{"id":19777940,"url":"https://github.com/datadome/sliceline","last_synced_at":"2025-05-16T11:03:55.781Z","repository":{"id":41301402,"uuid":"508642446","full_name":"DataDome/sliceline","owner":"DataDome","description":"✂️ Fast slice finding for Machine Learning model debugging.","archived":false,"fork":false,"pushed_at":"2025-04-28T08:53:44.000Z","size":1087,"stargazers_count":91,"open_issues_count":4,"forks_count":6,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-05-16T11:03:52.176Z","etag":null,"topics":["contrast-set-mining","ml-debug","python"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DataDome.png","metadata":{"files":{"readme":"README.rst","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2022-06-29T10:19:32.000Z","updated_at":"2025-04-28T08:53:41.000Z","dependencies_parsed_at":"2023-01-25T21:01:37.416Z","dependency_job_id":"2d204531-7cbb-42ad-86f4-c69b74948cea","html_url":"https://github.com/DataDome/sliceline","commit_stats":null,"previous_names":[],"tags_count":16,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataDome%2Fsliceline","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataDome%2Fsliceline/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataDome%2Fsliceline/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DataDome%2Fsliceline/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DataDome","download_url":"https://codeload.github.com/DataDome/sliceline/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254518384,"owners_count":22084374,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["contrast-set-mining","ml-debug","python"],"created_at":"2024-11-12T05:27:12.292Z","updated_at":"2025-05-16T11:03:55.758Z","avatar_url":"https://github.com/DataDome.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"Sliceline\n=========\n\nSliceline is a Python library for fast slice finding for Machine\nLearning model debugging.\n\nIt is an implementation of `SliceLine: Fast, Linear-Algebra-based Slice\nFinding for ML Model\nDebugging \u003chttps://mboehm7.github.io/resources/sigmod2021b_sliceline.pdf\u003e`__,\nfrom Svetlana Sagadeeva and Matthias Boehm of Graz University of\nTechnology.\n\n👉 Getting started\n------------------\n\nGiven an input dataset ``X`` and a model error vector ``errors``,\nSliceLine finds the top slices in ``X`` that identify where a ML model\nperforms significantly worse.\n\nYou can use sliceline as follows:\n\n.. code:: python\n\n   from sliceline.slicefinder import Slicefinder\n\n   slice_finder = Slicefinder()\n\n   slice_finder.fit(X, errors)\n\n   print(slice_finder.top_slices_)\n\n   X_trans = slice_finder.transform(X)\n\nWe invite you to check the `demo\nnotebooks \u003chttps://github.com/DataDome/sliceline/blob/main/notebooks\u003e`__\nfor a more thorough tutorial:\n\n1. Implementing Sliceline on Titanic dataset\n2. Implementing Sliceline on California housing dataset\n\n🛠 Installation\n---------------\n\nSliceline is intended to work with **Python 3.10 or above**. Installation\ncan be done with ``pip``:\n\n.. code:: sh\n\n   pip install sliceline\n\nThere are `wheels\navailable \u003chttps://pypi.org/project/sliceline/#files\u003e`__ for Linux,\nMacOS, and Windows, which means that you most probably won’t have to\nbuild Sliceline from source.\n\nYou can install the latest development version from GitHub as so:\n\n.. code:: sh\n\n   pip install git+https://github.com/DataDome/sliceline --upgrade\n\nOr, through SSH:\n\n.. code:: sh\n\n   pip install git+ssh://git@github.com/datadome/sliceline.git --upgrade\n\n🔗 Useful links\n---------------\n\n-  `Documentation \u003chttps://sliceline.readthedocs.io/en/stable/\u003e`__\n-  `Package releases \u003chttps://pypi.org/project/sliceline/#history\u003e`__\n-  `SliceLine paper \u003chttps://mboehm7.github.io/resources/sigmod2021b_sliceline.pdf\u003e`__\n\n👐 Contributing\n---------------\n\nFeel free to contribute in any way you like, we’re always open to new\nideas and approaches.\n\n-  `Open a\n   discussion \u003chttps://github.com/DataDome/sliceline/discussions/new\u003e`__\n   if you have any question or enquiry whatsoever. It’s more useful to\n   ask your question in public rather than sending us a private email.\n   It’s also encouraged to open a discussion before contributing, so\n   that everyone is aligned and unnecessary work is avoided.\n-  Feel welcome to `open an\n   issue \u003chttps://github.com/DataDome/sliceline/issues/new/choose\u003e`__ if\n   you think you’ve spotted a bug or a performance issue.\n\nPlease check out the `contribution\nguidelines \u003chttps://github.com/DataDome/sliceline/blob/main/CONTRIBUTING.md\u003e`__\nif you want to bring modifications to the code base.\n\n📝 License\n----------\n\nSliceline is free and open-source software licensed under the `3-clause BSD license \u003chttps://github.com/DataDome/sliceline/blob/main/LICENSE\u003e`__.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatadome%2Fsliceline","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdatadome%2Fsliceline","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatadome%2Fsliceline/lists"}