{"id":21432469,"url":"https://github.com/gagolews/clustering-benchmarks","last_synced_at":"2025-04-10T03:56:14.131Z","repository":{"id":59535721,"uuid":"257528567","full_name":"gagolews/clustering-benchmarks","owner":"gagolews","description":"A framework for benchmarking clustering algorithms","archived":false,"fork":false,"pushed_at":"2025-04-08T11:44:52.000Z","size":203207,"stargazers_count":38,"open_issues_count":1,"forks_count":6,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-10T03:56:07.741Z","etag":null,"topics":["benchmark-suite","benchmarking","cluster","cluster-analysis","clustering","clustering-algorithms","clustering-benchmarks","clustering-evaluation","data","data-science","dataset","datasets","ground-truth","machine-learning"],"latest_commit_sha":null,"homepage":"http://clustering-benchmarks.gagolewski.com/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gagolews.png","metadata":{"files":{"readme":"README.md","changelog":"NEWS","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-04-21T08:22:08.000Z","updated_at":"2025-04-08T11:44:56.000Z","dependencies_parsed_at":"2025-01-01T21:11:38.201Z","dependency_job_id":"32e56535-e5d3-4a98-8da9-ce2b5c891b16","html_url":"https://github.com/gagolews/clustering-benchmarks","commit_stats":{"total_commits":117,"total_committers":2,"mean_commits":58.5,"dds":"0.042735042735042694","last_synced_commit":"4b59be94c124a6be3234906ae3200b4611ef4b92"},"previous_names":[],"tags_count":8,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gagolews%2Fclustering-benchmarks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gagolews%2Fclustering-benchmarks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gagolews%2Fclustering-benchmarks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gagolews%2Fclustering-benchmarks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gagolews","download_url":"https://codeload.github.com/gagolews/clustering-benchmarks/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248155001,"owners_count":21056542,"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":["benchmark-suite","benchmarking","cluster","cluster-analysis","clustering","clustering-algorithms","clustering-benchmarks","clustering-evaluation","data","data-science","dataset","datasets","ground-truth","machine-learning"],"created_at":"2024-11-22T23:18:40.002Z","updated_at":"2025-04-10T03:56:14.105Z","avatar_url":"https://github.com/gagolews.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003ca href=\"https://clustering-benchmarks.gagolewski.com\"\u003e\u003cimg src=\"https://www.gagolewski.com/_static/img/clustbench.png\" align=\"right\" height=\"128\" width=\"128\" /\u003e\u003c/a\u003e\n# [A Framework for Benchmarking Clustering Algorithms](https://clustering-benchmarks.gagolewski.com/)\n\nMaintained/edited/authored by [Marek Gagolewski](https://www.gagolewski.com).\n\nThis project aims to:\n\n* **aggregate, polish, and standardise the existing clustering benchmark\n    batteries** referred to across the machine learning and data mining\n    literature,\n* introduce **new datasets** of different dimensionalities,\n    sizes, and cluster types,\n* propose a **consistent methodology** for evaluating clustering algorithms.\n\nSee \u003chttps://clustering-benchmarks.gagolewski.com/\u003e for more details.\n\n**How to cite**:\nGagolewski M., A framework for benchmarking clustering algorithms,\n*SoftwareX* **20**, 2022, 101270, \u003chttps://clustering-benchmarks.gagolewski.com\u003e,\nDOI: [10.1016/j.softx.2022.101270](https://doi.org/10.1016/j.softx.2022.101270).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgagolews%2Fclustering-benchmarks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgagolews%2Fclustering-benchmarks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgagolews%2Fclustering-benchmarks/lists"}