explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-30 23:47:31 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update DocBin

Browse Source
This commit is contained in:
Matthew Honnibal 2020-06-20 20:12:54 +02:00
parent 0a8b6631a2
commit 652f31d3ee
1 changed files with 1 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/tokens/_serialize.py
View File

@ -14,7 +14,6 @@ ALL_ATTRS = (
"TAG", "TAG",
"HEAD", "HEAD",
"DEP", "DEP",
"SENT_START",
"ENT_IOB", "ENT_IOB",
"ENT_TYPE", "ENT_TYPE",
"LEMMA", "LEMMA",
@ -112,8 +111,7 @@ class DocBin(object):
for i in range(len(self.tokens)): for i in range(len(self.tokens)):
tokens = self.tokens[i] tokens = self.tokens[i]
spaces = self.spaces[i] spaces = self.spaces[i]
words = [vocab.strings[orth] for orth in tokens[:, orth_col]] doc = Doc(vocab, words=tokens[:, orth_col], spaces=spaces)
doc = Doc(vocab, words=words, spaces=spaces)
doc = doc.from_array(self.attrs, tokens) doc = doc.from_array(self.attrs, tokens)
doc.cats = self.cats[i] doc.cats = self.cats[i]
if self.store_user_data: if self.store_user_data: