Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Make DocBin output stable data (set iteration)

This commit is contained in:
Matthew Honnibal 2020-09-25 22:20:44 +02:00
parent 26afd3bd90
commit 092ce4648e
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/tokens/_serialize.py
View File

@ -171,7 +171,7 @@ class DocBin:
"tokens": tokens.tobytes("C"), "tokens": tokens.tobytes("C"),
"spaces": spaces.tobytes("C"), "spaces": spaces.tobytes("C"),
"lengths": numpy.asarray(lengths, dtype="int32").tobytes("C"), "lengths": numpy.asarray(lengths, dtype="int32").tobytes("C"),
"strings": list(self.strings), "strings": list(sorted(self.strings)),
"cats": self.cats, "cats": self.cats,
"flags": self.flags, "flags": self.flags,
} }