explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 18:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'develop' of https://github.com/honnibal/spaCy into develop

Browse Source
This commit is contained in:
Matthew Honnibal 2015-10-22 18:48:44 +02:00
commit 46fbf29019
2 changed files with 27 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
spacy/en/download.py
View File

@ -1,5 +1,4 @@
from __future__ import print_function from __future__ import print_function
from os import path
import sys import sys
import os import os
import tarfile import tarfile
@ -15,45 +14,44 @@ AWS_STORE = 'https://s3-us-west-1.amazonaws.com/media.spacynlp.com'
ALL_DATA_DIR_URL = '%s/en_data_all-%s.tgz' % (AWS_STORE, VERSION) ALL_DATA_DIR_URL = '%s/en_data_all-%s.tgz' % (AWS_STORE, VERSION)
DEST_DIR = path.join(path.dirname(path.abspath(__file__)), 'data') DEST_DIR = os.path.dirname(os.path.abspath(__file__))
def download_file(url, dest_dir): def download_file(url, download_path):
return uget.download(url, dest_dir, console=sys.stdout) return uget.download(url, download_path, console=sys.stdout)
def install_data(url, dest_dir): def install_data(url, extract_path, download_path):
filename = download_file(url, dest_dir) try:
t = tarfile.open(filename) os.makedirs(extract_path)
t.extractall(dest_dir) except FileExistsError:
pass
tmp = download_file(url, download_path)
def install_parser_model(url, dest_dir): assert tmp == download_path
filename = download_file(url, dest_dir) t = tarfile.open(download_path)
t = tarfile.open(filename, mode=":gz") t.extractall(extract_path)
t.extractall(dest_dir)
def install_dep_vectors(url, dest_dir):
download_file(url, dest_dir)
@plac.annotations( @plac.annotations(
force=("Force overwrite", "flag", "f", bool), force=("Force overwrite", "flag", "f", bool),
) )
def main(data_size='all', force=False): def main(data_size='all', force=False):
if data_size == 'all': filename = ALL_DATA_DIR_URL.rsplit('/', 1)[1]
data_url = ALL_DATA_DIR_URL download_path = os.path.join(DEST_DIR, filename)
elif data_size == 'small': data_path = os.path.join(DEST_DIR, 'data')
data_url = SM_DATA_DIR_URL
if force and path.exists(DEST_DIR): if force and os.path.exists(download_path):
shutil.rmtree(DEST_DIR) os.unlink(download_path)
if not os.path.exists(DEST_DIR): if force and os.path.exists(data_path):
os.makedirs(DEST_DIR) shutil.rmtree(data_path)
install_data(data_url, DEST_DIR) if os.path.exists(data_path):
print('data already installed at %s, overwrite with --force' % DEST_DIR)
sys.exit(1)
install_data(ALL_DATA_DIR_URL, DEST_DIR, download_path)
if __name__ == '__main__': if __name__ == '__main__':

5
spacy/language.py
View File

@ -1,5 +1,6 @@
from os import path from os import path
from warnings import warn from warnings import warn
import io
try: try:
import ujson as json import ujson as json
@ -248,8 +249,8 @@ class Language(object):
self.entity.model.end_training(path.join(data_dir, 'ner', 'model')) self.entity.model.end_training(path.join(data_dir, 'ner', 'model'))
self.tagger.model.end_training(path.join(data_dir, 'pos', 'model')) self.tagger.model.end_training(path.join(data_dir, 'pos', 'model'))
strings_loc = path.join(data_dir, 'vocab', 'strings.txt') strings_loc = path.join(data_dir, 'vocab', 'strings.json')
with io.open(strings_loc, 'w', encoding='utf8'): with io.open(strings_loc, 'w', encoding='utf8') as file_:
self.vocab.strings.dump(file_) self.vocab.strings.dump(file_)
with open(path.join(data_dir, 'vocab', 'serializer.json'), 'w') as file_: with open(path.join(data_dir, 'vocab', 'serializer.json'), 'w') as file_: