Ensure all metric score methods return float, not int

[Copilot]

The similarity metric returned literal integers 0 and 1 in edge cases, violating the declared float return type.

Changes

• similarity.py: Changed return 0 → return 0.0 and return 1 → return 1.0
• test_float_returns.py: Added type assertions for all metrics (Similarity, BLEU, CHRF) covering edge cases including None inputs

Example

from signwriting_evaluation.metrics.similarity import SignWritingSimilarityMetric

metric = SignWritingSimilarityMetric()
score = metric.score(None, None)

# Before: score = 0 (int)
# After:  score = 0.0 (float)
assert isinstance(score, float)

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• huggingface.co
  • Triggering command: /usr/bin/python3 python3 -m pytest signwriting_evaluation/metrics/ -v (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Score can return integer values</issue_title>
<issue_description>In the similarity metric, we return an integer score (return 0)
https://github.com/sign-language-processing/signwriting-evaluation/blob/main/signwriting_evaluation/metrics/similarity.py#L153

make sure across all metrics, that all our returns are floats, and make a test for that</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes Score can return integer values #7

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.