mlr

Aggregation object.

BenchmarkResult object.

Create a classification task.

Create a cluster task.

Confusion matrix

Create a cost-sensitive classification task.

Failure model.

Create control structures for feature selection.

Result of feature selection.

Query properties of learners.

Query properties of measures.

Create a multilabel task.

Prediction object.

Internal construction / wrapping of learner object.

Create a regression task.

Prediction from resampling.

ResampleResult object.

Create a survival task.

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

Description object for task.

Control object for tuning

Create control structures for multi-criteria tuning.

Result of multi-criteria tuning.

Result of tuning.

Compute new measures for existing ResampleResult

Aggregation methods.

European Union Agricultural Workforces clustering task.

Show and visualize the steps of feature selection.

Converts predictions to a format package ROCR can handle.

Run machine learning benchmarks as distributed experiments.

Wisconsin Breast Cancer classification task.

Benchmark experiment for multiple learners and tasks.

Boston Housing regression task.

Get or delete mlr cache directory

Confusion matrix.

Calculate receiver operator measures.

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

Change Task Data

Exported for internal use only.

Check output returned by predictLearner.

Configures the behavior of the package.

Convert BenchmarkResult to a rank-matrix.

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

Iris cost-sensitive classification task.

Generate dummy variables for factor features.

Create (spatial) resampling plot objects.

Crossover.

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

Drop some features of task.

Estimate relative overfitting.

Estimate the residual variance.

Bspline mlq features

DTW kernel features

Extract functional principal component analysis features.

Extract features from functional data.

Fast Fourier transform features.

Multiresolution feature extraction.

Time-Series Feature Heuristics

Discrete Wavelet transform features.

Filter features by thresholding filter values.

Perform a posthoc Friedman-Nemenyi test.

Perform overall Friedman test for a BenchmarkResult.

FuelSubset functional data regression task.

Generate classifier calibration data.

Generate data for critical-differences plot.

Generate feature importance.

Calculates feature filter values.

Generate hyperparameter effect data.

Generates a learning curve.

Generate partial dependence.

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

Extract the aggregated performance values from a benchmark result.

Extract the feature selection results from a benchmark result.

Extract the feature selection results from a benchmark result.

Return learner ids used in benchmark.

Return learner short.names used in benchmark.

Return learners used in benchmark.

Return measures IDs used in benchmark.

Return measures used in benchmark.

Extract all models from benchmark result.

Extract the test performance values from a benchmark result.

Extract the predictions from a benchmark result.

Extract all task descriptions from benchmark result (DEPRECATED).

Extract all task descriptions from benchmark result.

Return task ids used in benchmark.

Extract the tuning results from a benchmark result.

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

Get the class weight parameter of a learner.

Confusion matrix.

Get default measure.

Return the error dump of FailureModel.

Return error message of FailureModel.

Returns the selected feature set and optimization path after training.

Calculates feature importance values for trained models.

Calculates feature importance values for a given learner.

Returns the filtered features.

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

Deprecated, use getLearnerModel instead.

Get current parameter settings for a learner.

Get the ID of the learner.

Get underlying R model of learner integrated into mlr.

Get the note for the learner.

Get the required R packages of the learner.

Get the parameter values of the learner.

Get the parameter set of the learner.

Get the predict type of the learner.

Get the short name of the learner.

Get the type of the learner.

Returns a list of mlr's options.

Retrieve binary classification measures for multilabel classification predictions.

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

Get the tuned hyperparameter settings from a nested tuning.

Extracts out-of-bag predictions from trained models.

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

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

Return the error dump of a failed Prediction.

Get probabilities for some classes.

Get response / truth from prediction object.

Get summarizing task description from prediction.

Deprecated, use getPredictionProbabilities instead.

Return the error dump of ResampleResult.

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

Get predictions from resample results.

Get task description from resample results (DEPRECATED).

Get task description from resample results (DEPRECATED).

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

Returns the predictions for each base learner.

Get the class levels for classification and multilabel tasks.

Extract costs in task.

Extract data in task.

Get a summarizing task description.

Deprecated, use getTaskDesc instead.

Get feature names of task.

Get formula of a task.

Get the id of the task.

Get number of features in task.

Get number of observations in task.

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

Get target data of task.

Get the type of the task.

Returns the optimal hyperparameters and optimization path after training.

Get the optimization path of a tuning result.

Gunpoint functional data classification task.

Check whether the object contains functional features.

Deprecated, use hasLearnerProperties instead.

Access help page of learner functions.

Get specific help for a learner's parameters.

Built-in imputation methods.

Impute and re-impute data

Iris classification task.

Is the model a FailureModel?

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

Convert arguments to control structure.

List of supported learning algorithms.

List ensemble filter methods.

List filter methods.

List the supported learner properties

Find matching learning algorithms.

List the supported measure properties.

Find matching measures.

List the supported task types in mlr

NCCTG Lung Cancer survival task.

Specify your own aggregation of measures.

Fuse learner with the bagging technique.

Exported for internal use only.

Only exported for internal use.

Classification via regression wrapper.

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

Creates a measure for non-standard misclassification costs.

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

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

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

Construct your own resampled performance measure.

Fuse learner with simple downsampling (subsampling).

Fuse learner with dummy feature creator.

Constructor for FDA feature extraction methods.

Fuse learner with an extractFDAFeatures method.

Fuse learner with feature selection.

Create a feature filter.

Create an ensemble feature filter.

Fuse learner with a feature filter method.

Generate a fixed holdout instance for resampling.

Create a data.frame containing functional features from a normal data.frame.

Create a custom imputation method.

Fuse learner with an imputation method.

Create learner object.

Create multiple learners at once.

Construct performance measure.

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

Creates a parameter set for model multiplexer tuning.

Fuse learner with multiclass method.

Use binary relevance method to create a multilabel learner.

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

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

Use nested stacking method to create a multilabel learner.

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

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

Fuse learner with preprocessing.

Fuse learner with preprocessing.

Classification of functional data by Generalized Linear Models.

Learner for kernel classification for functional data.

Learner for nonparametric classification for functional data.

Fuse learner with removal of constant features preprocessing.

Create a description object for a resampling strategy.

Instantiates a resampling strategy object.

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

Create a stacked learner object.

Exported for internal use.

Exported for internal use.

Create control object for hyperparameter tuning with CMAES.

Create control object for hyperparameter tuning with predefined design.

Create control object for hyperparameter tuning with GenSA.

Create control object for hyperparameter tuning with grid search.

Create control object for hyperparameter tuning with Irace.

Create control object for hyperparameter tuning with MBO.

Create control object for hyperparameter tuning with random search.

Fuse learner with tuning.

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

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

Induced model of learner.

Performance measures.

Merge different BenchmarkResult objects.

Merges small levels of factors into new level.

mlr: Machine Learning in R

mlr documentation families

Motor Trend Car Road Tests clustering task.

Normalize features.

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

Supported parallelization methods

Measure performance of prediction.

Phoneme functional data multilabel classification task.

PimaIndiansDiabetes classification task.

Create box or violin plots for a BenchmarkResult.

Create a bar chart for ranks in a BenchmarkResult.

Plot a benchmark summary.

Plot calibration data using ggplot2.

Plot critical differences for a selected measure.

Plot filter values using ggplot2.

Plot the hyperparameter effects data

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

Plot learning curve data using ggplot2.

Plot a partial dependence with ggplot2.

Plots a ROC curve using ggplot2.

Create residual plots for prediction objects or benchmark results.

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

Plots multi-criteria results after tuning using ggplot2.

Predict new data.

Predict new data with an R learner.

Reduce results of a batch-distributed benchmark.

Re-extract features from a data set

Re-impute a data set

Remove constant features from a data set.

Remove hyperparameters settings of a learner.

Fit models according to a resampling strategy.

Feature selection by wrapper approach.

Set aggregation function of measure.

Set the hyperparameters of a learner object.

Only exported for internal use.

Set the id of a learner object.

Set the ID of a learner object.

Set parameters of performance measures

Set the probability threshold the learner should use.

Set the type of predictions the learner should return.

Set threshold of prediction object.

Simplify measure names.

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

Sonar classification task.

Spam classification task.

J. Muenchow's Ecuador landslide data set

Subset data in task.

Summarize columns of data.frame or task.

Summarizes factors of a data.frame by tabling them.

Train a learning algorithm.

Train an R learner.

Hyperparameter tuning.

Hyperparameter tuning for multiple measures at once.

Tune prediction threshold.

Wisonsin Prognostic Breast Cancer (WPBC) survival task.

Yeast multilabel classification task.