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

Fix loading of text categories in GoldParse

This commit is contained in:
Matthew Honnibal 2017-07-22 20:04:03 +02:00
parent 6ffec9dfea
commit ed6c85fa3c
1 changed files with 2 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
spacy/gold.pyx
View File

@ -148,7 +148,7 @@ def minibatch(items, size=8):
''' '''
items = iter(items) items = iter(items)
while True: while True:
batch_size = next(size) #if hasattr(size, '__next__') else size batch_size = next(size) if hasattr(size, '__next__') else size
batch = list(cytoolz.take(int(batch_size), items)) batch = list(cytoolz.take(int(batch_size), items))
if len(batch) == 0: if len(batch) == 0:
break break
@ -428,17 +428,7 @@ cdef class GoldParse:
self.c.has_dep = <int*>self.mem.alloc(len(doc), sizeof(int)) self.c.has_dep = <int*>self.mem.alloc(len(doc), sizeof(int))
self.c.ner = <Transition*>self.mem.alloc(len(doc), sizeof(Transition)) self.c.ner = <Transition*>self.mem.alloc(len(doc), sizeof(Transition))
self.cats = [] self.cats = list(cats)
for item in cats:
if isinstance(item, int):
self.cats.append((0, len(doc.text), self.vocab.strings[item]))
elif isinstance(item, str):
self.cats.append((0, len(doc.text), item))
elif hasattr(item, '__len__') and len(item) == 3:
start_char, end_char, label = item
if isinstance(label, int):
label = self.vocab.strings[label]
self.cats.append((start_char, end_char, label))
self.words = [None] * len(doc) self.words = [None] * len(doc)
self.tags = [None] * len(doc) self.tags = [None] * len(doc)
self.heads = [None] * len(doc) self.heads = [None] * len(doc)