Evaluations

Metrics

ontolearner.evaluation.metrics.non_taxonomic_re_metrics(y_true: List[Dict[str, str]], y_pred: List[Dict[str, str]]) → Dict[str, float | int]

ontolearner.evaluation.metrics.taxonomy_discovery_metrics(y_true: List[Dict[str, str]], y_pred: List[Dict[str, str]]) → Dict[str, float | int]

ontolearner.evaluation.metrics.term_typing_metrics(y_true: List[Dict[str, List[str]]], y_pred: List[Dict[str, List[str]]]) → Dict[str, float | int]

Compute precision, recall, and F1-score for term typing using (term, type) pair-level matching instead of ID-based lookups.

Parameters:

• y_true – List of ground truth dicts, each with keys {“term”: str, “types”: List[str]}

• y_pred – List of predicted dicts, same format as y_true

Returns:

Containing precision, recall, and F1-score

Return type:

Dict

ontolearner.evaluation.metrics.text2onto_metrics(y_true: Dict[str, Any], y_pred: Dict[str, Any], similarity_threshold: float = 0.8) → Dict[str, Any]

Expects:

y_true = {“terms”: [{“doc_id”: str, “term”: str}, …],

“types”: [{“doc_id”: str, “type”: str}, …]}

y_pred = same shape

Returns:

{…}, “types”: {…}}

Return type:

{“terms”