explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-14 18:22:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix converters

Browse Source
This commit is contained in:
Matthew Honnibal 2017-05-26 11:32:34 -05:00
parent 70afcfec3e
commit 5a87bcf35f
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/cli/converters/iob2json.py
View File

@ -3,6 +3,7 @@ from __future__ import unicode_literals
from ...compat import json_dumps, path2str from ...compat import json_dumps, path2str
from ...util import prints from ...util import prints
from ...gold import iob_to_biluo
def iob2json(input_path, output_path, n_sents=10, *a, **k): def iob2json(input_path, output_path, n_sents=10, *a, **k):
@ -29,9 +30,10 @@ def read_iob(file_):
continue continue
tokens = [t.rsplit('|', 2) for t in line.split()] tokens = [t.rsplit('|', 2) for t in line.split()]
words, pos, iob = zip(*tokens) words, pos, iob = zip(*tokens)
biluo = iob_to_biluo(iob)
sentences.append([ sentences.append([
{'orth': w, 'tag': p, 'ner': ent} {'orth': w, 'tag': p, 'ner': ent}
for (w, p, ent) in zip(words, pos, iob) for (w, p, ent) in zip(words, pos, biluo)
]) ])
sentences = [{'tokens': sent} for sent in sentences] sentences = [{'tokens': sent} for sent in sentences]
paragraphs = [{'sentences': [sent]} for sent in sentences] paragraphs = [{'sentences': [sent]} for sent in sentences]