Anthony Blaom, PhD
Anthony Blaom, PhD
After some preparation and [discussion](https://github.com/alan-turing-institute/MLJ.jl/issues/901), I am announcing a new standard for MLJ model doc-strings, documented [here](https://alan-turing-institute.github.io/MLJ.jl/dev/adding_models_for_general_use/#Document-strings). I believe detailed doc-strings can greatly improve the on-ramp for new MLJ users,...
The MLJ model API only says that model reporting feature importances should report them in the `report` output by `fit`. But it says nothing about the actual format of this...
In support of https://github.com/JuliaAI/MLJBase.jl/pull/806.
**edited** A new package MLJTestIntegration.jl is under development to provide integration tests for the MLJ ecosystem at large. Some issues have been revealed there for the regressors in the following...
https://imbalanced-learn.readthedocs.io/en/stable/over_sampling.html#over-sampling This is just to kick off a discussion. I see oversampling/undersampling as transformers plus model wrappers. Here's a rough POC for this: ```julia # using MLJ, TableOperations, Tables import...
A number of feature-reduction strategies only make sense in the context of a supervised learning task because they must consult a target variable when trained. For example, one might wants...
For starters: Add a tool to have models compete, based on paired cv scores?
~~Will build on [task interface design](https://github.com/alan-turing-institute/MLJ.jl/issues/68#issue-406616952)~~
- [x] #861 - [x] update compat for MLJBase 0.19 when released - [x] update compat for OpenML to 0.2 - [x] update compat for MLJEnsembles to 0.2 - [x]...
I am referring to [this `getobs` interface](https://mldatapatternjl.readthedocs.io/en/latest/) which is being migrated to [MLUtils.jl](https://github.com/JuliaML/MLUtils.jl/issues/2). To allow for certain kinds of training using data that does not fit into memory, I should...