{"id":13400794,"url":"https://github.com/ModelOriented/iBreakDown","last_synced_at":"2025-03-14T06:31:56.239Z","repository":{"id":44597801,"uuid":"153493807","full_name":"ModelOriented/iBreakDown","owner":"ModelOriented","description":"Break Down with interactions for local explanations (SHAP, BreakDown, iBreakDown)","archived":false,"fork":false,"pushed_at":"2023-11-30T22:28:10.000Z","size":107333,"stargazers_count":79,"open_issues_count":4,"forks_count":15,"subscribers_count":10,"default_branch":"master","last_synced_at":"2024-09-30T20:38:39.517Z","etag":null,"topics":["breakdown","iml","interpretability","shapley","xai"],"latest_commit_sha":null,"homepage":"https://ModelOriented.github.io/iBreakDown/","language":"R","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ModelOriented.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":".github/CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2018-10-17T17:04:39.000Z","updated_at":"2024-02-11T02:28:46.000Z","dependencies_parsed_at":"2023-11-30T23:27:23.375Z","dependency_job_id":"260780a7-d56e-463a-9a75-591a238b07c9","html_url":"https://github.com/ModelOriented/iBreakDown","commit_stats":{"total_commits":221,"total_committers":11,"mean_commits":20.09090909090909,"dds":"0.46153846153846156","last_synced_commit":"28896b70501cf95b0da891cec85e6281106fe3d3"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ModelOriented%2FiBreakDown","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ModelOriented%2FiBreakDown/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ModelOriented%2FiBreakDown/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ModelOriented%2FiBreakDown/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ModelOriented","download_url":"https://codeload.github.com/ModelOriented/iBreakDown/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243537926,"owners_count":20307098,"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":["breakdown","iml","interpretability","shapley","xai"],"created_at":"2024-07-30T19:00:55.538Z","updated_at":"2025-03-14T06:31:56.233Z","avatar_url":"https://github.com/ModelOriented.png","language":"R","readme":"# Model Agnostic Local Attributions  \u003cimg src=\"man/figures/logo.png\" align=\"right\" width=\"150\"/\u003e\n\n[![R build status](https://github.com/ModelOriented/iBreakDown/workflows/R-CMD-check/badge.svg)](https://github.com/ModelOriented/iBreakDown/actions?query=workflow%3AR-CMD-check)\n[![Coverage\nStatus](https://img.shields.io/codecov/c/github/ModelOriented/iBreakDown/master.svg)](https://codecov.io/github/ModelOriented/iBreakDown?branch=master)\n[![CRAN_Status_Badge](http://www.r-pkg.org/badges/version/iBreakDown)](https://cran.r-project.org/package=iBreakDown)\n[![Total Downloads](http://cranlogs.r-pkg.org/badges/grand-total/iBreakDown?color=orange)](http://cranlogs.r-pkg.org/badges/grand-total/iBreakDown)\n\n## Overview\n\nThe `iBreakDown` package is a model agnostic tool for explanation of predictions from black boxes ML models.\nBreak Down Table shows contributions of every variable to a final prediction. \nBreak Down Plot presents variable contributions in a concise graphical way. \nSHAP (Shapley Additive Attributions) values are calculated as average from random Break Down profiles.\nThis package works for binary classifiers as well as regression models. \n\n`iBreakDown` is a successor of the [breakDown](https://github.com/pbiecek/breakDown) package. It is faster (complexity `O(p)` instead of `O(p^2)`). It supports variable interactions and interactive explanations with D3.js visualizations. It is imported and used to compute model explanations in multiple packages e.g. [`DALEX`](https://github.com/ModelOriented/DALEX), [`modelStudio`](https://github.com/ModelOriented/modelStudio), [`arenar`](https://github.com/ModelOriented/ArenaR).\n\nMethodology behind the **iBreakDown** package is described in the [arXiv paper](https://arxiv.org/abs/1903.11420) and [Explanatory Model Analysis](https://ema.drwhy.ai/breakDown.html) book. It is a part of [DrWhy.AI](http://DrWhy.AI) universe. \n\n## Installation\n\n```{r}\n# the easiest way to get iBreakDown is to install it from CRAN:\ninstall.packages(\"iBreakDown\")\n\n# Or the the development version from GitHub:\n# install.packages(\"devtools\")\ndevtools::install_github(\"ModelOriented/iBreakDown\")\n```\n\n## Learn more\n\nFind more examples in the EMA book: https://ema.drwhy.ai/.\n\nThis version also works with **D3**:\n[see an example](https://modeloriented.github.io/iBreakDown/prototypeDemo.html) and [demo](https://modeloriented.github.io/iBreakDown/articles/vignette_iBreakDown_titanic.html#plot-attributions-with-d3).\n\n![plotD3](man/figures/plotD3.png)\n\n## Acknowledgments\n\nWork on this package was financially supported by the `NCN Opus grant 2016/21/B/ST6/02176`.\n","funding_links":[],"categories":["R","Technical Resources"],"sub_categories":["Open Source/Access Responsible AI Software Packages"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FModelOriented%2FiBreakDown","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FModelOriented%2FiBreakDown","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FModelOriented%2FiBreakDown/lists"}