evaluate_predictions

evaluate_predictions(mappings: Iterable[SemanticMapping], *, accept_unspecified: bool = True, _tag: str | None = None) → dict[frozenset[str], Evaluation]

Stratify and evaluate predicted mappings against curated mappings.

Parameters:

mappings – A pool of positive, negative, and predicted semantic mappings :param accept_unspecified: Whether to consider mappings that do not have an explicit justification (i.e., using semapv:UnspecifiedMatching) as having been manually curated. See stratify() for more details.

Returns:

A mapping from unordered prefix pairs to evaluation objects