deidentify
deidentify copied to clipboard
A Python library to de-identify medical records with state-of-the-art NLP methods.
Hi, I just released deduce 2.0.0 which has breaking changes, also breaking deidentify it seems. For now I fixed it by pinning
The `FlairTagger` (and possibly `CRFTagger`) ignores empty documents. The length of the output documents does not match the length of the input documents. We should either allow empty documents, or...
This should (hopefully) fix corpus loading on windows systems
This should upgrade Deidentify to Deduce 2
File "/usr/local/lib/python3.10/dist-packages/deidentify/taggers/__init__.py", line 1, in from .deduce_tagger import DeduceTagger File "/usr/local/lib/python3.10/dist-packages/deidentify/taggers/deduce_tagger.py", line 4, in from deidentify.methods.deduce import run_deduce File "/usr/local/lib/python3.10/dist-packages/deidentify/methods/deduce/run_deduce.py", line 14, in NAME_PREFIX_REGEX = re.compile(r'({})\.?\s*'.format('|'.join(deduce.lookup_lists.PREFIXES)), AttributeError: module 'deduce' has...