面向电力领域的中文分词工具
Project description
电力领域中文分词模型
ecws 是面向电力领域的基础中文分词模型组件,目标是打造电力领域的自然语言处理基础能力
安装指南
ecws 依赖以下包:
- torch==1.5.1
- allennlp==1.0.0
版本号
R3.0.5
模型命名
NLP-ECWS-R3.0.5
安装
- 第一步,安装 ecws
使用 pip 安装
pip install ecws
或从源代码安装
git clone https://github.com/rises-tech/ecws.git
cd NLP-ECWS
pip install -e .
- 下载
ecws.model
文件
Model Name | Download Link |
---|---|
ecws.v3.model | BaiduPan 提取码:ecws |
- python引用方式:
from ecws.segment import Segmenter
model_path = 'ecws.model'
predict = Segmenter(model_path)
d = predict.seg(sent)
- 接口demo界面
http://120.27.25.150:8082/
- web api 调用方式
def webservice_ecws(sentence):
data = {'sent': sentence}
url = 'http://120.27.25.150:8082/predict'
r = requests.post(url, json=data)
data = json.loads(r.text)
seg = data['spans']
return seg
其中返回的结果是一个字典,字段'sent'中包含分词结果。
- 电力自然语言处理演示平台
开发者
@ 张强<<alxor@live.cn>> @ 宋博川<<abc_hhhh@163.com>>
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ecws-3.0.5.tar.gz
(18.4 kB
view details)
Built Distribution
ecws-3.0.5-py3-none-any.whl
(29.7 kB
view details)
File details
Details for the file ecws-3.0.5.tar.gz
.
File metadata
- Download URL: ecws-3.0.5.tar.gz
- Upload date:
- Size: 18.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/49.6.0 requests-toolbelt/0.9.1 tqdm/4.36.1 CPython/3.7.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 71961efe7e22a6b68a8febe10bd289311d3a630a718f5eed6f29a91d61de375b |
|
MD5 | 8d420a1ccbfc14702bf401a35361fa92 |
|
BLAKE2b-256 | 7e0bdb0b5bf600c378784d883e9917b1ee310743e3db2d6303c13b3a8f712f35 |
File details
Details for the file ecws-3.0.5-py3-none-any.whl
.
File metadata
- Download URL: ecws-3.0.5-py3-none-any.whl
- Upload date:
- Size: 29.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/49.6.0 requests-toolbelt/0.9.1 tqdm/4.36.1 CPython/3.7.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | e64ee66bc88a1b7053ec023202edabccf2313677deb41adef3df90093b5dd1d7 |
|
MD5 | c62f6f5bee7665770c0731afc633aed9 |
|
BLAKE2b-256 | faffea14d3718d150608b0ba115c42d8765aa3c58cdd229cce9d622e5232d14b |