https://github.com/interpretml/gam-changer
Editing machine learning models to reflect human knowledge and values
https://github.com/interpretml/gam-changer
interpretability machine-learning visualization
Last synced: 10 months ago
JSON representation
Editing machine learning models to reflect human knowledge and values
- Host: GitHub
- URL: https://github.com/interpretml/gam-changer
- Owner: interpretml
- License: mit
- Created: 2021-12-03T01:12:18.000Z (about 4 years ago)
- Default Branch: master
- Last Pushed: 2023-10-03T06:55:41.000Z (over 2 years ago)
- Last Synced: 2025-04-04T05:51:12.616Z (10 months ago)
- Topics: interpretability, machine-learning, visualization
- Language: JavaScript
- Homepage: https://interpret.ml/gam-changer
- Size: 18.7 MB
- Stars: 124
- Watchers: 7
- Forks: 11
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Governance: GOVERNANCE.md
Awesome Lists containing this project
README
Interactive visualization tool to help domain experts and data scientists easily and responsibly edit Generalized Additive Models (GAMs).
[](https://github.com/interpretml/gam-changer/actions)
[](https://pypi.org/project/gamchanger/)
[](https://interpret.ml/gam-changer/notebook/retro/notebooks/?path=gam_changer_adult.ipynb)
[](https://github.com/interpretml/gam-changer/blob/master/LICENSE)
[](https://doi.org/10.1145/3534678.3539074)
[](https://arxiv.org/abs/2206.15465)
📺 Video
📖 "Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values"
## GAM Changer Features
---
## Get Started
For a live demo, visit: http://interpret.ml/gam-changer/
### How to Edit My Own GAMs?
You can use this demo to edit your own GAMs: choose the `my model` tab and upload the `model.json` (model weights) and `sample.json` (sample data to evaluate the model).
If you use [EBM](https://github.com/interpretml/interpret), you can generate these two files easily with the GAM Changer python package.
```shell
# First install the GAM Changer python package
pip install gamchanger
```
```python
import gamchanger as gc
from json import dump
# Extract model weights
model_data = gc.get_model_data(ebm)
# Generate sample data
sample_data = gc.get_sample_data(ebm, x_test, y_test)
# Save to `model.json` and `sample.json`
dump(model_data, open('./model.json', 'w'))
dump(sample_data, open('./sample.json', 'w'))
```
### Computational Notebook Widget
You can use GAM Changer directly in your computational notebooks (e.g., Jupyter Notebook, VSCode Notebook, Google Colab).
Check out three live notebook demos below.
|Jupyter Lite|Binder|Google Colab|
|:---:|:---:|:---:|
|[](https://interpret.ml/gam-changer/notebook/retro/notebooks/?path=gam_changer_adult.ipynb)|[](https://mybinder.org/v2/gh/interpretml/gam-changer/master?urlpath=lab/tree/examples/gam_changer_adult.ipynb)|[](https://colab.research.google.com/drive/1OgAVZKqs2VwmY13QuOjCxlOEyexsYjtm?usp=sharing)|
Use the following snippet to load GAM Changer in your favorite notebooks:
```python
# Install the GAM Changer python package
!pip install gamchanger
import gamchanger as gc
# Load GAM Changer with the model and sample data
gc.visualize(ebm, x_feed, y_feed)
```
### Load Edited Models
After finishing editing a model, you can save the new model along with all the editing history to a `*.gamchanger` file by clicking the save button. You can load the new model in Python:
```python
from json import load
import gamchanger as gc
# Load the `*.gamchanger` file
gc_dict = load(open('./edit-8-27-2021.gamchanger', 'r'))
# This will return a deep copy of your original EBM where edits are applied
new_ebm = gc.get_edited_model(ebm, gc_dict)
```
## Development
Clone or download this repository:
```bash
git clone git@github.com:interpretml/gam-changer.git
# use degit if you don't want to download commit histories
degit interpretml/gam-changer.git
```
Install the dependencies:
```bash
npm install
```
Then run GAM Changer:
```bash
npm run dev
```
Navigate to [localhost:5000](https://localhost:5005). You should see GAM Changer running in your browser :)
## Credits
GAM Changer is created by Jay Wang,
Alex Kale,
Harsha Nori,
Peter Stella,
Mark Nunnally,
Polo Chau,
Mickey Vorvoreanu,
Jenn Wortman Vaughan,
and Rich Caruana,
which was the result of a research collaboration between
Microsoft Research, NYU Langone Health, Georgia Tech and University of Washington.
Jay Wang and Alex Kale were summer interns at Microsoft Research.
We thank Steven Drucker, Adam Fourney, Saleema Amershi, Dean Carignan, Rob DeLine, Haekyu Park, and the InterpretML team for their support and constructive feedback.
## Citation
```bibTeX
@inproceedings{wangInterpretabilityThenWhat2022,
title = {Interpretability, {{Then What}}? {{Editing Machine Learning Models}} to {{Reflect Human Knowledge}} and {{Values}}},
shorttitle = {Interpretability, {{Then What}}?},
booktitle = {Proceedings of the 28th {{ACM SIGKDD International Conference}} on {{Knowledge Discovery}} \& {{Data Mining}}},
author = {Wang, Zijie J. and Kale, Alex and Nori, Harsha and Stella, Peter and Nunnally, Mark E. and Chau, Duen Horng and Vorvoreanu, Mihaela and Vaughan, Jennifer Wortman and Caruana, Rich},
year = {2022},
url = {https://interpret.ml/gam-changer},
}
```
## License
The software is available under the [MIT License](./LICENSE).
## Contact
If you have any questions, feel free to [open an issue](https://github.com/interpretml/gam-changer/issues/new) or contact [Jay Wang](https://zijie.wang).