en_core_web_sm-2.0.0.tar.gz
Spacy是自然语言处理需要使用的一个工具包,加载模型后就可以做分词,词性标注等任务啦。 当你执行这条命令python -m spacy download en。但是没有网的时候,可能这个包有用。
spaCy >=2.0.0a18
代码片段和文件信息
#!/usr/bin/env python
# coding: utf8
from __future__ import unicode_literals
import io
import json
from os import path walk
from shutil import copy
from setuptools import setup
def load_meta(fp):
with io.open(fp encoding=‘utf8‘) as f:
return json.load(f)
def list_files(data_dir):
output = []
for root _ filenames in walk(data_dir):
for filename in filenames:
if not filename.startswith(‘.‘):
output.append(path.join(root filename))
output = [path.relpath(p path.dirname(data_dir)) for p in output]
output.append(‘meta.json‘)
return output
def list_requirements(meta):
parent_package = meta.get(‘parent_package‘ ‘spacy‘)
requirements = [parent_package + meta[‘spacy_version‘]]
if ‘setup_requires‘ in meta:
requirements += meta[‘setup_requires‘]
return requirements
def setup_package():
root = path.abspath(path.dirname(__file__))
meta_path = path.join(root ‘meta.json‘)
meta = load_meta(meta_path)
model_name = str(meta[‘lang‘] + ‘_‘ + meta[‘name‘])
model_dir = path.join(model_name model_name + ‘-‘ + meta[‘version‘])
copy(meta_path path.join(model_name))
copy(meta_path model_dir)
setup(
name=model_name
description=meta[‘description‘]
author=meta[‘author‘]
author_email=meta[‘email‘]
url=meta[‘url‘]
version=meta[‘version‘]
license=meta[‘license‘]
packages=[model_name]
package_data={model_name: list_files(model_dir)}
install_requires=list_requirements(meta)
zip_safe=False
)
if __name__ == ‘__main__‘:
setup_package()
版权声明:本文内容由互联网用户自发贡献,该文观点仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌抄袭侵权/违法违规的内容, 请发送邮件举报,一经查实,本站将立刻删除。
评论列表(条)