dnn-inference

🔬 dnn-inf: significance tests of feature relevance for a black-box model

dnn-inference is a Python module for hypothesis testing based on black-box models, including deep neural networks.

GitHub repo: https://github.com/statmlben/dnn-inference
Documentation: https://dnn-inference.readthedocs.io
PyPi: https://pypi.org/project/dnn-inference
Open Source: MIT license
Paper: arXiv:2103.04985

Installation

Dependencies

dnn-inference requires: Python>=3.8 + requirements.txt

pip install -r requirements.txt

User installation

Install dnn-inference using pip

pip install dnn_inference
pip install git+https://github.com/statmlben/dnn-inference.git

Reference

If you use this code please star the repository and cite the following paper:

@misc{dai2021significance,
      title={Significance tests of feature relevance for a blackbox learner},
      author={Ben Dai and Xiaotong Shen and Wei Pan},
      year={2021},
      eprint={2103.04985},
      archivePrefix={arXiv},
      primaryClass={stat.ML}
}

Notebook

MNIST dataset: Notebook1
Boston house prices dataset: Notebook2

Metadata

Release files for dnn-inference 0.16

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for dnn-inference 0.16
File	Size	Uploaded
dnn-inference-0.16.tar.gz	22.5 kB	Jul 12, 2022	Details

Release files / dnn-inference-0.16.tar.gz

Download URL	dnn-inference-0.16.tar.gz
Size	22.5 kB
Tags	Source
SHA-256 checksum How to use checksums	`f7af9ac533cb0bc5235054d65681cc27b71e825de54fb898ab8130dd25294011`
BLAKE2b-256 checksum How to use checksums	`58f9c35b54e9c83d4444709e824df065303a7c4354ea24554dc85f00a50749c4`
Upload date	Jul 12, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.1 CPython/3.10.4`