ADD: Improve evaluation + make CLI runnable

[adamovanja]

this PR:

• makes running tuned model experiments runnable via the CLI and a configuration file (see run_n_eval_tune.py)
• includes refined model evaluation over all experiments (see eval_best_trial_overall.py)
• refines model evaluation over one experiment
• loosens codecov threshold restriction while package is still in development

[codecov]

Codecov Report

Attention: Patch coverage is 0% with 247 lines in your changes are missing coverage. Please review.

Project coverage is 60.94%. Comparing base (a094e8e) to head (c85d6c4).

Files	Patch %	Lines
q2_ritme/evaluate_models.py	0.00%	121 Missing ⚠️
q2_ritme/evaluate_all_experiments.py	0.00%	54 Missing ⚠️
q2_ritme/run_n_eval_tune.py	0.00%	46 Missing ⚠️
q2_ritme/eval_best_trial_overall.py	0.00%	23 Missing ⚠️
q2_ritme/tune_models.py	0.00%	3 Missing ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##             main       #8       +/-   ##
===========================================
- Coverage   84.01%   60.94%   -23.07%     
===========================================
  Files          15       17        +2     
  Lines         613      845      +232     
  Branches       35       67       +32     
===========================================
  Hits          515      515               
- Misses         97      329      +232     
  Partials        1        1               

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