基于bertopic对中文文档进行主题建模

Project description

About

一个基于bertopic对中文文档进行主题建模的包。

Install

$ pip3 install -U bertopic_base_chinese

Director

bertopic_base_chinese
- _model.py

_model.py

BERTopic类重写了__init__()，设置embedding_model为"paraphrase-multilingual-MiniLM-L12-v2"，以及选取tokenizer为jieba.lcut，初始化类参数。

Usage

from bertopic_base_chinese import BERTopic

docs = ["我爱北京天安门", "我家大门常打开，开放怀抱等你"]
topic_model = BERTopic()
topics, probs = topic_model.fit_transform(docs)

Contact us

may.xiaoya.zhang@gmail.com

Project details

Release history Release notifications | RSS feed

This version

0.0.1

Dec 21, 2023

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

bertopic_base_chinese-0.0.1.tar.gz (2.3 kB view details)

Uploaded Dec 21, 2023 Source

File details

Details for the file bertopic_base_chinese-0.0.1.tar.gz.

File metadata

Download URL: bertopic_base_chinese-0.0.1.tar.gz
Upload date: Dec 21, 2023
Size: 2.3 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/4.0.2 CPython/3.8.10

File hashes

Hashes for bertopic_base_chinese-0.0.1.tar.gz
Algorithm	Hash digest
SHA256	`495acdc81a31a4c4e6dd361538221bb6bc2d2adaf6e3348f09dc1071fff8c26c`
MD5	`f235e4785f9e7606b91a2219e3d02259`
BLAKE2b-256	`19a967f3cabab763db3290752e01230f8457faebc298cb70038a7fac7423b9f3`