General Case Example: PipeOpCopy | First Steps: Inheriting from PipeOp | Channel Definitions | Train and Predict | Putting it Together | Special Case: Preprocessing | Example: PipeOpDropNA | Example: PipeOpScaleAlways | Special Case: Preprocessing with Simple Train | Example: PipeOpDropConst | Example: PipeOpScaleAlwaysSimple | Hyperparameters | Hyperparameter Example: PipeOpScale
Package: mlr3pipelines 0.12.0
Martin Binder
mlr3pipelines: Preprocessing Operators and Pipelines for 'mlr3'
Dataflow programming toolkit that enriches 'mlr3' with a diverse set of pipelining operators ('PipeOps') that can be composed into graphs. Operations exist for data preprocessing, model fitting, and ensemble learning. Graphs can themselves be treated as 'mlr3' 'Learners' and can therefore be resampled, benchmarked, and tuned.
Authors:
mlr3pipelines_0.12.0.tar.gz
mlr3pipelines_0.12.0.zip(r-4.7-any)mlr3pipelines_0.12.0.zip(r-4.6-any)mlr3pipelines_0.12.0.zip(r-4.5-any)
mlr3pipelines_0.12.0.tgz(r-4.6-any)mlr3pipelines_0.12.0.tgz(r-4.5-any)
mlr3pipelines_0.12.0.tar.gz(r-4.7-any)mlr3pipelines_0.12.0.tar.gz(r-4.6-any)
mlr3pipelines_0.12.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
mlr3pipelines/json (API)
| # Install 'mlr3pipelines' in R: |
| install.packages('mlr3pipelines', repos = c('https://mlr-org.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/mlr-org/mlr3pipelines/issues
Pkgdown/docs site:https://mlr3pipelines.mlr-org.com
baggingdata-sciencedataflow-programmingensemble-learningmachine-learningmlr3pipelinespreprocessingstacking
Last updated from:696baf0ea2 (on v0.12.0). Checks:8 OK, 1 ERROR. Indexed: yes.
| Target | Result | Time | Files | Syslog |
|---|---|---|---|---|
| linux-devel | OK | 383 | ||
| source / vignettes | OK | 357 | ||
| linux-release | OK | 310 | ||
| macos-release | OK | 250 | ||
| macos-oldrel | OK | 317 | ||
| windows-devel | OK | 282 | ||
| windows-release | OK | 227 | ||
| windows-oldrel | ERROR | 158 | ||
| wasm-release | OK | 120 |
Exports:%>>!%%>>%%among%add_class_hierarchy_cacheas_graphas_pipeopas.CnfAtomas.CnfClauseas.CnfFormulaas.data.tableas.Multiplicityassert_graphassert_pipeopchain_graphsCnfAtomCnfClauseCnfFormulaCnfSymbolCnfUniverseconcat_graphsfilter_noopFilterEnsembleGraphGraphLearnergunionis_noopis.MultiplicityLearnerClassifAvgLearnerRegrAvgmlr_graphsmlr_pipeopsMultiplicityNO_OPpipeline_baggingpipeline_branchpipeline_convert_typespipeline_greplicatepipeline_ovrpipeline_robustifypipeline_stackingpipeline_targettrafoPipeOpPipeOpADASPipeOpBLSmotePipeOpBoxCoxPipeOpBranchPipeOpChunkPipeOpClassBalancingPipeOpClassifAvgPipeOpClassWeightsPipeOpClassWeightsExPipeOpColApplyPipeOpCollapseFactorsPipeOpColRolesPipeOpCopyPipeOpDateFeaturesPipeOpDecodePipeOpEncodePipeOpEncodeImpactPipeOpEncodeLmerPipeOpEncodePLPipeOpEncodePLQuantilesPipeOpEncodePLTreePipeOpEnsemblePipeOpFeatureUnionPipeOpFilterPipeOpFixFactorsPipeOpHistBinPipeOpICAPipeOpImputePipeOpImputeConstantPipeOpImputeHistPipeOpImputeLearnerPipeOpImputeMeanPipeOpImputeMedianPipeOpImputeModePipeOpImputeOORPipeOpImputeSamplePipeOpInfoPipeOpIsomapPipeOpKernelPCAPipeOpLearnerPipeOpLearnerCVPipeOpLearnerPICVPlusPipeOpLearnerQuantilesPipeOpMaterializePipeOpMissIndPipeOpModelMatrixPipeOpMultiplicityExplyPipeOpMultiplicityImplyPipeOpMutatePipeOpNearmissPipeOpNMFPipeOpNOPPipeOpOVRSplitPipeOpOVRUnitePipeOpPCAPipeOpProxyPipeOpQuantileBinPipeOpRandomProjectionPipeOpRandomResponsePipeOpRegrAvgPipeOpRemoveConstantsPipeOpRenameColumnsPipeOpReplicatePipeOpRowApplyPipeOpScalePipeOpScaleMaxAbsPipeOpScaleRangePipeOpSelectPipeOpSmotePipeOpSmoteNCPipeOpSpatialSignPipeOpSplinesPipeOpSubsamplePipeOpTargetInvertPipeOpTargetMutatePipeOpTargetTrafoPipeOpTargetTrafoScaleRangePipeOpTaskPreprocPipeOpTaskPreprocSimplePipeOpTextVectorizerPipeOpThresholdPipeOpTomekPipeOpTuneThresholdPipeOpUnbranchPipeOpVtreatPipeOpYeoJohnsonpopospplpplspreprocregister_autoconvert_functionreset_autoconvert_registerreset_class_hierarchy_cacheselector_allselector_cardinality_greater_thanselector_grepselector_intersectselector_invertselector_missingselector_nameselector_negativeselector_non_missingselector_non_negativeselector_non_positiveselector_non_zeroselector_noneselector_positiveselector_setdiffselector_typeselector_union
Dependencies:backportscheckmateclicodetoolsdata.tabledigestevaluatefuturefuture.applyglobalslgrlistenvmiraimlbenchmlr3mlr3measuresmlr3miscnanonextpalmerpenguinsparadoxparallellyPRROCR6rlanguuid
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| mlr3pipelines: Preprocessing Operators and Pipelines for 'mlr3' | mlr3pipelines-package mlr3pipelines |
| PipeOp Composition Operator | %>>!% %>>% concat_graphs |
| Add a Class Hierarchy to the Cache | add_class_hierarchy_cache |
| Conversion to mlr3pipelines Graph | as_graph |
| Conversion to mlr3pipelines PipeOp | as_pipeop |
| Convert an object to a Multiplicity | as.Multiplicity |
| Assertion for mlr3pipelines Graph | assert_graph |
| Assertion for mlr3pipelines PipeOp | assert_pipeop |
| Chain a Series of Graphs | chain_graphs |
| Remove NO_OPs from a List | filter_noop |
| Graph Base Class | Graph |
| Disjoint Union of Graphs | gunion |
| Test for NO_OP | is_noop |
| Check if an object is a Multiplicity | is.Multiplicity |
| Filter Ensemble | FilterEnsemble mlr_filters_ensemble |
| Dictionary of (sub-)graphs | mlr_graphs |
| Create a bagging learner | mlr_graphs_bagging pipeline_bagging |
| Branch Between Alternative Paths | mlr_graphs_branch pipeline_branch |
| Convert Column Types | mlr_graphs_convert_types pipeline_convert_types |
| Create Disjoint Graph Union of Copies of a Graph | mlr_graphs_greplicate pipeline_greplicate |
| Create A Graph to Perform "One vs. Rest" classification. | mlr_graphs_ovr pipeline_ovr |
| Robustify a learner | mlr_graphs_robustify pipeline_robustify |
| Create A Graph to Perform Stacking. | mlr_graphs_stacking pipeline_stacking |
| Transform and Re-Transform the Target Variable | mlr_graphs_targettrafo pipeline_targettrafo |
| Optimized Weighted Average of Features for Classification and Regression | LearnerClassifAvg LearnerRegrAvg mlr_learners_avg mlr_learners_classif.avg mlr_learners_regr.avg |
| Encapsulate a Graph as a Learner | GraphLearner mlr_learners_graph |
| Dictionary of PipeOps | mlr_pipeops |
| ADAS Balancing | mlr_pipeops_adas PipeOpADAS |
| BLSMOTE Balancing | mlr_pipeops_blsmote PipeOpBLSmote |
| Box-Cox Transformation of Numeric Features | mlr_pipeops_boxcox PipeOpBoxCox |
| Path Branching | mlr_pipeops_branch PipeOpBranch |
| Chunk Input into Multiple Outputs | mlr_pipeops_chunk PipeOpChunk |
| Class Balancing | mlr_pipeops_classbalancing PipeOpClassBalancing |
| Majority Vote Prediction | mlr_pipeops_classifavg PipeOpClassifAvg |
| Class Weights for Sample Weighting | mlr_pipeops_classweights PipeOpClassWeights |
| Class Weights for Sample Weighting - Extended | mlr_pipeops_classweightsex PipeOpClassWeightsEx |
| Apply a Function to each Column of a Task | mlr_pipeops_colapply PipeOpColApply |
| Collapse Factors | mlr_pipeops_collapsefactors PipeOpCollapseFactors |
| Change Column Roles of a Task | mlr_pipeops_colroles PipeOpColRoles |
| Copy Input Multiple Times | mlr_pipeops_copy PipeOpCopy |
| Preprocess Date Features | mlr_pipeops_datefeatures PipeOpDateFeatures |
| Reverse Factor Encoding | mlr_pipeops_decode PipeOpDecode |
| Factor Encoding | mlr_pipeops_encode PipeOpEncode |
| Conditional Target Value Impact Encoding | mlr_pipeops_encodeimpact PipeOpEncodeImpact |
| Impact Encoding with Random Intercept Models | mlr_pipeops_encodelmer PipeOpEncodeLmer |
| Piecewise Linear Encoding using Quantiles | mlr_pipeops_encodeplquantiles PipeOpEncodePLQuantiles |
| Piecewise Linear Encoding using Decision Trees | mlr_pipeops_encodepltree PipeOpEncodePLTree |
| Aggregate Features from Multiple Inputs | mlr_pipeops_featureunion PipeOpFeatureUnion |
| Feature Filtering | mlr_pipeops_filter PipeOpFilter |
| Fix Factor Levels | mlr_pipeops_fixfactors PipeOpFixFactors |
| Split Numeric Features into Equally Spaced Bins | mlr_pipeops_histbin PipeOpHistBin |
| Independent Component Analysis | mlr_pipeops_ica PipeOpICA |
| Impute Features by a Constant | mlr_pipeops_imputeconstant PipeOpImputeConstant |
| Impute Numeric, Integer, POSIXct or Date Features by Histogram | mlr_pipeops_imputehist PipeOpImputeHist |
| Impute Features by Fitting a Learner | mlr_pipeops_imputelearner PipeOpImputeLearner |
| Impute Numeric, Integer, POSIXct or Date Features by their Mean | mlr_pipeops_imputemean PipeOpImputeMean |
| Impute Numeric, Integer, POSIXct or Date Features by their Median | mlr_pipeops_imputemedian PipeOpImputeMedian |
| Impute Features by their Mode | mlr_pipeops_imputemode PipeOpImputeMode |
| Out of Range Imputation | mlr_pipeops_imputeoor PipeOpImputeOOR |
| Impute Features by Sampling | mlr_pipeops_imputesample PipeOpImputeSample |
| Customizable Information Printer | mlr_pipeops_info PipeOpInfo |
| Algorithm for Dimensionality Reduction | mlr_pipeops_isomap PipeOpIsomap |
| Kernelized Principal Component Analysis | mlr_pipeops_kernelpca PipeOpKernelPCA |
| Wrap a Learner into a PipeOp | mlr_pipeops_learner PipeOpLearner |
| Wrap a Learner into a PipeOp with Cross-validated Predictions as Features | mlr_pipeops_learner_cv PipeOpLearnerCV |
| Wrap a Learner into a PipeOp with Cross-validation Plus Confidence Intervals as Predictions | mlr_pipeops_learner_pi_cvplus PipeOpLearnerPICVPlus |
| Wrap a Learner into a PipeOp to predict multiple Quantiles | mlr_pipeops_learner_quantiles PipeOpLearnerQuantiles |
| Materialize Task View | mlr_pipeops_materialize PipeOpMaterialize |
| Add Missing Indicator Columns | mlr_pipeops_missind PipeOpMissInd |
| Transform Columns by Constructing a Model Matrix | mlr_pipeops_modelmatrix PipeOpModelMatrix |
| Explicate a Multiplicity | mlr_pipeops_multiplicityexply PipeOpMultiplicityExply |
| Implicate a Multiplicity | mlr_pipeops_multiplicityimply PipeOpMultiplicityImply |
| Add Features According to Expressions | mlr_pipeops_mutate PipeOpMutate |
| Nearmiss Down-Sampling | mlr_pipeops_nearmiss PipeOpNearmiss |
| Non-negative Matrix Factorization | mlr_pipeops_nmf PipeOpNMF |
| Simply Push Input Forward | mlr_pipeops_nop PipeOpNOP |
| Split a Classification Task into Binary Classification Tasks | mlr_pipeops_ovrsplit PipeOpOVRSplit |
| Unite Binary Classification Tasks | mlr_pipeops_ovrunite PipeOpOVRUnite |
| Principal Component Analysis | mlr_pipeops_pca PipeOpPCA |
| Wrap another PipeOp or Graph as a Hyperparameter | mlr_pipeops_proxy PipeOpProxy |
| Split Numeric Features into Quantile Bins | mlr_pipeops_quantilebin PipeOpQuantileBin |
| Project Numeric Features onto a Randomly Sampled Subspace | mlr_pipeops_randomprojection PipeOpRandomProjection |
| Generate a Randomized Response Prediction | mlr_pipeops_randomresponse PipeOpRandomResponse |
| Weighted Prediction Averaging | mlr_pipeops_regravg PipeOpRegrAvg |
| Remove Constant Features | mlr_pipeops_removeconstants PipeOpRemoveConstants |
| Rename Columns | mlr_pipeops_renamecolumns PipeOpRenameColumns |
| Replicate the Input as a Multiplicity | mlr_pipeops_replicate PipeOpReplicate |
| Apply a Function to each Row of a Task | mlr_pipeops_rowapply PipeOpRowApply |
| Center and Scale Numeric Features | mlr_pipeops_scale PipeOpScale |
| Scale Numeric Features with Respect to their Maximum Absolute Value | mlr_pipeops_scalemaxabs PipeOpScaleMaxAbs |
| Linearly Transform Numeric Features to Match Given Boundaries | mlr_pipeops_scalerange PipeOpScaleRange |
| Remove Features Depending on a Selector | mlr_pipeops_select PipeOpSelect |
| SMOTE Balancing | mlr_pipeops_smote PipeOpSmote |
| SMOTENC Balancing | mlr_pipeops_smotenc PipeOpSmoteNC |
| Normalize Data Row-wise | mlr_pipeops_spatialsign PipeOpSpatialSign |
| Transforms Numeric Features into Spline Basis Expansions | mlr_pipeops_splines PipeOpSplines |
| Subsampling | mlr_pipeops_subsample PipeOpSubsample |
| Invert Target Transformations | mlr_pipeops_targetinvert PipeOpTargetInvert |
| Transform a Target by a Function | mlr_pipeops_targetmutate PipeOpTargetMutate |
| Linearly Transform a Numeric Target to Match Given Boundaries | mlr_pipeops_targettrafoscalerange PipeOpTargetTrafoScaleRange |
| Bag-of-word Representation of Character Features | mlr_pipeops_textvectorizer PipeOpTextVectorizer |
| Change the Threshold of a Classification Prediction | mlr_pipeops_threshold PipeOpThreshold |
| Tomek Down-Sampling | mlr_pipeops_tomek PipeOpTomek |
| Tune the Threshold of a Classification Prediction | mlr_pipeops_tunethreshold PipeOpTuneThreshold |
| Unbranch Different Paths | mlr_pipeops_unbranch PipeOpUnbranch |
| Transform a Target without an Explicit Inversion | mlr_pipeops_updatetarget PipeOpUpdateTarget |
| Interface to the vtreat Package | mlr_pipeops_vtreat PipeOpVtreat |
| Yeo-Johnson Transformation of Numeric Features | mlr_pipeops_yeojohnson PipeOpYeoJohnson |
| Housing Data for 506 Census Tracts of Boston | mlr_tasks_boston_housing |
| Multiplicity | Multiplicity |
| No-Op Sentinel Used for Alternative Branching | NO_OP |
| PipeOp Base Class | PipeOp |
| Piecewise Linear Encoding Base Class | PipeOpEncodePL |
| Ensembling Base Class | PipeOpEnsemble |
| Imputation Base Class | PipeOpImpute |
| Target Transformation Base Class | PipeOpTargetTrafo |
| Task Preprocessing Base Class | PipeOpTaskPreproc |
| Simple Task Preprocessing Base Class | PipeOpTaskPreprocSimple |
| Shorthand PipeOp Constructor | po pos |
| Shorthand Graph Constructor | ppl ppls |
| Simple Pre-processing | preproc |
| Add Autoconvert Function to Conversion Register | register_autoconvert_function |
| Reset Autoconvert Register | reset_autoconvert_register |
| Reset the Class Hierarchy Cache | reset_class_hierarchy_cache |
| Selector Functions | Selector selector_all selector_cardinality_greater_than selector_grep selector_intersect selector_invert selector_missing selector_name selector_negative selector_none selector_non_missing selector_non_negative selector_non_positive selector_non_zero selector_positive selector_setdiff selector_type selector_union |
| Configure Validation for a GraphLearner | set_validate.GraphLearner |