edsnlp.pipelines.ner.umls.factory

create_component(nlp, name='eds.umls', attr='NORM', ignore_excluded=False, ignore_space_tokens=False, term_matcher=TerminologyTermMatcher.exact, term_matcher_config={}, pattern_config=dict(languages=['FRE'], sources=None))

Create a component to recognize and normalize terms in document that normalize to UMLS concepts.

PARAMETER	DESCRIPTION
nlp	spaCy Language object. TYPE: Language
name	The name of the pipe TYPE: str DEFAULT: 'eds.umls'
attr	Attribute to match on, eg TEXT, NORM, etc. TYPE: Union[str, Dict[str, str]] DEFAULT: 'NORM'
ignore_excluded	Whether to skip excluded tokens during matching. TYPE: bool DEFAULT: False
ignore_space_tokens	Whether to skip space tokens during matching. TYPE: bool DEFAULT: False
term_matcher	The term matcher to use, either TerminologyTermMatcher.exact or TerminologyTermMatcher.simstring TYPE: TerminologyTermMatcher DEFAULT: TerminologyTermMatcher.exact
term_matcher_config	The configuration for the term matcher TYPE: Dict[str, Any] DEFAULT: {}
pattern_config	The pattern retriever configuration TYPE: Dict[str, Any] DEFAULT: dict(languages=['FRE'], sources=None)

Source code in edsnlp/pipelines/ner/umls/factory.py

@Language.factory(
    "eds.umls", default_config=DEFAULT_CONFIG, assigns=["doc.ents", "doc.spans"]
)
def create_component(
    nlp: Language,
    name: str = "eds.umls",
    attr: Union[str, Dict[str, str]] = "NORM",
    ignore_excluded: bool = False,
    ignore_space_tokens: bool = False,
    term_matcher: TerminologyTermMatcher = TerminologyTermMatcher.exact,
    term_matcher_config: Dict[str, Any] = {},
    pattern_config: Dict[str, Any] = dict(
        languages=["FRE"],
        sources=None,
    ),
):
    """
    Create a component to recognize and normalize terms in document that
    normalize to UMLS concepts.

    Parameters
    ----------
    nlp: Language
        spaCy `Language` object.
    name: str
        The name of the pipe
    attr: Union[str, Dict[str, str]]
        Attribute to match on, eg `TEXT`, `NORM`, etc.
    ignore_excluded: bool
        Whether to skip excluded tokens during matching.
    ignore_space_tokens: bool
        Whether to skip space tokens during matching.
    term_matcher: TerminologyTermMatcher
        The term matcher to use, either `TerminologyTermMatcher.exact` or
        `TerminologyTermMatcher.simstring`
    term_matcher_config: Dict[str, Any]
        The configuration for the term matcher
    pattern_config: Dict[str, Any]
        The pattern retriever configuration
    """

    return TerminologyMatcher(
        nlp,
        label="umls",
        regex=None,
        terms=patterns.get_patterns(pattern_config),
        attr=attr,
        ignore_excluded=ignore_excluded,
        ignore_space_tokens=ignore_space_tokens,
        term_matcher=term_matcher,
        term_matcher_config=term_matcher_config,
    )