Closed s-weil closed 7 months ago
Attention: 32 lines
in your changes are missing coverage. Please review.
Comparison is base (
4719e96
) 47.00% compared to head (8f887a5
) 47.16%. Report is 2 commits behind head on developer.
Files | Patch % | Lines |
---|---|---|
src/FSharp.Stats/ML/Unsupervised/KNN.fs | 28.20% | 25 Missing and 3 partials :warning: |
tests/FSharp.Stats.Tests/ML.fs | 94.28% | 0 Missing and 4 partials :warning: |
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.
Thanks for this awsome and well prepared addition @s-weil!
Thank you for contributing to FSharp.Stats. Please take the time to tell us a bit more about your PR.
Closes 300
Please list the changes introduced in this PR
Description
The KNN algorithm is implemented in different versions [see
ML\Unsupervised\KNN.fs
], namelyNOTE: further specialisations of the algorithm for improved performance exist and versions are possible (such as a vector version). Moreover one could consider the feature of parallelized predictions (may only make sense in case of a big point cloud).