Set aggregation function of measure.
Result of feature selection.
Aggregation methods.
Create a classification / regression task for a given data set.
crossover
Confusion matrix.
Get a description of all possible parameter settings for a learner.
Get probabilities for some classes.
Prediction object.
Returns the optimal hyperparameters and optimization path.
Converts predictions to a format package ROCR can handle.
Prediction from resampling.
Fuse learner with tuning.
Returns the list of models fitted in bagging.
Description object for task.
Measure performance of prediction.
Fuse learner with the bagging technique.
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
. Induced model of learner.
Feature selection by wrapper approach.
Get formula of a task.
Create control structures for tuning.
Get underlying R model of learner integrated into mlr.
Get feature names of task.
Find matching learning algorithms.
Set the type of predictions the learner should return.
Convert arguments to control structure.
Configures the behaviour of the package.
Filter features by using a numerical importance criterion.
Calculates numerical importance values for all features.
Thresholding of these values can be used to select useful features.
Look at package FSelector for details on the filter algorithms.
Creates a measure for non-standard misclassification costs.
Fit models according to a resampling strategy.
Subset data in task.
Instantiates a resampling strategy object.
Train an R learner.
Result of tuning.
Get target column of task.
Set the hyperparameters of a learner object.
Hyperparameter tuning.
Only exported for internal use.
Construct performance measure.
Fuse learner with filter method.
Set threshold of prediction object.
Create learner object.
Get current parameter settings for a learner.
Generate a fixed holdout instance for resampling.
List of supported learning algorithms.
makeCustomResampledMeasure
Construct your own resampled performance measure.
Returns the filtered features.
Train a learning algorithm.
makeFeatSelControlExhaustive
Create control structures for feature selection.
Predict new data with an R learner.
Fuse learner with preprocessing.
Internal construction / wrapping of learner object.
Get formula of a task as a string.
Tune prediction threshold.
Predict new data.
Create a description object for a resampling strategy.
Extract data in task. Useful in trainLearner
when you add a learning
machine to the package. Performance measures.