Learn R Programming

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

mlr (version 2.0)

mlr: Machine Learning in R.

Description

Interface to a large number of classification and regression techniques, including machine-readable parameter descriptions. There is also a n experimental extension for surival analysis and cost-sensitive learning. Generic resampling, including cross-validation, bootstrapping and subsampling. Hyperparameter tuning with modern optimization techniques. Filter and wrapper methods for feature selection. Extension of basic learners with additional operations common in machine learning.

Copy Link

Version

Install

install.packages('mlr')

Monthly Downloads

7,379

Version

2.0

License

BSD_3_clause + file LICENSE

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/berndbischl/mlr

Maintainer

Bernd Bischl

Last Published

July 4th, 2014

Functions in mlr (2.0)

Feature selection by wrapper approach.

BenchmarkResult

Result of a benchmark run.

getTaskFeatureNames

Get feature names of task.

plotLearnerPrediction

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

getLearnerModel

Get underlying R model of learner integrated into mlr.

plotThreshVsPerf

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

listFilterMethods

Returns all available feature filter methods.

Aggregation methods.

makeImputeMethod

Create a custom imputation method.

estimateResidualVariance

Estimate the residual variance

makeBaggingWrapper

Fuse learner with the bagging technique.

Predict new data with an R learner.

makeCostSensClassifWrapper

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

createDummyFeatures

Generate dummy variables for factor features.

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

makePreprocWrapper

Fuse learner with preprocessing.

Result of tuning.

Extract costs in task.

makeCostMeasure

Creates a measure for non-standard misclassification costs.

Configures the behavior of the package.

Internal construction / wrapping of learner object.

ResamplePrediction

Prediction from resampling.

Set the hyperparameters of a learner object.

Drop some features of task.

getFeatSelResult

Returns the selected feature set and optimization path after training or benchmarking.

Get number of feature in task.

Is the model a FailureModel?

getCostSensWeightedPairsModels

Returns the list of fitted models.

getFilteredFeatures

Returns the filtered features.

Returns the optimal hyperparameters and optimization path after training or benchmarking.

Get current parameter settings for a learner.

makeClassifTask

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

makeFeatSelControlExhaustive

Create control structures for feature selection.

makeOverBaggingWrapper

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

getTaskFormulaAsString

Get formula of a task.

getBaggingModels

Returns the list of models fitted in bagging.

Extract data in task.

Train a learning algorithm.

Measure performance of prediction.

Create learner object.

Extract the predictions from a benchmark result.

Set threshold of prediction object.

Find matching measures.

Set the id of a learner object.

makeAggregation

Specifiy your own aggregation of measures

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

Train an R learner.

Display all possible hyperparameter settings for a learner that mlr knows.

makeModelMultiplexer

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

makeCustomResampledMeasure

Construct your own resampled performance measure.

Set the type of predictions the learner should return.

Re-impute a data set

Boston Housing regression task

Only exported for internal use.

getCostSensClassifModel

Returns the underlying classification model.

getProbabilities

Get probabilities for some classes.

removeConstantFeatures

Remove constant features from a data set.

makeTuneWrapper

Fuse learner with tuning.

getPerformances

Extract performance measures of bechmark result.

Built in imputation methods The built-ins are:

imputeConstant(const)for imputation using a constant value,
imputeMedian()for imputation using the median,
imputeMode()for imputation using the mode,
imputeMin(multiplier)for imputation using the minimum,
imputeMax(multiplier)for imputation using the maximum,
imputeNormal(mean, sd)for imputation using normally distributed random values. Mean and standard deviation will be calculated from the data if not provided.
imputeHist(breaks, use.mids)for imputation using random values with probabilities calculated usingtableorhist.
imputeLearner(learner, preimpute)for imputations using the response of a classification or regression learner.

predict.WrappedModel

Predict new data.

makeCostSensWeightedPairsWrapper

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

Tune prediction threshold.

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

Result of getFilterValues.

learnerArgsToControl

Convert arguments to control structure.

getCostSensRegrModels

Returns the list of fitted models.

Hyperparameter tuning.

Prediction object.

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

Subset data in task.

makeFixedHoldoutInstance

Generate a fixed holdout instance for resampling.

Result of feature selection.

Filter features by thresholding filter values.

Set aggregation function of measure.

makeFilterWrapper

Fuse learner with a feature filter method.

makeModelMultiplexerParamSet

Creates a parameter set for model multiplexer tuning.

getAggrPerformances

Extract the aggregated measures of a benchmark result.

plotFilterValues

Plot filter values.

asROCRPrediction

Converts predictions to a format package ROCR can handle.

LearnerProperties

Set, add, remove or query properties of learners

analyzeFeatSelResult

Show and visualize the steps of feature selection.

Description object for task.

An aggregation method reduces the performance values of the test (and possibly the training sets) to a single value. To see all possible, implemented aggregations look at aggregations.

makeUndersampleWrapper

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

makeWrappedModel

Induced model of learner.

getFilterValues

Calculates feature filter values.

Benchmark experiment for multiple learners and tasks.

makeImputeWrapper

Fuse learner with an imputation method.

normalizeFeatures

Normalize features

makeCostSensRegrWrapper

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

Confusion matrix.

makeWeightedClassesWrapper

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

Get target column of task.

makeDownsampleWrapper

Fuse learner with simple downsampling (subsampling).

getFilterResult

Returns a filter result after training or benchmarking.

Sonar classification task

makeSMOTEWrapper

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

makeResampleInstance

Instantiates a resampling strategy object.

Find matching learning algorithms.

makeResampleDesc

Create a description object for a resampling strategy.

makeFeatSelWrapper

Fuse learner with feature selection.

Construct performance measure.

Returns a list of mlr's options

Iris classification task

Fit models according to a resampling strategy.

makeTuneControlCMAES

Create control structures for tuning.

Impute and re-impute data

Performance measures.

List of supported learning algorithms.