public class DRF extends SharedTreeModelBuilder<DRF.DRFModel>
| Modifier and Type | Class and Description |
|---|---|
static class |
DRF.DRFModel
DRF model holding serialized tree and implementing logic for scoring a row
|
SharedTreeModelBuilder.Score, SharedTreeModelBuilder.ScoreBuildHistogramJob.ValidatedJob.Response2CMAdaptorJob.ChunkProgress, Job.ChunkProgressJob, Job.ColumnsJob, Job.ColumnsResJob, Job.Fail, Job.FrameJob, Job.HexJob, Job.JobCancelledException, Job.JobState, Job.List, Job.ModelJob, Job.ModelJobWithoutClassificationField, Job.Progress, Job.ProgressMonitor, Job.ValidatedJobRequest2.ColumnSelect, Request2.Dependent, Request2.DoClassBoolean, Request2.DRFCopyDataBoolean, Request2.MultiVecSelect, Request2.MultiVecSelectType, Request2.TypeaheadKey, Request2.VecClassSelect, Request2.VecSelectRequest.API, Request.Default, Request.Filter, Request.Validator<V>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.WarningCellBuilderRequestArguments.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>RequestStatics.RequestTypeConstants.Extensions, Constants.Schemes, Constants.Suffixes| Modifier and Type | Field and Description |
|---|---|
protected int |
_mtry |
protected long |
_seed |
boolean |
build_tree_one_node |
static DocGen.FieldDoc[] |
DOC_FIELDS |
_distribution, _nclass, _ncols, _nrows, balance_classes, DECIDED_ROW, importance, max_after_balance_size, max_depth, MAX_SUPPORTED_LEVELS, min_rows, nbins, ntrees, OUT_OF_BAG, score_each_iteration_cmDomain, _names, _responseName, _sourceResponseDomain, _train, _valid, _validResponse, _validResponseDomain, validationclassificationresponsecols, ignored_cols, ignored_cols_by_namesource_fjtask, description, destination_key, end_time, exception, job_key, LIST, start_time, state_parms, response_info_requestHelp, SUPPORTS_ONLY_V1, SUPPORTS_ONLY_V2, SUPPORTS_V1_V2ARRAY_BUILDER, ARRAY_HEADER_ROW_BUILDER, ARRAY_ROW_BUILDER, ARRAY_ROW_ELEMENT_BUILDER, ARRAY_ROW_SINGLECOL_BUILDER, ELEMENT_BUILDER, GSON_BUILDER, OBJECT_BUILDER, ROOT_OBJECT_queryHtml_argumentsALPHA, 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, 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 and Description |
|---|
DRF() |
| Modifier and Type | Method and Description |
|---|---|
protected DRF.DRFModel |
buildModel(DRF.DRFModel model,
Frame fr,
java.lang.String[] names,
java.lang.String[][] domains,
Timer t_build)
Builds model
|
protected Chunk |
chk_oobt(Chunk[] chks) |
protected VarImp |
doVarImpCalc(DRF.DRFModel model,
DTree[] ktrees,
int tid,
Frame fTrain,
boolean scale)
On-the-fly version for varimp.
|
protected void |
execImpl()
Compute a DRF tree.
|
protected boolean |
inBagRow(Chunk[] chks,
int row) |
protected void |
init()
Invoked before job runs.
|
protected void |
initAlgo(DRF.DRFModel initialModel)
Initialize algorithm - e.g., allocate algorithm specific datastructure.
|
protected void |
initWorkFrame(DRF.DRFModel initialModel,
Frame fr)
Initialize working frame.
|
static java.lang.String |
link(Key k,
java.lang.String content)
Return the query link to this page
|
protected Log.Tag.Sys |
logTag()
Returns a log tag for a particular model builder (e.g., DRF, GBM)
|
protected DTree.DecidedNode |
makeDecided(DTree.UndecidedNode udn,
DHistogram[] hs) |
protected DRF.DRFModel |
makeModel(DRF.DRFModel model,
double err,
ConfusionMatrix cm,
VarImp varimp,
AUC validAUC) |
protected DRF.DRFModel |
makeModel(DRF.DRFModel model,
DTree[] ktrees,
DTree.TreeModel.TreeStats tstats) |
protected DRF.DRFModel |
makeModel(Key outputKey,
Key dataKey,
Key testKey,
java.lang.String[] names,
java.lang.String[][] domains,
java.lang.String[] cmDomain) |
protected RequestBuilders.Response |
redirect() |
Frame |
score(Frame fr) |
protected float |
score1(Chunk[] chks,
float[] fs,
int row) |
buildLayer, buildModel, chk_nids, chk_resp, chk_tree, chk_work, cleanUp, createRNG, data_row, doScoring, isClassification, isDecidedRow, isOOBRow, makeAUC, nid2Oob, oob2Nid, printGenerateTrees, progress, speedDescription, speedValue, vec_nids, vec_respgetCMDomain, getOrigValidation, getValidAdaptor, getValidation, getVectorDomain, hasValidation, prepareValidationWithModel, toJSONregisteredselectFrame, selectVecsall, 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, start, waitUntilJobEnded, waitUntilJobEndedcreate, fillResponseInfo, filterNaCols, input, logStart, makeJsonBox, serveGrid, set, split, superServeGrid, supportedVersions, toStringaddToNavbar, addToNavbar, addToNavbar, DocExampleFail, DocExampleSucc, href, href, hrefType, HTMLHelp, htmlTemplate, initializeNavBar, log, mapTypeahead, ReSTHelp, serve, serveJava, serveResponse, toDocGET, toHTML, toJava, wrap, wrap, wrap, writeJSONFieldsbuild, buildJSONResponseBox, buildResponseHeader, namebuildQuery, checkArguments, queryArgumentValueSetarguments, argumentsToJson, frameColumnNameToIndex, vaCategoryNames, vaCategoryNames, vaColumnNameToIndexcheckJsonName, encodeRedirectArgs, JSON2HTML, jsonError, requestName, Str2JSONclone, frozenType, init, newInstance, read, toDocField, write, writeJSONpublic static DocGen.FieldDoc[] DOC_FIELDS
@Request.API(help="Run on one node only; no network overhead but fewer cpus used. Suitable for small datasets.", filter=hex.drf.DRF.myClassFilter.class, importance=SECONDARY) public boolean build_tree_one_node
@Request.API(help="Computed number of split features", importance=EXPERT) protected int _mtry
@Request.API(help="Autogenerated seed", importance=EXPERT) protected long _seed
protected Log.Tag.Sys logTag()
SharedTreeModelBuilderlogTag in class SharedTreeModelBuilder<DRF.DRFModel>protected DRF.DRFModel makeModel(Key outputKey, Key dataKey, Key testKey, java.lang.String[] names, java.lang.String[][] domains, java.lang.String[] cmDomain)
makeModel in class SharedTreeModelBuilder<DRF.DRFModel>protected DRF.DRFModel makeModel(DRF.DRFModel model, double err, ConfusionMatrix cm, VarImp varimp, AUC validAUC)
makeModel in class SharedTreeModelBuilder<DRF.DRFModel>protected DRF.DRFModel makeModel(DRF.DRFModel model, DTree[] ktrees, DTree.TreeModel.TreeStats tstats)
makeModel in class SharedTreeModelBuilder<DRF.DRFModel>public static java.lang.String link(Key k, java.lang.String content)
protected void execImpl()
protected RequestBuilders.Response redirect()
protected void init()
Jobinit in class SharedTreeModelBuilder<DRF.DRFModel>protected void initAlgo(DRF.DRFModel initialModel)
SharedTreeModelBuilderinitAlgo in class SharedTreeModelBuilder<DRF.DRFModel>protected void initWorkFrame(DRF.DRFModel initialModel, Frame fr)
SharedTreeModelBuilderinitWorkFrame in class SharedTreeModelBuilder<DRF.DRFModel>initialModel - initial modelfr - working frame which contains train data and additional columns prepared by this builder.protected DRF.DRFModel buildModel(DRF.DRFModel model, Frame fr, java.lang.String[] names, java.lang.String[][] domains, Timer t_build)
SharedTreeModelBuilderbuildModel in class SharedTreeModelBuilder<DRF.DRFModel>model - initial model created by SharedTreeModelBuilder.makeModel(Key, Key, Key, String[], String[][], String[]) method.fr - training dataset which can contain additional temporary vectors prepared by buildModel() method.names - names of columns in trainFr used for model trainingdomains - domains of columns in trainFr used for model trainingt_build - timer to measure model building processprotected VarImp doVarImpCalc(DRF.DRFModel model, DTree[] ktrees, int tid, Frame fTrain, boolean scale)
The page says: "In every tree grown in the forest, put down the oob cases and count the number of votes cast for the correct class. Now randomly permute the values of variable m in the oob cases and put these cases down the tree. Subtract the number of votes for the correct class in the variable-m-permuted oob data from the number of votes for the correct class in the untouched oob data. The average of this number over all trees in the forest is the raw importance score for variable m."
doVarImpCalc in class SharedTreeModelBuilder<DRF.DRFModel>protected float score1(Chunk[] chks, float[] fs, int row)
score1 in class SharedTreeModelBuilder<DRF.DRFModel>protected boolean inBagRow(Chunk[] chks, int row)
inBagRow in class SharedTreeModelBuilder<DRF.DRFModel>protected DTree.DecidedNode makeDecided(DTree.UndecidedNode udn, DHistogram[] hs)
makeDecided in class SharedTreeModelBuilder<DRF.DRFModel>