Skip to main content

基于NLP的中文情感倾向分析库

Project description

Cemotion是Python下的中文NLP库,可以进行 中文情感倾向分析。

Cemotion的模型经循环神经网络训练得到,会为 中文文本 返回 0~1之间的 情感倾向置信度。您可以批量分析中文文本的情感,并部署至Linux、macOS、Windows等生产环境中,无需关注内部原理。

该模块供Apple Silicon使用,已经过M1测试。请按该文档安装ARM Python、TensorFlow、scikit-learn环境。

安装方法

前提: 根据 https://www.cyberlight.xyz/passage/tensorflow-apple-m1 此文方法安装ARM Python和TensorFlow(TensorFlow需要装到conda虚拟环境中,通读全文后,请使用文章末尾的方法安装TensorFlow)

此时,我们假定您已安装相关环境,并创建了名为py38的conda虚拟环境

1.进入命令窗口,激活conda虚拟环境,安装scikit-learn

conda activate py38 #激活虚拟环境 此处虚拟环境名称为py38(您可以自定义名称)
conda install scikit-learn #安装scikit-learn

之后输入以下命令安装Cemotion

pip install --upgrade pip
pip install cemotion-apple

使用方法

#按文本字符串分析
from cemotion import Cemotion

str_text1 = '配置顶级,不解释,手机需要的各个方面都很完美'
str_text2 = '院线看电影这么多年以来,这是我第一次看电影睡着了。简直是史上最大烂片!没有之一!侮辱智商!大家小心警惕!千万不要上当!再也不要看了!'

c = Cemotion()
print('"', str_text1 , '"\n' , '预测值:{:6f}'.format(c.predict(str_text1) ) , '\n')
print('"', str_text2 , '"\n' , '预测值:{:6f}'.format(c.predict(str_text2) ) , '\n')
#返回内容(该模块返回了这句话的情感置信度,值在0到1之间):
text mode
" 配置顶级,不解释,手机需要的各个方面都很完美 "
 预测值:0.999931 

text mode
" 院线看电影这么多年以来,这是我第一次看电影睡着了。简直是史上最大烂片!没有之一!侮辱智商!大家小心警惕!千万不要上当!再也不要看了! "
 预测值:0.000001 
#使用列表进行批量分析
from cemotion import Cemotion

list_text = ['内饰蛮年轻的,而且看上去质感都蛮好,貌似本田所有车都有点相似,满高档的!',
'总而言之,是一家不会再去的店。']

c = Cemotion()
print(c.predict(list_text))
#返回内容(该模块返回了列表中每句话的情感置信度,值在0到1之间):
list mode
[['内饰蛮年轻的,而且看上去质感都蛮好,貌似本田所有车都有点相似,满高档的!', 0.999907], ['总而言之,是一家不会再去的店。', 0.049015]]

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

Cemotion-apple-0.3.3.tar.gz (5.9 kB view details)

Uploaded Source

Built Distribution

Cemotion_apple-0.3.3-py3-none-any.whl (6.7 kB view details)

Uploaded Python 3

File details

Details for the file Cemotion-apple-0.3.3.tar.gz.

File metadata

  • Download URL: Cemotion-apple-0.3.3.tar.gz
  • Upload date:
  • Size: 5.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/53.0.0 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.8.6

File hashes

Hashes for Cemotion-apple-0.3.3.tar.gz
Algorithm Hash digest
SHA256 a10f7340c313bef102052e838093e84d6df8bad49d64b1adda7f6b00711741af
MD5 433a66fd69ca551f70eafbaf2867f004
BLAKE2b-256 084b1f057d86155b8395ce8ee17c7134622d587a0f62b0d7adeddbe1f162f044

See more details on using hashes here.

File details

Details for the file Cemotion_apple-0.3.3-py3-none-any.whl.

File metadata

  • Download URL: Cemotion_apple-0.3.3-py3-none-any.whl
  • Upload date:
  • Size: 6.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/53.0.0 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.8.6

File hashes

Hashes for Cemotion_apple-0.3.3-py3-none-any.whl
Algorithm Hash digest
SHA256 4b792c3977520b428b50088555662287794467761fce1fd04c44e7c30031edcd
MD5 3a84a5129cc3a23fc3f2e4695268e060
BLAKE2b-256 1f8276933d386f5d7b7af29b5d7cad6ffed7055f7942f491258d43a029a32273

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page