Releases: Machine-Learning-for-Medical-Language/ctakes-client-py
Releases · Machine-Learning-for-Medical-Language/ctakes-client-py
5.1.0
This release adds the ability to query the termexists cNLP transformer when listing polarity. It's another polarity model that's similar to the default negation model, but may be a bit better.
The model can be installed from docker hub.
Set URL_CNLP_TERM_EXISTS to point at the correct endpoint (defaults to http://localhost:8000/termexists/process).
Use it like so:
from ctakesclient.transformer import TransformerModel, list_polarity
list_polarity(text, spans, model=TransformerModel.TERM_EXISTS)
5.0.0
4.0.0
3.0.0
A few breaking changes in this major release:
- Support for Python 3.7 has been dropped (slightly before it goes end-of-life)
- All network calls have been changed to be async methods. Specifically, the following API calls are now async:
- client.post
- client.extract
- transformer.list_polarity
- transformer.map_polarity
These new async calls also take an optional client kwarg parameter, to provide an existing
httpx.AsyncClient session.
2.1.1
2.1.0
2.0.0
1.3.1
1.3.0
1.2.0
New API
-
ctakesclient.filesystem.covid_symptoms() -> List[BsvConcept]- Returns a list of known covid symptoms
-
ctakesclient.filesystem.umls_semantic_groups() -> List[BsvSemanticType]- Returns a list of UMLS semantic groups
Changed API
ctakesclient.filesystem.map_cui_pref()- now accepts either a string or a list of
BsvConcepts(previously it only accepted a filename string). This is to make it easier to use with the above new API.
- now accepts either a string or a list of
Features
polarity-diff-reportnow has a--mentionargument that lets you filter by certain kinds of mentions (e.g.--mention=DiseaseDisorderMention)
Fixes
- Non-latin1 characters in physician notes no longer throws an exception
- An exception is now thrown if there was an error talking to the cTAKES or cNLP servers