hex.deeplearning

Class DeepLearning

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.ModelJob

water.Job.ValidatedJob

hex.deeplearning.DeepLearning

All Implemented Interfaces:

java.lang.Cloneable, Freezable

public class DeepLearning
extends Job.ValidatedJob

Deep Learning Neural Net implementation based on MRTask2

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	DeepLearning.Activation Activation functions
static class	DeepLearning.ClassSamplingMethod
static class	DeepLearning.InitialWeightDistribution
static class	DeepLearning.Loss Loss functions CrossEntropy is recommended

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.Fail, Job.FrameJob, Job.HexJob, Job.JobCancelledException, Job.JobState, Job.List, Job.ModelJob, 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.CaseModeSelect, RequestArguments.CaseSelect, RequestArguments.ClassifyBool, RequestArguments.DRFCopyDataBool, RequestArguments.EnumArgument<T extends java.lang.Enum<T>>, RequestArguments.ExistingFile, RequestArguments.FrameClassVec, RequestArguments.FrameKeyMultiVec, RequestArguments.FrameKeyVec, RequestArguments.GeneralFile, RequestArguments.H2OCategoryStrata, RequestArguments.H2OCategoryWeights, RequestArguments.H2OExistingKey, RequestArguments.H2OGLMModelKey, RequestArguments.H2OHexKey, RequestArguments.H2OHexKeyCol, RequestArguments.H2OIllegalArgumentException, RequestArguments.H2OKey, RequestArguments.H2OKey2, RequestArguments.H2OKMeansModelKey, RequestArguments.H2OModelKey<TM extends OldModel,TK extends TypeaheadKeysRequest>, RequestArguments.HexAllColumnSelect, RequestArguments.HexColumnSelect, RequestArguments.HexKeyClassCol, RequestArguments.HexNonClassColumnSelect, RequestArguments.HexNonConstantColumnSelect, RequestArguments.HexPCAColumnSelect, RequestArguments.InputCheckBox, RequestArguments.InputSelect<T>, RequestArguments.InputText<T>, RequestArguments.Int, RequestArguments.LongInt, RequestArguments.MultipleSelect<T>, RequestArguments.MultipleText<T>, RequestArguments.NTree, RequestArguments.NumberSequence, RequestArguments.NumberSequenceFloat, RequestArguments.Real, RequestArguments.Record<T>, RequestArguments.RFModelKey, 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
DeepLearning.Activation	activation
boolean	adaptive_rate
boolean	balance_classes
Key	checkpoint
double	classification_stop
boolean	diagnostics
static DocGen.FieldDoc[]	DOC_FIELDS
static java.lang.String	DOC_GET
double	epochs
double	epsilon
boolean	expert_mode
boolean	fast_mode
boolean	force_load_balance
int[]	hidden
double[]	hidden_dropout_ratios
boolean	ignore_const_cols
DeepLearning.InitialWeightDistribution	initial_weight_distribution
double	initial_weight_scale
double	input_dropout_ratio
double	l1
double	l2
DeepLearning.Loss	loss
float	max_after_balance_size
int	max_confusion_matrix_size
int	max_hit_ratio_k
double	max_w2
long	momentum_ramp
double	momentum_stable
double	momentum_start
boolean	nesterov_accelerated_gradient
boolean	quiet_mode
double	rate
double	rate_annealing
double	rate_decay
double	regression_stop
boolean	replicate_training_data
double	rho
double	score_duty_cycle
double	score_interval
long	score_training_samples
long	score_validation_samples
DeepLearning.ClassSamplingMethod	score_validation_sampling
long	seed
boolean	shuffle_training_data
boolean	single_node_mode
long	train_samples_per_iteration
boolean	variable_importances

Fields inherited from class water.Job.ValidatedJob

_cmDomain, _names, _responseName, _sourceResponseDomain, _train, _valid, _validResponse, _validResponseDomain, validation

Fields inherited from class water.Job.ModelJob

classification, 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

_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, 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, 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, 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
DeepLearning()

Method Summary

Methods

Modifier and Type	Method and Description
void	delete() Delete job related keys
void	execImpl() Train a Deep Learning model, assumes that all members are populated
DeepLearningModel	initModel() Create an initial Deep Learning model, typically to be trained by trainModel(model)
static java.lang.String	link(Key k, java.lang.String content) Return a query link to this page
static java.lang.String	link(Key k, java.lang.String content, Key cp, java.lang.String response, Key val) Return a query link to this page
float	progress() Report the relative progress of building a Deep Learning model (measured by how many epochs are done)
protected void	queryArgumentValueSet(RequestArguments.Argument arg, java.util.Properties inputArgs) Helper to handle arguments based on existing input values
protected RequestBuilders.Response	redirect() Redirect to the model page for that model that is trained by this job
protected void	registered(RequestServer.API_VERSION ver) Helper to specify which arguments trigger a refresh on change
boolean	toHTML(java.lang.StringBuilder sb) Print model parameters as JSON
DeepLearningModel	trainModel(DeepLearningModel model) Train a Deep Learning neural net model
DeepLearningModel	trainModel(DeepLearningModel model, double epochs) Incrementally train an existing model

Methods inherited from class water.Job.ValidatedJob

getCMDomain, getOrigValidation, getValidAdaptor, getValidation, getVectorDomain, hasValidation, init, prepareValidationWithModel, 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, invoke, isCancelledOrCrashed, isCancelledXX, isCrashed, isDone, isEnded, isRunning, isRunning, onCancelled, 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, input, logStart, makeJsonBox, serveGrid, set, split, superServeGrid, supportedVersions, 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, 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, vaCategoryNames, vaCategoryNames, vaColumnNameToIndex

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

checkpoint

public Key checkpoint

expert_mode

public boolean expert_mode

activation

public DeepLearning.Activation activation

hidden

public int[] hidden

epochs

public double epochs

train_samples_per_iteration

public long train_samples_per_iteration

seed

public long seed

adaptive_rate

public boolean adaptive_rate

rho

public double rho

epsilon

public double epsilon

rate

public double rate

rate_annealing

public double rate_annealing

rate_decay

public double rate_decay

momentum_start

public double momentum_start

momentum_ramp

public long momentum_ramp

momentum_stable

public double momentum_stable

nesterov_accelerated_gradient

public boolean nesterov_accelerated_gradient

input_dropout_ratio

public double input_dropout_ratio

hidden_dropout_ratios

public double[] hidden_dropout_ratios

l1

public double l1

l2

public double l2

max_w2

public double max_w2

initial_weight_distribution

public DeepLearning.InitialWeightDistribution initial_weight_distribution

initial_weight_scale

public double initial_weight_scale

loss

public DeepLearning.Loss loss

score_interval

public double score_interval

score_training_samples

public long score_training_samples

score_validation_samples

public long score_validation_samples

score_duty_cycle

public double score_duty_cycle

classification_stop

public double classification_stop

regression_stop

public double regression_stop

quiet_mode

public boolean quiet_mode

max_confusion_matrix_size

public int max_confusion_matrix_size

max_hit_ratio_k

public int max_hit_ratio_k

balance_classes

public boolean balance_classes

max_after_balance_size

public float max_after_balance_size

score_validation_sampling

public DeepLearning.ClassSamplingMethod score_validation_sampling

diagnostics

public boolean diagnostics

variable_importances

public boolean variable_importances

fast_mode

public boolean fast_mode

ignore_const_cols

public boolean ignore_const_cols

force_load_balance

public boolean force_load_balance

replicate_training_data

public boolean replicate_training_data

single_node_mode

public boolean single_node_mode

shuffle_training_data

public boolean shuffle_training_data

Constructor Detail

DeepLearning

public DeepLearning()

Method Detail

registered

protected void registered(RequestServer.API_VERSION ver)

Helper to specify which arguments trigger a refresh on change

Overrides:

registered in class Job.ModelJob

Parameters:

ver -

queryArgumentValueSet

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

Helper to handle arguments based on existing input values

Overrides:

queryArgumentValueSet in class RequestQueries

Parameters:

arg -

inputArgs -

toHTML

public boolean toHTML(java.lang.StringBuilder sb)

Print model parameters as JSON

Overrides:

toHTML in class Request

link

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

Return a query link to this page

Parameters:

k - Model Key

content - Link text

Returns:

HTML Link

link

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

Return a query link to this page

Parameters:

k - Model Key

content - Link text

cp - Key to checkpoint to continue training with (optional)

response - Response

val - Validation data set key

Returns:

HTML Link

progress

public float progress()

Report the relative progress of building a Deep Learning model (measured by how many epochs are done)

Overrides:

progress in class Job

Returns:

floating point number between 0 and 1

execImpl

public final void execImpl()

Train a Deep Learning model, assumes that all members are populated

Overrides:

execImpl in class Func

redirect

protected RequestBuilders.Response redirect()

Redirect to the model page for that model that is trained by this job

Overrides:

redirect in class Job

Returns:

Response

initModel

public final DeepLearningModel initModel()

Create an initial Deep Learning model, typically to be trained by trainModel(model)

Returns:

Randomly initialized model

trainModel

public final DeepLearningModel trainModel(DeepLearningModel model,
                           double epochs)

Incrementally train an existing model

Parameters:

model - Initial model

epochs - How many epochs to train for

Returns:

Updated model

trainModel

public final DeepLearningModel trainModel(DeepLearningModel model)

Train a Deep Learning neural net model

Parameters:

model - Input model (e.g., from initModel(), or from a previous training run)

Returns:

Trained model

delete

public void delete()

Delete job related keys