Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

https://github.com/SauceCat/PDPbox

python partial dependence plot toolbox
https://github.com/SauceCat/PDPbox

Last synced: about 1 month ago
JSON representation

python partial dependence plot toolbox

Host: GitHub
URL: https://github.com/SauceCat/PDPbox
Owner: SauceCat
License: mit
Created: 2017-06-26T08:01:54.000Z (almost 7 years ago)
Default Branch: master
Last Pushed: 2023-06-05T02:44:20.000Z (12 months ago)
Last Synced: 2024-02-29T22:22:01.069Z (3 months ago)
Language: Jupyter Notebook
Homepage: http://pdpbox.readthedocs.io/en/latest/
Size: 303 MB
Stars: 806
Watchers: 17
Forks: 130
Open Issues: 30
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- License: LICENSE.txt

Lists

awesome-python-data-science - PDPbox - Partial dependence plot toolbox. (Model Explanation / Others)
awesome-production-machine-learning - PDPBox - This repository is inspired by ICEbox. The goal is to visualize the impact of certain features towards model prediction for any supervised learning algorithm. (Industry Strength Visualisation)
awesome-machine-learning-interpretability - PDPbox
Awesome-explainable-AI - https://github.com/SauceCat/PDPbox - learn ![](https://img.shields.io/github/stars/SauceCat/PDPbox?style=social) (Python Libraries(sort in alphabeta order) / Evaluation methods)
awesome-python-machine-learning-resources - GitHub - 36% open · ⏱️ 14.03.2021): (数据可视化)
awesome-production-machine-learning - PDPBox - This repository is inspired by ICEbox. The goal is to visualize the impact of certain features towards model prediction for any supervised learning algorithm. (now support all scikit-learn algorithms) (Industrial Strength Visualisation libraries)
Awesome-AIML-Data-Ops - PDPBox - This repository is inspired by ICEbox. The goal is to visualize the impact of certain features towards model prediction for any supervised learning algorithm. (now support all scikit-learn algorithms) (Visualisation libraries)
awesome-production-machine-learning - PDPBox - This repository is inspired by ICEbox. The goal is to visualize the impact of certain features towards model prediction for any supervised learning algorithm. (now support all scikit-learn algorithms) (Industrial Strength Visualisation libraries)
awesome-python-data-science - SauceCat/PDPbox - Partial dependence plot toolbox. (Exploration)
awesome-stars - SauceCat/PDPbox - python partial dependence plot toolbox (Jupyter Notebook)
awesome-python-data-science - PDPbox - Partial dependence plot toolbox. (Model Explanation / NLP)

README

# PDPbox
[![PyPI version](https://badge.fury.io/py/PDPbox.svg)](https://badge.fury.io/py/PDPbox)
[![codecov](https://codecov.io/gh/SauceCat/PDPbox/branch/master/graph/badge.svg?token=wIGFZIoSKJ)](https://codecov.io/gh/SauceCat/PDPbox)
![Build Status](https://github.com/SauceCat/PDPbox/actions/workflows/tox-test.yml/badge.svg)

Python **P**artial **D**ependence **P**lot tool**box**.

Visualize the influence of certain features on model predictions for supervised machine learning algorithms,
utilizing partial dependence plots.

For a comprehensive explanation, I recommend referring to the [Partial Dependence Plot (PDP)](https://christophm.github.io/interpretable-ml-book/pdp.html) chapter in Christoph Molnar's book, [Interpretable Machine Learning](https://christophm.github.io/interpretable-ml-book/).

## I am back! :smirk_cat:

After four years...

I'm delighted to see how popular PDPbox has become; it has exceeded all my expectations.
When I first embarked on this project, it was a modest endeavor,
simply to whet my appetite for real-world Python package development.

With the shift in my career path towards deep learning in 2018, I had to halt the development and maintenance of PDPbox.
As I no longer actively used it and several other outstanding packages such as
[lime](https://github.com/marcotcr/lime) and [shap](https://github.com/slundberg/shap) were emerging.

However, as the years have passed, I have seen PDPbox gain a significant presence in the community.
It's been referenced in various online courses and books, demonstrating its valuable role.
Despite well-known limitations of partial dependence plots,
their simplicity and intuitiveness might have made them a popular starting point for many,
appealing to a broad range of audiences.

Given this, I feel a renewed sense of responsibility to revisit the project, refine the existing code,
potentially add new features, and create additional tutorials.
I'm excited about this next phase and look forward to contributing more to the open source community.

## Installation

- through pip
```
$ pip install pdpbox
```

- through git (latest develop version)
```
$ git clone https://github.com/SauceCat/PDPbox.git
$ cd PDPbox
$ python setup.py install
```

## Reference

- Documentation: http://pdpbox.readthedocs.io/en/latest/
- Tutorials: tutorials
- Change Log: CHANGELOG.md

## Testing
### Test with `pytest`

```
cd /PDPbox
python -m pytest tests
```

### Test with `tox`
PDPbox can be tested using `tox`.

- First install `tox`

```
$ pip install tox
```

- Call `tox` inside the pdpbox clone directory. This will run tests with python3.9.

- To test the documentation, call `tox -e docs`.
The documentation should open up in your browser if it is successfully build.
Otherwise, the problem with the documentation will be reported in the output of the command.

## Gallery
- **PDP:** PDP for a single feature