https://github.com/jianlins/pyfastner

https://github.com/jianlins/pyfastner

Last synced: 9 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/jianlins/pyfastner
• Owner: jianlins
• License: apache-2.0
• Created: 2017-12-15T16:40:50.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2024-09-03T22:09:24.000Z (3 months ago)
• Last Synced: 2024-09-09T23:08:28.908Z (2 months ago)
• Language: Python
• Size: 130 KB
• Stars: 2
• Watchers: 2
• Forks: 1
• Open Issues: 1
• Metadata Files:
  • Readme: README
  • License: LICENSE

Awesome Lists containing this project

README

        
PyFastNER

PyFastNER is the python implementation of FastNER, which is orginally developed using Java. It uses hash function to process multiple rules at the same time. Similar to FastNER, PyFastNER supports token-based rules (FastNER--under developing) and character-based rules (FastCNER). It is licensed under the Apache License, Version 2.0.

Install:

pip install PyFastNER

Examples:

Here is a simiple example of using external dictionary to find matches in an input string. It will return a dictionary of spans grouped by the named entity types.

from PyFastNER.FastCNER import FastCNER

# initiate fastner using external rule file

fastner = FastCNER('conf/crule_test.tsv')

# process an input string

res = fastner.processString('Pt came with fever, T 102.0F.')

# display processed results

for type in res.keys():

	for span in res[type]:

		print(span)

Here is another example if you need process a sentence within a document, where you just need to tell the offset of the sentence to the beginning of the document.

from PyFastNER.FastCNER import FastCNER

fastner = FastCNER('conf/crule_test.tsv')

res = fastner.processString('Pt came with fever, T 102.0F.',134)

For more examples, please refer to TestFastCNER.py