explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #278 from elyase/patch-1

Browse Source 
replace codecs.open with io.open
This commit is contained in:
Matthew Honnibal 2016-03-02 00:41:23 +11:00
commit ae2b479312
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
bin/get_freqs.py
View File

@ -8,7 +8,6 @@ from os import path
import os
import bz2
import ujson
import codecs
from preshed.counter import PreshCounter
from joblib import Parallel, delayed
import io
@ -37,7 +36,7 @@ def count_freqs(input_loc, output_loc):
doc = tokenizer(json_comment['body'])
doc.count_by(ORTH, counts=counts)
with codecs.open(output_loc, 'w', 'utf8') as file_:
with io.open(output_loc, 'w', 'utf8') as file_:
for orth, freq in counts:
string = tokenizer.vocab.strings[orth]
if not string.isspace():