Python bindings to TrustyAI's explainability library.
Install from PyPi with
pip install trustyai
To install additional experimental features, also use
pip install trustyai[extras]
The minimum dependencies can be installed (from the root directory) with
pip install .
If running the examples or developing, also install the development dependencies:
pip install '.[dev]'
Alternatively create a container image and run it using
$ docker build -f Dockerfile -t python-trustyai:latest .
$ docker run --rm -it -p 8888:8888 python-trustyai:latest
The Jupyter server will be available at localhost:8888
.
You can also run the example Jupyter notebooks
using mybinder.org
:
Check out the ReadTheDocs page for API references and examples.
There are several working examples available in the examples repository.
Please see the CONTRIBUTING.md file for instructions on how to contribute to this project.