[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-annoviko--pyclustering":3,"tool-annoviko--pyclustering":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":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":80,"owner_email":81,"owner_twitter":79,"owner_website":79,"owner_url":82,"languages":83,"stars":115,"forks":116,"last_commit_at":117,"license":118,"difficulty_score":23,"env_os":119,"env_gpu":120,"env_ram":120,"env_deps":121,"category_tags":129,"github_topics":130,"view_count":23,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":141,"updated_at":142,"faqs":143,"releases":173},2147,"annoviko\u002Fpyclustering","pyclustering","pyclustering is a Python, C++ data mining library.","pyclustering 是一款专注于数据挖掘的开源库，同时提供 Python 和 C++ 两种语言实现。它主要解决了用户在聚类分析、振荡网络及神经网络建模方面的算法需求，内置了多种经典与前沿算法（如 X-Means 等），帮助用户高效处理数据分组与模式识别任务。\n\n该工具特别适合数据科学家、算法研究人员以及需要底层算法控制的开发者使用。其独特的技术亮点在于“双核”架构：每个算法都同时拥有 Python 和 C++ 版本。默认情况下，pyclustering 会自动调用高性能的 C++ 核心以确保运算速度；若遇到平台兼容性问题或用户有特殊调试需求，也可通过简单参数切换至纯 Python 实现，兼顾了执行效率与灵活性。此外，它依赖常见的科学计算库（如 NumPy、SciPy），易于集成到现有的数据分析工作流中。\n\n需要注意的是，该项目自 2021 年起已停止官方维护，不再更新新功能或修复问题。因此，它更适合用于学习算法原理、复现历史研究或作为轻量级项目的参考实现，而在追求长期稳定支持的生产环境中，建议用户评估替代方案。","Warning - Attention Users\n=========================\n\n**Please be aware that the `pyclustering` library is no longer supported as of 2021 due to personal reasons. There will be no further maintenance, issue addressing, or feature development for this repository.**\n\n**For continued usage, I recommend seeking alternative solutions.**\n\n**Thank you for your understanding.**\n\n\nBuild Status\n============\n\n|Build Status Linux MacOS| |Build Status Win| |Coverage Status| |PyPi| |Download Counter| |JOSS|\n\n\nPyClustering\n============\n\n**pyclustering** is a Python, C++ data mining library (clustering\nalgorithm, oscillatory networks, neural networks). The library provides\nPython and C++ implementations (C++ pyclustering library) of each algorithm or\nmodel. C++ pyclustering library is a part of pyclustering and supported for\nLinux, Windows and MacOS operating systems.\n\n**Version**: 0.11.dev\n\n**License**: The 3-Clause BSD License\n\n**E-Mail**: pyclustering@yandex.ru\n\n**Documentation**: https:\u002F\u002Fpyclustering.github.io\u002Fdocs\u002F0.10.1\u002Fhtml\u002F\n\n**Homepage**: https:\u002F\u002Fpyclustering.github.io\u002F\n\n**PyClustering Wiki**: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fwiki\n\n\n\nDependencies\n============\n\n**Required packages**: scipy, matplotlib, numpy, Pillow\n\n**Python version**: >=3.6 (32-bit, 64-bit)\n\n**C++ version**: >= 14 (32-bit, 64-bit)\n\n\n\nPerformance\n===========\n\nEach algorithm is implemented using Python and C\u002FC++ language, if your platform is not supported then Python\nimplementation is used, otherwise C\u002FC++. Implementation can be chosen by `ccore` flag (by default it is always\n'True' and it means that C\u002FC++ is used), for example:\n\n.. code:: python\n\n    # As by default - C\u002FC++ part of the library is used\n    xmeans_instance_1 = xmeans(data_points, start_centers, 20, ccore=True);\n\n    # The same - C\u002FC++ part of the library is used by default\n    xmeans_instance_2 = xmeans(data_points, start_centers, 20);\n\n    # Switch off core - Python is used\n    xmeans_instance_3 = xmeans(data_points, start_centers, 20, ccore=False);\n\n\n\nInstallation\n============\n\nInstallation using pip3 tool:\n\n.. code:: bash\n\n    $ pip3 install pyclustering\n\nManual installation from official repository using Makefile:\n\n.. code:: bash\n\n    # get sources of the pyclustering library, for example, from repository\n    $ mkdir pyclustering\n    $ cd pyclustering\u002F\n    $ git clone https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering.git .\n\n    # compile CCORE library (core of the pyclustering library).\n    $ cd ccore\u002F\n    $ make ccore_64bit      # build for 64-bit OS\n\n    # $ make ccore_32bit    # build for 32-bit OS\n\n    # return to parent folder of the pyclustering library\n    $ cd ..\u002F\n\n    # install pyclustering library\n    $ python3 setup.py install\n\n    # optionally - test the library\n    $ python3 setup.py test\n\nManual installation using CMake:\n\n.. code:: bash\n\n    # get sources of the pyclustering library, for example, from repository\n    $ mkdir pyclustering\n    $ cd pyclustering\u002F\n    $ git clone https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering.git .\n\n    # generate build files.\n    $ mkdir build\n    $ cmake ..\n\n    # build pyclustering-shared target depending on what was generated (Makefile or MSVC solution)\n    # if Makefile has been generated then\n    $ make pyclustering-shared\n\n    # return to parent folder of the pyclustering library\n    $ cd ..\u002F\n\n    # install pyclustering library\n    $ python3 setup.py install\n\n    # optionally - test the library\n    $ python3 setup.py test\n\nManual installation using Microsoft Visual Studio solution:\n\n1. Clone repository from: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering.git\n2. Open folder `pyclustering\u002Fccore`\n3. Open Visual Studio project `ccore.sln`\n4. Select solution platform: `x86` or `x64`\n5. Build `pyclustering-shared` project.\n6. Add pyclustering folder to python path or install it using setup.py\n\n.. code:: bash\n\n    # install pyclustering library\n    $ python3 setup.py install\n\n    # optionally - test the library\n    $ python3 setup.py test\n\n\n\nProposals, Questions, Bugs\n==========================\n\nIn case of any questions, proposals or bugs related to the pyclustering please contact to pyclustering@yandex.ru or create an issue here.\n\n\n\nPyClustering Status\n===================\n\n+----------------------+------------------------------+-------------------------------------+---------------------------------+\n| Branch               | master                       | 0.10.dev                            | 0.10.1.rel                      |\n+======================+==============================+=====================================+=================================+\n| Build (Linux, MacOS) | |Build Status Linux MacOS|   | |Build Status Linux MacOS 0.10.dev| | |Build Status Linux 0.10.1.rel| |\n+----------------------+------------------------------+-------------------------------------+---------------------------------+\n| Build (Win)          | |Build Status Win|           | |Build Status Win 0.10.dev|         | |Build Status Win 0.10.1.rel|   |\n+----------------------+------------------------------+-------------------------------------+---------------------------------+\n| Code Coverage        | |Coverage Status|            | |Coverage Status 0.10.dev|          | |Coverage Status 0.10.1.rel|    |\n+----------------------+------------------------------+-------------------------------------+---------------------------------+\n\n\n\nCite the Library\n================\n\nIf you are using pyclustering library in a scientific paper, please, cite the library:\n\nNovikov, A., 2019. PyClustering: Data Mining Library. Journal of Open Source Software, 4(36), p.1230. Available at: http:\u002F\u002Fdx.doi.org\u002F10.21105\u002Fjoss.01230.\n\nBibTeX entry:\n\n.. code::\n\n    @article{Novikov2019,\n        doi         = {10.21105\u002Fjoss.01230},\n        url         = {https:\u002F\u002Fdoi.org\u002F10.21105\u002Fjoss.01230},\n        year        = 2019,\n        month       = {apr},\n        publisher   = {The Open Journal},\n        volume      = {4},\n        number      = {36},\n        pages       = {1230},\n        author      = {Andrei Novikov},\n        title       = {{PyClustering}: Data Mining Library},\n        journal     = {Journal of Open Source Software}\n    }\n\n\n\nBrief Overview of the Library Content\n=====================================\n\n**Clustering algorithms and methods (module pyclustering.cluster):**\n\n+------------------------+---------+-----+\n| Algorithm              | Python  | C++ |\n+========================+=========+=====+\n| Agglomerative          | ✓       | ✓   |\n+------------------------+---------+-----+\n| BANG                   | ✓       |     |\n+------------------------+---------+-----+\n| BIRCH                  | ✓       |     |\n+------------------------+---------+-----+\n| BSAS                   | ✓       | ✓   |\n+------------------------+---------+-----+\n| CLARANS                | ✓       |     |\n+------------------------+---------+-----+\n| CLIQUE                 | ✓       | ✓   |\n+------------------------+---------+-----+\n| CURE                   | ✓       | ✓   |\n+------------------------+---------+-----+\n| DBSCAN                 | ✓       | ✓   |\n+------------------------+---------+-----+\n| Elbow                  | ✓       | ✓   |\n+------------------------+---------+-----+\n| EMA                    | ✓       |     |\n+------------------------+---------+-----+\n| Fuzzy C-Means          | ✓       | ✓   |\n+------------------------+---------+-----+\n| GA (Genetic Algorithm) | ✓       | ✓   |\n+------------------------+---------+-----+\n| G-Means                | ✓       | ✓   |\n+------------------------+---------+-----+\n| HSyncNet               | ✓       | ✓   |\n+------------------------+---------+-----+\n| K-Means                | ✓       | ✓   |\n+------------------------+---------+-----+\n| K-Means++              | ✓       | ✓   |\n+------------------------+---------+-----+\n| K-Medians              | ✓       | ✓   |\n+------------------------+---------+-----+\n| K-Medoids              | ✓       | ✓   |\n+------------------------+---------+-----+\n| MBSAS                  | ✓       | ✓   |\n+------------------------+---------+-----+\n| OPTICS                 | ✓       | ✓   |\n+------------------------+---------+-----+\n| ROCK                   | ✓       | ✓   |\n+------------------------+---------+-----+\n| Silhouette             | ✓       | ✓   |\n+------------------------+---------+-----+\n| SOM-SC                 | ✓       | ✓   |\n+------------------------+---------+-----+\n| SyncNet                | ✓       | ✓   |\n+------------------------+---------+-----+\n| Sync-SOM               | ✓       |     |\n+------------------------+---------+-----+\n| TTSAS                  | ✓       | ✓   |\n+------------------------+---------+-----+\n| X-Means                | ✓       | ✓   |\n+------------------------+---------+-----+\n\n\n**Oscillatory networks and neural networks (module pyclustering.nnet):**\n\n+--------------------------------------------------------------------------------+---------+-----+\n| Model                                                                          | Python  | C++ |\n+================================================================================+=========+=====+\n| CNN (Chaotic Neural Network)                                                   | ✓       |     |\n+--------------------------------------------------------------------------------+---------+-----+\n| fSync (Oscillatory network based on Landau-Stuart equation and Kuramoto model) | ✓       |     |\n+--------------------------------------------------------------------------------+---------+-----+\n| HHN (Oscillatory network based on Hodgkin-Huxley model)                        | ✓       | ✓   |\n+--------------------------------------------------------------------------------+---------+-----+\n| Hysteresis Oscillatory Network                                                 | ✓       |     |\n+--------------------------------------------------------------------------------+---------+-----+\n| LEGION (Local Excitatory Global Inhibitory Oscillatory Network)                | ✓       | ✓   |\n+--------------------------------------------------------------------------------+---------+-----+\n| PCNN (Pulse-Coupled Neural Network)                                            | ✓       | ✓   |\n+--------------------------------------------------------------------------------+---------+-----+\n| SOM (Self-Organized Map)                                                       | ✓       | ✓   |\n+--------------------------------------------------------------------------------+---------+-----+\n| Sync (Oscillatory network based on Kuramoto model)                             | ✓       | ✓   |\n+--------------------------------------------------------------------------------+---------+-----+\n| SyncPR (Oscillatory network for pattern recognition)                           | ✓       | ✓   |\n+--------------------------------------------------------------------------------+---------+-----+\n| SyncSegm (Oscillatory network for image segmentation)                          | ✓       | ✓   |\n+--------------------------------------------------------------------------------+---------+-----+\n\n\n**Graph Coloring Algorithms (module pyclustering.gcolor):**\n\n+------------------------+---------+-----+\n| Algorithm              | Python  | C++ |\n+========================+=========+=====+\n| DSatur                 | ✓       |     |\n+------------------------+---------+-----+\n| Hysteresis             | ✓       |     |\n+------------------------+---------+-----+\n| GColorSync             | ✓       |     |\n+------------------------+---------+-----+\n\n\n**Containers (module pyclustering.container):**\n\n+------------------------+---------+-----+\n| Algorithm              | Python  | C++ |\n+========================+=========+=====+\n| KD Tree                | ✓       | ✓   |\n+------------------------+---------+-----+\n| CF Tree                | ✓       |     |\n+------------------------+---------+-----+\n\n\n\nExamples in the Library\n=======================\n\nThe library contains examples for each algorithm and oscillatory network model:\n\n**Clustering examples:** ``pyclustering\u002Fcluster\u002Fexamples``\n\n**Graph coloring examples:** ``pyclustering\u002Fgcolor\u002Fexamples``\n\n**Oscillatory network examples:** ``pyclustering\u002Fnnet\u002Fexamples``\n\n.. image:: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fblob\u002Fmaster\u002Fdocs\u002Fimg\u002Fexample_cluster_place.png\n   :alt: Where are examples?\n\n\n\nCode Examples\n=============\n\n**Data clustering by CURE algorithm**\n\n.. code:: python\n\n    from pyclustering.cluster import cluster_visualizer;\n    from pyclustering.cluster.cure import cure;\n    from pyclustering.utils import read_sample;\n    from pyclustering.samples.definitions import FCPS_SAMPLES;\n\n    # Input data in following format [ [0.1, 0.5], [0.3, 0.1], ... ].\n    input_data = read_sample(FCPS_SAMPLES.SAMPLE_LSUN);\n\n    # Allocate three clusters.\n    cure_instance = cure(input_data, 3);\n    cure_instance.process();\n    clusters = cure_instance.get_clusters();\n\n    # Visualize allocated clusters.\n    visualizer = cluster_visualizer();\n    visualizer.append_clusters(clusters, input_data);\n    visualizer.show();\n\n**Data clustering by K-Means algorithm**\n\n.. code:: python\n\n    from pyclustering.cluster.kmeans import kmeans, kmeans_visualizer\n    from pyclustering.cluster.center_initializer import kmeans_plusplus_initializer\n    from pyclustering.samples.definitions import FCPS_SAMPLES\n    from pyclustering.utils import read_sample\n\n    # Load list of points for cluster analysis.\n    sample = read_sample(FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS)\n\n    # Prepare initial centers using K-Means++ method.\n    initial_centers = kmeans_plusplus_initializer(sample, 2).initialize()\n\n    # Create instance of K-Means algorithm with prepared centers.\n    kmeans_instance = kmeans(sample, initial_centers)\n\n    # Run cluster analysis and obtain results.\n    kmeans_instance.process()\n    clusters = kmeans_instance.get_clusters()\n    final_centers = kmeans_instance.get_centers()\n\n    # Visualize obtained results\n    kmeans_visualizer.show_clusters(sample, clusters, final_centers)\n\n**Data clustering by OPTICS algorithm**\n\n.. code:: python\n\n    from pyclustering.cluster import cluster_visualizer\n    from pyclustering.cluster.optics import optics, ordering_analyser, ordering_visualizer\n    from pyclustering.samples.definitions import FCPS_SAMPLES\n    from pyclustering.utils import read_sample\n\n    # Read sample for clustering from some file\n    sample = read_sample(FCPS_SAMPLES.SAMPLE_LSUN)\n\n    # Run cluster analysis where connectivity radius is bigger than real\n    radius = 2.0\n    neighbors = 3\n    amount_of_clusters = 3\n    optics_instance = optics(sample, radius, neighbors, amount_of_clusters)\n\n    # Performs cluster analysis\n    optics_instance.process()\n\n    # Obtain results of clustering\n    clusters = optics_instance.get_clusters()\n    noise = optics_instance.get_noise()\n    ordering = optics_instance.get_ordering()\n\n    # Visualize ordering diagram\n    analyser = ordering_analyser(ordering)\n    ordering_visualizer.show_ordering_diagram(analyser, amount_of_clusters)\n\n    # Visualize clustering results\n    visualizer = cluster_visualizer()\n    visualizer.append_clusters(clusters, sample)\n    visualizer.show()\n\n**Simulation of oscillatory network PCNN**\n\n.. code:: python\n\n    from pyclustering.nnet.pcnn import pcnn_network, pcnn_visualizer\n\n    # Create Pulse-Coupled neural network with 10 oscillators.\n    net = pcnn_network(10)\n\n    # Perform simulation during 100 steps using binary external stimulus.\n    dynamic = net.simulate(50, [1, 1, 1, 0, 0, 0, 0, 1, 1, 1])\n\n    # Allocate synchronous ensembles from the output dynamic.\n    ensembles = dynamic.allocate_sync_ensembles()\n\n    # Show output dynamic.\n    pcnn_visualizer.show_output_dynamic(dynamic, ensembles)\n\n**Simulation of chaotic neural network CNN**\n\n.. code:: python\n\n    from pyclustering.cluster import cluster_visualizer\n    from pyclustering.samples.definitions import SIMPLE_SAMPLES\n    from pyclustering.utils import read_sample\n    from pyclustering.nnet.cnn import cnn_network, cnn_visualizer\n\n    # Load stimulus from file.\n    stimulus = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE3)\n\n    # Create chaotic neural network, amount of neurons should be equal to amount of stimulus.\n    network_instance = cnn_network(len(stimulus))\n\n    # Perform simulation during 100 steps.\n    steps = 100\n    output_dynamic = network_instance.simulate(steps, stimulus)\n\n    # Display output dynamic of the network.\n    cnn_visualizer.show_output_dynamic(output_dynamic)\n\n    # Display dynamic matrix and observation matrix to show clustering phenomenon.\n    cnn_visualizer.show_dynamic_matrix(output_dynamic)\n    cnn_visualizer.show_observation_matrix(output_dynamic)\n\n    # Visualize clustering results.\n    clusters = output_dynamic.allocate_sync_ensembles(10)\n    visualizer = cluster_visualizer()\n    visualizer.append_clusters(clusters, stimulus)\n    visualizer.show()\n\n\n\nIllustrations\n=============\n\n**Cluster allocation on FCPS dataset collection by DBSCAN:**\n\n.. image:: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fblob\u002Fmaster\u002Fdocs\u002Fimg\u002Ffcps_cluster_analysis.png\n   :alt: Clustering by DBSCAN\n\n**Cluster allocation by OPTICS using cluster-ordering diagram:**\n\n.. image:: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fblob\u002Fmaster\u002Fdocs\u002Fimg\u002Foptics_example_clustering.png\n   :alt: Clustering by OPTICS\n\n\n**Partial synchronization (clustering) in Sync oscillatory network:**\n\n.. image:: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fblob\u002Fmaster\u002Fdocs\u002Fimg\u002Fsync_partial_synchronization.png\n   :alt: Partial synchronization in Sync oscillatory network\n\n\n**Cluster visualization by SOM (Self-Organized Feature Map)**\n\n.. image:: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fblob\u002Fmaster\u002Fdocs\u002Fimg\u002Ftarget_som_processing.png\n   :alt: Cluster visualization by SOM\n\n\n\n.. |Build Status Linux MacOS| image:: https:\u002F\u002Ftravis-ci.org\u002Fannoviko\u002Fpyclustering.svg?branch=master\n   :target: https:\u002F\u002Ftravis-ci.org\u002Fannoviko\u002Fpyclustering\n.. |Build Status Win| image:: https:\u002F\u002Fci.appveyor.com\u002Fapi\u002Fprojects\u002Fstatus\u002F4uly2exfp49emwn0\u002Fbranch\u002Fmaster?svg=true\n   :target: https:\u002F\u002Fci.appveyor.com\u002Fproject\u002Fannoviko\u002Fpyclustering\u002Fbranch\u002Fmaster\n.. |Coverage Status| image:: https:\u002F\u002Fcoveralls.io\u002Frepos\u002Fgithub\u002Fannoviko\u002Fpyclustering\u002Fbadge.svg?branch=master&ts=1\n   :target: https:\u002F\u002Fcoveralls.io\u002Fgithub\u002Fannoviko\u002Fpyclustering?branch=master\n.. |DOI| image:: https:\u002F\u002Fzenodo.org\u002Fbadge\u002FDOI\u002F10.5281\u002Fzenodo.4280556.svg\n   :target: https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.4280556\n.. |PyPi| image:: https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Fpyclustering.svg\n   :target: https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Fpyclustering\n.. |Build Status Linux MacOS 0.10.dev| image:: https:\u002F\u002Ftravis-ci.org\u002Fannoviko\u002Fpyclustering.svg?branch=0.10.dev\n   :target: https:\u002F\u002Ftravis-ci.org\u002Fannoviko\u002Fpyclustering\n.. |Build Status Win 0.10.dev| image:: https:\u002F\u002Fci.appveyor.com\u002Fapi\u002Fprojects\u002Fstatus\u002F4uly2exfp49emwn0\u002Fbranch\u002F0.10.dev?svg=true\n   :target: https:\u002F\u002Fci.appveyor.com\u002Fproject\u002Fannoviko\u002Fpyclustering\u002Fbranch\u002F0.9.dev\n.. |Coverage Status 0.10.dev| image:: https:\u002F\u002Fcoveralls.io\u002Frepos\u002Fgithub\u002Fannoviko\u002Fpyclustering\u002Fbadge.svg?branch=0.10.dev&ts=1\n   :target: https:\u002F\u002Fcoveralls.io\u002Fgithub\u002Fannoviko\u002Fpyclustering?branch=0.9.dev\n.. |Build Status Linux 0.10.1.rel| image:: https:\u002F\u002Ftravis-ci.org\u002Fannoviko\u002Fpyclustering.svg?branch=0.10.1.rel\n   :target: https:\u002F\u002Ftravis-ci.org\u002Fannoviko\u002Fpyclustering\n.. |Build Status Win 0.10.1.rel| image:: https:\u002F\u002Fci.appveyor.com\u002Fapi\u002Fprojects\u002Fstatus\u002F4uly2exfp49emwn0\u002Fbranch\u002F0.10.1.rel?svg=true\n   :target: https:\u002F\u002Fci.appveyor.com\u002Fproject\u002Fannoviko\u002Fpyclustering\u002Fbranch\u002F0.10.1.rel\n.. |Coverage Status 0.10.1.rel| image:: https:\u002F\u002Fcoveralls.io\u002Frepos\u002Fgithub\u002Fannoviko\u002Fpyclustering\u002Fbadge.svg?branch=0.10.1.rel&ts=1\n   :target: https:\u002F\u002Fcoveralls.io\u002Fgithub\u002Fannoviko\u002Fpyclustering?branch=0.10.1.rel\n.. |Download Counter| image:: https:\u002F\u002Fpepy.tech\u002Fbadge\u002Fpyclustering\n   :target: https:\u002F\u002Fpepy.tech\u002Fproject\u002Fpyclustering\n.. |JOSS| image:: http:\u002F\u002Fjoss.theoj.org\u002Fpapers\u002F10.21105\u002Fjoss.01230\u002Fstatus.svg\n   :target: https:\u002F\u002Fdoi.org\u002F10.21105\u002Fjoss.01230\n","警告 - 用户请注意\n=========================\n\n**请注意，由于个人原因，`pyclustering` 库自 2021 年起已不再维护。该仓库将不再进行任何维护、问题修复或功能开发。**\n\n**如需继续使用，建议寻找其他替代方案。**\n\n**感谢您的理解。**\n\n\n构建状态\n============\n\n|Linux MacOS 构建状态| |Windows 构建状态| |覆盖率状态| |PyPI| |下载计数| |JOSS|\n\n\nPyClustering\n============\n\n**pyclustering** 是一个基于 Python 和 C++ 的数据挖掘库（包括聚类算法、振荡网络和神经网络）。该库为每种算法或模型提供了 Python 和 C++ 实现（C++ pyclustering 库）。C++ pyclustering 库是 pyclustering 的一部分，支持 Linux、Windows 和 macOS 操作系统。\n\n**版本**: 0.11.dev\n\n**许可证**: 第三条款 BSD 许可证\n\n**电子邮件**: pyclustering@yandex.ru\n\n**文档**: https:\u002F\u002Fpyclustering.github.io\u002Fdocs\u002F0.10.1\u002Fhtml\u002F\n\n**主页**: https:\u002F\u002Fpyclustering.github.io\u002F\n\n**PyClustering Wiki**: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fwiki\n\n\n\n依赖项\n============\n\n**所需包**: scipy, matplotlib, numpy, Pillow\n\n**Python 版本**: >=3.6（32位、64位）\n\n**C++ 版本**: >= 14（32位、64位）\n\n\n\n性能\n===========\n\n每个算法都同时提供了 Python 和 C\u002FC++ 实现。如果当前平台不支持 C\u002FC++ 实现，则会自动使用 Python 实现；否则将优先使用 C\u002FC++ 实现。可以通过 `ccore` 标志来选择实现方式（默认值为 `True`，表示使用 C\u002FC++），例如：\n\n.. code:: python\n\n    # 默认情况下使用 C\u002FC++ 部分\n    xmeans_instance_1 = xmeans(data_points, start_centers, 20, ccore=True);\n\n    # 同样，默认使用 C\u002FC++ 部分\n    xmeans_instance_2 = xmeans(data_points, start_centers, 20);\n\n    # 关闭核心部分，使用 Python 实现\n    xmeans_instance_3 = xmeans(data_points, start_centers, 20, ccore=False);\n\n\n\n安装\n============\n\n使用 pip3 工具安装：\n\n.. code:: bash\n\n    $ pip3 install pyclustering\n\n从官方仓库使用 Makefile 手动安装：\n\n.. code:: bash\n\n    # 获取 pyclustering 库的源代码，例如从仓库中克隆\n    $ mkdir pyclustering\n    $ cd pyclustering\u002F\n    $ git clone https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering.git .\n\n    # 编译 CCORE 库（pyclustering 库的核心部分）\n    $ cd ccore\u002F\n    $ make ccore_64bit      # 为 64 位操作系统构建\n\n    # $ make ccore_32bit    # 为 32 位操作系统构建\n\n    # 返回到 pyclustering 库的父目录\n    $ cd ..\u002F\n\n    # 安装 pyclustering 库\n    $ python3 setup.py install\n\n    # 可选：测试库\n    $ python3 setup.py test\n\n使用 CMake 手动安装：\n\n.. code:: bash\n\n    # 获取 pyclustering 库的源代码，例如从仓库中克隆\n    $ mkdir pyclustering\n    $ cd pyclustering\u002F\n    $ git clone https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering.git .\n\n    # 生成构建文件\n    $ mkdir build\n    $ cmake ..\n\n    # 根据生成的文件类型（Makefile 或 MSVC 解决方案）构建 pyclustering-shared 目标\n    # 如果生成的是 Makefile，则执行以下命令：\n    $ make pyclustering-shared\n\n    # 返回到 pyclustering 库的父目录\n    $ cd ..\u002F\n\n    # 安装 pyclustering 库\n    $ python3 setup.py install\n\n    # 可选：测试库\n    $ python3 setup.py test\n\n使用 Microsoft Visual Studio 解决方案手动安装：\n\n1. 克隆仓库：https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering.git\n2. 打开 `pyclustering\u002Fccore` 文件夹\n3. 打开 Visual Studio 项目 `ccore.sln`\n4. 选择解决方案平台：`x86` 或 `x64`\n5. 构建 `pyclustering-shared` 项目。\n6. 将 pyclustering 文件夹添加到 Python 路径中，或使用 setup.py 进行安装。\n\n.. code:: bash\n\n    # 安装 pyclustering 库\n    $ python3 setup.py install\n\n    # 可选：测试库\n    $ python3 setup.py test\n\n\n\n建议、问题与 Bug\n==========================\n\n如有关于 pyclustering 的任何问题、建议或 Bug，请联系 pyclustering@yandex.ru 或在此处提交 Issue。\n\n\n\nPyClustering 状态\n===================\n\n+----------------------+------------------------------+-------------------------------------+---------------------------------+\n| 分支               | master                       | 0.10.dev                            | 0.10.1.rel                      |\n+======================+==============================+=====================================+=================================+\n| 构建（Linux、MacOS） | |Build Status Linux MacOS|   | |Build Status Linux MacOS 0.10.dev| | |Build Status Linux 0.10.1.rel| |\n+----------------------+------------------------------+-------------------------------------+---------------------------------+\n| 构建（Windows）          | |Build Status Win|           | |Build Status Win 0.10.dev|         | |Build Status Win 0.10.1.rel|   |\n+----------------------+------------------------------+-------------------------------------+---------------------------------+\n| 代码覆盖率        | |Coverage Status|            | |Coverage Status 0.10.dev|          | |Coverage Status 0.10.1.rel|    |\n+----------------------+------------------------------+-------------------------------------+---------------------------------+\n\n\n\n引用该库\n================\n\n如果您在科学论文中使用了 pyclustering 库，请引用该库：\n\nNovikov, A., 2019. PyClustering: Data Mining Library. Journal of Open Source Software, 4(36), p.1230. Available at: http:\u002F\u002Fdx.doi.org\u002F10.21105\u002Fjoss.01230.\n\nBibTeX 条目：\n\n.. code::\n\n    @article{Novikov2019,\n        doi         = {10.21105\u002Fjoss.01230},\n        url         = {https:\u002F\u002Fdoi.org\u002F10.21105\u002Fjoss.01230},\n        year        = 2019,\n        month       = {apr},\n        publisher   = {The Open Journal},\n        volume      = {4},\n        number      = {36},\n        pages       = {1230},\n        author      = {Andrei Novikov},\n        title       = {{PyClustering}: Data Mining Library},\n        journal     = {Journal of Open Source Software}\n    }\n\n\n\n库内容简要概述\n=====================================\n\n**聚类算法与方法（模块 pyclustering.cluster）：**\n\n+------------------------+---------+-----+\n| 算法                   | Python  | C++ |\n+========================+=========+=====+\n| 层次聚类             | ✓       | ✓   |\n+------------------------+---------+-----+\n| BANG                   | ✓       |     |\n+------------------------+---------+-----+\n| BIRCH                  | ✓       |     |\n+------------------------+---------+-----+\n| BSAS                   | ✓       | ✓   |\n+------------------------+---------+-----+\n| CLARANS                | ✓       |     |\n+------------------------+---------+-----+\n| CLIQUE                 | ✓       | ✓   |\n+------------------------+---------+-----+\n| CURE                   | ✓       | ✓   |\n+------------------------+---------+-----+\n| DBSCAN                 | ✓       | ✓   |\n+------------------------+---------+-----+\n| 肘部法则               | ✓       | ✓   |\n+------------------------+---------+-----+\n| EMA                    | ✓       |     |\n+------------------------+---------+-----+\n| 模糊C均值              | ✓       | ✓   |\n+------------------------+---------+-----+\n| GA（遗传算法）         | ✓       | ✓   |\n+------------------------+---------+-----+\n| G-Means                | ✓       | ✓   |\n+------------------------+---------+-----+\n| HSyncNet               | ✓       | ✓   |\n+------------------------+---------+-----+\n| K均值                 | ✓       | ✓   |\n+------------------------+---------+-----+\n| K均值++               | ✓       | ✓   |\n+------------------------+---------+-----+\n| K中位数               | ✓       | ✓   |\n+------------------------+---------+-----+\n| K中心点               | ✓       | ✓   |\n+------------------------+---------+-----+\n| MBSAS                  | ✓       | ✓   |\n+------------------------+---------+-----+\n| OPTICS                 | ✓       | ✓   |\n+------------------------+---------+-----+\n| ROCK                   | ✓       | ✓   |\n+------------------------+---------+-----+\n| 轮廓系数             | ✓       | ✓   |\n+------------------------+---------+-----+\n| SOM-SC                 | ✓       | ✓   |\n+------------------------+---------+-----+\n| SyncNet                | ✓       | ✓   |\n+------------------------+---------+-----+\n| Sync-SOM               | ✓       |     |\n+------------------------+---------+-----+\n| TTSAS                  | ✓       | ✓   |\n+------------------------+---------+-----+\n| X-Means                | ✓       | ✓   |\n+------------------------+---------+-----+\n\n\n**振荡网络与神经网络（模块 pyclustering.nnet）：**\n\n+--------------------------------------------------------------------------------+---------+-----+\n| 模型                                                                   | Python  | C++ |\n+================================================================================+=========+=====+\n| CNN（混沌神经网络）                                                    | ✓       |     |\n+--------------------------------------------------------------------------------+---------+-----+\n| fSync（基于Landau-Stuart方程和Kuramoto模型的振荡网络）                 | ✓       |     |\n+--------------------------------------------------------------------------------+---------+-----+\n| HHN（基于Hodgkin-Huxley模型的振荡网络）                                | ✓       | ✓   |\n+--------------------------------------------------------------------------------+---------+-----+\n| 滞后振荡网络                                                         | ✓       |     |\n+--------------------------------------------------------------------------------+---------+-----+\n| LEGION（局部兴奋全局抑制振荡网络）                                     | ✓       | ✓   |\n+--------------------------------------------------------------------------------+---------+-----+\n| PCNN（脉冲耦合神经网络）                                               | ✓       | ✓   |\n+--------------------------------------------------------------------------------+---------+-----+\n| SOM（自组织映射）                                                      | ✓       | ✓   |\n+--------------------------------------------------------------------------------+---------+-----+\n| Sync（基于Kuramoto模型的振荡网络）                                     | ✓       | ✓   |\n+--------------------------------------------------------------------------------+---------+-----+\n| SyncPR（用于模式识别的振荡网络）                                       | ✓       | ✓   |\n+--------------------------------------------------------------------------------+---------+-----+\n| SyncSegm（用于图像分割的振荡网络）                                     | ✓       | ✓   |\n+--------------------------------------------------------------------------------+---------+-----+\n\n\n**图着色算法（模块 pyclustering.gcolor）：**\n\n+------------------------+---------+-----+\n| 算法                   | Python  | C++ |\n+========================+=========+=====+\n| DSatur                 | ✓       |     |\n+------------------------+---------+-----+\n| 滞后                   | ✓       |     |\n+------------------------+---------+-----+\n| GColorSync             | ✓       |     |\n+------------------------+---------+-----+\n\n\n**容器（模块 pyclustering.container）：**\n\n+------------------------+---------+-----+\n| 算法                   | Python  | C++ |\n+========================+=========+=====+\n| KD树                   | ✓       | ✓   |\n+------------------------+---------+-----+\n| CF树                   | ✓       |     |\n+------------------------+---------+-----+\n\n\n\n库中的示例\n=======================\n\n该库为每个算法和振荡网络模型都提供了示例：\n\n**聚类示例：** ``pyclustering\u002Fcluster\u002Fexamples``\n\n**图着色示例：** ``pyclustering\u002Fgcolor\u002Fexamples``\n\n**振荡网络示例：** ``pyclustering\u002Fnnet\u002Fexamples``\n\n.. image:: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fblob\u002Fmaster\u002Fdocs\u002Fimg\u002Fexample_cluster_place.png\n   :alt: 示例在哪里？\n\n\n\n代码示例\n=============\n\n**使用CURE算法进行数据聚类**\n\n.. code:: python\n\n    from pyclustering.cluster import cluster_visualizer;\n    from pyclustering.cluster.cure import cure;\n    from pyclustering.utils import read_sample;\n    from pyclustering.samples.definitions import FCPS_SAMPLES;\n\n    # 输入数据格式为 [ [0.1, 0.5], [0.3, 0.1], ... ]。\n    input_data = read_sample(FCPS_SAMPLES.SAMPLE_LSUN);\n\n    # 分配三个聚类。\n    cure_instance = cure(input_data, 3);\n    cure_instance.process();\n    clusters = cure_instance.get_clusters();\n\n    # 可视化分配的聚类。\n    visualizer = cluster_visualizer();\n    visualizer.append_clusters(clusters, input_data);\n    visualizer.show();\n\n**使用K均值算法进行数据聚类**\n\n.. code:: python\n\nfrom pyclustering.cluster.kmeans import kmeans, kmeans_visualizer\n    from pyclustering.cluster.center_initializer import kmeans_plusplus_initializer\n    from pyclustering.samples.definitions import FCPS_SAMPLES\n    from pyclustering.utils import read_sample\n\n    # 加载用于聚类分析的数据点列表。\n    sample = read_sample(FCPS_SAMPLES.SAMPLE_TWO_DIAMONDS)\n\n    # 使用K-Means++方法准备初始聚类中心。\n    initial_centers = kmeans_plusplus_initializer(sample, 2).initialize()\n\n    # 使用准备好的初始中心创建K-Means算法实例。\n    kmeans_instance = kmeans(sample, initial_centers)\n\n    # 运行聚类分析并获取结果。\n    kmeans_instance.process()\n    clusters = kmeans_instance.get_clusters()\n    final_centers = kmeans_instance.get_centers()\n\n    # 可视化得到的结果\n    kmeans_visualizer.show_clusters(sample, clusters, final_centers)\n\n**使用OPTICS算法进行数据聚类**\n\n.. code:: python\n\n    from pyclustering.cluster import cluster_visualizer\n    from pyclustering.cluster.optics import optics, ordering_analyser, ordering_visualizer\n    from pyclustering.samples.definitions import FCPS_SAMPLES\n    from pyclustering.utils import read_sample\n\n    # 从某个文件中读取用于聚类的样本\n    sample = read_sample(FCPS_SAMPLES.SAMPLE_LSUN)\n\n    # 在连接半径大于实际值的情况下运行聚类分析\n    radius = 2.0\n    neighbors = 3\n    amount_of_clusters = 3\n    optics_instance = optics(sample, radius, neighbors, amount_of_clusters)\n\n    # 执行聚类分析\n    optics_instance.process()\n\n    # 获取聚类结果\n    clusters = optics_instance.get_clusters()\n    noise = optics_instance.get_noise()\n    ordering = optics_instance.get_ordering()\n\n    # 可视化排序图\n    analyser = ordering_analyser(ordering)\n    ordering_visualizer.show_ordering_diagram(analyser, amount_of_clusters)\n\n    # 可视化聚类结果\n    visualizer = cluster_visualizer()\n    visualizer.append_clusters(clusters, sample)\n    visualizer.show()\n\n**振荡网络PCNN的仿真**\n\n.. code:: python\n\n    from pyclustering.nnet.pcnn import pcnn_network, pcnn_visualizer\n\n    # 创建一个包含10个振子的脉冲耦合神经网络。\n    net = pcnn_network(10)\n\n    # 使用二进制外部刺激在100个步骤内进行仿真。\n    dynamic = net.simulate(50, [1, 1, 1, 0, 0, 0, 0, 1, 1, 1])\n\n    # 从输出动态中提取同步集合。\n    ensembles = dynamic.allocate_sync_ensembles()\n\n    # 显示输出动态。\n    pcnn_visualizer.show_output_dynamic(dynamic, ensembles)\n\n**混沌神经网络CNN的仿真**\n\n.. code:: python\n\n    from pyclustering.cluster import cluster_visualizer\n    from pyclustering.samples.definitions import SIMPLE_SAMPLES\n    from pyclustering.utils import read_sample\n    from pyclustering.nnet.cnn import cnn_network, cnn_visualizer\n\n    # 从文件中加载刺激信号。\n    stimulus = read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE3)\n\n    # 创建一个混沌神经网络，其神经元数量应与刺激信号的数量相同。\n    network_instance = cnn_network(len(stimulus))\n\n    # 在100个步骤内进行仿真。\n    steps = 100\n    output_dynamic = network_instance.simulate(steps, stimulus)\n\n    # 显示网络的输出动态。\n    cnn_visualizer.show_output_dynamic(output_dynamic)\n\n    # 显示动态矩阵和观测矩阵，以展示聚类现象。\n    cnn_visualizer.show_dynamic_matrix(output_dynamic)\n    cnn_visualizer.show_observation_matrix(output_dynamic)\n\n    # 可视化聚类结果。\n    clusters = output_dynamic.allocate_sync_ensembles(10)\n    visualizer = cluster_visualizer()\n    visualizer.append_clusters(clusters, stimulus)\n    visualizer.show()\n\n\n\n插图\n=============\n\n**使用DBSCAN对FCPS数据集集合进行聚类分配：**\n\n.. image:: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fblob\u002Fmaster\u002Fdocs\u002Fimg\u002Ffcps_cluster_analysis.png\n   :alt: DBSCAN聚类\n\n**使用OPTICS及其聚类排序图进行聚类分配：**\n\n.. image:: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fblob\u002Fmaster\u002Fdocs\u002Fimg\u002Foptics_example_clustering.png\n   :alt: OPTICS聚类\n\n\n**Sync振荡网络中的部分同步（聚类）：**\n\n.. image:: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fblob\u002Fmaster\u002Fdocs\u002Fimg\u002Fsync_partial_synchronization.png\n   :alt: Sync振荡网络中的部分同步\n\n\n**通过SOM（自组织特征映射）进行聚类可视化**\n\n.. image:: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fblob\u002Fmaster\u002Fdocs\u002Fimg\u002Ftarget_som_processing.png\n   :alt: SOM聚类可视化\n\n\n\n.. |Linux MacOS构建状态| image:: https:\u002F\u002Ftravis-ci.org\u002Fannoviko\u002Fpyclustering.svg?branch=master\n   :target: https:\u002F\u002Ftravis-ci.org\u002Fannoviko\u002Fpyclustering\n.. |Windows构建状态| image:: https:\u002F\u002Fci.appveyor.com\u002Fapi\u002Fprojects\u002Fstatus\u002F4uly2exfp49emwn0\u002Fbranch\u002Fmaster?svg=true\n   :target: https:\u002F\u002Fci.appveyor.com\u002Fproject\u002Fannoviko\u002Fpyclustering\u002Fbranch\u002Fmaster\n.. |覆盖率状态| image:: https:\u002F\u002Fcoveralls.io\u002Frepos\u002Fgithub\u002Fannoviko\u002Fpyclustering\u002Fbadge.svg?branch=master&ts=1\n   :target: https:\u002F\u002Fcoveralls.io\u002Fgithub\u002Fannoviko\u002Fpyclustering?branch=master\n.. |DOI| image:: https:\u002F\u002Fzenodo.org\u002Fbadge\u002FDOI\u002F10.5281\u002Fzenodo.4280556.svg\n   :target: https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.4280556\n.. |PyPi| image:: https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Fpyclustering.svg\n   :target: https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Fpyclustering\n.. |Linux MacOS 0.10.dev构建状态| image:: https:\u002F\u002Ftravis-ci.org\u002Fannoviko\u002Fpyclustering.svg?branch=0.10.dev\n   :target: https:\u002F\u002Ftravis-ci.org\u002Fannoviko\u002Fpyclustering\n.. |Windows 0.10.dev构建状态| image:: https:\u002F\u002Fci.appveyor.com\u002Fapi\u002Fprojects\u002Fstatus\u002F4uly2exfp49emwn0\u002Fbranch\u002F0.10.dev?svg=true\n   :target: https:\u002F\u002Fci.appveyor.com\u002Fproject\u002Fannoviko\u002Fpyclustering\u002Fbranch\u002F0.9.dev\n.. |0.10.dev覆盖率状态| image:: https:\u002F\u002Fcoveralls.io\u002Frepos\u002Fgithub\u002Fannoviko\u002Fpyclustering\u002Fbadge.svg?branch=0.10.dev&ts=1\n   :target: https:\u002F\u002Fcoveralls.io\u002Fgithub\u002Fannoviko\u002Fpyclustering?branch=0.9.dev\n.. |Linux 0.10.1.rel构建状态| image:: https:\u002F\u002Ftravis-ci.org\u002Fannoviko\u002Fpyclustering.svg?branch=0.10.1.rel\n   :target: https:\u002F\u002Ftravis-ci.org\u002Fannoviko\u002Fpyclustering\n.. |Windows 0.10.1.rel构建状态| image:: https:\u002F\u002Fci.appveyor.com\u002Fapi\u002Fprojects\u002Fstatus\u002F4uly2exfp49emwn0\u002Fbranch\u002F0.10.1.rel?svg=true\n   :target: https:\u002F\u002Fci.appveyor.com\u002Fproject\u002Fannoviko\u002Fpyclustering\u002Fbranch\u002F0.10.1.rel\n.. |0.10.1.rel覆盖率状态| image:: https:\u002F\u002Fcoveralls.io\u002Frepos\u002Fgithub\u002Fannoviko\u002Fpyclustering\u002Fbadge.svg?branch=0.10.1.rel&ts=1\n   :target: https:\u002F\u002Fcoveralls.io\u002Fgithub\u002Fannoviko\u002Fpyclustering?branch=0.10.1.rel\n.. |下载次数| image:: https:\u002F\u002Fpepy.tech\u002Fbadge\u002Fpyclustering\n   :target: https:\u002F\u002Fpepy.tech\u002Fproject\u002Fpyclustering\n.. |JOSS| image:: http:\u002F\u002Fjoss.theoj.org\u002Fpapers\u002F10.21105\u002Fjoss.01230\u002Fstatus.svg\n   :target: https:\u002F\u002Fdoi.org\u002F10.21105\u002Fjoss.01230","# PyClustering 快速上手指南\n\n> **⚠️ 重要提示**：该库自 2021 年起已停止维护（不再修复漏洞或开发新功能）。建议在新项目中评估替代方案，或仅将其用于学习研究及遗留系统维护。\n\nPyClustering 是一个提供聚类算法、振荡网络和神经网络实现的 Python\u002FC++ 数据挖掘库。其核心优势在于大多数算法同时提供 Python 和 C++ 实现，默认调用 C++ 核心以获得更高性能。\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**：>= 3.6 (支持 32 位和 64 位)\n*   **C++ 编译器**：>= C++14 标准（若使用默认的高性能 C++ 核心）\n*   **前置依赖包**：\n    *   `scipy`\n    *   `matplotlib`\n    *   `numpy`\n    *   `Pillow`\n\n## 安装步骤\n\n### 方式一：使用 pip 安装（推荐）\n\n这是最快捷的安装方式，适用于大多数用户。\n\n```bash\npip3 install pyclustering\n```\n\n*注：国内用户若下载缓慢，可指定清华镜像源：*\n```bash\npip3 install pyclustering -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n### 方式二：手动源码安装（适用于需要自定义编译的场景）\n\n如果您需要修改底层 C++ 代码或使用特定构建配置，可从 GitHub 克隆源码进行编译。\n\n**1. 获取源码**\n```bash\nmkdir pyclustering\ncd pyclustering\u002F\ngit clone https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering.git .\n```\n\n**2. 编译 C++ 核心 (CCORE)**\n*使用 Makefile (Linux\u002FmacOS):*\n```bash\ncd ccore\u002F\nmake ccore_64bit      # 编译 64 位版本\n# make ccore_32bit    # 如需 32 位版本\ncd ..\u002F\n```\n\n*或使用 CMake:*\n```bash\nmkdir build\ncd build\ncmake ..\nmake pyclustering-shared\ncd ..\u002F\n```\n\n**3. 安装 Python 包**\n```bash\npython3 setup.py install\n```\n\n*(可选) 运行测试验证安装：*\n```bash\npython3 setup.py test\n```\n\n## 基本使用\n\nPyClustering 的核心特性是可以通过 `ccore` 参数切换后端实现：\n*   `ccore=True` (默认)：使用 C++ 实现，性能更优。\n*   `ccore=False`：使用纯 Python 实现。\n\n以下以 **X-Means** 聚类算法为例：\n\n```python\nfrom pyclustering.cluster.xmeans import xmeans\n\n# 准备数据 (data_points), 初始中心 (start_centers) 和最大聚类数\n# 此处仅为示例变量，实际使用时请替换为真实数据\ndata_points = [[1, 2], [1.5, 1.8], [5, 8], [8, 8], [1, 0.6], [9, 11]]\nstart_centers = [[1, 2], [5, 8]]\n\n# 示例 1: 使用默认的 C++ 核心 (推荐)\nxmeans_instance_1 = xmeans(data_points, start_centers, 20)\nxmeans_instance_1.process()\nclusters_1 = xmeans_instance_1.get_clusters()\n\n# 示例 2: 显式指定使用 C++ 核心\nxmeans_instance_2 = xmeans(data_points, start_centers, 20, ccore=True)\nxmeans_instance_2.process()\n\n# 示例 3: 强制使用纯 Python 实现 (无需 C++ 环境或调试时)\nxmeans_instance_3 = xmeans(data_points, start_centers, 20, ccore=False)\nxmeans_instance_3.process()\nclusters_3 = xmeans_instance_3.get_clusters()\n\nprint(\"聚类结果:\", clusters_3)\n```\n\n库中包含了丰富的算法模块，主要位于：\n*   `pyclustering.cluster`: 各类聚类算法 (K-Means, DBSCAN, BIRCH 等)\n*   `pyclustering.nnet`: 神经网络与振荡网络 (SOM, PCNN, SyncNet 等)\n*   `pyclustering.gcolor`: 图着色算法\n*   `pyclustering.container`: 数据结构 (KD-Tree 等)\n\n更多详细用法请参考官方文档：https:\u002F\u002Fpyclustering.github.io\u002Fdocs\u002F","某生物信息学团队正在处理一批高维度的基因表达数据，需要快速识别具有相似表达模式的细胞群以辅助疾病研究。\n\n### 没有 pyclustering 时\n- 研究人员需手动从零编写 K-Means 或 X-Means 等复杂聚类算法的底层逻辑，耗时数周且极易引入数学推导错误。\n- 面对百万级基因数据点，纯 Python 实现的循环计算效率极低，单次聚类分析往往需要等待数小时才能出结果。\n- 缺乏现成的振荡网络（如 Kuramoto 模型）实现，难以模拟神经元同步等动态生物过程，限制了研究深度。\n- 可视化结果依赖自行拼接 Matplotlib 代码，无法直接生成清晰的簇分布图，增加了结果验证的难度。\n- 跨语言协作困难，C++ 后端的高性能模块需单独开发，导致算法原型与生产环境性能差异巨大。\n\n### 使用 pyclustering 后\n- 直接调用库中成熟的 X-Means 和 G-Means 算法接口，将算法验证周期从数周缩短至几小时，确保数学逻辑准确无误。\n- 利用内置的 C++ 核心加速模块（ccore），在默认配置下即可实现比纯 Python 快数十倍的运算速度，轻松处理大规模数据集。\n- 一键启用振荡网络和神经网络模型，无需额外编码即可模拟复杂的生物动态系统，拓展了分析维度。\n- 集成化的可视化功能可直接绘制聚类中心和样本分布，帮助研究员直观判断分组效果，大幅提升决策效率。\n- 同一套代码自动根据环境切换 Python 或 C++ 后端，既保证了开发灵活性，又确保了部署时的极致性能。\n\npyclustering 通过提供高性能、多语言支持的成熟算法库，让科研人员能专注于数据洞察而非重复造轮子。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fannoviko_pyclustering_fed5253f.png","annoviko","Andrei Novikov","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fannoviko_bb55f091.jpg","PhD in Computer Science. Software Architect at ThermoFisher Scientific.",null,"Eindhoven, the Netherlands","spb.andr@yandex.ru","https:\u002F\u002Fgithub.com\u002Fannoviko",[84,88,92,96,99,103,107,111],{"name":85,"color":86,"percentage":87},"Python","#3572A5",60.6,{"name":89,"color":90,"percentage":91},"C++","#f34b7d",37,{"name":93,"color":94,"percentage":95},"TeX","#3D6117",0.6,{"name":97,"color":98,"percentage":95},"C","#555555",{"name":100,"color":101,"percentage":102},"Shell","#89e051",0.5,{"name":104,"color":105,"percentage":106},"PowerShell","#012456",0.4,{"name":108,"color":109,"percentage":110},"Makefile","#427819",0.3,{"name":112,"color":113,"percentage":114},"CMake","#DA3434",0.1,1212,263,"2026-04-01T12:23:30","BSD-3-Clause","Linux, macOS, Windows","未说明",{"notes":122,"python":123,"dependencies":124},"该库自 2021 年起已停止维护，不再修复问题或开发新功能。核心算法提供 Python 和 C++ 双实现，默认使用 C++ 核心（ccore=True）以提升性能，若平台不支持则自动回退至 Python 实现。C++ 核心编译需要 C++14 或更高版本支持。",">=3.6",[125,126,127,128],"scipy","matplotlib","numpy","Pillow",[54,51,13],[131,132,133,134,135,136,137,138,139,140],"clustering","oscillatory-networks","data-mining","neural-networks","python3","c-plus-plus","machine-learning","algorithms","data-science","python","2026-03-27T02:49:30.150509","2026-04-06T07:12:44.058737",[144,149,154,159,164,169],{"id":145,"question_zh":146,"answer_zh":147,"source_url":148},9887,"如何优化 OPTICS 算法在处理大规模高维数据时的性能？","维护者已降低算法复杂度以提升性能。对于文本等高维数据（如 50k 数据点，5k 特征），如果性能仍然不足，建议尝试其他聚类算法或使用其他专用库（如 scikit-learn 或 ELKI）。此外，数据的复杂性也会显著影响聚类速度。","https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F521",{"id":150,"question_zh":151,"answer_zh":152,"source_url":153},9888,"运行 BIRCH 算法时遇到 'ValueError: The truth value of an array...' 错误或参数错误怎么办？","这是一个已知问题。如果需要从 CF-entries 中提取索引信息，可以使用以下补丁代码：\n```python\nbirch_instance.process()\ncf_entries = birch_instance.get_cf_entries()\nfor entry in cf_entries:\n    print(entry.indexes)\n```\n关于直径（diameter）参数报错，请检查版本兼容性。注意，直接使用条目中的点索引而非聚合计算（LS, SS）可能会影响聚类结果，特别是异常值的识别。","https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F570",{"id":155,"question_zh":156,"answer_zh":157,"source_url":158},9889,"pyclustering 的 k-medoids 算法是否支持 Gower 距离矩阵或自定义距离矩阵？","支持。在初始化 `kmedoids` 实例时，需将 `data_type` 参数设置为 `'distance_matrix'`。输入的距离矩阵必须是 `numpy.array` 或 `list` 类型，且仅包含数值元素（支持 `numpy.nan`），不能包含字符串。示例代码如下：\n```python\nfrom pyclustering.cluster.kmedoids import kmedoids\n# D 为预计算的距离矩阵\ninitial_medoids = [...] # 初始介中心索引\nkmedoids_instance = kmedoids(D, initial_medoids, data_type='distance_matrix')\nkmedoids_instance.process()\nclusters = kmedoids_instance.get_clusters()\n```","https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F499",{"id":160,"question_zh":161,"answer_zh":162,"source_url":163},9890,"如何在 K-Medoids 算法中指定聚类数量或使用自定义距离函数？","K-Medoids 的聚类数量由初始介中心（initial medoids）的数量决定。你需要预先选择 N 个索引作为初始介中心，算法最终会返回 N 个聚类。可以通过随机采样生成初始索引：\n```python\nimport numpy as np\nfrom pyclustering.cluster.kmedoids import kmedoids\n\nMEDOID_COUNT = 3 # 想要的聚类数\nsample = [...] # 你的数据\nmedoid_indexes = len(sample)\n# 随机选择不重复的索引作为初始介中心\ninitial_medoid_indexes = np.random.choice(medoid_indexes, size=MEDOID_COUNT, replace=False)\n\nkmedoids_instance = kmedoids(sample, initial_medoid_indexes)\nkmedoids_instance.process()\n```","https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F417",{"id":165,"question_zh":166,"answer_zh":167,"source_url":168},9891,"pyclustering 是否内置了 K-Means 聚类的纯度（Purity Score）评估指标？","目前 pyclustering 库中没有内置 K-Means 的纯度评分功能。用户需要自行编写代码来计算纯度分数，以便比较不同距离度量下的聚类效果。","https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F620",{"id":170,"question_zh":171,"answer_zh":172,"source_url":158},9892,"在使用距离矩阵进行聚类时，对数据格式有什么具体要求？","数据容器（如 `numpy.array` 或 `list`）必须支持通过索引访问元素（即实现 `__getitem__`）。矩阵中的所有元素必须是数值类型（包括 `float('NaN')` 或 `numpy.nan`），严禁包含字符串（str）类型，否则会导致计算错误。",[174,179,184,189,194,199,204,209,214,219,224,229,234,239,244,249,254,259],{"id":175,"version":176,"summary_zh":177,"released_at":178},107174,"0.10.1.2","**pyclustering 0.10.1.2 library** is a collection of clustering algorithms, oscillatory networks, etc.\r\n\r\n**CORRECTED MAJOR BUGS:**\r\n\r\n- Corrected bug with empty clusters for K-Medoids (C++ `pyclustering::clst::kmeadois`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F659","2020-11-25T22:33:07",{"id":180,"version":181,"summary_zh":182,"released_at":183},107175,"0.10.1.1","**pyclustering 0.10.1.1 library** is a collection of clustering algorithms, oscillatory networks, etc.\r\n\r\n**CORRECTED MAJOR BUGS:**\r\n\r\n- Corrected bug with incorrect cluster allocation for K-Medoids (C++ `pyclustering::clst::kmeadois`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F659","2020-11-24T19:47:10",{"id":185,"version":186,"summary_zh":187,"released_at":188},107176,"0.10.1","**pyclustering 0.10.1 library** is a collection of clustering algorithms, oscillatory networks, etc.\r\n\r\n**GENERAL CHANGES**:\r\n\r\n- The library is distributed under `BSD-3-Clause` library.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F517\r\n\r\n- C++ pyclustering can be built using CMake.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F603\r\n\r\n- Supported dumping and loading for DBSCAN algorithm via `pickle` (Python: `pyclustering.cluster.dbscan`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F650\r\n\r\n- Package installer resolves all required dependencies automatically.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F647\r\n\r\n- Introduced human-readable error for genetic clustering algorithm in case of non-normalized data (Python: `pyclustering.cluster.ga`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F597\r\n\r\n- Optimized windows implementation `parallel_for` and `parallel_for_each` by using `pyclustering::parallel` instead of `PPL` that affects all algorithms which use these functions (C++: `pyclustering::parallel`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F642\r\n\r\n- Optimized `parallel_for` algorithm for short cycles that affects all algorithms which use `parallel_for` (C++: `pyclustering::parallel`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F642\r\n\r\n- Introduced `kstep` parameter for `elbow` algorithm to use custom K search steps (Python: `pyclustering.cluster.elbow`, C++: `pyclustering::cluster::elbow`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F489\r\n\r\n- Introduced `p_step` parameter for `parallel_for` function (C++: `pyclustering::parallel`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F640\r\n\r\n- Optimized python implementation of K-Medoids algorithm (Python: `pyclustering.cluster.kmedoids`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F526\r\n\r\n- C++ pyclustering CLIQUE interface returns human-readable errors (Python: `pyclustering.cluster.clique`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F635\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F634\r\n\r\n- Introduced `metric` parameter for X-Means algorithm to use custom metric for clustering (Python: `pyclustering.cluster.xmeans`; C++ `pyclustering::clst::xmeans`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F619\r\n\r\n- Introduced `alpha` and `beta` probabilistic bounds for MNDL splitting criteria for X-Means algorithm (Python: `pyclustering.cluster.xmeans`; C++: `pyclustering::clst::xmeans`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F624\r\n\r\n\r\n**CORRECTED MAJOR BUGS**:\r\n\r\n- Corrected bug with a command `python3 -m pyclustering.tests` that was using the current folder to find tests to run (Python: `pyclustering`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F648\r\n\r\n- Corrected bug with Elbow algorithm where `kmax` is not used to calculate `K` (Python: `pyclustering.cluster.elbow`; C++: `pyclustering::clst::elbow`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F639\r\n\r\n- Corrected implementation of K-Medians (PAM) algorithm that is aligned with original algorithm (Python: `pyclustering.cluster.kmedoids`; C++: `pyclustering::clst::kmedoids`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F503\r\n\r\n- Corrected literature references that were for K-Medians (PAM) implementation (Python: `pyclustering.cluster.kmedoids`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fpull\u002F572\r\n\r\n- Corrected bug when K-Medoids updates input parameter `initial_medoids` that were provided to the algorithm (Python: `pyclustering.cluster.kmedoids`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F630\r\n\r\n- Corrected bug with Euclidean distance when numpy is used (Python: `pyclustering.utils.metric`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F625\r\n\r\n- Corrected bug with Minkowski distance when numpy is used (Python: `pyclustering.utils.metric`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F626\r\n\r\n- Corrected bug with Gower distance when numpy calculation is used and data shape is bigger than 1 (Python: `pyclustering.utils.metric`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F627\r\n\r\n- Corrected MNDL splitting criteria for X-Means algorithm (Python: `pyclustering.cluster.xmeans`; C++: `pyclustering::clst::xmeans`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F623","2020-11-19T09:25:43",{"id":190,"version":191,"summary_zh":192,"released_at":193},107177,"0.10.0.1","**pyclustering 0.10.0.1 library** is a collection of clustering algorithms and methods, oscillatory networks, etc.\r\n\r\nGENERAL CHANGES:\r\n\r\n- Metadata of the library is updated.\r\n  See: no reference\r\n\r\n- Supported command `test` for `setup.py` script (Python: `pyclustering`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F607\r\n\r\n- Introduced parameter `random_seed` for algorithms\u002Fmodels to control the seed of the random functionality: `kmeans++`, `random_center_initializer`, `ga`, `gmeans`, `xmeans`, `som`, `somsc`, `elbow`, `silhouette_ksearch` (Python: `pyclustering.cluster`; C++: `pyclustering.clst`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F578\r\n\r\n- Introduced parameter `k_max` to G-Means algorithm to use it as an optional stop condition for the algorithm (Python: `pyclustering.cluster.gmeans`; C++: `pyclustering::clst::gmeans`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F602\r\n\r\n- Implemented method `save()` for `cluster_visualizer` and `cluster_visualizer_multidim` to save visualization to file (Python: `pyclustering.cluster`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F601\r\n\r\n- Optimization of CURE algorithm using balanced KD-tree (Python: `pyclustering.cluster.cure`; C++: `pyclustering::clst::cure`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F589\r\n\r\n- Optimization of OPTICS algorithm using balanced KD-tree (Python: `pyclustering.cluster.optics`; C++: `pyclustering::clst::optics`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F588\r\n\r\n- Optimization of DBSCAN algorithm using balanced KD-tree (Python: `pyclustering.cluster.dbscan`; C++: `pyclustering::clst::dbscan`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F587\r\n\r\n- Implemented new optimized balanced KD-tree `kdtree_balanced` (Python: `pyclustering.cluster.kdtree`; C++: `pyclustering::container::kdtree_balanced`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F379\r\n\r\n- Implemented KD-tree graphical visualizer `kdtree_visualizer` for KD-trees with 2-dimensional data (Python: `pyclustering.container.kdtree`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F586\r\n\r\n- Updated interface of each clustering algorithm in C\u002FC++ pyclustering `cluster_data` is substituted by concrete classes (C++ `pyclustering::clst`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F577\r\n\r\n\r\nCORRECTED MAJOR BUGS:\r\n\r\n- Bug with wrong data type for `scores` in Silhouette K-search algorithm in case of using C++ (Python: `pyclustering.cluster.silhouette`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F606\r\n\r\n- Bug with a random distribution in the random center initializer (Python: `pyclustering.cluster.center_initializer`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F573\r\n\r\n- Bug with incorrect converting Index List and Object List to Labeling when clusters do not contains one or more points from an input data (Python `pyclustering.cluster.encoder`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F596\r\n\r\n- Bug with an exception in case of using user-defined metric for K-Means algorithm (Python `pyclustering.cluster.kmeans`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fpull\u002F600\r\n\r\n- Memory leakage in the interface between python and C++ pyclustering library in case of CURE algorithm usage (C++ `pyclustering`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F581","2020-08-17T09:21:48",{"id":195,"version":196,"summary_zh":197,"released_at":198},107178,"0.10.0","**pyclustering 0.10.0 library** is a collection of clustering algorithms and methods, oscillatory networks, etc.\r\n\r\nGENERAL CHANGES:\r\n\r\n- Supported command `test` for `setup.py` script (Python: `pyclustering`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F607\r\n\r\n- Introduced parameter `random_seed` for algorithms\u002Fmodels to control the seed of the random functionality: `kmeans++`, `random_center_initializer`, `ga`, `gmeans`, `xmeans`, `som`, `somsc`, `elbow`, `silhouette_ksearch` (Python: `pyclustering.cluster`; C++: `pyclustering.clst`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F578\r\n\r\n- Introduced parameter `k_max` to G-Means algorithm to use it as an optional stop condition for the algorithm (Python: `pyclustering.cluster.gmeans`; C++: `pyclustering::clst::gmeans`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F602\r\n\r\n- Implemented method `save()` for `cluster_visualizer` and `cluster_visualizer_multidim` to save visualization to file (Python: `pyclustering.cluster`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F601\r\n\r\n- Optimization of CURE algorithm using balanced KD-tree (Python: `pyclustering.cluster.cure`; C++: `pyclustering::clst::cure`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F589\r\n\r\n- Optimization of OPTICS algorithm using balanced KD-tree (Python: `pyclustering.cluster.optics`; C++: `pyclustering::clst::optics`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F588\r\n\r\n- Optimization of DBSCAN algorithm using balanced KD-tree (Python: `pyclustering.cluster.dbscan`; C++: `pyclustering::clst::dbscan`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F587\r\n\r\n- Implemented new optimized balanced KD-tree `kdtree_balanced` (Python: `pyclustering.cluster.kdtree`; C++: `pyclustering::container::kdtree_balanced`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F379\r\n\r\n- Implemented KD-tree graphical visualizer `kdtree_visualizer` for KD-trees with 2-dimensional data (Python: `pyclustering.container.kdtree`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F586\r\n\r\n- Updated interface of each clustering algorithm in C\u002FC++ pyclustering `cluster_data` is substituted by concrete classes (C++ `pyclustering::clst`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F577\r\n\r\n\r\nCORRECTED MAJOR BUGS:\r\n\r\n- Bug with wrong data type for `scores` in Silhouette K-search algorithm in case of using C++ (Python: `pyclustering.cluster.silhouette`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F606\r\n\r\n- Bug with a random distribution in the random center initializer (Python: `pyclustering.cluster.center_initializer`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F573\r\n\r\n- Bug with incorrect converting Index List and Object List to Labeling when clusters do not contains one or more points from an input data (Python `pyclustering.cluster.encoder`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F596\r\n\r\n- Bug with an exception in case of using user-defined metric for K-Means algorithm (Python `pyclustering.cluster.kmeans`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fpull\u002F600\r\n\r\n- Memory leakage in the interface between python and C++ pyclustering library in case of CURE algorithm usage (C++ `pyclustering`).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F581","2020-08-17T08:43:51",{"id":200,"version":201,"summary_zh":202,"released_at":203},107179,"0.9.3.1","**pyclustering 0.9.3.1 library** is a collection of clustering algorithms and methods, oscillatory networks, etc.\r\n\r\nCORRECTED MAJOR BUGS:\r\n\r\n- Hotfix for the CF-tree - call method with incorrect amount of arguments.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F570","2019-12-24T08:48:14",{"id":205,"version":206,"summary_zh":207,"released_at":208},107180,"0.9.3","**pyclustering 0.9.3 library** is a collection of clustering algorithms and methods, oscillatory networks, etc.\r\n\r\nGENERAL CHANGES:\r\n- Introduced `get_cf_clusters` and `get_cf_entries` methods for BIRCH algorithm to get CF-entry encoding information (pyclustering.cluster.birch).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F569\r\n\r\n- Introduced `predict` method for SOMSC algorithm to find closest clusters for specified points (pyclustering.cluster.somsc).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F546\r\n\r\n- Parallel optimization of C++ pyclustering compilation process.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F553\r\n\r\n- Include folder for easy integration to other C++ projects.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F554\r\n\r\n- Introduced new targets to build static libraries on Windows platform.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F555\r\n\r\n- Introduced new targets to build static libraries on Linux\u002FMacOS platforms.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F556\r\n\r\n\r\nCORRECTED MAJOR BUGS:\r\n- Bug with incorrect finding of closest CF-entry (pyclustering.container.cftree).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F564\r\n\r\n- Bug with incorrect BIRCH clustering due incorrect leaf analysis (pyclustering.cluster.birch).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F563\r\n\r\n- Bug with incorrect search procedure of farthest nodes in CF-tree (pyclustering.container.cftree).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F551\r\n\r\n- Bug with crash during clustering with the same points in case of BIRCH (pyclustering.cluster.birch).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F561","2019-12-23T09:42:29",{"id":210,"version":211,"summary_zh":212,"released_at":213},107181,"0.9.2","**pyclustering 0.9.2 library** is a collection of clustering algorithms and methods, oscillatory networks, etc.\r\n\r\nGENERAL CHANGES:\r\n- Introduced checking of input arguments for clustering algorithm to provide human-readable errors (pyclustering.cluster).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F548\r\n\r\n- Implemented functionality to perform Anderson-Darling test for Gaussian distribution (ccore.stats).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F550\r\n\r\n- Implemented new clustering algorithm G-Means (pyclustering.cluster.gmeans, ccore.clst.gmeans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F506\r\n\r\n- Introduced parameter `repeat` to improve parameters in X-Means algorithm (pyclustering.cluster.xmeans, ccore.clst.xmeans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F525\r\n\r\n- Introduced new distance metric: Gower (pyclustering.utils.metric, ccore.utils.metric).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F544\r\n\r\n- Introduced sampling algorithms `reservoir_r` and `reservoir_x` (pyclustering.utils.sampling).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F542\r\n\r\n- Introduced parameter `data_type` to Silhouette method to use distance matrix (pyclustering.cluster.silhouette, ccore.clst.silhouette).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F543\r\n\r\n- Optimization of HHN (Hodgkin-Huxley Neural Network) by parallel processing (ccore.nnet.hhn).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F541\r\n\r\n- Introduced `get_total_wce` method for `xmeans` algorithm to find WCE (pyclustering.cluster.xmeans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F508\r\n\r\nCORRECTED MAJOR BUGS:\r\n- Incorrect center initialization in K-Means++ when candidates are not farthest (pyclustering.cluster.center_initializer).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F549","2019-10-10T07:16:16",{"id":215,"version":216,"summary_zh":217,"released_at":218},107182,"0.9.1","**pyclustering 0.9.1 library** is a collection of clustering algorithms and methods, oscillatory networks, neural networks, etc.\r\n\r\nGENERAL CHANGES:\r\n- Introduced `predict` method for X-Means algorithm to find closest clusters for particular points (pyclustering.cluster.xmeans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F540\r\n\r\n- Optimization of OPTICS algorithm by reducing complexity (ccore.clst.optics).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F521\r\n\r\n- Optimization of K-Medians algorithm by parallel processing (ccore.clst.kmedians).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F529\r\n\r\n- Introduced `predict` method for K-Medoids algorithm to find closest clusters for particular points (pyclustering.cluster.kmedoids).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F527\r\n\r\n- Introduced `predict` method for K-Means algorithm to find closest clusters for particular points (pyclustering.cluster.kmeans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F515\r\n\r\n- Parallel optimization of Elbow method. (ccore.clst.elbow).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F511","2019-09-04T11:25:46",{"id":220,"version":221,"summary_zh":222,"released_at":223},107183,"0.9.0","**pyclustering 0.9.0 library** is a collection of clustering algorithms and methods, oscillatory networks, neural networks, etc.\r\n\r\nGENERAL CHANGES:\r\n- CCORE (pyclustering core) is supported for MacOS.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F486\r\n\r\n- Introduced parallel Fuzzy C-Means algorithm (pyclustering.cluster.fcm, ccore.clst.fcm).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F386\r\n\r\n- Introduced new 'itermax' parameter for K-Means, K-Medians, K-Medoids algorithm to control maximum amount of iterations (pyclustering.cluster, ccore.clst).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F496\r\n\r\n- Implemented Silhouette and Silhouette K-Search algorithm for CCORE (ccore.clst.silhouette, ccore.clst.silhouette_ksearch).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F490\r\n\r\n- Implemented CLIQUE algorithms (pyclustering.cluster.clique, ccore.clst.clique).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F381\r\n\r\n- Introduced new distance metrics: Canberra and Chi Square (pyclustering.utils.metric, ccore.utils.metric).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F482\r\n\r\n- Optimization of CURE algorithm (C++ implementation) by using heap (multiset) instead of list to store clusters in queue (ccore.clst.cure).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F479\r\n\r\nCORRECTED MAJOR BUGS:\r\n- Bug with crossover mask generation for genetic clustering algorithm (pyclustering.cluster.ga).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fpull\u002F474\r\n\r\n- Bug with hanging of K-Medians algorithm for some cases when algorithm is initialized by wrong amount of centers (ccore.clst.kmedians).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F498\r\n\r\n- Bug with incorrect center initialization, when the same point can be placed to result more than once (pyclustering.cluster.center_initializer, ccore.clst.kmeans_plus_plus).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F497\r\n\r\n- Bug with incorrect clustering in case of CURE python implementation when clusters are allocated incorrectly (pyclustering.cluster.cure).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F483\r\n\r\n- Bug with incorrect distance calculation for kmeans++ in case of index representation for centers (pyclustering.cluster.center_initializer).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F485","2019-04-18T13:46:56",{"id":225,"version":226,"summary_zh":227,"released_at":228},107184,"0.8.2-joss","**pyclustering 0.8.2-joss library** is a collection of clustering algorithms and methods, oscillatory networks, neural networks, etc. \r\n\r\nIt is a special release for [JOSS](https:\u002F\u002Fjoss.theoj.org\u002F) (The Journal of Open Source Software). This version contains only cosmetic changes related to documentation and project description that have been introduced after JOSS reivew.","2019-04-11T19:25:33",{"id":230,"version":231,"summary_zh":232,"released_at":233},107185,"0.8.2","**pyclustering 0.8.2 library** is a collection of clustering algorithms and methods, oscillatory networks, neural networks, etc.\r\n\r\nGENERAL CHANGES:\r\n- Implemented Silhouette method and Silhouette KSearcher to find out proper amount of clusters (pyclustering.cluster.silhouette).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F416\r\n\r\n- Introduced new 'return_index' parameter for kmeans_plus_plus and random_center_initializer algorithms (method 'initialize') to initialize initial medoids (pyclustering.cluster.center_initializer).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F421\r\n\r\n- Display warning instead of throwing error if matplotlib or Pillow cannot be imported (MAC OS X problems).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F455\r\n\r\n- Implemented Random Center Initializer for CCORE (ccore.clst.random_center_initializer).\r\n  See: no reference.\r\n\r\n- Implemented Elbow method to find out proper amount of clusters in dataset (pyclustering.cluster.elbow, ccore.clst.elbow).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F416\r\n\r\n- Introduced new method 'get_optics_objects' for OPTICS algorithm to obtain detailed information about ordering (pyclustering.cluster.optics, ccore.clst.optics).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F464\r\n\r\n- Added new clustering answers for SAMPLE SIMPLE data collections (pyclustering.samples).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F459\r\n\r\n- Implemented multidimensional cluster visualizer (pyclustering.cluster).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F450\r\n\r\n- Parallel optimization of K-Medoids algorithm (ccore.clst.kmedoids).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F447\r\n\r\n- Parallel optimization of K-Means and X-Means (that uses K-Means) algorithms (ccore.clst.kmeans, ccore.clst.xmeans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F451\r\n\r\n- Introduced new threshold parameter 'amount of block points' to BANG algorithm to allocate outliers more precisely (pyclustering.cluster.bang).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F446\r\n\r\n- Optimization of conveying results from C++ to Python for K-Medians and K-Medoids (pyclustering.cluster.kmedoids, pyclustering.cluster.kmedians).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F445\r\n\r\n- Implemented cluster generator (pyclustering.cluster.generator).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F444\r\n\r\n- Implemented BANG animator to render animation of clustering process (pyclustering.cluster.bang).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F442\r\n\r\n- Optimization of CURE algorithm by using Euclidean Square distance (pyclustering.cluster.cure, ccore.clst.cure).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F439\r\n\r\n- Supported numpy.ndarray points in KD-tree (pyclustering.container.kdtree).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F438\r\n\r\n\r\nCORRECTED MAJOR BUGS:\r\n- Bug with clustering failure in case of non-numpy user defined metric for K-Means algorithm (pyclustering.cluster.kmeans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F471\r\n\r\n- Bug with animation of correlation matrix in case of new versions of matplotlib (pyclustering.nnet.sync).\r\n  See: no reference.\r\n\r\n- Bug with SOM and pickle when it was not possible to store and load network using pickle (pyclustering.nnet.som).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F456\r\n\r\n- Bug with DBSCAN when points are marked as a noise (pyclustering.cluster.dbscan).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F462\r\n\r\n- Bug with randomly enabled connection weights in case of SyncNet based algorithms using CCORE interface (pyclustering.nnet.syncnet).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F452\r\n\r\n- Bug with calculation weighted connection for Sync based clustering algorithms in C++ implementation (ccore.nnet.syncnet).\r\n  See: no reference\r\n\r\n- Bug with failure in case of numpy.ndarray data type in python part of CURE algorithm (pyclustering.cluster.cure).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F438\r\n\r\n- Bug with BANG algorithm with empty dimensions - when data contains column with the same values (pyclustering.cluster.bang).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F449\r\n","2018-11-19T11:38:29",{"id":235,"version":236,"summary_zh":237,"released_at":238},107186,"0.8.1","**pyclustering 0.8.1 library** is collection of clustering algorithms, oscillatory networks, neural networks, etc.\r\n\r\nGENERAL CHANGES:\r\n- Implemented feature to use specific metric for distance calculation in K-Means algorithm (pyclustering.cluster.kmeans, ccore.clst.kmeans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F434\r\n\r\n- Implemented BANG-clustering algorithm with result visualizer (pyclustering.cluster.bang).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F424\r\n\r\n- Implemented feature to use specific metric for distance calculation in K-Medians algorithm (pyclustering.cluster.kmedians, ccore.clst.kmedians).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F429\r\n\r\n- Supported new type of input data for K-Medoids - distance matrix (pyclustering.cluster.kmedoids, ccore.clst.kmedoids).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F418\r\n\r\n- Implemented TTSAS algorithm (pyclustering.cluster.ttsas, ccore.clst.ttsas).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F398\r\n\r\n- Implemented MBSAS algorithm (pyclustering.cluster.mbsas, ccore.clst.mbsas).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F398\r\n\r\n- Implemented BSAS algorithm (pyclustering.cluster.bsas, ccore.clst.bsas).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F398\r\n\r\n- Implemented feature to use specific metric for distance calculation in K-Medoids algorithm (pyclustering.cluster.kmedoids, ccore.clst.kmedoids).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F417\r\n\r\n- Implemented distance metric collection (pyclustering.utils.metric, ccore.utils.metric).\r\n  See: no reference.\r\n\r\n- Supported new type of input data for OPTICS - distance matrix (pyclustering.cluster.optics, ccore.clst.optics).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F412\r\n\r\n- Supported new type of input data for DBSCAN - distance matrix (pyclustering.cluster.dbscan, ccore.clst.dbscan).\r\n  See: no reference.\r\n\r\n- Implemented K-Means observer and visualizer to visualize and animate clustering results (pyclustering.cluster.kmeans, ccore.clst.kmeans).\r\n  See: no reference.\r\n\r\nCORRECTED MAJOR BUGS:\r\n- Bug with out of range in K-Medians (pyclustering.cluster.kmedians, ccore.clst.kmedians).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F428\r\n\r\n- Bug with fast linking in PCNN (python implementation only) that wasn't used despite the corresponding option (pyclustering.nnet.pcnn).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F419","2018-05-29T08:17:51",{"id":240,"version":241,"summary_zh":242,"released_at":243},107187,"0.8.0","**pyclustering 0.8.0 library** is collection of clustering algorithms, oscillatory networks, neural networks, etc.\r\n\r\nGENERAL CHANGES:\r\n- Optimization K-Means++ algorithm using numpy (pyclustering.cluster.center_initializer).\r\n  See: no reference.\r\n\r\n- Implemented K-Means++ initializer for CCORE (ccore.clst.kmeans_plus_plus).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F382\r\n\r\n- Optimization of X-Means clustering process by using KMeans++ for initial centers of split regions (pyclustering.cluster.xmeans, ccore.clst.xmeans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F382\r\n\r\n- Implemented parallel Sync-family algorithms for C\u002FC++ implementation (CCORE) only (ccore.sync).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F170\r\n\r\n- C\u002FC++ implementation is used by default to increase performance.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F393\r\n\r\n- Ignore 'ccore' flag to use C\u002FC++ if platform is not supported (pyclustering.core).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F393\r\n\r\n- Optimization of python implementation of the K-Means algorithm using numpy (pyclustering.cluster.kmeans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F403\r\n\r\n- Implemented dynamic visualizer for oscillatory networks (pyclustering.nnet.dynamic_visualizer).\r\n  See: no reference.\r\n\r\n- Implemented C\u002FC++ Hodgkin-Huxley oscillatory network for image segmentation in CCORE to increase performance (ccore.hhn, pyclustering.nnet.hhn).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F217\r\n\r\n- Performance optimization for CCORE on linux platform.\r\n  See: no reference.\r\n\r\n- 32-bit platform of CCORE is supported for Linux OS.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F253\r\n\r\n- 32-bit platform of CCORE is supported for Windows OS.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F253\r\n\r\n- Implemented method 'get_probabilities()' for obtaining belong probability in EM-algorithm (pyclustering.cluster.ema).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F387\r\n\r\n- Python implementation of CURE algorithm method 'get_clusters()' returns list of indexes (pyclustering.cluster.cure).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F384\r\n\r\n- Implemented parallel processing for X-Means algorithm (ccore.clst.xmeans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F372\r\n\r\n- Implemented pool threads for parallel processing (ccore.parallel).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F383\r\n\r\n- Optimization of OPTICS algorithm using KD-tree for searching nearest neighbors (pyclustering.cluster.optics, ccore.optics).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F370\r\n\r\n- Optimization of DBSCAN algorithm using KD-tree for searching nearest neighbors (pyclustering.cluster.dbscan, ccore.dbscan).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F369\r\n\r\n\r\nCORRECTED MAJOR BUGS:\r\n- Incorrect type of medoid's index in K-Medians algorithm in case of Python 2.x (pyclustering.cluster.kmedoids).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F415\r\n\r\n- Hanging of method 'find_node' in KD-tree if it does not contain node with specified point and payload (pyclustering.container.kdtree).\r\n  See: no reference.\r\n\r\n- Incorrect clustering by CURE algorithm in some cases when data have a lot of identical points (pyclustering.cluster.cure).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F414\r\n\r\n- Segmentation fault in CURE algorithm in some cases when data have a lot of identical points (ccore.clst.cure).\r\n  See: no reference.\r\n\r\n- Incorrect segmentation by Python version of syncsegm - oscillatory network based on sync for image segmentation (pyclustering.nnet.syncsegm).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F409\r\n\r\n- Zero value of sigma under logarithm function in Python version of pyclustering X-Means algorithm (pyclustering.cluster.xmeans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F407\r\n\r\n- Amplitude threshold is ignored during synchronous ensembles allocation for amplitude output dynamic 'allocate_sync_ensembles' - affect HNN, LEGION (pyclustering.utils).\r\n  See: no reference.\r\n\r\n- Wrong indexes can be returned during synchronous ensembles allocation for amplitude output dynamic 'allocate_sync_ensembles' - affect HNN, LEGION (pyclustering.utils).\r\n  See: no reference.\r\n\r\n- Amount of allocated clusters can be differ from amount of centers in X-Means algorithm (ccore.clst.xmeans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F389\r\n\r\n- Amount of allocated clusters can be bigger than kmax in X-Means algorithm (pyclustering.cluster.xmeans, ccore.clst.xmeans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F388\r\n\r\n- Corrected bug with returned nullptr in method 'kdtree_searcher::find_nearest_node()' (ccore.container.kdtree).\r\n  See: no reference.","2018-02-23T15:37:30",{"id":245,"version":246,"summary_zh":247,"released_at":248},107188,"0.7.2","pyclustering 0.7.2 library is collection of clustering algorithms, oscillatory networks, neural networks, etc.\r\n\r\nGENERAL CHANGES (pyclustering):\r\n- Correction for setup failure with PKG-INFO.rst.","2017-10-23T09:53:34",{"id":250,"version":251,"summary_zh":252,"released_at":253},107189,"0.7.1","**pyclustering 0.7.1** library is collection of clustering algorithms, osicllatory networks, neural networks, etc.\r\n\r\nGENERAL CHANGES (pyclustering):\r\n- Metadata of the package is updated.","2017-10-19T10:48:25",{"id":255,"version":256,"summary_zh":257,"released_at":258},107190,"0.7.0","**pyclustering 0.7.0** library is collection of clustering algorithms, oscllatory networks, neural networks, etc.\r\n\r\nGENERAL CHANGES (pyclustering):\r\n- Implemented Expectation-Maximization clustering algorithm for Gaussian Mixute Model and clustering visualizer for this particular algorithm (pyclustering.cluster.ema)\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F16\r\n\r\n- Implemented Genetic Clustering Algorithm (GCA) and clustering visualizer for this particular algorithm (pyclustering.cluster.ga)\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F360\r\n\r\n- Implemented feature to obtain and visualize evolution of order parameter and local order parameter for Sync network and Sync-based algorithms (pyclustering.nnet.sync).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F355\r\n\r\n- Implemented K-Means++ method for initialization of initial centers for algorithms like K-Means or X-Means (pyclustering.cluster.center_initializer).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F354\r\n\r\n- Implemented fSync oscillatory network that is based on Landau-Stuart equation and Kuramoto model (pyclustering.nnet.fsync).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F168\r\n\r\n- Optimization of pyclustering client to core library 'CCORE' library (pyclustering.core).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F289\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F351\r\n\r\n- Implemented feature to show network structure of Sync family oscillatory networks in case 'ccore' usage.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F344\r\n\r\n- Implemented feature to colorize OPTICS ordering diagram when amount of clusters is specified.\r\n  See: no reference.\r\n\r\n- Improved clustering results in case of usage MNDL splitting criterion for small datasets.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F328\r\n\r\n- Feature to display connectivity radius on cluster-ordering diagram by ordering_visualizer (pyclustering.cluster.optics).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F314\r\n\r\n- Feature to use CCORE implementation of OPTICS algorithm to take advance in performance (pyclustering.cluster.optics).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F120\r\n\r\n- Implemented feature to shows animation of pattern recognition process that has been performed by the SyncPR oscillatory network. Method 'animate_pattern_recognition()' of class 'syncpr_visualizer' (pyclustering.nnet.syncpr).\r\n  See: https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Ro7KbApL4MQ\r\n  See: https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=iIusOsGehoY\r\n\r\n- Implemented feature to obtain nodes of specified level of CF-tree. Method 'get_level_nodes()' of class 'cftree' (pyclustering.container.cftree).\r\n  See: no reference.\r\n\r\n- Implemented feature to allocate\u002Fdisplay\u002Fanimate phase matrix: 'allocate_phase_matrix()', 'show_phase_matrix()', 'animate_phase_matrix()' (pyclustering.nnet.sync).\r\n  See: no reference.\r\n\r\n- Implemented chaotic neural network where clustering phenomenon can be observed: 'cnn_network', 'cnn_dynamic', 'cnn_visualizer' (pyclustering.nnet.cnn).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F301\r\n\r\n- Implemented feature to analyse ordering diagram using amout of clusters that should be allocated as an input parameter to calculate correct connvectity radius for clustering (pyclustering.cluster.optics).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F307\r\n\r\n- Implemented feature to omit usage of initial centers - X-Means starts processing from random initial center (pyclustering.cluster.xmeans).\r\n  See: no reference.\r\n\r\n- Implemented feature for cluster visualizer: cluster attributes (pyclustering.cluster).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F295\r\n\r\n- Implemented SOM-SC algorithm (SOM Simple Clustering) (pyclustering.cluster.somsc).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F321\r\n\r\n\r\nGENERAL CHANGES (ccore):\r\n- Implemented feature to obtain and visualize evolution of order parameter and local order parameter for Sync network and Sync-based algorithms (ccore.nnet.sync).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F355\r\n\r\n- Cygwin x64 platform is supported (ccore).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F353\r\n\r\n- Optimization of CCORE library interface (ccore.interface).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F289\r\n\r\n- Implemented MNDL splitting crinterion for X-Means algorithm (ccore.cluster_analysis.xmeans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F159\r\n\r\n- Implemented OPTICS algorithm and interface for client that results all clustering results (ccore.cluster_analysis.optics).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F120\r\n\r\n- Implmeneted packing of connectivity matrix of Sync family oscillatory networks (ccore.interface.sync_interface).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F344\r\n\r\n\r\nCORRECTED MAJOR BUGS:\r\n- Bug with segmentation fault during 'free()' on some linux operating systems","2017-10-16T20:23:36",{"id":260,"version":261,"summary_zh":262,"released_at":263},107191,"0.6.6","**pyclustring 0.6.6** library is collection of clustering algorithms, oscllatory networks, neural networks, etc.\r\n\r\nGENERAL CHANGES (pyclustering):\r\n- Implemented phase oscillatory network syncpr (pyclustering.nnet.syncpr).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F208\r\n- Feature for pyclustering.nnet.syncpr that allows to use ccore library for solving.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F232\r\n- Optimized simulation algorithm for sync oscillatory network (pyclustering.nnet.sync) when collecting results are not requested.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F233\r\n- Images of english alphabet 100x100.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fcommit\u002Faa28f1a8a363fbeb5f074d22ec1e8258a1dd0579\r\n- Implemented feature to use rectangular network structures in oscillatory networks.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F259\r\n- Implemented CLARANS algorithm (pyclustering.cluster.clarans).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F52\r\n- Implemented feature to analyse and visualize results of hysteresis oscillatory network (pyclustering.nnet.hysteresis).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F75\r\n- Implemented feature to analyse and visualize results of graph coloring algorithm based on hysteresis oscillatory network (pyclustering.gcolor.hysteresis).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F75\r\n- Implemented ant colony based algorithm for TSP problem (pyclustering.tsp.antcolony).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fpull\u002F277\r\n- Implemented feature to use CCORE K-Medians algorithm using argument 'ccore' to ensure high performance (pyclustering.cluster.kmedians).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F231\r\n- Implemented feature to place several plots on each row using parameter 'maximum number of rows' for cluster visualizer (pyclustering.cluster).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F274\r\n- Implemented feature to specify initial number of neighbors to calculate initial connectivity radius and increase percent of number of neighbors (or radius if total number of object is exceeded) on each step (pyclustering.cluster.hsyncnet).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F284\r\n- Implemented double-layer oscillatory network based on modified Kuramoto model for image segmentation (pyclustering.nnet.syncsegm).\r\n  See: no reference\r\n- Added new examples and demos.\r\n  See: no reference\r\n- Implemented feature to use CCORE K-Medoids algorithm using argument 'ccore' to ensure high performance (pyclustering.cluster.kmedoids).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F230\r\n- Implemented feature for CURE algorithm that provides additional information about clustering results: representative points and mean point of each cluster (pyclustering.cluster.cure).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F292\r\n- Implemented feature to animate analysed output dynamic of Sync family oscillatory networks (sync_visualizer, syncnet_visualizer): correlation matrix, phase coordinates, cluster allocation (pyclustering.nnet.sync, pyclustering.cluster.syncnet).\r\n  See: https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=5S5mFYVihso\r\n  See: https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Vd-ww9PcZvI\r\n  See: https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=QYPqWoyNHO8\r\n  See: https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=RA0MiC2WlbY\r\n- Improved algorithm SYNC-SOM: accuracy of clustering and calculation are improved in line with proof of concept where connection between oscillator in the second layer (that is represented by the self-organized feature map) should be created in line with classical radius like in SyncNet, but indirectly: if objects that correspond to two different neurons can be connected than neurons should be also connected with each other (pyclustering.cluster.syncsom).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F297\r\n\r\nGENERAL CHANGES (ccore):\r\n- Implemented phase oscillatory network for pattern recognition syncpr (ccore.cluster.syncpr).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F232\r\n- Implemented agglomerative algorithm for cluster analysis (ccore.cluster.agglomerative).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F212\r\n- Implemented feature to use rectangular network structures in oscillatory networks.\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F259\r\n- Implemented ant colony based algorithm for TSP problem (ccore.tsp.antcolony).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fpull\u002F277\r\n- Implemented K-Medians algorithm for cluster analysis (ccore.cluster.kmedians).\r\n  See: https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F231\r\n- Implemented feature to specify initial number of neighbors to calculate initial connectivity radius and increase percent of number of neighbors (or radius if total number of object is exceeded) on each step (ccore.cluster.hsyncnet).\r\n  https:\u002F\u002Fgithub.com\u002Fannoviko\u002Fpyclustering\u002Fissues\u002F284\r\n- Implemented K-Medoids algorithm f","2016-10-07T16:26:02"]