https://github.com/AustinRochford/PyCEbox

⬛ Python Individual Conditional Expectation Plot Toolbox
https://github.com/AustinRochford/PyCEbox

interpretability machine-learning

Last synced: 3 months ago
JSON representation

⬛ Python Individual Conditional Expectation Plot Toolbox

• Host: GitHub
• URL: https://github.com/AustinRochford/PyCEbox
• Owner: AustinRochford
• License: mit
• Created: 2015-12-02T15:49:34.000Z (about 9 years ago)
• Default Branch: master
• Last Pushed: 2020-05-29T15:11:16.000Z (over 4 years ago)
• Last Synced: 2024-10-04T10:48:24.539Z (5 months ago)
• Topics: interpretability, machine-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 1.15 MB
• Stars: 164
• Watchers: 6
• Forks: 35
• Open Issues: 5
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-production-machine-learning - PyCEbox - Python Individual Conditional Expectation Plot Toolbox (Industrial Strength Visualisation libraries)
• Awesome-explainable-AI - https://github.com/AustinRochford/PyCEbox
• awesome-production-machine-learning - PyCEbox - Python Individual Conditional Expectation Plot Toolbox. (Industry Strength Visualisation)

README

        
# ⬛ PyCEbox

Python Individual Conditional Expectation Plot Toolbox

![Individual conditional expectation plot](./img/ice_demo.png)

A Python implementation of individual conditional expecation plots inspired by R's [ICEbox](https://cran.r-project.org/web/packages/ICEbox/index.html). Individual conditional expectation plots were introduced in _Peeking Inside the Black Box: Visualizing Statistical Learning with Plots of Individual Conditional Expectation_ ([arXiv:1309.6392](http://arxiv.org/abs/1309.6392)).

## Quickstart

`pycebox` is [available](https://pypi.python.org/pypi/pycebox) on PyPI and can be installed with `pip install pycebox.`

The [tutorial](https://github.com/AustinRochford/PyCEbox/blob/master/notebooks/PyCEBox%20Tutorial.ipynb) recreates the first example in the above paper using `pycebox`.

## Development

For easy development and prototyping using IPython notebooks, a Docker environment is included.  To run an IPython notebook with access to your development version of `pycebox`, run `PORT=8889 sh ./start_container.sh`.  A Jupyter notebook server with access to your development version of `pycebox` should be available at `http://localhost:8889/tree`.

To run the `pycebox`'s tests in your development container

1. Access a bash shell on the container with `docker exec -it pycebox bash`.

2. Change to the `pycebox` directory with `cd ../pycebox`

3. Run the tests with `pytest test/test.py`

## Documentation

For details of `pycebox`'s API, consult the [documentation](http://austinrochford.github.io/PyCEbox/docs/).

## License

This library is distributed under the [MIT License](https://raw.githubusercontent.com/AustinRochford/PyCEbox/master/LICENSE).