mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-24 00:46:28 +03:00
Fix concatenation in iob2json converter
This commit is contained in:
parent
4896ce3320
commit
31681d20e0
|
@ -1,5 +1,6 @@
|
|||
# coding: utf8
|
||||
from __future__ import unicode_literals
|
||||
from cytoolz import partition_all, concat
|
||||
|
||||
from ...compat import json_dumps, path2str
|
||||
from ...util import prints
|
||||
|
@ -10,22 +11,24 @@ def iob2json(input_path, output_path, n_sents=10, *a, **k):
|
|||
"""
|
||||
Convert IOB files into JSON format for use with train cli.
|
||||
"""
|
||||
# TODO: This isn't complete yet -- need to map from IOB to
|
||||
# BILUO
|
||||
with input_path.open('r', encoding='utf8') as file_:
|
||||
docs = read_iob(file_)
|
||||
if n_sents:
|
||||
lines = [' '.join(para) for para in partition_all(n_sents, file_)]
|
||||
else:
|
||||
lines = file_
|
||||
sentences = read_iob(lines)
|
||||
|
||||
output_filename = input_path.parts[-1].replace(".iob", ".json")
|
||||
output_file = output_path / output_filename
|
||||
with output_file.open('w', encoding='utf-8') as f:
|
||||
f.write(json_dumps(docs))
|
||||
prints("Created %d documents" % len(docs),
|
||||
f.write(json_dumps(sentences))
|
||||
prints("Created %d documents" % len(sentences),
|
||||
title="Generated output file %s" % path2str(output_file))
|
||||
|
||||
|
||||
def read_iob(file_):
|
||||
def read_iob(raw_sents):
|
||||
sentences = []
|
||||
for line in file_:
|
||||
for line in raw_sents:
|
||||
if not line.strip():
|
||||
continue
|
||||
tokens = [t.split('|') for t in line.split()]
|
||||
|
|
Loading…
Reference in New Issue
Block a user