Name		Name	Last commit message	Last commit date
Latest commit History 14 Commits
.gitignore		.gitignore
README.md		README.md
features_engineering.py		features_engineering.py
lgb_models.py		lgb_models.py
main.py		main.py
tree.txt		tree.txt
utils.py		utils.py
w2v.py		w2v.py

Repository files navigation

TianChi_OGeek

数据问题:train部分数据第1815102行漏了个引号，手动删除或不上引号即可
代码进行了更新，之前版本的代码通过tag回滚
当前版本代码实现了通过词向量作为文本特征进行文本聚类，需要耗费内存较大，低于16G请勿尝试
由于ignore了原始文件，项目结构树

About

No description, website, or topics provided.

Report repository

Releases

Packages

No packages published

Languages

Python 100.0%