search

JuliaML / MLUtils.jl

Utilities and abstractions for Machine Learning tasks
MIT License
109 stars 22 forks source link

Add `make_regression` utility #31

Closed Chandu-4444 closed 2 years ago

Chandu-4444 commented 2 years ago

Regarding issue #15

codecov-commenter commented 2 years ago

Codecov Report

Merging #31 (89f342a) into main (8972d42) will increase coverage by 1.55%. The diff coverage is 100.00%.

:exclamation: Current head 89f342a differs from pull request most recent head 92842e2. Consider uploading reports for the commit 92842e2 to get more accurate results

@@            Coverage Diff             @@
##             main      #31      +/-   ##
==========================================
+ Coverage   89.89%   91.45%   +1.55%     
==========================================
  Files          14       17       +3     
  Lines         475      667     +192     
==========================================
+ Hits          427      610     +183     
- Misses         48       57       +9
Impacted Files Coverage Δ
src/Datasets/generators.jl 100.00% <100.00%> (ø)
src/observation.jl 85.33% <0.00%> (-1.63%) :arrow_down:
src/randobs.jl 100.00% <0.00%> (ø)
src/resample.jl 100.00% <0.00%> (ø)
src/splitobs.jl 100.00% <0.00%> (ø)
src/Datasets/datasets.jl 100.00% <0.00%> (ø)
src/dataiterator.jl 100.00% <0.00%> (ø)
src/shuffleobs.jl 100.00% <0.00%> (ø)
src/batchview.jl 78.18% <0.00%> (+1.25%) :arrow_up:
src/dataloader.jl 94.44% <0.00%> (+2.44%) :arrow_up:
... and 2 more

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 8972d42...92842e2. Read the comment docs.

CarloLucibello commented 2 years ago

please add some tests

Chandu-4444 commented 2 years ago

Sure, I thought about adding tests after you review the code. I'll add them now.

CarloLucibello commented 2 years ago

I think this generative model should be more consistent with scikitlearn: https://github.com/scikit-learn/scikit-learn/blob/7e1e6d09b/sklearn/datasets/_samples_generator.py#L506 We can assume effective_rank=None and eventually implement that part later.