Learn R Programming
⚠️There's a newer version (2.19.1) of this package.Take me there.

mlr (version 2.19.0)

Machine Learning in R

Description

Interface to a large number of classification and regression techniques, including machine-readable parameter descriptions. There is also an experimental extension for survival analysis, clustering and general, example-specific cost-sensitive learning. Generic resampling, including cross-validation, bootstrapping and subsampling. Hyperparameter tuning with modern optimization techniques, for single- and multi-objective problems. Filter and wrapper methods for feature selection. Extension of basic learners with additional operations common in machine learning, also allowing for easy nested resampling. Most operations can be parallelized.

Copy Link

Version

Install

install.packages('mlr')

Monthly Downloads

9,216

Version

2.19.0

License

BSD_2_clause + file LICENSE

Issues

8

Pull Requests

5

Stars

1,644

Forks

405

Maintainer

Patrick Schratz

Last Published

February 22nd, 2021

Functions in mlr (2.19.0)

Task

Create a classification, regression, survival, cluster, cost-sensitive classification or multilabel task.
Aggregation

Aggregation object.
BenchmarkResult

BenchmarkResult object.
TaskDesc

Description object for task.
makeSurvTask

Create a survival task.
ResampleResult

ResampleResult object.
agri.task

European Union Agricultural Workforces clustering task.
makeCostSensTask

Create a cost-sensitive classification task.
ConfusionMatrix

Confusion matrix
Prediction

Prediction object.
RLearner

Internal construction / wrapping of learner object.
analyzeFeatSelResult

Show and visualize the steps of feature selection.
TuneMultiCritResult

Result of multi-criteria tuning.
addRRMeasure

Compute new measures for existing ResampleResult
aggregations

Aggregation methods.
calculateConfusionMatrix

Confusion matrix.
calculateROCMeasures

Calculate receiver operator measures.
TuneResult

Result of tuning.
createDummyFeatures

Generate dummy variables for factor features.
convertMLBenchObjToTask

Convert a machine learning benchmark / demo object from package mlbench to a task.
costiris.task

Iris cost-sensitive classification task.
FeatSelResult

Result of feature selection.
MeasureProperties

Query properties of measures.
LearnerProperties

Query properties of learners.
makeClassifTask

Create a classification task.
checkPredictLearnerOutput

Check output returned by predictLearner.
makeMultilabelTask

Create a multilabel task.
checkLearner

Exported for internal use only.
makeClusterTask

Create a cluster task.
makeRegrTask

Create a regression task.
createSpatialResamplingPlots

Create (spatial) resampling plot objects.
extractFDAMultiResFeatures

Multiresolution feature extraction.
dropFeatures

Drop some features of task.
extractFDATsfeatures

Time-Series Feature Heuristics
estimateRelativeOverfitting

Estimate relative overfitting.
extractFDAWavelets

Discrete Wavelet transform features.
filterFeatures

Filter features by thresholding filter values.
getBMRFeatSelResults

Extract the feature selection results from a benchmark result.
generateLearningCurveData

Generates a learning curve.
TuneControl

Control object for tuning
fuelsubset.task

FuelSubset functional data regression task.
generatePartialDependenceData

Generate partial dependence.
generateThreshVsPerfData

Generate threshold vs. performance(s) for 2-class classification.
getBMRAggrPerformances

Extract the aggregated performance values from a benchmark result.
getBMRTaskIds

Return task ids used in benchmark.
getBMRFilteredFeatures

Extract the feature selection results from a benchmark result.
getBMRTuneResults

Extract the tuning results from a benchmark result.
getHyperPars

Get current parameter settings for a learner.
generateCalibrationData

Generate classifier calibration data.
getFunctionalFeatures

Get only functional features from a task or a data.frame.
getHomogeneousEnsembleModels

Deprecated, use getLearnerModel instead.
ResamplePrediction

Prediction from resampling.
getLearnerPackages

Get the required R packages of the learner.
capLargeValues

Convert large/infinite numeric values in a data.frame or task.
TuneMultiCritControl

Create control structures for multi-criteria tuning.
getLearnerParVals

Get the parameter values of the learner.
getOOBPreds

Extracts out-of-bag predictions from trained models.
getRRDump

Return the error dump of ResampleResult.
getTaskTargets

Get target data of task.
getRRPredictionList

Get list of predictions for train and test set of each single resample iteration.
getOOBPredsLearner

Provides out-of-bag predictions for a given model and the corresponding learner.
getCaretParamSet

Get tuning parameters from a learner of the caret R-package.
getClassWeightParam

Get the class weight parameter of a learner.
getLearnerParamSet

Get the parameter set of the learner.
getLearnerPredictType

Get the predict type of the learner.
getPredictionProbabilities

Get probabilities for some classes.
getTaskType

Get the type of the task.
changeData

Change Task Data
getLearnerId

Get the ID of the learner.
getMultilabelBinaryPerformances

Retrieve binary classification measures for multilabel classification predictions.
getNestedTuneResultsOptPathDf

Get the opt.paths from each tuning step from the outer resampling.
getMlrOptions

Returns a list of mlr's options.
getRRTaskDescription

Get task description from resample results (DEPRECATED).
getNestedTuneResultsX

Get the tuned hyperparameter settings from a nested tuning.
getResamplingIndices

Get the resampling indices from a tuning or feature selection wrapper..
isFailureModel

Is the model a FailureModel?
joinClassLevels

Join some class existing levels to new, larger class levels for classification problems.
lung.task

NCCTG Lung Cancer survival task.
listTaskTypes

List the supported task types in mlr
getTaskDesc

Get a summarizing task description.
getTaskDescription

Deprecated, use getTaskDesc instead.
getPredictionResponse

Get response / truth from prediction object.
FailureModel

Failure model.
hasFunctionalFeatures

Check whether the object contains functional features.
gunpoint.task

Gunpoint functional data classification task.
asROCRPrediction

Converts predictions to a format package ROCR can handle.
batchmark

Run machine learning benchmarks as distributed experiments.
listFilterEnsembleMethods

List ensemble filter methods.
FeatSelControl

Create control structures for feature selection.
downsample

Downsample (subsample) a task or a data.frame.
crossover

Crossover.
listFilterMethods

List filter methods.
getTuneResult

Returns the optimal hyperparameters and optimization path after training.
bc.task

Wisconsin Breast Cancer classification task.
benchmark

Benchmark experiment for multiple learners and tasks.
makeAggregation

Specify your own aggregation of measures.
makeFilter

Create a feature filter.
generateCritDifferencesData

Generate data for critical-differences plot.
extractFDAFPCA

Extract functional principal component analysis features.
extractFDADTWKernel

DTW kernel features
generateFeatureImportanceData

Generate feature importance.
getTuneResultOptPath

Get the optimization path of a tuning result.
bh.task

Boston Housing regression task.
cache_helpers

Get or delete mlr cache directory
makeFilterEnsemble

Create an ensemble feature filter.
makeFixedHoldoutInstance

Generate a fixed holdout instance for resampling.
makeFilterWrapper

Fuse learner with a feature filter method.
extractFDAFeatures

Extract features from functional data.
listMeasureProperties

List the supported measure properties.
configureMlr

Configures the behavior of the package.
convertBMRToRankMatrix

Convert BenchmarkResult to a rank-matrix.
getBMRMeasures

Return measures used in benchmark.
makeMultilabelBinaryRelevanceWrapper

Use binary relevance method to create a multilabel learner.
makeClassifTaskDesc

Exported for internal use.
makeMulticlassWrapper

Fuse learner with multiclass method.
makeWeightedClassesWrapper

Wraps a classifier for weighted fitting where each class receives a weight.
makeStackedLearner

Create a stacked learner object.
makeBaggingWrapper

Fuse learner with the bagging technique.
getBMRTaskDescriptions

Extract all task descriptions from benchmark result (DEPRECATED).
getBMRModels

Extract all models from benchmark result.
extractFDAFourier

Fast Fourier transform features.
makeLearner

Create learner object.
makeExtractFDAFeatMethod

Constructor for FDA feature extraction methods.
makeDummyFeaturesWrapper

Fuse learner with dummy feature creator.
makeImputeWrapper

Fuse learner with an imputation method.
getLearnerShortName

Get the short name of the learner.
getBMRTaskDescs

Extract all task descriptions from benchmark result.
getFeatSelResult

Returns the selected feature set and optimization path after training.
getFeatureImportance

Calculates feature importance values for trained models.
getLearnerType

Get the type of the learner.
makeWrappedModel

Induced model of learner.
getPredictionTaskDesc

Get summarizing task description from prediction.
mergeBenchmarkResults

Merge different BenchmarkResult objects.
measures

Performance measures.
makeCostSensRegrWrapper

Wraps a regression learner for use in cost-sensitive learning.
makeBaseWrapper

Exported for internal use only.
listMeasures

Find matching measures.
plotBMRBoxplots

Create box or violin plots for a BenchmarkResult.
plotBMRRanksAsBarChart

Create a bar chart for ranks in a BenchmarkResult.
makeChainModel

Only exported for internal use.
getProbabilities

Deprecated, use getPredictionProbabilities instead.
generateFilterValuesData

Calculates feature filter values.
estimateResidualVariance

Estimate the residual variance.
makeMultilabelStackingWrapper

Use stacking method (stacked generalization) to create a multilabel learner.
makeMultilabelNestedStackingWrapper

Use nested stacking method to create a multilabel learner.
makeMeasure

Construct performance measure.
makeCostSensWeightedPairsWrapper

Wraps a classifier for cost-sensitive learning to produce a weighted pairs model.
makeLearners

Create multiple learners at once.
generateHyperParsEffectData

Generate hyperparameter effect data.
getTaskClassLevels

Get the class levels for classification and multilabel tasks.
getTaskId

Get the id of the task.
getStackedBaseLearnerPredictions

Returns the predictions for each base learner.
makeOverBaggingWrapper

Fuse learner with the bagging technique and oversampling for imbalancy correction.
makePreprocWrapper

Fuse learner with preprocessing.
makeResampleInstance

Instantiates a resampling strategy object.
getTaskNFeats

Get number of features in task.
makeRLearner.classif.fdausc.np

Learner for nonparametric classification for functional data.
makeTuneControlMBO

Create control object for hyperparameter tuning with MBO.
makeRLearner.classif.fdausc.kernel

Learner for kernel classification for functional data.
makeSMOTEWrapper

Fuse learner with SMOTE oversampling for imbalancy correction in binary classification.
extractFDABsignal

Bspline mlq features
plotResiduals

Create residual plots for prediction objects or benchmark results.
removeConstantFeatures

Remove constant features from a data set.
plotROCCurves

Plots a ROC curve using ggplot2.
spatial.task

J. Muenchow's Ecuador landslide data set
reimpute

Re-impute a data set
impute

Impute and re-impute data
iris.task

Iris classification task.
makeCostMeasure

Creates a measure for non-standard misclassification costs.
learners

List of supported learning algorithms.
learnerArgsToControl

Convert arguments to control structure.
normalizeFeatures

Normalize features.
subsetTask

Subset data in task.
removeHyperPars

Remove hyperparameters settings of a learner.
phoneme.task

Phoneme functional data multilabel classification task.
simplifyMeasureNames

Simplify measure names.
tuneParams

Hyperparameter tuning.
oversample

Over- or undersample binary classification task to handle class imbalancy.
resample

Fit models according to a resampling strategy.
smote

Synthetic Minority Oversampling Technique to handle class imbalancy in binary classification.
mlr-package

mlr: Machine Learning in R
pid.task

PimaIndiansDiabetes classification task.
makeCostSensClassifWrapper

Wraps a classification learner for use in cost-sensitive learning.
setPredictThreshold

Set the probability threshold the learner should use.
makeTuneControlRandom

Create control object for hyperparameter tuning with random search.
mergeSmallFactorLevels

Merges small levels of factors into new level.
setHyperPars2

Only exported for internal use.
summarizeColumns

Summarize columns of data.frame or task.
setMeasurePars

Set parameters of performance measures
setHyperPars

Set the hyperparameters of a learner object.
reextractFDAFeatures

Re-extract features from a data set
reduceBatchmarkResults

Reduce results of a batch-distributed benchmark.
tuneParamsMultiCrit

Hyperparameter tuning for multiple measures at once.
makeExtractFDAFeatsWrapper

Fuse learner with an extractFDAFeatures method.
makeFeatSelWrapper

Fuse learner with feature selection.
getConfMatrix

Confusion matrix.
friedmanPostHocTestBMR

Perform a posthoc Friedman-Nemenyi test.
getBMRLearnerIds

Return learner ids used in benchmark.
friedmanTestBMR

Perform overall Friedman test for a BenchmarkResult.
getBMRLearnerShortNames

Return learner short.names used in benchmark.
summarizeLevels

Summarizes factors of a data.frame by tabling them.
getBMRMeasureIds

Return measures IDs used in benchmark.
getBMRLearners

Return learners used in benchmark.
getBMRPerformances

Extract the test performance values from a benchmark result.
getDefaultMeasure

Get default measure.
makeImputeMethod

Create a custom imputation method.
makeMultilabelClassifierChainsWrapper

Use classifier chains method (CC) to create a multilabel learner.
makeFunctionalData

Create a data.frame containing functional features from a normal data.frame.
getFeatureImportanceLearner.regr.randomForestSRC

Calculates feature importance values for a given learner.
getTaskCosts

Extract costs in task.
getBMRPredictions

Extract the predictions from a benchmark result.
getFilteredFeatures

Returns the filtered features.
makeTuneControlDesign

Create control object for hyperparameter tuning with predefined design.
makeTuneControlGenSA

Create control object for hyperparameter tuning with GenSA.
makeMultilabelDBRWrapper

Use dependent binary relevance method (DBR) to create a multilabel learner.
getFailureModelDump

Return the error dump of FailureModel.
performance

Measure performance of prediction.
parallelization

Supported parallelization methods
getLearnerNote

Get the note for the learner.
getFailureModelMsg

Return error message of FailureModel.
getLearnerModel

Get underlying R model of learner integrated into mlr.
getParamSet

Get a description of all possible parameter settings for a learner.
getTaskData

Extract data in task.
getTaskTargetNames

Get the name(s) of the target column(s).
helpLearnerParam

Get specific help for a learner's parameters.
getTaskSize

Get number of observations in task.
getRRPredictions

Get predictions from resample results.
getPredictionDump

Return the error dump of a failed Prediction.
imputations

Built-in imputation methods.
listLearners

Find matching learning algorithms.
listLearnerProperties

List the supported learner properties
makePreprocWrapperCaret

Fuse learner with preprocessing.
getRRTaskDesc

Get task description from resample results (DEPRECATED).
getTaskFormula

Get formula of a task.
getTaskFeatureNames

Get feature names of task.
hasProperties

Deprecated, use hasLearnerProperties instead.
makeClassificationViaRegressionWrapper

Classification via regression wrapper.
helpLearner

Access help page of learner functions.
makeConstantClassWrapper

Wraps a classification learner to support problems where the class label is (almost) constant.
makeTaskDescInternal

Exported for internal use.
makeRLearner.classif.fdausc.glm

Classification of functional data by Generalized Linear Models.
makeTuneControlCMAES

Create control object for hyperparameter tuning with CMAES.
makeCustomResampledMeasure

Construct your own resampled performance measure.
mlrFamilies

mlr documentation families
makeTuneControlIrace

Create control object for hyperparameter tuning with Irace.
makeTuneControlGrid

Create control object for hyperparameter tuning with grid search.
makeDownsampleWrapper

Fuse learner with simple downsampling (subsampling).
plotHyperParsEffect

Plot the hyperparameter effects data
mtcars.task

Motor Trend Car Road Tests clustering task.
makeModelMultiplexer

Create model multiplexer for model selection to tune over multiple possible models.
makeRemoveConstantFeaturesWrapper

Fuse learner with removal of constant features preprocessing.
makeModelMultiplexerParamSet

Creates a parameter set for model multiplexer tuning.
makeResampleDesc

Create a description object for a resampling strategy.
makeTuneWrapper

Fuse learner with tuning.
trainLearner

Train an R learner.
makeUndersampleWrapper

Fuse learner with simple ove/underrsampling for imbalancy correction in binary classification.
plotBMRSummary

Plot a benchmark summary.
plotLearningCurve

Plot learning curve data using ggplot2.
plotCalibration

Plot calibration data using ggplot2.
predictLearner

Predict new data with an R learner.
plotCritDifferences

Plot critical differences for a selected measure.
plotFilterValues

Plot filter values using ggplot2.
predict.WrappedModel

Predict new data.
plotPartialDependence

Plot a partial dependence with ggplot2.
setId

Set the id of a learner object.
yeast.task

Yeast multilabel classification task.
setLearnerId

Set the ID of a learner object.
sonar.task

Sonar classification task.
spam.task

Spam classification task.
train

Train a learning algorithm.
setPredictType

Set the type of predictions the learner should return.
selectFeatures

Feature selection by wrapper approach.
plotThreshVsPerf

Plot threshold vs. performance(s) for 2-class classification using ggplot2.
plotLearnerPrediction

Visualizes a learning algorithm on a 1D or 2D data set.
setAggregation

Set aggregation function of measure.
plotTuneMultiCritResult

Plots multi-criteria results after tuning using ggplot2.
setThreshold

Set threshold of prediction object.
wpbc.task

Wisonsin Prognostic Breast Cancer (WPBC) survival task.
tuneThreshold

Tune prediction threshold.