src.models
.tokenize
¶
-
src.models.
tokenize
( doc , tag = None ) [source] ¶ -
Utility function to Tokenize a single tweet.
- Parameters
-
- doc str
-
Text to be tokenized.
- tag int, str or NoneType, default=None
-
Document identifier. If None, returns list of tokens instead of tagged document.
- Returns
-
- document list or gensim.models.doc2vec.TaggedDocument
-
Tokenized, tagged document