{"id":38511206,"url":"https://github.com/aai-institute/kyle","last_synced_at":"2026-01-17T06:22:12.221Z","repository":{"id":39799722,"uuid":"377495696","full_name":"aai-institute/kyle","owner":"aai-institute","description":"A library for calibrating classifiers and computing calibration metrics","archived":false,"fork":false,"pushed_at":"2022-11-28T12:22:44.000Z","size":12396,"stargazers_count":14,"open_issues_count":4,"forks_count":1,"subscribers_count":5,"default_branch":"develop","last_synced_at":"2025-09-23T03:23:12.443Z","etag":null,"topics":["calibration","machine-learning","ml-classifiers","transferlab"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/aai-institute.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-06-16T12:53:37.000Z","updated_at":"2025-08-02T13:11:08.000Z","dependencies_parsed_at":"2023-01-22T10:00:38.356Z","dependency_job_id":null,"html_url":"https://github.com/aai-institute/kyle","commit_stats":null,"previous_names":["aai-institute/kyle","appliedai-initiative/kyle"],"tags_count":8,"template":false,"template_full_name":null,"purl":"pkg:github/aai-institute/kyle","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aai-institute%2Fkyle","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aai-institute%2Fkyle/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aai-institute%2Fkyle/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aai-institute%2Fkyle/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aai-institute","download_url":"https://codeload.github.com/aai-institute/kyle/tar.gz/refs/heads/develop","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aai-institute%2Fkyle/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28502211,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-17T04:31:57.058Z","status":"ssl_error","status_checked_at":"2026-01-17T04:31:45.816Z","response_time":85,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["calibration","machine-learning","ml-classifiers","transferlab"],"created_at":"2026-01-17T06:22:12.108Z","updated_at":"2026-01-17T06:22:12.190Z","avatar_url":"https://github.com/aai-institute.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Kyle - a Calibration Toolkit\n\n## Note:\nThis library is currently in the alpha stage and breaking changes can happen at any time. Some\ncentral features are currently missing and will be added soon.\n\n## Overview\nThis library contains utils for measuring and visualizing calibration of probabilistic classifiers as well as for \nrecalibrating them. Currently, only methods for recalibration through post-processing are supported, although we plan\nto include calibration specific training algorithms as well in the future.\n\nKyle is model agnostic, any probabilistic classifier can be wrapped with a thin wrapper called `CalibratableModel` which\nsupports multiple calibration algorithms. For a quick intro overview of the API have a look at the calibration demo \nnotebook (the notebook with executed cells can be found in the docu).\n\nApart from tools for analysing models, kyle also offers support for developing and testing custom calibration metrics\nand algorithms. In order not to have to rely on evaluation data sets and trained models for delivering labels and confidence \nvectors, with kyle custom samplers based on fake classifiers can be constructed. A note explaining the\ntheory behind fake classifiers will be published soon.\nThese samplers can\nalso be fit on some data set in case you want to mimic it. Using the fake classifiers, an arbitrary number of ground \ntruth labels and miscalibrated confidence vectors can be generated to help you analyse your algorithms (common use cases\nwill be analysis of variance and bias of calibration metrics and benchmarking of recalibration algorithms).\n\n\nCurrently, several algorithms in kyle use the [calibration framework library](https://github.com/fabiankueppers/calibration-framework) under the hood although this is subject \nto change.\n\n## Installation\nKyle can be installed from pypi, e.g. with\n```\npip install kyle-calibration\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faai-institute%2Fkyle","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faai-institute%2Fkyle","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faai-institute%2Fkyle/lists"}