MultivariateStats + StatsAPI

[tpoisot]

Closes #203 (replaces #204)

NB this bumps the Julia version to 1.9, as the MV code is only loaded when MultivariateStats is loaded, using the new Weak Dependencies system -- the same thing will happen for Clustering

[github-actions]

Documentation for this PR at https://poisotlab.github.io/SpeciesDistributionToolkit.jl/previews/PR210/

[codecov-commenter]

Codecov Report

Attention: 11 lines in your changes are missing coverage. Please review.

Comparison is base (639a48d) 52.83% compared to head (7ae5b8f) 52.49%.
Report is 1 commits behind head on next.

Additional details and impacted files

@@            Coverage Diff             @@
##             next     #210      +/-   ##
==========================================
- Coverage   52.83%   52.49%   -0.34%     
==========================================
  Files          59       60       +1     
  Lines        1711     1722      +11     
==========================================
  Hits          904      904              
- Misses        807      818      +11     

Flag	Coverage Δ
unittests	52.49% <0.00%> (-0.34%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files	Coverage Δ
src/SpeciesDistributionToolkit.jl	100.00% <ø> (ø)
src/integrations/makie.jl	0.00% <ø> (ø)
src/quality_of_life.jl	0.00% <0.00%> (ø)

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[tpoisot]

This currently supports fit, predict, and transform for PCA, kPCA, PPCA, MDS, Metric MDS, and Whitening, which should be a good enough basis to work from -- the code is slow but I'll optimize later

[tpoisot]

@gottacatchenall check this out, I think this doesn't suffer from the fit issue with StatsBase

[gottacatchenall]

That's interesting, I haven't seen StatsAPI before but thats a clever way of avoiding namespace conflicts