Implement clipping on beta

[oooo26]

• Implement clipping after each primary fitting, see Incorrect optimal support size in a multitask learning problem with nonnegativity constraints #510 ;
• Add relative pytest;
• R API should be updated for two new parameters beta_low, beta_high; (TODO)

[Mamba413]

@oooo26 , I have just seen the test file. If either beta_low or beta_high is set, any bug will occur?

[oooo26]

@oooo26 , I have just seen the test file. If either beta_low or beta_high is set, any bug will occur?

Thank you for checking! There is no bug. But let me add more tests on that.

[oooo26]

And please also note that:

• C++ code allows beta_low>beta_high, but it will ignore the beta range limitation if so. Python side will check and raise error;
• If enable normalization, the final beta would be possible to outside the range limitation. Because clipping is implemented during fitting.

[codecov]

Codecov Report

Patch coverage: 100.00% and project coverage change: +0.01% 🎉

Comparison is base (9c97655) 97.73% compared to head (9b40936) 97.74%.
Report is 1 commits behind head on master.

Additional details and impacted files

@@            Coverage Diff             @@
##           master     #516      +/-   ##
==========================================
+ Coverage   97.73%   97.74%   +0.01%     
==========================================
  Files           7        7              
  Lines         970      977       +7     
==========================================
+ Hits          948      955       +7     
  Misses         22       22              

Flag	Coverage Δ
Python	97.74% <100.00%> (+0.01%)	⬆️

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

Files Changed	Coverage Δ
python/abess/bess_base.py	98.90% <100.00%> (+0.02%)	⬆️

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

[Mamba413]

Thanks! I think this is fine, and we can merge it.

[bbayukari]

R API has been updated in 96ed869.