SpacyGrounder

class SpacyGrounder(matcher: Matcher[R], spacy_model: str | spacy.Language)[source]

Bases: Grounder[R], WrappedMatcher[R], Generic[R]

An annotator that works via spacy.

Warning

SpaCy is very difficult to get working on modern versions of Python, due to its dependence on NumPy’s pre-2.0 release. You’re on your own, good luck!

Create a grounder based on a pre-defined matcher and a SpaCy NER model.

Parameters:

  • matcher – A pre-defined matcher

  • spacy_model – The name of a SpaCy model. See https://allenai.github.io/scispacy/ for a list of biomedical and clincal NER models from scispacy.

In the following example, a SpaCy grounder is instantiated using an underlying Gilda matcher, which incorporates the disease branch of Medical Subject Headings (MeSH). You’ll need to install a SciSpaCy model first with pip install https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.4/en_core_sci_sm-0.5.4.tar.gz.

import spacy
from ssslm import GildaMatcher, SpacyGrounder

spacy_model = spacy.load("en_core_sci_sm")

matcher = GildaMatcher.default()
grounder = SpacyGrounder(
    matcher=matcher,
    spacy_model=spacy_model,
)
annotations = grounder.annotate(
    "The APOE e4 mutation is correlated with risk for Alzheimer's disease."
)

Methods Summary

annotate(text, **kwargs)

Annotate the text using a combination of the spacy annotator, and the wrapped matcher.

Methods Documentation

annotate(text: str, **kwargs: Any) → list[Annotation][source]

Annotate the text using a combination of the spacy annotator, and the wrapped matcher.