explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-26 09:14:32 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Add Language.batch() method, to support multi-threaded jobs

Browse Source
This commit is contained in:
Matthew Honnibal 2016-02-01 09:01:13 +01:00
parent b3802562d6
commit 98fbdf2856
1 changed files with 11 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
spacy/language.py
View File

@ -269,6 +269,17 @@ class Language(object):
self.entity(tokens)
return tokens
def batch(self, texts, tag=True, parse=True, entity=True):
if tag is False:
return [self(text, tag=tag, parse=parse, entity=entity)
for text in texts]
docs = []
for text in texts:
doc = self(text, tag=True, parse=False, entity=entity)
if self.parser and parse:
self.parser.parse_batch(docs)
return docs
def end_training(self, data_dir=None):
if data_dir is None:
data_dir = self.data_dir