Perform (weighted) prediction averaging from regression Predictions by connecting PipeOpRegrAvg to multiple PipeOpLearner outputs.

The resulting "response" prediction is a weighted average of the incoming "response" predictions. "se" prediction is currently not aggregated but discarded if present.

Weights can be set as a parameter; if none are provided, defaults to equal weights for each prediction. Defaults to equal weights for each model.


R6Class inheriting from PipeOpEnsemble/PipeOp.


PipeOpRegrAvg$new(innum = 0, id = "regravg", param_vals = list())
  • innum :: numeric(1)
    Determines the number of input channels. If innum is 0 (default), a vararg input channel is created that can take an arbitrary number of inputs.

  • id :: character(1) Identifier of the resulting object, default "regravg".

  • param_vals :: named list
    List of hyperparameter settings, overwriting the hyperparameter settings that would otherwise be set during construction. Default list().

Input and Output Channels

Input and output channels are inherited from PipeOpEnsemble. Instead of a Prediction, a PredictionRegr is used as input and output during prediction.


The $state is left empty (list()).


The parameters are the parameters inherited from the PipeOpEnsemble.


Inherits from PipeOpEnsemble by implementing the private$weighted_avg_predictions() method.


Only fields inherited from PipeOpEnsemble/PipeOp.


Only methods inherited from PipeOpEnsemble/PipeOp.

See also


library("mlr3") # Simple Bagging gr = greplicate(n = 5, po("subsample") %>>% po("learner", lrn("classif.rpart")) ) %>>% po("classifavg") resample(tsk("iris"), GraphLearner$new(gr), rsmp("holdout"))
#> <ResampleResult> of 1 iterations #> * Task: iris #> * Learner: subsample_1.subsample_2.subsample_3.subsample_4.subsample_5.classif.rpart_1.classif.rpart_2.classif.rpart_3.classif.rpart_4.classif.rpart_5.classifavg #> * Warnings: 0 in 0 iterations #> * Errors: 0 in 0 iterations