Metadata-Version: 2.1
Name: devnet
Version: 0.1.0
Summary: Unofficial pytorch implementation of deviation network for table data.
Home-page: https://github.com/y-kamiya/devnet
License: MIT
Author: Yuji Kamiya
Author-email: y.kamiya0@gmail.com
Requires-Python: >=3.7.1,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Requires-Dist: hydra-core (>=1.1.1,<2.0.0)
Requires-Dist: logzero (>=1.7.0,<2.0.0)
Requires-Dist: matplotlib (>=3.5.1,<4.0.0)
Requires-Dist: pandas (==1.3.5)
Requires-Dist: sklearn (>=0.0,<0.1)
Requires-Dist: torch (>=1.10.2,<2.0.0)
Project-URL: Repository, https://github.com/y-kamiya/devnet
Description-Content-Type: text/markdown

# Devnet
Unofficial pytorch implementation of deviation network for table data.

paper of deviation network  
https://arxiv.org/abs/1911.08623

original keras implementation by authors of the paper is here  
https://github.com/GuansongPang/deviation-network

## Setup
install poetry followed by  
https://python-poetry.org/docs/master/#installing-with-the-official-installer

install dependencies
```
poetry install
```

## Usage
train model with train/eval.csv under dataroot
```
poetry python src/main.py dataroot=data/debug epochs=10 eval_interval=10
```

predict score and output result
```
poetry python src/main.py predict_only=true predict_input=data/debug/eval.csv model_path=data/debug/models/example.pth
```

