-
`fit!(machine(MLJLinearModels.LogisticClassifier(penalty = :l1), X, y)` leads to far worse results than `glmnet(X, y, Binomial())` for some datasets. When this happens, MLJLInearModels warns `Warning:…
jbrea updated
2 years ago
-
**Submitting author:** @ayush-1506 (Ayush Shridhar)
**Repository:** https://github.com/FluxML/MLJFlux.jl
**Version:** v0.1.10
**Editor:** @melissawm
**Reviewer:** @krystophny, @morganericsson
**A…
-
@targos I'm a little bit lost and I don't know what I did wrong because I had to put back the eslint-plugins other the test failed.
https://github.com/mljs/regression-robust-polynomial/commit/d0f1c…
-
Currently, there are only a few models available via this interface. I suggest implementing also adding a `FormulaRegressor` for arbitrary formulas, via `StatsModels.@formula(...)`.
@ablaom, what d…
-
```julia
julia> rms
RootMeanSquaredError() @017
```
This was introduced to help debugging, for the case where one has multiple instances of the same MLJ object. But I find I don't really use i…
-
Place to collect questions
-
As reported by slack user, this code is taking way too long:
```julia
using MLJ
X = MLJ.table(randn(200,10000));
y = randn(200)
model = ConstantRegressor()
mach = machine(model, X, y);
```
-
Flux has pinned Zygote at 0.6 but I am using MLJ which requires 0.9 as an absolute minimum. Is it possible if you could update Zygote?
-
I'm training a pretty simple model:
shallow_net = Chain( …
-
In line with #416, I propose we move `UnivariateFinite` out to a new package called `CategoricalDistributions.jl`.
If this were okay with the current host of MLJBase.jl (I need to check this @voll…