百度实体抽取模型
Project description
pyUnit-NER 
NER模块集合
安装
pip install pyunit-ner
推荐使用Docker部署
docker pull jtyoui/pyunit-ner docker run -d -P jtyoui/pyunit-ner
默认官方数据集训练的模型(只能识别:人名、地名、机构名)
默认的参数和映射表
import pprint from pyunit_ner import ernie_st, ernie_match, parseNER def test(): # 默认的模型参数和映射表 model = '/home/jtyoui/Documents/model' s = ernie_st(new_model_path=model) data = ernie_match('刘万光对李伟说:在贵阳市南明村永乐乡发生了一件恐怖的事情', s) result = parseNER(data) return result if __name__ == '__main__': pprint.pprint(test())
抽取实体接口文档
http://ip:port/docs
请求报文
参数名 | 类型 | NULL | 说明 |
---|---|---|---|
data | string | Yes | 数据 |
请求示例
import requests url = "http://127.0.0.1:9000/pyunit/ner?data=我在贵州贵阳观山湖" headers = {'Content-Type': "application/x-www-form-urlencoded"} response = requests.get(url).json() print(response)
返回报文
参数名 | 类型 | NULL | 说明 |
---|---|---|---|
msg | string | Yes | 返回消息 |
data | list | Yes | 标注数据类型 |
address | list | Yes | 地址 |
person | list | Yes | 人名 |
org | list | Yes | 机构名 |
{ "code": 200, "entity": { "address": [ "贵州贵阳观山湖" ], "number": [ "6", "6", "4", "5", "4", "5", "4", "5", "5" ], "organization": [], "person": [], "word": [ "我", "在", "贵", "州", "贵", "阳", "观", "山", "湖" ] }, "msg": "success" }
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
pyunit_ner-2021.8.2.tar.gz
(101.9 kB
view hashes)
Built Distribution
pyunit_ner-2021.8.2-py3-none-any.whl
(100.5 kB
view hashes)
Close
Hashes for pyunit_ner-2021.8.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d8ec843dd18f4447d13bc592d033b9a4788654f8ad7da95ed7d01e5d20917486 |
|
MD5 | 12b5d350ca7450872db88a5ff4d2413f |
|
BLAKE2-256 | f7d99d168027678b7cee02850e0e8896aee8bd5df70d87fc22d4b762b2f57c54 |