{"full_name":"scikit-learn/scikit-learn","owner":"scikit-learn","name":"scikit-learn","url":"https://github.com/scikit-learn/scikit-learn","description":"scikit-learn: machine learning in Python","homepage":"https://scikit-learn.org","topics":[],"language":"Python","license":"BSD-3-Clause","avatar":"https://avatars.githubusercontent.com/u/365630?v=4","created_at":"2010-08-17T09:43:38Z","pushed_at":"2026-11-10T03:58:32Z","metrics":{"stars":68123,"forks":27660,"watchers":2123,"issues":12371,"prs":21776,"releases":51,"issues_open":null,"issues_closed":null,"prs_open":null,"prs_closed":null,"prs_merged":null,"discussions":883},"growth":{"day":{"stars":21,"forks":2,"base_day":"2026-11-09"}},"history":{"dates":["2026-11-09","2026-11-10"],"stars":[68102,68123],"forks":[27658,27660],"watchers":[2123,2123],"issues_open":[null,null],"prs_open":[null,null]},"boards":{},"same_owner":[],"issues":[{"number":11536,"title":"Liblinear convergence failure everywhere?","comments":70,"created_at":"2018-07-15T21:14:11Z"},{"number":30662,"title":"HistGradientBoostingClassifier/Regressor 15x slowdown on small data problems compared to disabled OpenMP threading","comments":68,"created_at":"2025-01-17T13:19:13Z"},{"number":3855,"title":"Resampler estimators that change the sample size in fitting","comments":68,"created_at":"2014-11-15T11:56:34Z"},{"number":5884,"title":"Implement Gower Similarity Coefficient","comments":63,"created_at":"2015-11-19T15:04:22Z"},{"number":25888,"title":"PERF `PairwiseDistancesReductions` subsequent work","comments":55,"created_at":"2023-03-17T08:16:19Z"},{"number":3482,"title":"Generalized additive models (GAMs)?","comments":52,"created_at":"2014-07-24T18:45:01Z"},{"number":9606,"title":"feature_importances_ should be a method in the ideal design","comments":47,"created_at":"2017-08-22T23:45:25Z"},{"number":735,"title":"Fixup naive_bayes","comments":45,"created_at":"2012-03-27T21:11:34Z"}],"discussions":[{"number":35287,"title":"How do you turn customer behaviour data into useful ML features and real business decisions?","comments":6,"category":"Q&A","created_at":"2026-11-01T20:14:37Z"},{"number":35148,"title":"Smart App Control compatibility guidance for scikit-learn 1.9.1 Windows cp313 wheel","comments":5,"category":"Q&A","created_at":"2026-10-15T13:09:14Z"},{"number":35051,"title":"Proposal: Practical Discriminant Analysis Example / Contribution","comments":2,"category":"Show and tell","created_at":"2026-09-29T15:00:12Z"},{"number":35025,"title":"tom","comments":3,"category":"General","created_at":"2026-09-24T09:44:50Z"},{"number":34998,"title":"Should the `log_loss` metric really be named the `mean_log_loss`?","comments":2,"category":"General","created_at":"2026-09-20T05:56:41Z"},{"number":34797,"title":"L-BFGS loss_gradient: is there real headroom in the Array API helpers on NumPy inputs?","comments":5,"category":"Q&A","created_at":"2026-08-23T07:24:42Z"},{"number":34780,"title":"Blog link discrepancy","comments":1,"category":"General","created_at":"2026-08-19T13:37:57Z"},{"number":34684,"title":"Is it appropriate to use the point order produced by np.where() as input for an SVM baseline?","comments":1,"category":"Ideas","created_at":"2026-08-09T04:50:57Z"}],"latest_release":{"name":"Scikit-learn 1.9.1","tag":"1.9.1","published_at":"2026-09-11T09:38:12Z","body":"We're happy to announce the 1.9.1 release.\r\n\r\nThis release contains a few bug fixes and is the first version supporting Python 3.15.\r\n\r\nYou can see the changelog here: https://scikit-learn.org/stable/whats_new/v1.9.html#version-1-9-1\r\n\r\nYou can upgrade with pip as usual:\r\n\r\n```\r\npip install -U scikit-learn\r\n```\r\n\r\nThe conda-forge builds can be installed using:\r\n\r\n```\r\nconda install -c conda-forge scikit-learn\r\n```\r\n\r\nThanks to everyone who contributed to this release !"},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-10T09:35:25Z","history_start":"2026-09-06"}