Closed ablaom closed 3 years ago
@rikhuijzer Be great if you can review this.
Merging #142 (ae4b3f5) into dev (2d23761) will increase coverage by
0.32%
. The diff coverage is100.00%
.
@@ Coverage Diff @@
## dev #142 +/- ##
==========================================
+ Coverage 86.99% 87.31% +0.32%
==========================================
Files 11 11
Lines 592 607 +15
==========================================
+ Hits 515 530 +15
Misses 77 77
Impacted Files | Coverage Δ | |
---|---|---|
src/strategies/explicit.jl | 92.00% <100.00%> (ø) |
|
src/tuned_models.jl | 92.79% <100.00%> (+0.52%) |
:arrow_up: |
Continue to review full report at Codecov.
Legend - Click here to learn more
Δ = absolute <relative> (impact)
,ø = not affected
,? = missing data
Powered by Codecov. Last update 2d23761...ae4b3f5. Read the comment docs.
Addresses #141
The main change are:
tuning=Explicit()
can have different typesTunedModel(models=<the model iterator>, ...)
with no need to specify arange
ortuning
strategy in that caseMakes use of very recent change in MLJBase 0.18.15: https://github.com/JuliaAI/MLJBase.jl/pull/596 .
From the the new
TunedModel
doc-string:Construct a model wrapper for hyperparameter optimization of a supervised learner, specifying the
tuning
strategy andmodel
to be mutated.As above but applied to an explicit iterator
models
of MLJ models (equivalent to specifyingtuning=Explicit()
andrange=models
above). Elements of the iterator need not have a common model type, but they must all beDeterministic
or all beProbabilistic
and this is not checked but inferred from the first element generated.See below for a complete list of options.
...
cc @rikhuijzer