherited from class water.api.Request

addToNavbar, addToNavbar, addToNavbar, DocExampleFail, DocExampleSucc, href, href, hrefType, HTMLHelp, htmlTemplate, initializeNavBar, log, mapTypeahead, ReSTHelp, serve, serveJava, serveResponse, toDocGET, toHTML, toJava, wrap, wrap, wrap, writeJSONFields

Methods inherited from class water.api.RequestBuilders

build, buildJSONResponseBox, buildResponseHeader, name

Methods inherited from class water.api.RequestQueries

buildQuery, checkArguments

Methods inherited from class water.api.RequestArguments

arguments, argumentsToJson, frameColumnNameToIndex

Methods inherited from class water.api.RequestStatics

checkJsonName, encodeRedirectArgs, JSON2HTML, jsonError, requestName, Str2JSON

Methods inherited from class water.Iced

clone, frozenType, init, newInstance, read, toDocField, write, writeJSON

Methods inherited from class java.lang.Object

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

Field Detail

DOC_FIELDS

public static DocGen.FieldDoc[] DOC_FIELDS

DOC_GET

public static final java.lang.String DOC_GET

See Also:

Constant Field Values

ntrees

@Request.API(help="Number of trees",
             filter=Request.Default.class,
             json=true,
             lmin=1L,
             lmax=2147483647L,
             importance=CRITICAL)
public int ntrees

mtries

@Request.API(help="Number of features to randomly select at each split.",
             filter=Request.Default.class,
             json=true,
             lmin=-1L,
             lmax=2147483647L,
             importance=SECONDARY)
public int mtries

max_depth

@Request.API(help="Max Depth",
             filter=Request.Default.class,
             json=true,
             lmin=0L,
             lmax=2147483647L,
             importance=CRITICAL)
public int max_depth

select_stat_type

@Request.API(help="Split Criterion Type",
             filter=Request.Default.class,
             json=true,
             importance=SECONDARY)
public Tree.SelectStatType select_stat_type

class_weights

public double[] class_weights

sampling_strategy

@Request.API(help="Sampling Strategy",
             filter=Request.Default.class,
             json=true,
             importance=SECONDARY)
public Sampling.Strategy sampling_strategy

sample_rate

@Request.API(help="Sampling Rate at each split.",
             filter=Request.Default.class,
             json=true,
             dmin=0.0,
             dmax=1.0,
             importance=EXPERT)
public double sample_rate

score_each_iteration

public boolean score_each_iteration

balance_classes

@Request.API(help="Balance training data class counts via over/under-sampling (for imbalanced data)",
             filter=Request.Default.class,
             json=true,
             importance=EXPERT)
public boolean balance_classes

For imbalanced data, balance training data class counts via over/under-sampling. This can result in improved predictive accuracy.

max_after_balance_size

@Request.API(help="Maximum relative size of the training data after balancing class counts (can be less than 1.0)",
             filter=Request.Default.class,
             json=true,
             dmin=0.001,
             importance=EXPERT)
public float max_after_balance_size

When classes are balanced, limit the resulting dataset size to the specified multiple of the original dataset size.

oobee

@Request.API(help="Out of bag error estimate",
             filter=Request.Default.class,
             json=true,
             importance=SECONDARY)
public boolean oobee

importance

@Request.API(help="Variable Importance",
             filter=Request.Default.class,
             json=true)
public boolean importance

_modelKey

public Key _modelKey

nbins

@Request.API(help="bin limit",
             filter=Request.Default.class,
             json=true,
             lmin=0L,
             lmax=65534L,
             importance=EXPERT)
public int nbins

seed

@Request.API(help="seed",
             filter=Request.Default.class,
             json=true,
             importance=EXPERT)
public long seed

verbose

@Request.API(help="Tree splits and extra statistics printed to stdout.",
             filter=Request.Default.class,
             json=true,
             importance=EXPERT)
public boolean verbose

_exclusiveSplitLimit

@Request.API(help="split limit",
             importance=EXPERT)
public int _exclusiveSplitLimit

drfParams

public SpeeDRF.DRFParams drfParams

Constructor Detail

SpeeDRF

public SpeeDRF()

Method Detail

link

public static java.lang.String link(Key k,
                    java.lang.String content)

Return the query link to this page

makeModel

protected SpeeDRFModel makeModel(SpeeDRFModel model,
                     double err,
                     ConfusionMatrix cm,
                     VarImp varimp,
                     AUCData validAUC)

queryArgumentValueSet

protected void queryArgumentValueSet(RequestArguments.Argument arg,
                         java.util.Properties inputArgs)

Description copied from class: Job.ValidatedJob

Helper to handle arguments based on existing input values

Overrides:

queryArgumentValueSet in class Job.ValidatedJob

init

protected void init()

Description copied from class: Job

Invoked before job runs. This is the place to checks arguments are valid or throw IllegalArgumentException. It will get invoked both from the Web and Java APIs.

Overrides:

init in class Job.ValidatedJob

execImpl

protected void execImpl()

Description copied from class: Func

The real implementation which should be provided by ancestors.

Overrides:

execImpl in class Func

redirect

protected RequestBuilders.Response redirect()

Overrides:

redirect in class Job

initModel

public SpeeDRFModel initModel(Frame train,
                     Frame test,
                     float[] priorDist)

score

public Frame score(Frame fr)

build

public static void build(Key jobKey,
         Key modelKey,
         SpeeDRF.DRFParams drfParams,
         Data localData,
         int ntrees,
         int numSplitFeatures,
         int[] rowsPerChunks)

Build random forest for data stored on this node.

crossValidate

public void crossValidate(Frame[] splits,
                 Frame[] cv_preds,
                 long[] offsets,
                 int i)

Cross-Validate a SpeeDRF model by building new models on N train/test holdout splits

Overrides:

crossValidate in class Job.ValidatedJob

Parameters:

splits - Frames containing train/test splits

cv_preds - Array of Frames to store the predictions for each cross-validation run

offsets - Array to store the offsets of starting row indices for each cross-validation run

i - Which fold of cross-validation to perform