# `Monty.Frameworks.Models.EvidenceMatching.FeatureEvidence.Scorer`
[🔗](https://github.com/d-led/ex.tbp.monty/blob/v0.1.0/packages/ex_tbp_monty_core/lib/monty/frameworks/models/evidence_matching/feature_evidence/scorer.ex#L1)

Turning one observation into evidence per node — the scorer family.

Mirrors `tbp/monty/frameworks/models/evidence_matching/feature_evidence/scorer.py`,
a module holding a protocol and its default implementation:

  * `...FeatureEvidence.Scorer.FeatureEvidenceScorer` is the protocol, as a
    behaviour;
  * `...Scorer.DefaultFeatureEvidenceScorer` is what a learning module gets
    unless it names another.

The scorer is where the three injected pieces meet: the calculator that turns
stored features into scores, the selector that decides whether this channel is
matched on its features at all, and the memory those features are read from.

---

*Consult [api-reference.md](api-reference.md) for complete listing*