Evaluation Code for Scenario Mining Challenge Release

[CainanD]

PR Summary

Added scenario mining evaluation code in preparation for the new challenge release. Since the tracking is the primary evaluation metric, overall code changes are pretty minimal. Some additional logic was added to evaluate how the tracker performs at classifying time steps. This requires no additional dependencies. Included in this pull request are two small .pkl files that contain the predicted and ground truth track data to test the evaluation function.

Testing

This pull request includes a unit test and sample data files for the added evaluation script. The evaluation script works as intended.

In order to ensure this PR works as intended, it is:

• [✅] unit tested.
• other or not applicable (additional detail/rationale required)

Compliance with Standards

As the author, I certify that this PR conforms to the following standards:

• [✅] Code changes conform to PEP8 and docstrings conform to the Google Python style guide.
• [✅] A well-written summary explains what was done and why it was done.
• [✅] The PR is adequately tested and the testing details and links to external results are included.

Testing details showing complete coverage of av2/evaluation/scenario_mining/eval.py:
logs_35428725033.zip
Visualization of ground truth data:
https://github.com/user-attachments/assets/a0ef5497-7672-4365-ae95-e37e5597d975

[benjaminrwilson]

Thanks, @CainanD! Looks good. Left a few comments. Also, was map_tutorial.ipynb meant to change?

[benjaminrwilson]

Awesome, looks good. Thank you for making the changes, @CainanD. I still see a diff on the map_tutorial.ipynb - let's reset that unless that's intended, otherwise I can go ahead and merge!