Break ties in rank calculation

[vivekjoshy]

Description of Changes

• Wrote at least one-line docstrings (for any new functions)
• Added test(s) covering the changes (if testable)

This makes some major bug fixes to both score-margins and tie-breaking. Amazingly, breaking ties seem to improve accuracy when ratings are not equal. The idea is prior ordinals are used to break ties resulting in a favorable bias towards the assumption that in the event of a tie, high rated players are still likely to perform better.

Accuracy has increased from a baseline of 67% to 70% on average and even 77% on some occasions during K-Fold cross validation.

cc: @philihp

Issue(s) Resolved

Fixes #166

Affirmation

By submitting this Pull Request or typing my (user)name below,
I affirm the Developer Certificate of Origin
with respect to all commits and content included in this PR,
and understand I am releasing the same under openskill.py's MIT license.

I certify the above statement is true and correct: @vivekjoshy

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 100.00%. Comparing base (3d23bc6) to head (b129a57).
Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff            @@
##              main      #168   +/-   ##
=========================================
  Coverage   100.00%   100.00%           
=========================================
  Files           10        10           
  Lines         2023      2048   +25     
  Branches       507       507           
=========================================
+ Hits          2023      2048   +25     

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

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.