https://github.com/datadome/sliceline
✂️ Fast slice finding for Machine Learning model debugging.
https://github.com/datadome/sliceline
contrast-set-mining ml-debug python
Last synced: about 1 year ago
JSON representation
✂️ Fast slice finding for Machine Learning model debugging.
- Host: GitHub
- URL: https://github.com/datadome/sliceline
- Owner: DataDome
- License: bsd-3-clause
- Created: 2022-06-29T10:19:32.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2025-04-28T08:53:44.000Z (about 1 year ago)
- Last Synced: 2025-05-16T11:03:52.176Z (about 1 year ago)
- Topics: contrast-set-mining, ml-debug, python
- Language: Jupyter Notebook
- Homepage:
- Size: 1.04 MB
- Stars: 91
- Watchers: 4
- Forks: 6
- Open Issues: 4
-
Metadata Files:
- Readme: README.rst
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Codeowners: .github/CODEOWNERS
Awesome Lists containing this project
README
Sliceline
=========
Sliceline is a Python library for fast slice finding for Machine
Learning model debugging.
It is an implementation of `SliceLine: Fast, Linear-Algebra-based Slice
Finding for ML Model
Debugging `__,
from Svetlana Sagadeeva and Matthias Boehm of Graz University of
Technology.
👉 Getting started
------------------
Given an input dataset ``X`` and a model error vector ``errors``,
SliceLine finds the top slices in ``X`` that identify where a ML model
performs significantly worse.
You can use sliceline as follows:
.. code:: python
from sliceline.slicefinder import Slicefinder
slice_finder = Slicefinder()
slice_finder.fit(X, errors)
print(slice_finder.top_slices_)
X_trans = slice_finder.transform(X)
We invite you to check the `demo
notebooks `__
for a more thorough tutorial:
1. Implementing Sliceline on Titanic dataset
2. Implementing Sliceline on California housing dataset
🛠 Installation
---------------
Sliceline is intended to work with **Python 3.10 or above**. Installation
can be done with ``pip``:
.. code:: sh
pip install sliceline
There are `wheels
available `__ for Linux,
MacOS, and Windows, which means that you most probably won’t have to
build Sliceline from source.
You can install the latest development version from GitHub as so:
.. code:: sh
pip install git+https://github.com/DataDome/sliceline --upgrade
Or, through SSH:
.. code:: sh
pip install git+ssh://git@github.com/datadome/sliceline.git --upgrade
🔗 Useful links
---------------
- `Documentation `__
- `Package releases `__
- `SliceLine paper `__
👐 Contributing
---------------
Feel free to contribute in any way you like, we’re always open to new
ideas and approaches.
- `Open a
discussion `__
if you have any question or enquiry whatsoever. It’s more useful to
ask your question in public rather than sending us a private email.
It’s also encouraged to open a discussion before contributing, so
that everyone is aligned and unnecessary work is avoided.
- Feel welcome to `open an
issue `__ if
you think you’ve spotted a bug or a performance issue.
Please check out the `contribution
guidelines `__
if you want to bring modifications to the code base.
📝 License
----------
Sliceline is free and open-source software licensed under the `3-clause BSD license `__.