John Zobolas
John Zobolas
- Rename: `weight` => `weights_learner` - Every learner that had property `weights` now gets a new hyperparameter: `use_weights` - Depends on https://github.com/mlr-org/mlr3/pull/1124
compatibility with `mlr3` 1.0.0, including the new `weights_learner`, is now fixed in #433
I second that. I would argue from a user-perspective, that I was surprized to find out that `filter`ing a task results in keeping the backend (but I guess there are...
Hi Will (@wmay), Thanks for your initiative! We will discuss this in the mlr3 workshop in two weeks. It seems keeping the `distr` prediction type and having a new `mlr3`-package...
Hi all, I have sent an email to arrange the call. Thanks for the interest! (let me know if you don't get it)
Dear all, short summary of the meeting: - Achim showed us a demo of [distributions3](https://cran.r-project.org/web/packages/distributions3/index.html) (lightweight, vectorized, `data.frame`- based) + the use of `prodist()` function for distributional predictions and how...
@BjarkeHautop thanks for the suggestion and PR! I edited a bit further the text adding the distinction between random and administrative censoring (+ better examples) which I think is important...
@larskotthoff good to merge, I refined it as much as I could!
@be-marc I think this should be good to merge - some account problem seesm to be the failure here, probably because this is from a fork?
Also I will try to prioritize for early Jan (@jemus42) :) You can ofc take the local implementation of this Learner for the benchmark (no need to install this version...