Metadata-Version: 2.1
Name: sk_in_torch
Version: 0.0.1
Summary: Torch models rewritten in sklearn format
Project-URL: Homepage, https://github.com/HaoLi111/sk_in_torch/
Project-URL: Issues, https://github.com/HaoLi111/sk_in_torch/issues
Author-email: Hao Li <haolircplanes@gmail.com>
License-File: LICENSE
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.8
Description-Content-Type: text/markdown

# sk_in_torch

Some torch models in sklearn format.

Goal:

Installation of pytorch is everywhere Why not use torch to compute some of the traditional models as well? Also, it is possible to make torch conform to sklearn's grammar, making it almost plug and play. Here are some of the results & I show you that sklearn and packages in sklearn style (like linear-tree) can work with these functions seamlessly.

Quickstart:


an early version of call is at https://www.kaggle.com/code/hli111111/sklearn-in-pytorch-with-gpu
note that you do not need to rewrite the classes if you import this.