Fast slice finding for Machine Learning model debugging.

Navigation

Verified details

These details have been verified by PyPI
Project links
GitHub Statistics
Maintainers
Avatar for datadome from gravatar.com datadome

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License Expression: BSD-3-Clause
    SPDX License Expression
  • Author: Antoine de Daran
  • Requires: Python <4, >=3.10
  • Provides-Extra: dev , optimized
Classifiers
Report project as malware

Project description

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:

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:

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:

pip install git+https://github.com/DataDome/sliceline --upgrade

Or, through SSH:

pip install git+ssh://git@github.com/datadome/sliceline.git --upgrade

⚡ Performance Optimization

Sliceline includes optional Numba JIT compilation for 5-50x performance improvements on scoring operations.

Quick Installation:

# With optimization support
pip install sliceline[optimized]

Benefits:

  • 5-6x faster scoring operations

  • 1.4-4.5x faster overall fit() performance

  • Up to 17% memory reduction on large datasets

  • Automatic fallback to pure NumPy if Numba not available

System Requirements:

Numba requires LLVM to be installed:

# macOS
brew install llvm

# Linux (Ubuntu/Debian)
sudo apt-get install llvm

Verify Optimization:

from sliceline import is_numba_available

print("Numba available:", is_numba_available())

See the performance benchmarks for detailed metrics.

👐 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.

Project details

Verified details

These details have been verified by PyPI
Project links
GitHub Statistics
Maintainers
Avatar for datadome from gravatar.com datadome

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License Expression: BSD-3-Clause
    SPDX License Expression
  • Author: Antoine de Daran
  • Requires: Python <4, >=3.10
  • Provides-Extra: dev , optimized
Classifiers

Release history Release notifications | RSS feed

This version

0.3.0

0.2.20

0.2.18

0.2.15

0.2.14

0.2.13

0.2.12

0.2.11

0.2.10

0.2.9

0.2.8

0.2.7

0.2.6

0.2.4

0.2.3

0.2.0

0.1.0

0.0.0

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sliceline-0.3.0.tar.gz (64.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

sliceline-0.3.0-py3-none-any.whl (22.2 kB view details)

Uploaded Python 3

File details

Details for the file sliceline-0.3.0.tar.gz.

File metadata

  • Download URL: sliceline-0.3.0.tar.gz
  • Upload date:
  • Size: 64.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for sliceline-0.3.0.tar.gz
Algorithm Hash digest
SHA256 ff2727aaa836c8ef7da71a5cd3b951e6bcb42719b1778c0240f1db25d26c28cc
MD5 a38f6efa66fc1af90196e6e0c815eba0
BLAKE2b-256 032e50d3fe7298bbf4d4d2a9612f10c7f3b02db0ad5ac410907ccba6c007e6c5

See more details on using hashes here.

Provenance

The following attestation bundles were made for sliceline-0.3.0.tar.gz:

Publisher: release.yml on DataDome/sliceline

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file sliceline-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: sliceline-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 22.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for sliceline-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 0459565e813f3ff8854282666475116f9f2de6d13e881c2f2e360cc212972b25
MD5 5b311666a37051a47cf320f992516fec
BLAKE2b-256 87d4bb58b704048e6f3d9ca4a96509ea26efff0d843c6ddff53565a2b74b8d1f

See more details on using hashes here.

Provenance

The following attestation bundles were made for sliceline-0.3.0-py3-none-any.whl:

Publisher: release.yml on DataDome/sliceline

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page