explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-10 19:57:17 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix iob converter

Browse Source
This commit is contained in:
Matthew Honnibal 2020-09-14 21:02:18 +02:00
parent fdd2340f6c
commit ae15fa9688
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/training/converters/iob2docs.py
View File

@ -1,12 +1,13 @@
from wasabi import Printer
from .conll_ner2docs import n_sents_info
from ...vocab import Vocab
from ...training import iob_to_biluo, tags_to_entities
from ...tokens import Doc, Span
from ...util import minibatch
def iob2docs(input_data, vocab, n_sents=10, no_print=False, *args, **kwargs):
def iob2docs(input_data, n_sents=10, no_print=False, *args, **kwargs):
"""
Convert IOB files with one sentence per line and tags separated with '|'
into Doc objects so they can be saved. IOB and IOB2 are accepted.
@ -18,6 +19,7 @@ def iob2docs(input_data, vocab, n_sents=10, no_print=False, *args, **kwargs):
I|PRP|O like|VBP|O London|NNP|I-GPE and|CC|O New|NNP|B-GPE York|NNP|I-GPE City|NNP|I-GPE .|.|O
I|PRP|O like|VBP|O London|NNP|B-GPE and|CC|O New|NNP|B-GPE York|NNP|I-GPE City|NNP|I-GPE .|.|O
"""
vocab = Vocab() # need vocab to make a minimal Doc
msg = Printer(no_print=no_print)
if n_sents > 0:
n_sents_info(msg, n_sents)