search

fslaborg / FSharp.Stats

statistical testing, linear algebra, machine learning, fitting and signal processing in F#
https://fslab.org/FSharp.Stats/
Other
205 stars 54 forks source link

Hyper Parameter Tuning #129

Closed HLWeil closed 2 years ago

HLWeil commented 3 years ago

First steps towards implementing #128

I plan on extending this PR with

Some questions I have:

What do you think about the basic types I set up? Does the placement in the project (folder- and namespace wise) seem sensible to you?

codecov-commenter commented 3 years ago

Codecov Report

Merging #129 (8fd4cc4) into developer (fcab9e3) will increase coverage by 0.20%. The diff coverage is 0.00%.

Impacted file tree graph

@@              Coverage Diff              @@
##           developer     #129      +/-   ##
=============================================
+ Coverage      22.99%   23.20%   +0.20%     
=============================================
  Files            109      115       +6     
  Lines          11670    12096     +426     
  Branches        2510     2617     +107     
=============================================
+ Hits            2684     2807     +123     
- Misses          8885     9181     +296     
- Partials         101      108       +7
Impacted Files Coverage Δ
...Stats/HyperParameterTuning/BayesianOptimization.fs 0.00% <0.00%> (ø)
...tats/HyperParameterTuning/EvolutionaryAlgorithm.fs 0.00% <0.00%> (ø)
...rc/FSharp.Stats/HyperParameterTuning/GridSearch.fs 0.00% <0.00%> (ø)
...Stats/HyperParameterTuning/HyperParameterTuning.fs 0.00% <0.00%> (ø)
.../FSharp.Stats/HyperParameterTuning/RandomSearch.fs 0.00% <0.00%> (ø)
src/FSharp.Stats/Intervals.fs 1.28% <0.00%> (-0.11%) :arrow_down:
src/FSharp.Stats/Signal/Normalization.fs 82.35% <0.00%> (-0.99%) :arrow_down:
tests/FSharp.Stats.Tests/Main.fs 0.00% <0.00%> (ø)
tests/FSharp.Stats.Tests/Matrix.fs 100.00% <0.00%> (ø)
...Sharp.Stats/ML/Unsupervised/IterativeClustering.fs 0.00% <0.00%> (ø)
... and 12 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 fcab9e3...8fd4cc4. Read the comment docs.

HLWeil commented 2 years ago

Will close this for now as this still requires quite some work