Linearly Transform a Numeric Target to Match Given Boundaries
Source:R/PipeOpTrafo.R
mlr_pipeops_targettrafoscalerange.RdLinearly transforms a numeric target of a TaskRegr so it is between lower
and upper. The formula for this is \(x' = offset + x * scale\),
where \(scale\) is \((upper - lower) / (max(x) - min(x))\) and
\(offset\) is \(-min(x) * scale + lower\). The same transformation is applied during training and
prediction.
Format
R6Class object inheriting from PipeOpTargetTrafo/PipeOp
Construction
id::character(1)
Identifier of resulting object, default"targettrafoscalerange".param_vals:: namedlist
List of hyperparameter settings, overwriting the hyperparameter settings that would otherwise be set during construction. Defaultlist().
Input and Output Channels
Input and output channels are inherited from PipeOpTargetTrafo.
Parameters
The parameters are the parameters inherited from PipeOpTargetTrafo, as well as:
lower::numeric(1)
Target value of smallest item of input target. Initialized to 0.upper::numeric(1)
Target value of greatest item of input target. Initialized to 1.
Internals
Overloads PipeOpTargetTrafo's .get_state(), .transform(), and
.invert(). Should be used in combination with PipeOpTargetInvert.
Fields
Only fields inherited from PipeOp.
Methods
Only methods inherited from PipeOpTargetTrafo/PipeOp.
See also
https://mlr-org.com/pipeops.html
Other PipeOps:
PipeOp,
PipeOpEncodePL,
PipeOpEnsemble,
PipeOpImpute,
PipeOpTargetTrafo,
PipeOpTaskPreproc,
PipeOpTaskPreprocSimple,
mlr_pipeops,
mlr_pipeops_adas,
mlr_pipeops_blsmote,
mlr_pipeops_boxcox,
mlr_pipeops_branch,
mlr_pipeops_chunk,
mlr_pipeops_classbalancing,
mlr_pipeops_classifavg,
mlr_pipeops_classweights,
mlr_pipeops_colapply,
mlr_pipeops_collapsefactors,
mlr_pipeops_colroles,
mlr_pipeops_copy,
mlr_pipeops_datefeatures,
mlr_pipeops_decode,
mlr_pipeops_encode,
mlr_pipeops_encodeimpact,
mlr_pipeops_encodelmer,
mlr_pipeops_encodeplquantiles,
mlr_pipeops_encodepltree,
mlr_pipeops_featureunion,
mlr_pipeops_filter,
mlr_pipeops_fixfactors,
mlr_pipeops_histbin,
mlr_pipeops_ica,
mlr_pipeops_imputeconstant,
mlr_pipeops_imputehist,
mlr_pipeops_imputelearner,
mlr_pipeops_imputemean,
mlr_pipeops_imputemedian,
mlr_pipeops_imputemode,
mlr_pipeops_imputeoor,
mlr_pipeops_imputesample,
mlr_pipeops_kernelpca,
mlr_pipeops_learner,
mlr_pipeops_learner_pi_cvplus,
mlr_pipeops_learner_quantiles,
mlr_pipeops_missind,
mlr_pipeops_modelmatrix,
mlr_pipeops_multiplicityexply,
mlr_pipeops_multiplicityimply,
mlr_pipeops_mutate,
mlr_pipeops_nearmiss,
mlr_pipeops_nmf,
mlr_pipeops_nop,
mlr_pipeops_ovrsplit,
mlr_pipeops_ovrunite,
mlr_pipeops_pca,
mlr_pipeops_proxy,
mlr_pipeops_quantilebin,
mlr_pipeops_randomprojection,
mlr_pipeops_randomresponse,
mlr_pipeops_regravg,
mlr_pipeops_removeconstants,
mlr_pipeops_renamecolumns,
mlr_pipeops_replicate,
mlr_pipeops_rowapply,
mlr_pipeops_scale,
mlr_pipeops_scalemaxabs,
mlr_pipeops_scalerange,
mlr_pipeops_select,
mlr_pipeops_smote,
mlr_pipeops_smotenc,
mlr_pipeops_spatialsign,
mlr_pipeops_subsample,
mlr_pipeops_targetinvert,
mlr_pipeops_targetmutate,
mlr_pipeops_textvectorizer,
mlr_pipeops_threshold,
mlr_pipeops_tomek,
mlr_pipeops_tunethreshold,
mlr_pipeops_unbranch,
mlr_pipeops_updatetarget,
mlr_pipeops_vtreat,
mlr_pipeops_yeojohnson
Examples
library(mlr3)
task = tsk("boston_housing")
po = PipeOpTargetTrafoScaleRange$new()
po$train(list(task))
#> $fun
#> NULL
#>
#> $output
#>
#> ── <TaskRegr> (506x18): Boston Housing Prices ──────────────────────────────────
#> • Target: cmedv.scaled
#> • Properties: -
#> • Features (17):
#> • dbl (12): age, b, crim, dis, indus, lat, lon, lstat, nox, ptratio, rm, zn
#> • int (3): rad, tax, tract
#> • fct (2): chas, town
#>
po$predict(list(task))
#> $fun
#> function (inputs)
#> {
#> assert_list(inputs, len = 1L, types = "Prediction")
#> list(private$.invert(inputs[[1L]], predict_phase_state))
#> }
#> <bytecode: 0x556148458260>
#> <environment: 0x55615ba18b88>
#>
#> $output
#>
#> ── <TaskRegr> (506x18): Boston Housing Prices ──────────────────────────────────
#> • Target: cmedv.scaled
#> • Properties: -
#> • Features (17):
#> • dbl (12): age, b, crim, dis, indus, lat, lon, lstat, nox, ptratio, rm, zn
#> • int (3): rad, tax, tract
#> • fct (2): chas, town
#>
#syntactic sugar for a graph using ppl():
ttscalerange = ppl("targettrafo", trafo_pipeop = PipeOpTargetTrafoScaleRange$new(),
graph = PipeOpLearner$new(LearnerRegrRpart$new()))
ttscalerange$train(task)
#> $targetinvert.output
#> NULL
#>
ttscalerange$predict(task)
#> $targetinvert.output
#>
#> ── <PredictionRegr> for 506 observations: ──────────────────────────────────────
#> row_ids truth response
#> 1 24.0 24.53538
#> 2 21.6 26.91481
#> 3 34.7 32.96875
#> --- --- ---
#> 504 23.9 24.53538
#> 505 22.0 24.53538
#> 506 19.0 20.96400
#>
ttscalerange$state$regr.rpart
#> $model
#> n= 506
#>
#> node), split, n, deviance, yval
#> * denotes terminal node
#>
#> 1) root 506 21.0260400 0.3895301
#> 2) town=Arlington,Ashland,Beverly,Boston Allston-Brighton,Boston Charlestown,Boston Dorchester,Boston Downtown,Boston East Boston,Boston Forest Hills,Boston Hyde Park,Boston Mattapan,Boston North End,Boston Roxbury,Boston Savin Hill,Boston South Boston,Boston West Roxbury,Braintree,Burlington,Cambridge,Chelsea,Danvers,Dedham,Everett,Framingham,Hamilton,Hanover,Holbrook,Hull,Lynn,Malden,Marshfield,Medford,Melrose,Middleton,Millis,Nahant,Natick,Norfolk,North Reading,Norwell,Norwood,Peabody,Pembroke,Quincy,Randolph,Reading,Revere,Rockland,Salem,Sargus,Scituate,Sharon,Somerville,Stoneham,Wakefield,Walpole,Waltham,Watertown,Weymouth,Wilmington,Winthrop,Woburn 400 7.5706490 0.3174944
#> 4) lstat>=14.4 176 1.6065670 0.2189646
#> 8) town=Boston Charlestown,Boston East Boston,Boston Forest Hills,Boston North End,Boston Roxbury,Boston Savin Hill,Boston South Boston,Chelsea,Lynn 93 0.4849460 0.1569654 *
#> 9) town=Arlington,Beverly,Boston Allston-Brighton,Boston Dorchester,Boston Downtown,Boston Hyde Park,Boston Mattapan,Cambridge,Everett,Framingham,Malden,Medford,Middleton,Norwood,Peabody,Quincy,Revere,Salem,Somerville,Waltham,Watertown 83 0.3635828 0.2884337 *
#> 5) lstat< 14.4 224 2.9129590 0.3949107
#> 10) lstat>=4.63 215 0.9995600 0.3787494
#> 20) lstat>=7.765 150 0.5226398 0.3547556 *
#> 21) lstat< 7.765 65 0.1912833 0.4341197 *
#> 11) lstat< 4.63 9 0.5157443 0.7809877 *
#> 3) town=Bedford,Belmont,Boston Back Bay,Boston Beacon Hill,Brookline,Canton,Cohasset,Concord,Dover,Duxbury,Hingham,Lexington,Lincoln,Lynnfield,Manchester,Marblehead,Medfield,Milton,Needham,Newton,Sherborn,Sudbury,Swampscott,Topsfield,Wayland,Wellesley,Wenham,Weston,Westwood,Winchester 106 3.5470870 0.6613627
#> 6) rm< 7.437 82 1.5639410 0.5961518
#> 12) crim< 4.12641 75 0.6617538 0.5730963
#> 24) rm< 6.727 27 0.1925600 0.4869959 *
#> 25) rm>=6.727 48 0.1564460 0.6215278 *
#> 13) crim>=4.12641 7 0.4351788 0.8431746 *
#> 7) rm>=7.437 24 0.4430451 0.8841667 *
#>
#> $param_vals
#> $param_vals$xval
#> [1] 0
#>
#>
#> $log
#> Empty data.table (0 rows and 3 cols): stage,class,msg
#>
#> $train_time
#> [1] 0.007
#>
#> $task_hash
#> [1] "88d153e8827d7aff"
#>
#> $feature_names
#> [1] "age" "b" "chas" "crim" "dis" "indus" "lat"
#> [8] "lon" "lstat" "nox" "ptratio" "rad" "rm" "tax"
#> [15] "town" "tract" "zn"
#>
#> $validate
#> NULL
#>
#> $mlr3_version
#> [1] ‘1.1.0’
#>
#> $data_prototype
#> Empty data.table (0 rows and 18 cols): cmedv.scaled,age,b,chas,crim,dis...
#>
#> $task_prototype
#> Empty data.table (0 rows and 18 cols): cmedv.scaled,age,b,chas,crim,dis...
#>
#> $train_task
#>
#> ── <TaskRegr> (506x18): Boston Housing Prices ──────────────────────────────────
#> • Target: cmedv.scaled
#> • Properties: -
#> • Features (17):
#> • dbl (12): age, b, crim, dis, indus, lat, lon, lstat, nox, ptratio, rm, zn
#> • int (3): rad, tax, tract
#> • fct (2): chas, town
#>
#> attr(,"class")
#> [1] "learner_state" "list"