Result of multi-criteria tuning.
Get target column of task.
Find matching learning algorithms.
Get current parameter settings for a learner.
Extract the predictions from a benchmark result.
Get feature names of task.
Extract the aggregated performance values from a benchmark result.
Generate a fixed holdout instance for resampling.
Boston Housing regression task
Get the name(s) of the target column(s).
Returns the selected feature set and optimization path after training.
Extract the feature selection results from a benchmark result.
Create control structures for multi-criteria tuning.
getHomogeneousEnsembleModels
Returns the list of fitted models.
ResampleResult object.
Result of feature selection.
European Union Agricultural Workforces clustering task
Description object for task.
Returns the filtered features.
Result of a benchmark run.
Return task ids used in benchmark.
Generate dummy variables for factor features.
Iris cost-sensitive classification task
Get probabilities for some classes.
Get number of features in task.
Wraps a regression learner for use in cost-sensitive learning.
Returns a list of mlr's options
Fuse learner with simple ove/underrsampling for imbalancy correction in binary classification.
Prediction from resampling.
Extract the tuning results from a benchmark result.
Set aggregation function of measure.
Specifiy your own aggregation of measures
Get a summarizing task description.
Create a classification, regression, survival, cluster, or cost-sensitive classification task.
Is the model a FailureModel?
Impute and re-impute data
Set, add, remove or query properties of learners
Failure model.
Calculates feature filter values.
Get underlying R model of learner integrated into mlr.
Return learner ids used in benchmark.
Converts predictions to a format package ROCR can handle.
Return error message of FailureModel.
Convert arguments to control structure.
Estimate the residual variance
Construct performance measure.
List filter methods
Benchmark experiment for multiple learners and tasks.
Prediction object.
Get a description of all possible parameter settings for a learner.
Get the id of the task.
Normalize features
Result of tuning.
Induced model of learner.
Get formula of a task.
Fuse learner with simple downsampling (subsampling).
Summarizes factors of a data.frame by tabling them.
Create a description object for a resampling strategy.
Wisonsin Prognostic Breast Cancer (WPBC) survival task
Extract data in task.
Remove hyperparameters settings of a learner.
Visualizes a learning algorithm on a 1D or 2D data set.
Motor Trend Car Road Tests clustering task
crossover
Plots multi-criteria results after tuning.
Find matching measures.
Confusion matrix.
Wisconsin Breast Cancer classification task
Only exported for internal use.
Create a custom imputation method.
Create learner object.
Create a stacked learner object.
Instantiates a resampling strategy object.
NCCTG Lung Cancer survival task
Predict new data.
makeCostSensWeightedPairsWrapper
Wraps a classifier for cost-sensitive learning to produce a weighted pairs model.
Creates a measure for non-standard misclassification costs.
Configures the behavior of the package.
Downsample (subsample) a task or a data.frame.
Join some class existing levels to new, larger class levels for classification problems.
Get the type of the task.
Iris classification task
Sonar classification task
Set the type of predictions the learner should return.
Extract the feature selection results from a benchmark result.
Show and visualize the steps of feature selection.
List of supported learning algorithms.
Fuse learner with multiclass method.
Plot filter values.
Re-impute a data set
Plot threshold vs. performance(s) for 2-class classification.
Subset data in task.
makeModelMultiplexerParamSet
Creates a parameter set for model multiplexer tuning.
Extract the test performance values from a benchmark result.
Feature selection by wrapper approach.
Over- or undersample binary classification task to handle class imbalancy.
Create model multiplexer for model selection to tune over multiple possible models.
Set the hyperparameters of a learner object.
Fuse learner with a feature filter method.
Aggregation methods.
Display all possible hyperparameter settings for a learner that mlr knows.
getStackedBaseLearnerPredictions
Returns the predictions for each base learner.
Extract costs in task.
Train a learning algorithm.
Create control structures for tuning.
Returns the optimal hyperparameters and optimization path after training.
Merges small levels of factors into new level.
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 imputing constant values shifted below the minimum
usingmin(x) - multiplier * diff(range(x))
,imputeMin(multiplier)
for imputing constant values shifted above the maximum
usingmax(x) + multiplier * diff(range(x))
,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 usingtable
orhist
.imputeLearner(learner, preimpute)
for imputations using the response
of a classification or regression learner. Aggregation object.
Set threshold of prediction object.
Fuse learner with the bagging technique.
Create a feature filter
Fit models according to a resampling strategy.
Fuse learner with the bagging technique and oversampling for imbalancy correction.
Visualize binary classification predictions via ViperCharts system.
makeWeightedClassesWrapper
Wraps a classifier for weighted fitting where each class receives a weight.
Fuse learner with an imputation method.
PimaIndiansDiabetes classification task
Train an R learner.
Internal construction / wrapping of learner object.
makeCustomResampledMeasure
Construct your own resampled performance measure.
Performance measures.
Fuse learner with preprocessing.
Tune prediction threshold.
Fuse learner with SMOTE oversampling for imbalancy correction in binary classification.
Set the probability threshold the learner should use.
Predict new data with an R learner.
Convert large/infinite numeric values in a data.frame or task.
Measure performance of prediction.
Synthetic Minority Oversampling Technique to handle class imbalancy in binary classification.
Create control structures for feature selection.
makeCostSensClassifWrapper
Wraps a classification learner for use in cost-sensitive learning.
Fuse learner with preprocessing
Fuse learner with tuning.
Drop some features of task.
Visualize binary classification predictions via ROCR ROC curves.
Fuse learner with feature selection.
Hyperparameter tuning.
Filter features by thresholding filter values.
Remove constant features from a data set.
Set the id of a learner object.
Summarize columns of data.frame or task.
Hyperparameter tuning for multiple measures at once.