explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-11 09:00:36 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix Corpus

Browse Source
This commit is contained in:
Matthew Honnibal 2020-06-20 21:49:15 +02:00
parent 450c6fe39c
commit 396dd60b3a
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/gold/corpus_docbin.py
View File

@ -68,9 +68,11 @@ class Corpus:
i += 1
return n
def train_dataset(self, nlp, **kwargs):
def train_dataset(self, nlp, shuffle=True, **kwargs):
ref_docs = self.read_docbin(nlp.vocab, self.walk_corpus(self.train_loc))
examples = list(self.make_examples(nlp, ref_docs, **kwargs))
examples = self.make_examples(nlp, ref_docs, **kwargs)
if shuffle:
examples = list(examples)
random.shuffle(examples)
yield from examples