word-sub

Manage Word Substitutions


License
MIT
Install
pip install word-sub==0.0.4

Documentation

WordSub

Install

pip install word-sub

Build

python setup.py sdist

twine upload dist/*

Usage

from word_sub import WordMappings

# Init a WordMappings Class

# NLTK and gensim Stopwords are available by default
wm = WordMappings()

# Override this with
wm = WordMappings(stopwords=False)

# Token substitution is implemented via __call__  
>>> wm('the dish ran away with the spoon'.split())
['dish', 'ran', 'away', 'spoon'] # Stopwords removed

# Add additional stopwords
>>> wm.add_pair(None, ['ran'])
>>> wm('the dish ran away with the spoon'.split())
['dish', 'away', 'spoon']

# Token substitution
>>> wm.add_pair('senior', ['sr', 'lead', 'head'])
>>> wm('lead manager'.split())
['senior', 'manager']

# Save and load via .save and .load