Registry / ai-ml / negspacy

negspacy

JSON →
library1.1.0pypypiunverified

A spaCy pipeline component implementing the NegEx algorithm for negating concepts in clinical text. Current version: 1.1.0. Release cadence is sporadic.

pip install negspacy
INSTALL
IMPORT
SIG · NEGSPACY
N
negspacy
ai-mlpythonv1.1.0
harness data pending
Install & Compatibility
Where this runs

No compatibility data collected yet for this library.

Code
Verified usage

Verified import paths — ran on the pinned version, not inferred.

Negex
✓ from negspacy import Negex
✗ from negspacy.negation import Negex

Add negspacy NegEx pipe to spaCy pipeline to detect negated entities.

import spacy from negspacy.negation import Negex from negspacy import termsets nlp = spacy.load("en_core_web_sm") nlp.add_pipe("negex", config={"ent_types": ["PERSON", "ORG"]}) # or Negex(nlp, ent_types=["PERSON", "ORG"]) doc = nlp("She does not have breast cancer.") for e in doc.ents: print(e.text, e._.negex)
Debug
Known issues
breakingnegspacy 1.x drops Python 3.6 support and is designed for spaCy 3.x. Ensure spaCy >=3.0 installed.
fix
Upgrade spaCy: pip install spacy>=3.0
affects: >=1.0.0
gotchaThe Negex component must be added after the entity recognizer (ner) in the pipeline; otherwise entities may not be recognized yet.
fix
Add pipe after 'ner': nlp.add_pipe('negex', after='ner')
affects: *
deprecatedUsing Negex(nlp, ...) constructor directly is deprecated; use nlp.add_pipe('negex', config={...}) instead.
fix
Use add_pipe pattern.
affects: >=0.1.0
Upgrade
Version history
1.1.0latest on PyPI · released Apr 20, 2026
Audit
Dependencies

No dependency data recorded yet.

Agent activity
20 hits · last 30 days
node
18
Anthropic
1
Resources
negspacy — pip install negspacy · libregistry