Lennart Schneider

I recently stumbled across the following rather weird behavior: If a custom function named `eval` is present in my `.GlobalEnv`, testing jobs with `external = TRUE` and potentially also submitting...

open up PipeOpLearnerCV to all resampling methods

4

Allow all resamplings currently listed in `mlr_resamplings` (and more, e.g. all that inherit from `Resampling`). Closes #500 ~If a resampling returns multiple predictions for a row id, then they are...

Replace subgraph

3

closes #538 todo: - [ ] varargs - [ ] better docs - [ ] more tests - [ ] complementary function that gives us the IDs of all pipeops...

encapsulate `train` and `predict` of `PipeOp`s. Adding active bindings: * `timings` * `log` * `warnings` * `errors` * `encapsulate` and private `.encapsulate` like `Learner`s have (by default, a `Learner`'s `encapsulate`...

add cross-method for training of encode impact

2

closes #423

PipeOpFilterRows

16

`PipeOpFilterRows` allows to filter the rows of the data of a task according to a filter parameter and adds an easy way for removing rows with missing values, related to...

pack_formula()

1

provide a helper that strips an environment of a formula of all variables that are not referred to by the formula. useful for i.e., `PipeOpMutate` and #410

#254 See https://tensorflow.rstudio.com/guide/tfdatasets/feature_columns/#crossed-column

#254 See https://github.com/bhmevik/pls

#254 See https://github.com/gdkrmr/dimRed/blob/master/R/isomap.R