[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-aeon-toolkit--aeon":3,"tool-aeon-toolkit--aeon":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",138956,2,"2026-04-05T11:33:21",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":67,"owner_avatar_url":76,"owner_bio":77,"owner_company":78,"owner_location":78,"owner_email":79,"owner_twitter":80,"owner_website":81,"owner_url":82,"languages":83,"stars":92,"forks":93,"last_commit_at":94,"license":95,"difficulty_score":96,"env_os":97,"env_gpu":98,"env_ram":98,"env_deps":99,"category_tags":105,"github_topics":106,"view_count":23,"oss_zip_url":78,"oss_zip_packed_at":78,"status":16,"created_at":122,"updated_at":123,"faqs":124,"releases":154},3584,"aeon-toolkit\u002Faeon","aeon","A toolkit for time series machine learning and deep learning","aeon 是一个专为时间序列数据打造的开源机器学习工具包，旨在帮助用户轻松应对预测、聚类和分类等复杂任务。它完美兼容广受欢迎的 scikit-learn 生态，将前沿的深度学习方法与经典的传统算法融为一体，让用户无需在不同框架间切换，即可在一个统一的环境中完成从数据处理到模型构建的全流程。\n\n对于经常受困于时间序列分析效率低下或算法复现困难的研究者和开发者而言，aeon 提供了一站式的解决方案。它不仅收录了大量业界领先的算法，还通过 Numba 技术进行了深度优化，显著提升了计算效率，让大规模数据处理变得更加流畅。此外，aeon 高度重视科研的可复现性，为学术探索提供了坚实可靠的基础。\n\n目前，aeon 特别适合从事数据科学、人工智能研究的专业开发人员使用。虽然其异常检测、可视化等部分模块仍处于实验阶段，但核心功能已非常成熟稳定。无论你是希望快速验证新想法的科研人员，还是需要在生产环境中部署高效模型的工程师，aeon 都能成为你处理时间序列数据的得力助手，助你在这一充满挑战的领域中发现更多价值。","\u003Cp align=\"center\">\n \u003Ca href=\"https:\u002F\u002Faeon-toolkit.org\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Faeon-toolkit_aeon_readme_f0d06407efa3.png\" width=\"50%\" alt=\"aeon logo\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n# ⌛ Welcome to aeon\n\n`aeon` is an open-source toolkit for time series machine learning.\n Fully compatible with [scikit-learn](https:\u002F\u002Fscikit-learn.org), it brings together\nthe latest machine learning methods alongside a wide range of classical approaches\nfor tasks such as forecasting, clustering, and classification.\n\nOur goal is to provide a comprehensive collection of state-of-the-art time\nseries algorithms, with efficient implementations powered by `numba`, and to promote\nreproducible research in the field of time series machine learning.\n\nThe latest `aeon` release is `v1.4.0`. You can view the full changelog\n[here](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fchangelog.html).\n\nOur webpage and documentation is available at https:\u002F\u002Faeon-toolkit.org.\n\nThe following modules are still considered experimental, and the [deprecation policy](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fdeveloper_guide\u002Fdeprecation.html)\ndoes not apply:\n\n- `anomaly_detection`\n- `forecasting`\n- `segmentation`\n- `similarity_search`\n- `visualisation`\n- `transformations.collection.self_supervised`\n- `transformations.collection.imbalance`\n\n| Overview | |\n|-----------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| **CI\u002FCD** | [![github-actions-release](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Faeon-toolkit\u002Faeon\u002Frelease.yml?logo=github&label=build%20%28release%29)](https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Factions\u002Fworkflows\u002Frelease.yml) [![github-actions-main](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Faeon-toolkit\u002Faeon\u002Fpr_pytest.yml?logo=github&branch=main&label=build%20%28main%29)](https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Factions\u002Fworkflows\u002Fpr_pytest.yml) [![github-actions-nightly](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Faeon-toolkit\u002Faeon\u002Fperiodic_tests.yml?logo=github&label=build%20%28nightly%29)](https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Factions\u002Fworkflows\u002Fperiodic_tests.yml) [![docs-main](https:\u002F\u002Fimg.shields.io\u002Freadthedocs\u002Faeon-toolkit\u002Fstable?logo=readthedocs&label=docs%20%28stable%29)](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002F) [![docs-main](https:\u002F\u002Fimg.shields.io\u002Freadthedocs\u002Faeon-toolkit\u002Flatest?logo=readthedocs&label=docs%20%28latest%29)](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002F) [![codecov](https:\u002F\u002Fcodecov.io\u002Fgh\u002Faeon-toolkit\u002Faeon\u002Fgraph\u002Fbadge.svg?token=I2eve2HzSF)](https:\u002F\u002Fcodecov.io\u002Fgh\u002Faeon-toolkit\u002Faeon) [![openssf-scorecard](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Faeon-toolkit_aeon_readme_cc45548238e3.png)](https:\u002F\u002Fscorecard.dev\u002Fviewer\u002F?uri=github.com\u002Faeon-toolkit\u002Faeon) |\n| **Code** | [![!pypi](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Faeon?logo=pypi&color=blue)](https:\u002F\u002Fpypi.org\u002Fproject\u002Faeon\u002F) [![!conda](https:\u002F\u002Fimg.shields.io\u002Fconda\u002Fvn\u002Fconda-forge\u002Faeon?logo=anaconda&color=blue)](https:\u002F\u002Fanaconda.org\u002Fconda-forge\u002Faeon) [![!python-versions](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fpyversions\u002Faeon?logo=python)](https:\u002F\u002Fwww.python.org\u002F) [![!black](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcode%20style-black-000000.svg)](https:\u002F\u002Fgithub.com\u002Fpsf\u002Fblack) [![license](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-BSD%203--Clause-green?logo=style)](https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fblob\u002Fmain\u002FLICENSE) [![binder](https:\u002F\u002Fmybinder.org\u002Fbadge_logo.svg)](https:\u002F\u002Fmybinder.org\u002Fv2\u002Fgh\u002Faeon-toolkit\u002Faeon\u002Fmain?filepath=examples) |\n| **Community** | [![!discord](https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?logo=discord&label=discord&message=chat&color=lightgreen)](https:\u002F\u002Fdiscord.gg\u002FD6rzqHGKRJ) [![!linkedin](https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?logo=data:image\u002Fsvg%2bxml;base64,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&label=LinkedIn&message=news&color=lightblue)](https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Faeon-toolkit\u002F) [![!medium](https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?logo=medium&label=Medium&message=blog&color=darkblue)](https:\u002F\u002Fmedium.com\u002F@aeon.toolkit) |\n| **Affiliation** | [![numfocus](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNumFOCUS-Affiliated%20Project-orange.svg?style=flat&colorA=E1523D&colorB=007D8A)](https:\u002F\u002Fnumfocus.org\u002Fsponsored-projects\u002Faffiliated-projects) |\n\n## ⚙️ Installation\n\n`aeon` requires a Python version of 3.10 or greater. Our full installation guide is\navailable in our [documentation](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Finstallation.html).\n\nThe easiest way to install `aeon` is via pip:\n\n```bash\npip install aeon\n```\n\nSome estimators require additional packages to be installed. If you want to install\nthe full package with all optional dependencies, you can use:\n\n```bash\npip install aeon[all_extras]\n```\n\nInstructions for installation from the [GitHub source](https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon)\ncan be found [here](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fdeveloper_guide\u002Fdev_installation.html).\n\n## ⏲️ Getting started\n\nThe best place to get started for all `aeon` packages is our [getting started guide](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fgetting_started.html).\n\nBelow we provide a quick example of how to use `aeon` for classification and clustering.\n\n### Classification\u002FRegression\n\nTime series classification looks to predict class labels fore unseen series using a\nmodel fitted from a collection of time series. The framework for regression is similar,\nreplace the classifier with a regressor and the labels with continuous values.\n\n```python\nimport numpy as np\nfrom aeon.classification.distance_based import KNeighborsTimeSeriesClassifier\n\nX = np.array([[[1, 2, 3, 4, 5, 5]], # 3D array example (univariate)\n [[1, 2, 3, 4, 4, 2]], # Three samples, one channel,\n [[8, 7, 6, 5, 4, 4]]]) # six series length\ny = np.array(['low', 'low', 'high']) # class labels for each sample\n\nclf = KNeighborsTimeSeriesClassifier(distance=\"dtw\")\nclf.fit(X, y) # fit the classifier on train data\n>>> KNeighborsTimeSeriesClassifier()\n\nX_test = np.array(\n [[[2, 2, 2, 2, 2, 2]], [[5, 5, 5, 5, 5, 5]], [[6, 6, 6, 6, 6, 6]]]\n)\ny_pred = clf.predict(X_test) # make class predictions on new data\n>>> ['low' 'high' 'high']\n```\n\n### Clustering\n\nTime series clustering groups similar time series together from a collection of\ntime series.\n\n```python\nimport numpy as np\nfrom aeon.clustering import TimeSeriesKMeans\n\nX = np.array([[[1, 2, 3, 4, 5, 5]], # 3D array example (univariate)\n [[1, 2, 3, 4, 4, 2]], # Three samples, one channel,\n [[8, 7, 6, 5, 4, 4]]]) # six series length\n\nclu = TimeSeriesKMeans(distance=\"dtw\", n_clusters=2)\nclu.fit(X) # fit the clusterer on train data\n>>> TimeSeriesKMeans(distance='dtw', n_clusters=2)\n\nclu.labels_ # get training cluster labels\n>>> array([0, 0, 1])\n\nX_test = np.array(\n [[[2, 2, 2, 2, 2, 2]], [[5, 5, 5, 5, 5, 5]], [[6, 6, 6, 6, 6, 6]]]\n)\nclu.predict(X_test) # Assign clusters to new data\n>>> array([1, 0, 0])\n```\n\n## 💬 Where to ask questions\n\n| Type | Platforms |\n|------------------------------------|-----------------------------------|\n| 🐛 **Bug Reports** | [GitHub Issue Tracker] |\n| ✨ **Feature Requests & Ideas** | [GitHub Issue Tracker] & [Discord] |\n| 💻 **Usage Questions** | [GitHub Discussions] & [Discord] |\n| 💬 **General Discussion** | [GitHub Discussions] & [Discord] |\n| 🏭 **Contribution & Development** | [Discord] |\n\n[GitHub Issue Tracker]: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fissues\n[GitHub Discussions]: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fdiscussions\n[Discord]: https:\u002F\u002Fdiscord.gg\u002FD6rzqHGKRJ\n\nFor enquiries about the project or collaboration, our email is\n[contact@aeon-toolkit.org](mailto:contact@aeon-toolkit.org).\n\n## 🔨 Contributing to aeon\n\nIf you are interested in contributing to `aeon`, please see our [contributing guide](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fcontributing.html)\nand have a read through before assigning an issue and creating a pull request. Be\naware that the `latest` version of the docs is the development version, and the `stable`\nversion is the latest release.\n\nThe `aeon` developers are volunteers so please be patient with responses to comments and\npull request reviews. If you have any questions, feel free to ask using the above\nmediums.\n\n## 📚 Citation\n\nIf you use `aeon` we would appreciate a citation of the following [paper](https:\u002F\u002Fjmlr.org\u002Fpapers\u002Fv25\u002F23-1444.html):\n\n```bibtex\n@article{aeon24jmlr,\n author = {Matthew Middlehurst and Ali Ismail-Fawaz and Antoine Guillaume and Christopher Holder and David Guijo-Rubio and Guzal Bulatova and Leonidas Tsaprounis and Lukasz Mentel and Martin Walter and Patrick Sch{{\\\"a}}fer and Anthony Bagnall},\n title = {aeon: a Python Toolkit for Learning from Time Series},\n journal = {Journal of Machine Learning Research},\n year = {2024},\n volume = {25},\n number = {289},\n pages = {1--10},\n url = {http:\u002F\u002Fjmlr.org\u002Fpapers\u002Fv25\u002F23-1444.html}\n}\n```\n\nIf you let us know about your paper using `aeon`, we will happily list it [here](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fpapers_using_aeon.html).\n\n## 👥 Further information\n\n`aeon` was forked from `sktime` `v0.16.0` in 2022 by an initial group of eight core\ndevelopers. You can read more about the project's history and governance structure in\nour [About Us page](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fabout.html).\n","\u003Cp align=\"center\">\n \u003Ca href=\"https:\u002F\u002Faeon-toolkit.org\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Faeon-toolkit_aeon_readme_f0d06407efa3.png\" width=\"50%\" alt=\"aeon logo\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n# ⌛ 欢迎使用 aeon\n\n`aeon` 是一个用于时间序列机器学习的开源工具包。\n它与 [scikit-learn](https:\u002F\u002Fscikit-learn.org) 完全兼容，将最新的机器学习方法与多种经典方法相结合，适用于预测、聚类和分类等任务。\n\n我们的目标是提供一套全面且先进的时间序列算法，并借助 `numba` 实现高效运行，同时推动时间序列机器学习领域的可重复性研究。\n\n`aeon` 的最新版本为 `v1.4.0`。您可以在[这里](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fchangelog.html)查看完整的变更日志。\n\n我们的官网和文档地址为：https:\u002F\u002Faeon-toolkit.org。\n\n以下模块目前仍处于实验阶段，不适用[弃用政策](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fdeveloper_guide\u002Fdeprecation.html)：\n\n- `anomaly_detection`\n- `forecasting`\n- `segmentation`\n- `similarity_search`\n- `visualisation`\n- `transformations.collection.self_supervised`\n- `transformations.collection.imbalance`\n\n| 概述 | |\n|-----------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| **CI\u002FCD** | [![github-actions-release](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Faeon-toolkit\u002Faeon\u002Frelease.yml?logo=github&label=build%20%28release%29)](https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Factions\u002Fworkflows\u002Frelease.yml) [![github-actions-main](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Faeon-toolkit\u002Faeon\u002Fpr_pytest.yml?logo=github&branch=main&label=build%20%28main%29)](https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Factions\u002Fworkflows\u002Fpr_pytest.yml) [![github-actions-nightly](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Faeon-toolkit\u002Faeon\u002Fperiodic_tests.yml?logo=github&label=build%20%28nightly%29)](https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Factions\u002Fworkflows\u002Fperiodic_tests.yml) [![docs-main](https:\u002F\u002Fimg.shields.io\u002Freadthedocs\u002Faeon-toolkit\u002Fstable?logo=readthedocs&label=docs%20%28stable%29)](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002F) [![docs-main](https:\u002F\u002Fimg.shields.io\u002Freadthedocs\u002Faeon-toolkit\u002Flatest?logo=readthedocs&label=docs%20%28latest%29)](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002F) [![codecov](https:\u002F\u002Fcodecov.io\u002Fgh\u002Faeon-toolkit\u002Faeon\u002Fgraph\u002Fbadge.svg?token=I2eve2HzSF)](https:\u002F\u002Fcodecov.io\u002Fgh\u002Faeon-toolkit\u002Faeon) [![openssf-scorecard](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Faeon-toolkit_aeon_readme_cc45548238e3.png)](https:\u002F\u002Fscorecard.dev\u002Fviewer\u002F?uri=github.com\u002Faeon-toolkit\u002Faeon) |\n| **代码** | [![!pypi](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Faeon?logo=pypi&color=blue)](https:\u002F\u002Fpypi.org\u002Fproject\u002Faeon\u002F) [![!conda](https:\u002F\u002Fimg.shields.io\u002Fconda\u002Fvn\u002Fconda-forge\u002Faeon?logo=anaconda&color=blue)](https:\u002F\u002Fanaconda.org\u002Fconda-forge\u002Faeon) [![!python-versions](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fpyversions\u002Faeon?logo=python)](https:\u002F\u002Fwww.python.org\u002F) [![!black](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcode%20style-black-000000.svg)](https:\u002F\u002Fgithub.com\u002Fpsf\u002Fblack) [![license](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-BSD%203--Clause-green?logo=style)](https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fblob\u002Fmain\u002FLICENSE) [![binder](https:\u002F\u002Fmybinder.org\u002Fbadge_logo.svg)](https:\u002F\u002Fmybinder.org\u002Fv2\u002Fgh\u002Faeon-toolkit\u002Faeon\u002Fmain?filepath=examples) |\n| **社区** | [![!discord](https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?logo=discord&label=discord&message=chat&color=lightgreen)](https:\u002F\u002Fdiscord.gg\u002FD6rzqHGKRJ) [![!linkedin](https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?logo=data:image\u002Fsvg%2bxml;base64,PHN2ZyByb2xlPSJpbWciIGZpbGw9IiNmZmZmZmYiIHZpZXdCb3g9IjAgMCAyNCAyNCIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj48dGl0bGU+TGlua2VkSW48L3RpdGxlPjxwYXRoIGQ9Ik0yMC40NDcgMjAuNDUyaC0zLjU1NHYtNS41NjljMC0xLjMyOC0uMDI3LTMuMDM3LTEuODUyLTMuMDM3LTEuODUzIDAtMi4xMzYgMS40NDUtMi4xMzYgMi45Mzl2NS42NjdIOS.35FWIWOWhzLjQxNHYxLjU2MWguMDQ6Yy40NzctLjkgMS42MzctMS44NSAzLjM3LTEuODUgMy42MDEgMCA0LjI2NyAyLjM3IDQuMjY3IDUuNDU1djYuMjg2ek01LjMzNyA7LjQzM2MtMS.144gMA02LjA2My0uOTI2LTIuMDYzLTIuMDY1IDAtMS.13gLS.925g2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2LjA6LT2L......| 概述 | |\n|-----------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| **CI\u002FCD** | [![github-actions-release](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Faeon-toolkit\u002Faeon\u002Frelease.yml?logo=github&label=build%20%28release%29)](https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Factions\u002Fworkflows\u002Frelease.yml) [![github-actions-main](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Faeon-toolkit\u002Faeon\u002Fpr_pytest.yml?logo=github&branch=main&label=build%20%28main%29)](https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Factions\u002Fworkflows\u002Fpr_pytest.yml) [![github-actions-nightly](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Faeon-toolkit\u002Faeon\u002Fperiodic_tests.yml?logo=github&label=build%20%28nightly%29)](https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Factions\u002Fworkflows\u002Fperiodic_tests.yml) [![docs-main](https:\u002F\u002Fimg.shields.io\u002Freadthedocs\u002Faeon-toolkit\u002Fstable?logo=readthedocs&label=docs%20%28stable%29)](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002F) [![docs-main](https:\u002F\u002Fimg.shields.io\u002Freadthedocs\u002Faeon-toolkit\u002Flatest?logo=readthedocs&label=docs%20%28latest%29)](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002F) [![codecov](https:\u002F\u002Fcodecov.io\u002Fgh\u002Faeon-toolkit\u002Faeon\u002Fgraph\u002Fbadge.svg?token=I2eve2HzSF)](https:\u002F\u002Fcodecov.io\u002Fgh\u002Faeon-toolkit\u002Faeon) [![openssf-scorecard](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Faeon-toolkit_aeon_readme_cc45548238e3.png)](https:\u002F\u002Fscorecard.dev\u002Fviewer\u002F?uri=github.com\u002Faeon-toolkit\u002Faeon) |\n| **代码** | [![!pypi](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Faeon?logo=pypi&color=blue)](https:\u002F\u002Fpypi.org\u002Fproject\u002Faeon\u002F) [![!conda](https:\u002F\u002Fimg.shields.io\u002Fconda\u002Fvn\u002Fconda-forge\u002Faeon?logo=anaconda&color=blue)](https:\u002F\u002Fanaconda.org\u002Fconda-forge\u002Faeon) [![!python-versions](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fpyversions\u002Faeon?logo=python)](https:\u002F\u002Fwww.python.org\u002F) [![!black](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcode%20style-black-000000.svg)](https:\u002F\u002Fgithub.com\u002Fpsf\u002Fblack) [![license](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-BSD%203--Clause-green?logo=style)](https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fblob\u002Fmain\u002FLICENSE) [![binder](https:\u002F\u002Fmybinder.org\u002Fbadge_logo.svg)](https:\u002F\u002Fmybinder.org\u002Fv2\u002Fgh\u002Faeon-toolkit\u002Faeon\u002Fmain?filepath=examples) |\n| **社区** | [![!discord](https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?logo=discord&label=discord&message=chat&color=lightgreen)](https:\u002F\u002Fdiscord.gg\u002FD6rzqHGKRJ) [![!linkedin](https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?logo=data:image\u002Fsvg%2bxml;base64,PHN2ZyByb2xlPSJpbWciIGZpbGw9IiNmZmZmZmYiIHZpZXdCb3g9IjAgMCAyNCAyNCIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj48dGl0bGU+TGlua2VkSW48L3RpdGxlPjxwYXRoIGQ9Ik0yMC40NDcgMjAuNDUyaC0zLjU1NHYtNS41NjljMC0xLjMyOC0uMDI3LTMuMDM3LTEuODUyLTMuMDM3LTEuODUzIDAtMi4xMzYgMS40NDUtMi4xMzYgMi45Mzl2NS42NjdIOS9aVlY5aDMuNDx2MS41NjFohuMDQ6Yy40NzctLjkgMS42MzctMS44NSAzLjM3LTEuODUgMy42MDEgMCA0LjI2NyAyLjM3IDQuMjY3IDUuNDU1djYuMjg2ek01LjMzNyA3LjQzM2MtMS4xNDQgMC0yLjA2My0uOTI2LTIuMDYzLTIuMDY1IDAtMS4xMzguOTItMi.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2.063g2......\n\n## ⚙️ 安装\n\n`aeon` 需要 Python 3.10 或更高版本。我们的完整安装指南可在 [文档](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Finstallation.html) 中找到。\n\n安装 `aeon` 的最简单方法是使用 pip：\n\n```bash\npip install aeon\n```\n\n某些估计器需要安装额外的包。如果您希望安装包含所有可选依赖项的完整包，可以使用：\n\n```bash\npip install aeon[all_extras]\n```\n\n从 [GitHub 源代码](https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon) 安装的说明可在 [这里](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fdeveloper_guide\u002Fdev_installation.html) 找到。\n\n## ⏲️ 入门\n\n对于所有 `aeon` 包来说，最好的入门地点是我们的 [入门指南](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fgetting_started.html)。\n\n下面我们提供一个关于如何使用 `aeon` 进行分类和聚类的快速示例。\n\n### 分类\u002F回归\n\n时间序列分类旨在利用从一组时间序列中拟合出的模型，对未见过的序列进行类别标签预测。回归框架与此类似，只需将分类器替换为回归器，并将标签替换为连续值即可。\n\n```python\nimport numpy as np\nfrom aeon.classification.distance_based import KNeighborsTimeSeriesClassifier\n\nX = np.array([[[1, 2, 3, 4, 5, 5]], # 三维数组示例（单变量）\n [[1, 2, 3, 4, 4, 2]], # 三个样本，单通道，\n [[8, 7, 6, 5, 4, 4]]]) # 六个序列长度\ny = np.array(['low', 'low', 'high']) # 每个样本的类别标签\n\nclf = KNeighborsTimeSeriesClassifier(distance=\"dtw\")\nclf.fit(X, y) # 在训练数据上拟合分类器\n>>> KNeighborsTimeSeriesClassifier()\n\nX_test = np.array(\n [[[2, 2, 2, 2, 2, 2]], [[5, 5, 5, 5, 5, 5]], [[6, 6, 6, 6, 6, 6]]]\n)\ny_pred = clf.predict(X_test) # 对新数据进行类别预测\n>>> ['low' 'high' 'high']\n```\n\n### 聚类\n\n时间序列聚类是从一组时间序列中将相似的时间序列分组在一起。\n\n```python\nimport numpy as np\nfrom aeon.clustering import TimeSeriesKMeans\n\nX = np.array([[[1, 2, 3, 4, 5, 5]], # 三维数组示例（单变量）\n [[1, 2, 3, 4, 4, 2]], # 三个样本，单通道，\n [[8, 7, 6, 5, 4, 4]]]) # 六个序列长度\n\nclu = TimeSeriesKMeans(distance=\"dtw\", n_clusters=2)\nclu.fit(X) # 在训练数据上拟合聚类器\n>>> TimeSeriesKMeans(distance='dtw', n_clusters=2)\n\nclu.labels_ # 获取训练集的聚类标签\n>>> array([0, 0, 1])\n\nX_test = np.array(\n [[[2, 2, 2, 2, 2, 2]], [[5, 5, 5, 5, 5, 5]], [[6, 6, 6, 6, 6, 6]]]\n)\nclu.predict(X_test) # 为新数据分配聚类\n>>> array([1, 0, 0])\n```\n\n## 💬 提问渠道\n\n| 类型 | 平台 |\n|------------------------------------|------------------------------|\n| 🐛 **Bug 报告** | [GitHub Issue Tracker] |\n| ✨ **功能请求与建议** | [GitHub Issue Tracker] & [Discord] |\n| 💻 **使用问题** | [GitHub Discussions] & [Discord] |\n| 💬 **一般讨论** | [GitHub Discussions] & [Discord] |\n| 🏭 **贡献与开发** | [Discord] |\n\n[GitHub Issue Tracker]: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fissues \n[GitHub Discussions]: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fdiscussions \n[Discord]: https:\u002F\u002Fdiscord.gg\u002FD6rzqHGKRJ \n\n如需咨询项目或合作事宜，请发送邮件至 [contact@aeon-toolkit.org](mailto:contact@aeon-toolkit.org)。\n\n## 🔨 参与 aeon 开发\n\n如果您有兴趣参与 `aeon` 的开发，请参阅我们的 [贡献指南](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fcontributing.html)，并在分配 issue 和创建 pull request 之前仔细阅读。请注意，文档的 `latest` 版本是开发版本，而 `stable` 版本则是最新发布的版本。\n\n`aeon` 的开发者均为志愿者，因此请耐心等待对评论和 pull request 审查的回复。如有任何疑问，欢迎通过上述渠道提出。\n\n## 📚 引用\n\n如果您使用了 `aeon`，我们非常感谢您引用以下论文：\n\n```bibtex\n@article{aeon24jmlr,\n author = {Matthew Middlehurst and Ali Ismail-Fawaz and Antoine Guillaume and Christopher Holder and David Guijo-Rubio and Guzal Bulatova and Leonidas Tsaprounis and Lukasz Mentel and Martin Walter and Patrick Sch{{\\\"a}}fer and Anthony Bagnall},\n title = {aeon: a Python Toolkit for Learning from Time Series},\n journal = {Journal of Machine Learning Research},\n year = {2024},\n volume = {25},\n number = {289},\n pages = {1--10},\n url = {http:\u002F\u002Fjmlr.org\u002Fpapers\u002Fv25\u002F23-1444.html}\n}\n```\n\n如果您在论文中使用了 `aeon`，请告知我们，我们将很乐意将其列在 [此处](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fpapers_using_aeon.html)。\n\n## 👥 更多信息\n\n`aeon` 于 2022 年由最初的八位核心开发者从 `sktime` `v0.16.0` 分支而来。您可以在我们的 [关于我们页面](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fabout.html) 中了解更多关于项目历史和治理结构的信息。","# aeon 快速上手指南\n\n`aeon` 是一个开源的时间序列机器学习工具包，完全兼容 `scikit-learn`。它集成了最新的前沿算法与经典方法，支持时间序列预测、聚类和分类等任务，底层由 `numba` 加速以确保高效运行。\n\n## 环境准备\n\n在开始之前，请确保您的开发环境满足以下要求：\n\n* **操作系统**：Linux, macOS 或 Windows\n* **Python 版本**：3.10 或更高版本\n* **前置依赖**：建议先更新 pip 和 setuptools\n ```bash\n pip install --upgrade pip setuptools\n ```\n\n## 安装步骤\n\n### 1. 基础安装（推荐）\n安装核心功能包，适用于大多数分类和聚类任务：\n```bash\npip install aeon\n```\n\n### 2. 完整安装（可选）\n如果您需要使用所有估算器（包括需要额外依赖的高级功能），请安装包含所有可选依赖的版本：\n```bash\npip install aeon[all_extras]\n```\n\n> **提示**：国内用户若遇到下载速度慢的问题，可使用清华或阿里云镜像源加速安装：\n> ```bash\n> pip install aeon -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n> ```\n\n## 基本使用\n\n`aeon` 的 API 设计风格与 `scikit-learn` 高度一致，主要流程为：准备数据 -> 实例化模型 -> `fit` (训练) -> `predict` (预测)。\n\n时间序列数据通常格式化为三维数组 `(n_samples, n_channels, n_timepoints)`。\n\n### 1. 时间序列分类\n\n以下示例演示如何使用基于动态时间规整（DTW）距离的 K 近邻分类器：\n\n```python\nimport numpy as np\nfrom aeon.classification.distance_based import KNeighborsTimeSeriesClassifier\n\n# 准备训练数据 (3 个样本，1 个通道，6 个时间点)\nX = np.array([[[1, 2, 3, 4, 5, 5]], \n [[1, 2, 3, 4, 4, 2]], \n [[8, 7, 6, 5, 4, 4]]]) \ny = np.array(['low', 'low', 'high']) # 类别标签\n\n# 初始化并训练模型\nclf = KNeighborsTimeSeriesClassifier(distance=\"dtw\")\nclf.fit(X, y)\n\n# 准备测试数据并进行预测\nX_test = np.array(\n [[[2, 2, 2, 2, 2, 2]], [[5, 5, 5, 5, 5, 5]], [[6, 6, 6, 6, 6, 6]]]\n)\ny_pred = clf.predict(X_test)\n\nprint(y_pred)\n# 输出: ['low' 'high' 'high']\n```\n\n### 2. 时间序列聚类\n\n以下示例演示如何将相似的时间序列分组：\n\n```python\nimport numpy as np\nfrom aeon.clustering import TimeSeriesKMeans\n\n# 准备数据\nX = np.array([[[1, 2, 3, 4, 5, 5]], \n [[1, 2, 3, 4, 4, 2]], \n [[8, 7, 6, 5, 4, 4]]]) \n\n# 初始化并训练聚类模型 (设定聚为 2 类)\nclu = TimeSeriesKMeans(distance=\"dtw\", n_clusters=2)\nclu.fit(X)\n\n# 获取训练数据的聚类标签\nprint(clu.labels_)\n# 输出: [0 0 1]\n\n# 对新数据进行聚类分配\nX_test = np.array(\n [[[2, 2, 2, 2, 2, 2]], [[5, 5, 5, 5, 5, 5]], [[6, 6, 6, 6, 6, 6]]]\n)\npredictions = clu.predict(X_test)\n\nprint(predictions)\n# 输出: [1 0 0]\n```\n\n更多详细用法和高级功能，请访问官方文档：https:\u002F\u002Faeon-toolkit.org","某能源公司的数据科学团队正致力于构建工业传感器故障预测系统，需要从海量时序数据中精准识别异常模式并分类故障类型。\n\n### 没有 aeon 时\n- 团队需手动拼接多个零散库来处理时序数据，导致代码耦合度高且难以维护，经常因版本冲突引发报错。\n- 缺乏统一接口，尝试不同分类算法（如动态时间规整与深度学习模型）时需重写大量数据预处理和评估代码。\n- 传统 Python 实现的算法在长序列数据上运行极慢，单次实验耗时数小时，严重拖慢了模型迭代节奏。\n- 难以复现论文中的前沿结果，因为缺少经过验证的标准实现，研究人员花费大量时间在调试基础算法而非优化业务逻辑。\n\n### 使用 aeon 后\n- 借助 aeon 与 scikit-learn 完全兼容的统一 API，团队能像调用普通分类器一样轻松切换数十种时序算法，代码结构清晰简洁。\n- 内置基于 numba 加速的高效实现，将原本数小时的训练过程缩短至几分钟，显著提升了实验反馈速度。\n- 直接调用库中集成的经典方法与最先进（SOTA）模型，无需重复造轮子，确保了实验结果的可复现性和可靠性。\n- 利用其丰富的变换模块和可视化工具，快速完成特征工程并直观展示聚类效果，让非技术背景的运维人员也能理解模型决策。\n\naeon 通过提供高效、统一且全面的时序机器学习解决方案，将团队从繁琐的工程实现中解放出来，专注于核心业务价值的挖掘。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Faeon-toolkit_aeon_f0d06407.png","aeon-toolkit","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Faeon-toolkit_e829ac40.png","A toolkit for conducting machine learning tasks with time series data ",null,"contact@aeon-toolkit.org","aeon_toolkit","aeon-toolkit.org\u002F","https:\u002F\u002Fgithub.com\u002Faeon-toolkit",[84,88],{"name":85,"color":86,"percentage":87},"Python","#3572A5",100,{"name":89,"color":90,"percentage":91},"Dockerfile","#384d54",0,1366,266,"2026-04-04T20:27:56","BSD-3-Clause",1,"","未说明",{"notes":100,"python":101,"dependencies":102},"该工具完全兼容 scikit-learn，核心算法由 numba 加速。部分估算器需要额外的可选依赖包，可通过 'pip install aeon[all_extras]' 安装完整功能。异常检测、预测、分割等模块目前仍被视为实验性功能。","3.10+",[103,104],"scikit-learn","numba",[13,14,54,15,51],[107,108,109,103,110,111,112,113,114,115,116,117,118,119,67,120,121],"data-mining","data-science","machine-learning","time-series","time-series-analysis","time-series-anomaly-detection","time-series-classification","time-series-clustering","time-series-regression","time-series-segmentation","forecasting","deep-learning","neural-network","ai","artificial-intelligence","2026-03-27T02:49:30.150509","2026-04-06T06:45:58.633957",[125,130,135,140,145,150],{"id":126,"question_zh":127,"answer_zh":128,"source_url":129},16402,"导入 aeon.classification.convolution_based 模块（如 Arsenal）时程序卡死或耗时过长怎么办？","这是一个已知问题，通常由 Numba 编译缓存和函数签名类型注解引起。在新环境中首次导入时，如果代码中包含显式的 Numba 类型签名（如 @njit(\"float32[:](...)\" )），会导致编译过程极慢甚至看似卡死。\n\n解决方案：\n1. 维护者已确认移除这些显式类型签名可以解决该问题，让 Numba 在首次运行时自动推断类型并缓存。\n2. 对于用户而言，确保使用的是最新版本的 aeon，因为开发团队已在后续版本中移除了导致缓慢的类型签名。\n3. 如果是旧版本，首次加载可能需要较长时间，这是正常的编译过程，后续加载会使用缓存从而变快。但如果在新虚拟环境中依然无限卡死，建议升级库版本。","https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fissues\u002F2179",{"id":131,"question_zh":132,"answer_zh":133,"source_url":134},16403,"如何在本地构建和预览项目文档？修改 docstring 后如何生效？","要在本地构建文档，请进入 docs 目录并运行 make html 命令。\n\n具体步骤：\n1. 终端执行：cd docs\n2. 终端执行：make html\n\n注意事项：\n- 如果只修改了普通文档文件，重新运行上述命令即可更新。\n- 如果修改了代码中的 docstring（文档字符串），必须确保所有 API 页面被重新生成。在某些情况下，可能需要清理之前的构建缓存再重新运行 make html。\n- 构建完成后，可以直接在浏览器中打开生成的 HTML 文件查看效果，无需启动额外的服务器。目前在 Linux 和 macOS 上该流程工作正常。","https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fissues\u002F1896",{"id":136,"question_zh":137,"answer_zh":138,"source_url":139},16404,"使用 joblib 保存并加载 Arsenal 模型后进行预测时出现 TypeError 错误怎么办？","该错误通常与数据类型不匹配或多线程环境（OpenMP）有关。错误信息 \"No matching definition for argument type(s)...\" 表明输入数据的类型与模型期望的类型不一致，或者是在多进程环境下调用导致的冲突。\n\n建议排查步骤：\n1. 检查输入数据格式：确保传入 predict 方法的数据是 numpy 数组且类型正确（例如 float64），而不是字符串列表。示例中使用了 np.array(['0.0', ...], dtype=np.float64)，请确认数据清洗步骤是否正确将字符串转换为了数值。\n2. 避免在多进程（mp.Process）环境中直接调用预测：维护者指出目前不支持在 multiprocessing.Process 中使用，因为这会触发 Gnu OpenMP 的 fork() 错误。请在主进程中直接进行预测操作。\n3. 确保训练集和测试集长度一致：早期版本存在因数据长度不等导致的问题，已在后续版本修复，请确保升级到最新版。","https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fissues\u002F1696",{"id":141,"question_zh":142,"answer_zh":143,"source_url":144},16405,"在文档字符串（docstrings）中应该使用单引号还是双引号来标记代码元素？","为了保持文档渲染的一致性，应遵循以下规范：\n\n1. 使用双反引号（``code``）来标记代码元素、参数值、类型名称或特定常量。例如：``int``、``None``、``-1``。这样在生成的 API 文档中会显示为代码块样式。\n2. 避免使用单反引号（'text'）或下划线（_text_）来表示代码，因为它们在渲染时可能会变成斜体，导致混淆。\n\n示例：\n- 正确：参数 random_state 的类型应为 ``int`` 或 ``RandomState``。\n- 错误：参数 random_state 的类型应为 _int_。\n\n开发者在提交代码前应检查 docstring 格式，确保所有代码引用都使用了双反引号。","https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fissues\u002F809",{"id":146,"question_zh":147,"answer_zh":148,"source_url":149},16406,"Binder 环境无法运行某些笔记本（Notebooks）是因为缺少依赖吗？","是的，这通常是因为 Binder 的安装配置未包含笔记本所需的可选依赖项。\n\n解决方法：\n1. 项目维护者需要更新 Binder 的配置文件（如 environment.yml 或 requirements.txt），明确列出所有笔记本运行所需的可选依赖包。\n2. 如果您是该项目的贡献者，可以检查具体的笔记本文件，识别其中导入的非核心库，并将其添加到项目的可选依赖列表中。\n3. 普通用户如果遇到此问题，可以尝试在本地克隆仓库，手动安装完整依赖（包括可选依赖：pip install aeon[all] 或类似命令），然后在本地运行注本来验证是否缺少特定包，并将缺失的包名反馈给项目维护者以便修复 Binder 配置。","https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fissues\u002F307",{"id":151,"question_zh":152,"answer_zh":153,"source_url":139},16407,"Arsenal 算法在处理不等长时间序列数据时是否支持？","在报告该问题的时期，Arsenal 算法尚不完全支持不等长序列的直接处理，这曾导致训练数据和测试数据长度不一致时报错。\n\n当前状态与解决方案：\n1. 维护者已经修复了导致训练\u002F测试数据长度不等时崩溃的具体 Bug。\n2. 关于原生支持不等长序列的功能，开发团队正在讨论和实现相关能力（参考相关 PR #1746）。\n3. 临时解决方案：在使用前，建议用户先将数据预处理为等长序列（例如通过填充或截断），或者使用项目中其他明确支持不等长序列的分类器，直到 Arsenal 的原生支持完全落地。请查阅最新的官方文档确认该功能是否已在最新版本中发布。",[155,160,165,170,175,180,185,190,195,200,205,210,215,220,225,230,235,240,245,250],{"id":156,"version":157,"summary_zh":158,"released_at":159},98737,"v0.11.1","请参阅我们的[变更日志](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fchangelog.html)，以查看此版本的所有更改。\n\n本次发布将是最后一个 0.X 子版本。除补丁外，下一个版本将是 1.0.0，其中包含大量框架层面的变更。\n\n## 亮点\n* STOMP 异常检测器\n* QUANT 回归器\n* 用于相似性搜索模块的序列搜索\n* 分段线性近似（PLA）集合转换\n\n## 新贡献者\n* @wenig 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2031 中做出了首次贡献\n\n## 全体贡献者\n[@baraline](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fbaraline)、[@CodeLionX](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FCodeLionX)、[@Cyril-Meyer](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FCyril-Meyer)、[@dguijo](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fdguijo)、[@IRKnyazev](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FIRKnyazev)、[@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FMatthewMiddlehurst)、[@Moonzyyy](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FMoonzyyy)、[@TonyBagnall](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FTonyBagnall)、[@wenig](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fwenig)\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fcompare\u002Fv0.11.0...v0.11.1","2024-09-07T12:18:47",{"id":161,"version":162,"summary_zh":163,"released_at":164},98738,"v0.11.0","请参阅我们的[变更日志](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fchangelog.html)，以查看此版本的所有更改。\n\n本次发布将是最后一个 0.X 子版本。除补丁外，下一个版本将是 1.0.0，其中包含大量框架层面的变更。\n\n## 亮点\n* 新增了近邻森林分类器\n* 新增了一个用于分类和回归的可组合集成模型\n* 在 AEBiGRUNetwork、AEDRNNNetwork 和 AEAttentionBiGRUNetwork 中引入了新的深度学习网络\n* 大量修复了 bug 并改进了文档\n\n## 新贡献者\n* @PatriceJada 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1619 中完成了首次贡献\n* @IRKnyazev 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1842 中完成了首次贡献\n* @Cyril-Meyer 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1851 中完成了首次贡献\n* @Datadote 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1873 中完成了首次贡献\n* @phershbe 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1915 中完成了首次贡献\n* @Sharathchenna 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1953 中完成了首次贡献\n* @aryanpola 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1949 中完成了首次贡献\n\n## 全体贡献者\n[@aadya940](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Faadya940)、[@aryanpola](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Faryanpola)、[@baraline](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fbaraline)、[@chrisholder](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fchrisholder)、[@CodeLionX](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FCodeLionX)、[@Cyril-Meyer](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FCyril-Meyer)、[@Datadote](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FDatadote)、[@dguijo](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fdguijo)、[@ghost](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fghost)、[@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fhadifawaz1999)、[@harshithasudhakar](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fharshithasudhakar)、[@IRKnyazev](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FIRKnyazev)、[@itsdivya1309](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fitsdivya1309)、[@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FMatthewMiddlehurst)、[@Moonzyyy](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FMoonzyyy)、[@PatriceJada](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FPatriceJada)、[@phershbe](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fphershbe)、[@Sharathchenna](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FSharathchenna)、[@TonyBagnall](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FTonyBagnall)\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fcompare\u002Fv0.10.0...v0.11.0","2024-08-21T11:37:56",{"id":166,"version":167,"summary_zh":168,"released_at":169},98739,"v0.10.0","请参阅我们的[变更日志](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fchangelog.html)，以查看此版本的所有更改。\n\n## 亮点\n* 停止对 Python 3.8 的支持\n* 宣布 v1.0.0 中的弃用内容，包括移除和重构当前的预测与转换框架\n* 新的异常检测方法：DWT-MLEAD、K-Means，以及用于 PyOD 的适配器\n* 面向异常检测和分割基准数据集的新数据加载器\n* 使用 aeon 距离的新近邻树分类器，后续还将推出近邻森林。*\n* 新的基于特征和虚拟聚类器\n* 新的 FLUSS 和 BinSeg 分割器\n* 增加了用于形状子序列的可视化工具\n\n## 新贡献者\n* @futuer-szd 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1640 中做出了首次贡献\n* @Moonzyyy 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1663 中做出了首次贡献\n* @adm-unl 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1707 中做出了首次贡献\n* @Abhash297 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1736 中做出了首次贡献\n* @ermshaua 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1755 中做出了首次贡献\n\n## 全体贡献者\n\n[@aadya940](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Faadya940)、[@Abhash297](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FAbhash297)、[@adm-unl](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fadm-unl)、[@baraline](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fbaraline)、[@chrisholder](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fchrisholder)、[@CodeLionX](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FCodeLionX)、[@ermshaua](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fermshaua)、[@futuer-szd](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Ffutuer-szd)、[@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fhadifawaz1999)、[@itsdivya1309](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fitsdivya1309)、[@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FMatthewMiddlehurst)、[@Moonzyyy](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FMoonzyyy)、[@patrickzib](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fpatrickzib)、[@TonyBagnall](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FTonyBagnall)、[@zy18811](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fzy18811)\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fcompare\u002Fv0.9.0...v0.10.0","2024-07-11T09:34:00",{"id":171,"version":172,"summary_zh":173,"released_at":174},98740,"v0.9.0","请参阅我们的[变更日志](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fchangelog.html)，以查看此版本的所有更改。\n\n## 亮点\n* 新的异常检测基类和 MERLIN 异常检测器\n* 实现了 RSAST 分类器\n* 修复了管道问题，并新增了聚类和集合转换器管道类\n* 改进了深度学习模块的模型加载能力\n* 随着我们将转换迁移到新接口，进行了大量弃用操作\n\n## 新贡献者\n* @nileenagp 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1472 中做出了首次贡献\n* @jasonmokk 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1515 中做出了首次贡献\n* @nirojasva 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1383 中做出了首次贡献\n* @maxwell1503 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1563 中做出了首次贡献\n\n## 全体贡献者\n\n[@aadya940](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Faadya940)、[@AnonymousCodes911](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FAnonymousCodes911)、[@baraline](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fbaraline)、[@chrisholder](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fchrisholder)、[@CodeLionX](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FCodeLionX)、[@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fhadifawaz1999)、[@itsdivya1309](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fitsdivya1309)、[@jasonmokk](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fjasonmokk)、[@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FMatthewMiddlehurst)、[@maxwell1503](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fmaxwell1503)、[@nileenagp](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fnileenagp)、[@nirojasva](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fnirojasva)、[@TonyBagnall](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FTonyBagnall)\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fcompare\u002Fv0.8.1...v0.9.0","2024-05-31T18:59:42",{"id":176,"version":177,"summary_zh":178,"released_at":179},98741,"v0.8.1","请参阅我们的[变更日志](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fchangelog.html)，以查看此版本的所有更改。\n\n## 亮点\n* 主要为错误修复、文档改进和新增弃用内容\n* 子梯度重心平均法现已可用于聚类\n\n## 新贡献者\n* @wayneadams 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1396 中做出了首次贡献\n* @griegner 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1458 中做出了首次贡献\n* @RishavKumarSinha 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1462 中做出了首次贡献\n\n## 全体贡献者\n\n[@aadya940](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Faadya940)、[@AnonymousCodes911](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FAnonymousCodes911)、[@chrisholder](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fchrisholder)、[@CodeLionX](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FCodeLionX)、[@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fhadifawaz1999)、[@harshithasudhakar](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fharshithasudhakar)、[@itsdivya1309](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fitsdivya1309)、[@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FMatthewMiddlehurst)、[@TonyBagnall](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FTonyBagnall)、[@tvilight4](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Ftvilight4)、[@vNtzYy](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FvNtzYy)\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fcompare\u002Fv0.8.0...v0.8.1","2024-04-25T09:55:34",{"id":181,"version":182,"summary_zh":183,"released_at":184},98742,"v0.8.0","See our [changelog](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fchangelog.html) to view all changes for this release.\r\n\r\n## Highlights\r\n- Deprecations from 0.7.0 have been removed, see the package deprecation sections for more details\r\n- typing-extensions has been added as a core dependency\r\n- The following deep learners are now available for regression: `IndividualLITERegressor`, `LITETimeRegressor` and `EncoderRegressor`\r\n- The `HydraRegressor` and `MultiRocketHydraRegressor` algorithms have been implemented for regression module\r\n- A wrapper for the `tslearn` `LearningShapelets` classifier has been added\r\n- Support for unequal length in pairwise distance calculation for the SBD and MSM distances is now available, this will be expanded to other distances in time\r\n\r\n## New Contributors\r\n* @harshithasudhakar made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1299\r\n* @tvilight4 made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1213\r\n* @vNtzYy made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1329\r\n\r\n## All Contributors\r\n[@aadya940](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Faadya940), [@AnonymousCodes911](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FAnonymousCodes911), [@chrisholder](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fchrisholder), [@CodeLionX](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FCodeLionX), [@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fhadifawaz1999), [@harshithasudhakar](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fharshithasudhakar), [@itsdivya1309](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fitsdivya1309), [@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FMatthewMiddlehurst), [@TonyBagnall](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FTonyBagnall), [@tvilight4](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Ftvilight4), [@vNtzYy](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FvNtzYy)\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fcompare\u002Fv0.7.1...v0.8.0","2024-04-05T10:10:05",{"id":186,"version":187,"summary_zh":188,"released_at":189},98743,"v0.7.1","See our [changelog](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fchangelog.html) to view all changes for this release.\r\n\r\n## Highlights\r\n- Adds the `RIST`, `Hydra`, `MR-Hydra` and `QUANT` classifiers\r\n- Adds the above for regression also, as well as `MLPRegressor`, `RDSTRegressor` and simple feature-based regressors\r\n- Adds the `SBD` distance\r\n- Website updates and improvements, including advertisement for GSoC 2024!\r\n\r\n## New Contributors\r\n* @Raya679 made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1163\r\n* @itsdivya1309 made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1146\r\n* @nimanzik made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1192\r\n* @Vedant222 made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1203\r\n* @aadya940 made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1215\r\n* @AnonymousCodes911 made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1245\r\n* @CodeLionX made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1236\r\n\r\n## All Contributors\r\n[@aadya940](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Faadya940), [@AnonymousCodes911](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FAnonymousCodes911), [@baraline](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fbaraline), [@chrisholder](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fchrisholder), [@CodeLionX](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FCodeLionX), [@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fhadifawaz1999), [@itsdivya1309](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fitsdivya1309), [@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FMatthewMiddlehurst), [@nimanzik](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fnimanzik), [@Raya679](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FRaya679), [@TonyBagnall](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FTonyBagnall), [@Vedant222](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FVedant222)\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fcompare\u002Fv0.7.0...v0.7.1","2024-03-04T18:44:31",{"id":191,"version":192,"summary_zh":193,"released_at":194},98744,"v0.7.0","See our [changelog](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fchangelog.html) to view all changes for this release.\r\n\r\n## Highlights\r\n\r\n- Implementations of the `SASTTransformer` and `SASTClassifier`\r\n- `fit_predict`\u002F`fit_predict_proba` methods in `BaseClassifier` for (sensibly) estimating accuracy on train data\r\n- ResNet based auto-encoder to deep learning `clustering` module\r\n- Introducing `BaseSegmenter` for segmentation module\r\n- Python 3.12 is now available!\r\n- Various additions, documentation updates, and implementations for the `visualisation` module\r\n- Many deprecations of old and unmaintained functionality (if you wish to help maintaining these, please get in touch!)\r\n\r\n## New Contributors\r\n* @frankl1 made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F958\r\n* @andregdmitri made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1065\r\n* @jose-gilberto made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1073\r\n* @julu98 made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F1112\r\n\r\n## All Contributors\r\n\r\n[@andregdmitri](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fandregdmitri), [@baraline](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fbaraline), [@dguijo](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fdguijo), [@frankl1](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Ffrankl1), [@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fhadifawaz1999), [@hedeershowk](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fhedeershowk), [@jose-gilberto](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fjose-gilberto), [@julu98](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fjulu98), [@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FMatthewMiddlehurst), [@patrickzib](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fpatrickzib), [@TonyBagnall](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FTonyBagnall), [@xiaopu222](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fxiaopu222), [@zy18811](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fzy18811)\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fcompare\u002Fv0.6.0...v0.7.0","2024-02-09T10:57:50",{"id":196,"version":197,"summary_zh":198,"released_at":199},98745,"v0.6.0","See our [changelog](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fchangelog.html) to view all changes for this release.\r\n\r\n## Highlights\r\n\r\n- A deprecation policy is now in place for aeon and its subpackages.\r\n- New classification algorithms are available in RED CoMETS and LITETime.\r\n- A clustering subpackage for deep learning clustering has been added.\r\n- A new experimental similarity search subpackage has been added, and the annotation module has been split into segmentation and anomaly detection.\r\n- Minkowski distance has been added to distances.\r\n- Lots of small improvements and bug fixes!\r\n\r\n## New Contributors\r\n\r\n* @zy18811 made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F779\r\n* @wwzeng1 made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F843\r\n* @PaulRabich made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F906\r\n* @xiaopu222 made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F918\r\n* @akshatvishu made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F904\r\n\r\n## All Contributors\r\n\r\n[@akshatvishu](https:\u002F\u002Fgithub.com\u002Fakshatvishu), [@baraline](https:\u002F\u002Fgithub.com\u002Fbaraline), [@chrisholder](https:\u002F\u002Fgithub.com\u002Fchrisholder), [@dguijo](https:\u002F\u002Fgithub.com\u002Fdguijo), [@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fhadifawaz1999), [@kevinlu1248](https:\u002F\u002Fgithub.com\u002Fkevinlu1248), [@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002FMatthewMiddlehurst), [@PaulRabich](https:\u002F\u002Fgithub.com\u002FPaulRabich), [@TonyBagnall](https:\u002F\u002Fgithub.com\u002FTonyBagnall), [@wwzeng1](https:\u002F\u002Fgithub.com\u002Fwwzeng1), [@xiaopu222](https:\u002F\u002Fgithub.com\u002Fxiaopu222), [@zy18811](https:\u002F\u002Fgithub.com\u002Fzy18811)\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fcompare\u002Fv0.5.0...v0.6.0","2023-12-12T13:26:46",{"id":201,"version":202,"summary_zh":203,"released_at":204},98746,"v0.5.0","See our [changelog](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fchangelog.html) to view all changes for this release.\r\n\r\nFollowing this release the deprecation policy remains suspended. Future releases may have breaking changes, so it may be wise to set an upper bound on the package version. It is likely a deprecation policy will be implemented and enforced starting v0.6.0, however.\r\n\r\n## Highlights\r\n\r\n- New distance measures with ADTW and ShapeDTW (@chrisholder, @hadifawaz1999)\r\n- Multiple new functions in the benchmarking module for creating figures i.e. Critical difference diagrams (@dguijo)\r\n- New example notebooks and tidied versions of existing ones\r\n- Lots of new bugfixes and testing to keep our estimators bug free (as much as possible at least)!\r\n\r\n## New Contributors\r\n\r\n* @sylvaincom made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F671\r\n* @hedeershowk made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F739\r\n* @steenrotsman made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F746\r\n* @kgmuzungu made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F745\r\n* @kevinlu1248 made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F777\r\n\r\n## All Contributors\r\n\r\n[@chrisholder](https:\u002F\u002Fgithub.com\u002Fchrisholder), [@dguijo](https:\u002F\u002Fgithub.com\u002Fdguijo), [@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fhadifawaz1999), [@haskarb](https:\u002F\u002Fgithub.com\u002Fhaskarb), [@hedeershowk](https:\u002F\u002Fgithub.com\u002Fhedeershowk), [@kevinlu1248](https:\u002F\u002Fgithub.com\u002Fkevinlu1248), [@kgmuzungu](https:\u002F\u002Fgithub.com\u002Fkgmuzungu), [@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002FMatthewMiddlehurst), [@patrickzib](https:\u002F\u002Fgithub.com\u002Fpatrickzib), [@steenrotsman](https:\u002F\u002Fgithub.com\u002Fsteenrotsman), [@sylvaincom](https:\u002F\u002Fgithub.com\u002Fsylvaincom), [@TonyBagnall](https:\u002F\u002Fgithub.com\u002FTonyBagnall)\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fcompare\u002Fv0.4.0...v0.5.0","2023-10-05T12:40:04",{"id":206,"version":207,"summary_zh":208,"released_at":209},98747,"v0.4.0","See our [changelog](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fchangelog.html) to view all changes for this release.\r\n\r\nFollowing this release the deprecation policy remains suspended. Future releases may have breaking changes, so it may be wise to set an upper bound on the package version.\r\n\r\n## Highlights\r\n\r\n- Data downloading functions for popular classification, regression and forecasting archives are now available\r\n- Implementations for the RSTSF interval-based and the RDST shapelet-based classifiers have been added to the classification module\r\n- Time series adaptations for the PAM, CLARA, CLARANS clustering algorithms have been added to the clustering module\r\n- The interval-based forests in the classification module have been reworked to use a new base class, including speed-ups and also allowing the implementation of regression versions (RISERegressor, CIFRegressor and DrCIFRegressor)\r\n- ResNet and FCN deep learning regressors are now available\r\n- Large portions of the website documentation have been overhauled, including the examples page and introduction notebooks for data types and data loading\r\n\r\n## All Contributors\r\n\r\n[@baraline](https:\u002F\u002Fgithub.com\u002Fbaraline), [@chrisholder](https:\u002F\u002Fgithub.com\u002Fchrisholder), [@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fhadifawaz1999), [@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002FMatthewMiddlehurst), [@TonyBagnall](https:\u002F\u002Fgithub.com\u002FTonyBagnall)\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fcompare\u002Fv0.3.0...v0.4.0","2023-07-29T11:02:33",{"id":211,"version":212,"summary_zh":213,"released_at":214},98748,"v0.3.0","See our [changelog](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fchangelog.html) to view all changes for this release.\r\n\r\nFollowing this release the deprecation policy remains suspended. Future releases may have breaking changes, so it may be wise to set an upper bound on the package version.\r\n\r\n## Highlights\r\n- An interface to the MrSQM algorithm has been added to the classification module.\r\n- k-NN estimators and the Elastic Ensemble classifier now support unequal length series.\r\n- The SAX transformation has been refactored to improve performance.\r\n- A new collection transformer base class has been added to the transformations module for more efficient transformation using collections of time series.\r\n- A rework of the benchmarking module has begun, starting with the introduction of functionality from `kotsu`\r\n\r\n\r\n## New Contributors\r\n* @DBCerigo made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F379\r\n* @RafaAyGar made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F335\r\n\r\n## All Contributors\r\n\r\n[@chrisholder](https:\u002F\u002Fgithub.com\u002Fchrisholder), [@DBCerigo](https:\u002F\u002Fgithub.com\u002FDBCerigo), [@GuiArcencio](https:\u002F\u002Fgithub.com\u002FGuiArcencio), [@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fhadifawaz1999), [@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002FMatthewMiddlehurst), [@RafaAyGar](https:\u002F\u002Fgithub.com\u002FRafaAyGar), [@TonyBagnall](https:\u002F\u002Fgithub.com\u002FTonyBagnall)\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fcompare\u002Fv0.2.0...v0.3.0","2023-06-10T10:52:24",{"id":216,"version":217,"summary_zh":218,"released_at":219},98749,"v0.2.0","See our [changelog](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fchangelog.html) to view all changes for this release.\r\n\r\nFollowing this release the deprecation policy remains suspended. Future releases may have breaking changes, so it may be wise to set an upper bound on the package version.\r\n\r\n## Highlights\r\n- aeon now supports Python 3.11!\r\n- New estimators are available in the regression package, including InceptionTime (@hadifawaz1999) and FreshPRINCE (@dguijo)\r\n- The distances module has been reworked, and the distances available are now faster (@chrisholder)\r\n- The RandomDilatedShapeletTransform for collections of series is now available (@baraline)\r\n- The 'Getting Started' page on the documentation has been rewritten with clearer introductions to each module\r\n\r\n## New Contributors\r\n* @baraline made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F310\r\n* @GuzalBulatova made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F404\r\n* @dguijo made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F384\r\n\r\n## All Contributors\r\n\r\n[@baraline](https:\u002F\u002Fgithub.com\u002Fbaraline), [@chrisholder](https:\u002F\u002Fgithub.com\u002Fchrisholder), [@dguijo](https:\u002F\u002Fgithub.com\u002Fdguijo), [@GuiArcencio](https:\u002F\u002Fgithub.com\u002FGuiArcencio), [@GuzalBulatova](https:\u002F\u002Fgithub.com\u002FGuzalBulatova), [@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fhadifawaz1999), [@lmmentel](https:\u002F\u002Fgithub.com\u002Flmmentel), [@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002FMatthewMiddlehurst), [@TonyBagnall](https:\u002F\u002Fgithub.com\u002FTonyBagnall)\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fcompare\u002Fv0.1.0...v0.2.0","2023-05-12T15:58:42",{"id":221,"version":222,"summary_zh":223,"released_at":224},98750,"v0.1.0","See our [changelog](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fchangelog.html) to view all changes for this release.\r\n\r\nFollowing this release the deprecation policy remains suspended. Future releases may have breaking changes, so it may be wise to set an upper bound on the package version.\r\n\r\n## Highlights\r\n- aeon is now available on PyPI!\r\n- pandas 2 support is available for core functionality\r\n- Deep learning approaches in the classification module have been reworked and are more configurable\r\n- New estimators for classification in Inception Time (@hadifawaz1999) and WEASEL 2.0 (@patrickzib)\r\n- Improved transformers for selecting channels of multivariate time series (@haskarb)\r\n\r\n## New Contributors\r\n* @MatthewMiddlehurst made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F10\r\n* @aiwalter made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F13\r\n* @TonyBagnall made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F12\r\n* @patrickzib made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F58\r\n* @lmmentel made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F60\r\n* @GuiArcencio made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F66\r\n* @scorcism made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F120\r\n* @chrisholder made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F132\r\n* @haskarb made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F135\r\n* @hadifawaz1999 made their first contribution in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F134\r\n\r\n## All Contributors\r\n\r\n[@aiwalter](https:\u002F\u002Fgithub.com\u002Faiwalter), [@chrisholder](https:\u002F\u002Fgithub.com\u002Fchrisholder), [@GuiArcencio](https:\u002F\u002Fgithub.com\u002FGuiArcencio), [@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fhadifawaz1999), [@haskarb](https:\u002F\u002Fgithub.com\u002Fhaskarb), [@lmmentel](https:\u002F\u002Fgithub.com\u002Flmmentel), [@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002FMatthewMiddlehurst), [@patrickzib](https:\u002F\u002Fgithub.com\u002Fpatrickzib), [@scorcism](https:\u002F\u002Fgithub.com\u002Fscorcism), [@TonyBagnall](https:\u002F\u002Fgithub.com\u002FTonyBagnall)\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fcompare\u002Fsktime-v0.16.0...v0.1.0","2023-04-14T11:03:57",{"id":226,"version":227,"summary_zh":228,"released_at":229},98751,"v0.1.0rc0","This is an early pre-release of `aeon`. \r\n\r\nThis is mainly for testing purposes, a full changelog of changes from `sktime` v0.16.0 will be provided in a later version or the release proper.\r\n\r\nTo install `aeon` pre-releases from PyPI, use:\r\n```\r\npython -m pip install --pre aeon\r\n```\r\n\u003Cdetails>\u003Csummary>Auto generated changelog:\u003C\u002Fsummary>\r\n\u003Cp>\r\n\r\n## What's Changed\r\n### 🚀 Features\r\n* [ENH] Dictionary Classifiers by @patrickzib in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F58\r\n* [ENH] `_fit_transform` method in `BaseTransformer` by @MatthewMiddlehurst in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F91\r\n* [ENH] Add `prefer=\"threads\"` to classification `Parallel` usage by @MatthewMiddlehurst in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F93\r\n* [ENH] Speedup EAgglo by factor 5-10x by @patrickzib in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F139\r\n* [ENH] Adds WEASEL v2 (with dilation) by @patrickzib in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F160\r\n### 🐛 Bug Fixes\r\n* [BUG] Update check_n_jobs by @MatthewMiddlehurst in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F14\r\n* [BUG] Fix Imputer bugs by @aiwalter in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F24\r\n* [BUG] Remove `ComposableTimeSeriesForestRegressor` by @MatthewMiddlehurst in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F92\r\n* [BUG] Fix tag in FeatureSelection and added tests by @aiwalter in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F13\r\n### Other Changes\r\n* Update FUNDING.yml by @MatthewMiddlehurst in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F10\r\n* Comment out all GitHub actions workflows. by @MatthewMiddlehurst in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3\r\n* Remove workflow files by @MatthewMiddlehurst in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F15\r\n* Delete contrib (and update codeowners) by @TonyBagnall in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F12\r\n* [GOV] Revert CoC to remove FK changes by @aiwalter in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F17\r\n* [GOV] Removed 7 days discussion period before votings. Removed weekend rule by adding 2 days instead by @aiwalter in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F41\r\n* [GOV] CC and CoC term limitation to 2 years by @aiwalter in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F22\r\n* [FORK] Update README (IN PROGRESS) by @MatthewMiddlehurst in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F43\r\n* [GOV] Updated team page by @aiwalter in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F19\r\n* [FORK] Revert #15 \"Remove workflow files\" (MERGE WHEN REPO PUBLIC) by @MatthewMiddlehurst in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F16\r\n* License Update by @MatthewMiddlehurst in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F56\r\n* [GOV] Added CoCC members as voted by core developers by @aiwalter in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F57\r\n* [MNT] remove shellcheck from pre-commit checks by @lmmentel in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F60\r\n* [DOC] Docs disclaimer by @MatthewMiddlehurst in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F64\r\n* [MNT] Bump versions of pre-commit checks by @lmmentel in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F62\r\n* [GOV] Removed CC Observer role by @aiwalter in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F49\r\n* [ENH] kNN Classifier and Regressor reimplementations by @GuiArcencio in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F66\r\n* [BUG] Fix documentation build errors by @lmmentel in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F73\r\n* [FORK] Update config files by @MatthewMiddlehurst in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F48\r\n* [GOV] proposal: CC and CoC should have disjoint membership by @aiwalter in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F23\r\n* [MNT] Fix wrong mail by @aiwalter in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F83\r\n* [DOC] Classifier docs tidy up by @TonyBagnall in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F52\r\n* Update README by @MatthewMiddlehurst in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F63\r\n* [ENH] Remove ProximityForest classifier by @TonyBagnall in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F86\r\n* [Bug] ClaSP Bugfixes by @patrickzib in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F95\r\n* [MNT] `convolution_based` rename by @MatthewMiddlehurst in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F90\r\n* [GOV] Appointment of CC and CoC members by @aiwalter in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F20\r\n* [ENH] remove TimeSeriesSVC by @TonyBagnall in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F105\r\n* [ENH] Remove the alignment module by @TonyBagnall in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F87\r\n* [ENH] Changed grid search parallelization to use backend param from e… by @aiwalter in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F82\r\n* [MNT] Remove hcrystalball wrapper by @aiwalter in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F115\r\n* Remove duplicate function by @scorcism in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F120\r\n* [ENH] Remove fit_predict_proba from Base-Class, Use sklearn cross_val_predict instead by @patrickzib in https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F117\r\n* [ENH] make single problem loaders for equal length pro","2023-03-18T12:18:45",{"id":231,"version":232,"summary_zh":233,"released_at":234},98732,"v1.4.0","请参阅我们的[变更日志](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fchangelog.html)，以查看此版本的所有更改。\n\n## 亮点\n\n- 新增了多项原生实现的估计器，包括：ROCKAD 异常检测器；K-Shape 聚类器；ElasticEnsemble 分类器中的 TS-QUAD 配置；ETS\u002FAutoETS 和 DeepARF 预测器；以及 STL、MSTL 和 LOWESS 变换器。\n- 大多数分类和回归数据现在都从 Zenodo 加载，其中包括重新推出的多变量分类数据集档案 Multiverse。\n- 废弃 Python 3.10，并支持 Python 3.14，同时调整了许多核心依赖项的版本约束。\n- 大量的错误修复和废弃操作。\n\n## 新贡献者\n\n* @Nithurshen 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3119 中做出了首次贡献\n* @satwiksps 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3111 中做出了首次贡献\n* @rwtarpit 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3130 中做出了首次贡献\n* @TUSHARDHOKRIYA 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3167 中做出了首次贡献\n* @Lucky-Lodhi2004 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3138 中做出了首次贡献\n* @Adityakushwaha2006 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3182 中做出了首次贡献\n* @PoojasPatel013 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3134 中做出了首次贡献\n* @devesh-047 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3243 中做出了首次贡献\n* @NikVince 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3281 中做出了首次贡献\n* @nimra06 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3225 中做出了首次贡献\n* @raphaelgimenezneto 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3258 中做出了首次贡献\n* @Varshinibhargav-17 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3255 中做出了首次贡献\n* @stephanielees 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3241 中做出了首次贡献\n* @jsquaredosquared 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3187 中做出了首次贡献\n* @vickysharma-prog 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3252 中做出了首次贡献\n* @samay2504 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3169 中做出了首次贡献\n* @kennaruk 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3346 中做出了首次贡献\n\n## 全体贡献者\n\n[@Adityakushwaha2006](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FAdityakushwaha2006), [@Ahmed-Zahran02](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FAhmed-Zahran02), [@alexbanwell1](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Falexbanwell1), [@chrisholder](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fchrisholder), [@Cyril-Meyer](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FCyril-Meyer), [@devesh-047](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fdevesh-047), [@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fhadifawaz1999), [@jsquaredosquared](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fjsquaredosquared), [@kennaruk](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fkennaruk), [@lucifer4073](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Flucifer4073), [@Lucky-Lodhi2004](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FLucky-Lodhi2004)","2026-03-23T21:35:44",{"id":236,"version":237,"summary_zh":238,"released_at":239},98733,"v1.3.0","请参阅我们的[变更日志](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fchangelog.html)，以查看此版本的所有更改。\n\n## 亮点\n\n- 预测模块及其框架进行了大规模更新。新增的预测器包括 ARIMA\u002FAutoARIMA、SETAR-Tree\u002FForest、Theta、TAR\u002FSETAR 以及深度学习模型。感谢所有贡献者，包括我们 2024 年 GSoC 的学生们！\n- Shapelet 变换及扩展算法现在支持不等长时间序列，并且速度得到了大幅提升。\n- KNN 和 KMeans 算法现支持 `n_jobs` 参数，以实现多线程处理。\n- 实现了 RehabPile 数据集集合的下载功能。\n- 在 collection transformers 模块中新增了用于不平衡分类问题的 ESMOTE 实现。\n- 将时间 Mixup 对比学习（TimeMCL）算法添加到了 transformations 包中的自监督模块中。\n\n## 新贡献者\n\n* @yarikoptic 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2653 中做出了首次贡献。\n* @CodeFor2001 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2941 中做出了首次贡献。\n* @angus924 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3003 中做出了首次贡献。\n* @PipaFlores 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3029 中做出了首次贡献。\n* @sarthakuwar 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2993 中做出了首次贡献。\n* @OutragedOctopus 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F3036 中做出了首次贡献。\n\n## 全体贡献者\n\n[@alexbanwell1](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Falexbanwell1), [@angus924](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fangus924), [@aryanpola](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Faryanpola), [@baraline](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fbaraline), [@chrisholder](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fchrisholder), [@CodeFor2001](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FCodeFor2001), [@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fhadifawaz1999), [@inclinedadarsh](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Finclinedadarsh), [@Kaustbh](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FKaustbh), [@kavya-r30](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fkavya-r30), [@LinGinQiu](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FLinGinQiu), [@lucifer4073](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Flucifer4073), [@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FMatthewMiddlehurst), [@OutragedOctopus](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FOutragedOctopus), [@PipaFlores](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FPipaFlores), [@Ramana-Raja](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FRamana-Raja), [@sarthakuwar](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fsarthakuwar), [@shinymack](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fshinymack), [@TinaJin0228](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FTinaJin0228), [@TonyBagnall](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FTonyBagnall), [@yarikoptic](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fyarikoptic)\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fcompare\u002Fv1.2.0...v1.3.0","2025-09-09T12:05:12",{"id":241,"version":242,"summary_zh":243,"released_at":244},98734,"v1.2.0","请参阅我们的 [变更日志](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fchangelog.html)，以查看此版本的所有更改。\n\n## 亮点\n\n- `aeon` v1.2.0 已停止对 Python 3.9 的支持，目前支持的版本为 Python 3.10 至 3.13。\n- 实现了针对整组时间序列的异常检测框架，并将模块重构为 `anomaly_detection.collection` 和 `anomaly_detection.series` 子模块。\n- `ProximityForest` 和 `ProximityTree` 分类器已得到改进，支持不等长和多变量时间序列，同时运行速度也显著提升。\n- 新增了 `TD-MVDC` 分类器的实现。\n- 预测模块得到了增强，增加了直接预测和递归预测方法，并引入了如 ETS 等新算法。该模块仍处于早期开发阶段，我们预计在未来的版本中会有框架上的调整。\n- 相似性搜索模块经过大幅重写，以符合 `aeon` 其他模块所采用的风格化框架。更多详情请参阅模块示例和文档。\n- 在 `aeon.transformations.collection.self_supervised` 中新增了一个用于自监督学习的实验性子包，首先实现了 `TRILITE` 算法。\n\n## 新贡献者\n\n* @Ahmed-Zahran02 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2737 中做出了首次贡献。\n* @SomtoOnyekwelu 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2764 中做出了首次贡献。\n* @saadaltohamy 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2644 中做出了首次贡献。\n* @nMaax 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2622 中做出了首次贡献。\n* @AnaghDeshpande 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2546 中做出了首次贡献。\n\n## 全体贡献者\n\n[@aadya940](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Faadya940), [@adityagh006](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fadityagh006), [@Ahmed-Zahran02](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FAhmed-Zahran02), [@AnaghDeshpande](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FAnaghDeshpande), [@aryanpola](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Faryanpola), [@baraline](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fbaraline), [@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fhadifawaz1999), [@inclinedadarsh](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Finclinedadarsh), [@Kaustbh](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FKaustbh), [@kavya-r30](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fkavya-r30), [@kevinzb56](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fkevinzb56), [@lucifer4073](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Flucifer4073), [@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FMatthewMiddlehurst), [@nMaax](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FnMaax), [@patrickzib](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fpatrickzib), [@pattplatt](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fpattplatt), [@Ramana-Raja](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FRamana-Raja), [@saadaltohamy](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fsaadaltohamy), [@SebastianSchmidl](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FSebastianSchmidl), [@shinymack](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fshinymack), [@SomtoOnyekwelu](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FSomtoOnyekwelu), [@steenrotsman](https:\u002F","2025-06-23T10:27:53",{"id":246,"version":247,"summary_zh":248,"released_at":249},98735,"v1.1.0","请参阅我们的[变更日志](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Fstable\u002Fchangelog.html)，以查看此版本的所有更改。\n\n## 亮点\n\n- 现已支持 Python 3.13，并提高了依赖项的版本范围。\n- `df-list` 集合现在要求采用 (`n_cases`, `n_channels`, `n_timepoints`) 的格式。请确保列表中的每个 DataFrame 都将通道作为第一维，时间点作为第二维。\n- 新增了 ROCKAD 异常检测器。\n- 新增了 KASBA 聚类器。\n- 大量文档改进和错误修复。\n\n## 新贡献者\n* @vedpawar2254 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2424 中做出了首次贡献。\n* @adilsonmedronha 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2440 中做出了首次贡献。\n* @dschrempf 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2464 中做出了首次贡献。\n* @inclinedadarsh 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2489 中做出了首次贡献。\n* @shinymack 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2488 中做出了首次贡献。\n* @kevinzb56 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2487 中做出了首次贡献。\n* @Akhil-Jasson 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2483 中做出了首次贡献。\n* @sumana-2705 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2419 中做出了首次贡献。\n* @YashviMehta03 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2494 中做出了首次贡献。\n* @lucifer4073 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2518 中做出了首次贡献。\n* @Nikitas100 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2484 中做出了首次贡献。\n* @tanishy7777 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2613 中做出了首次贡献。\n* @Kaustbh 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2589 中做出了首次贡献。\n* @TinaJin0228 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2717 中做出了首次贡献。\n* @ayushsingh9720 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2617 中做出了首次贡献。\n* @HaroonAzamFiza 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2738 中做出了首次贡献。\n* @adityagh006 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2735 中做出了首次贡献。\n* @Val-2608 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2640 中做出了首次贡献。\n* @Ramana-Raja 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2704 中做出了首次贡献。\n\n## 全体贡献者\n\n[@aadya940](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Faadya940), [@adilsonmedronha](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fadilsonmedronha), [@adityagh006](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fadityagh006), [@Akhil-Jasson](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FAkhil-Jasson), [@aryanpola](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Faryanpola), [@ayushsingh9720](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fayushsingh9720), [@chrisholder](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fchrisholder), [@Cyril-Meyer](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FCyril-Meyer), [@dschrempf](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fdschrempf), [@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fhadifawaz1999), [@HaroonAzamFi","2025-04-13T15:11:06",{"id":251,"version":252,"summary_zh":253,"released_at":254},98736,"v1.0.0","aeon 的首个主要版本发布。\n\n请参阅我们的[变更日志](https:\u002F\u002Fwww.aeon-toolkit.org\u002Fen\u002Flatest\u002Fchangelog.html)，以查看此版本的所有更改。\n\n## 亮点\n\n- 引入了一个新的实验性预测模块，取代了旧的模块（目前功能较为有限，但我们将在未来扩展该框架及可用的估计器）。\n- 重构并扩展了聚类模块，包括深度学习聚类。\n- 显式地将转换模块拆分为序列转换器和集合转换器。\n- 扩展了异常检测模块。\n- 全新测试套件，代码覆盖率现已达到 91%。\n- 增强了可视化工具。\n- 改进了文档和示例。\n- 引入了更多支持多变量的深度学习估计器。\n\n## 新贡献者\n\n* @notaryanramani 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2029 中做出了首次贡献\n* @danielroberts20 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2064 中做出了首次贡献\n* @ferewi 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2091 中做出了首次贡献\n* @LinGinQiu 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2141 中做出了首次贡献\n* @georgejl7 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2173 中做出了首次贡献\n* @fspinna 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2062 中做出了首次贡献\n* @emmanuel-ferdman 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2275 中做出了首次贡献\n* @pattplatt 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2342 中做出了首次贡献\n* @kavya-r30 在 https:\u002F\u002Fgithub.com\u002Faeon-toolkit\u002Faeon\u002Fpull\u002F2364 中做出了首次贡献\n\n## 全体贡献者\n\n[@aadya940](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Faadya940), [@alexbanwell1](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Falexbanwell1), [@aryanpola](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Faryanpola), [@baraline](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fbaraline), [@chrisholder](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fchrisholder), [@Cyril-Meyer](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FCyril-Meyer), [@danielroberts20](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fdanielroberts20), [@Datadote](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FDatadote), [@emmanuel-ferdman](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Femmanuel-ferdman), [@ferewi](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fferewi), [@fspinna](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Ffspinna), [@georgejl7](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fgeorgejl7), [@griegner](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fgriegner), [@hadifawaz1999](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fhadifawaz1999), [@IRKnyazev](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FIRKnyazev), [@itsdivya1309](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fitsdivya1309), [@kavya-r30](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fkavya-r30), [@LinGinQiu](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FLinGinQiu), [@MatthewMiddlehurst](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FMatthewMiddlehurst), [@Moonzyyy](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FMoonzyyy), [@notaryanramani](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fnotaryanramani), [@patrickzib](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fpatrickzib), [@pattplatt](https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fpattplatt), [@SebastianSchmidl](htt","2024-11-28T10:35:57"]