[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-Yimeng-Zhang--feature-engineering-and-feature-selection":3,"tool-Yimeng-Zhang--feature-engineering-and-feature-selection":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",140436,2,"2026-04-05T23:32:43",[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":79,"owner_email":79,"owner_twitter":79,"owner_website":79,"owner_url":80,"languages":81,"stars":90,"forks":91,"last_commit_at":92,"license":79,"difficulty_score":93,"env_os":94,"env_gpu":94,"env_ram":94,"env_deps":95,"category_tags":104,"github_topics":105,"view_count":112,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":113,"updated_at":114,"faqs":115,"releases":121},451,"Yimeng-Zhang\u002Ffeature-engineering-and-feature-selection","feature-engineering-and-feature-selection","A Guide for Feature Engineering and Feature Selection, with implementations and examples in Python.","feature-engineering-and-feature-selection 是一份专注于机器学习核心环节——特征工程与特征选择的综合指南。它不仅系统讲解了相关理论知识，还提供了基于 Python 的代码实现与具体示例，帮助用户从零构建对数据的理解。\n\n在机器学习项目中，数据和特征的质量直接决定了模型性能的上限，但市面上往往缺乏系统性的学习资料。feature-engineering-and-feature-selection 正是为了解决这一问题而生，它详细阐述了数据问题的本质、各种特征处理技术的原理、适用场景及其优缺点，让读者不仅知其然，更知其所以然。\n\n这份指南非常适合机器学习初学者、数据科学家以及希望优化模型性能的开发者阅读。其亮点在于“理论与实践并重”，既不是枯燥的代码堆砌，也不是空洞的理论说教，而是深入剖析了“为什么、怎么做、何时做”的决策逻辑。项目提供了 PDF 和 Markdown 两种格式，方便用户随时查阅，是提升数据挖掘能力的实用参考手册。","# Feature Engineering & Feature Selection\n\nA comprehensive guide [[pdf]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.pdf) [[markdown]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md) for **Feature Engineering** and **Feature Selection**, with implementations and examples in Python.\n\n## Motivation\n\nFeature Engineering & Selection is the most essential part of building a useable machine learning project, even though hundreds of cutting-edge machine learning algorithms coming in these days like deep learning and transfer learning. Indeed, like what Prof Domingos, the author of  'The Master Algorithm' says:\n\n> “At the end of the day, some machine learning projects succeed and some fail. What makes the difference? Easily the most important factor is the features used.”\n>\n> — Prof. Pedro Domingos\n\n![001](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FYimeng-Zhang_feature-engineering-and-feature-selection_readme_ff333afca999.png)\n\n\n\nData and feature has the most impact on a ML project and sets the limit of how well we can do, while models and algorithms are just approaching that limit. However, few materials could be found that systematically introduce the art of feature engineering, and even fewer could explain the rationale behind. This repo is my personal notes from learning ML and serves as a reference for Feature Engineering & Selection.\n\n## Download\n\nDownload the PDF here:\n\n- https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.pdf\n\nSame, but in markdown:\n\n- https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md\n\nPDF has a much readable format, while Markdown has auto-generated anchor link to navigate from outer source. GitHub sucks at displaying markdown with complex grammar, so I would suggest read the PDF or download the repo and read markdown with [Typora](https:\u002F\u002Ftypora.io\u002F). \n\n\n\n## What You'll Learn\n\nNot only a collection of hands-on functions, but also explanation on  **Why**, **How** and **When** to adopt **Which** techniques of feature engineering in data mining. \n\n- the nature and risk of data problem we often encounter\n- explanation of the various feature engineering & selection techniques\n- rationale to use it\n- pros & cons of each method \n- code & example\n\n\n\n## Getting Started\n\nThis repo is mainly used as a reference for anyone who are doing feature engineering, and most of the modules are implemented through scikit-learn or its communities.\n\nTo run the demos or use the customized function,  please download the ZIP file from the repo or just copy-paste any part of the code you find helpful. They should all be very easy to understand.\n\n**Required Dependencies**:\n\n- Python 3.5, 3.6 or 3.7\n- numpy>=1.15\n- pandas>=0.23\n- scipy>=1.1.0\n- scikit_learn>=0.20.1\n- seaborn>=0.9.0\n\n\n\n## Table of Contents and Code Examples\n\nBelow is a list of methods currently implemented in the repo. \n\n**1. Data Exploration**\n\n  -    1.1 Variables \n  -    1.2 Variable Identification  \n       -  Check Data Types   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#12-variable-identification)  [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)\n  -    1.3 Univariate Analysis  \n       -  Descriptive Analysis   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#13-univariate-analysis)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)  \n       -  Discrete Variable Barplot   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#13-univariate-analysis)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)  \n       -  Discrete Variable Countplot   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#13-univariate-analysis)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)  \n       -  Discrete Variable Boxplot   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#13-univariate-analysis)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)  \n       -  Continuous Variable Distplot   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#13-univariate-analysis)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)\n  -    1.4 Bi-variate Analysis  \n       -  Scatter Plot   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#14-bi-variate-analysis)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)  \n       -  Correlation Plot   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#14-bi-variate-analysis)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)  \n       -  Heat Map   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#14-bi-variate-analysis)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)\n\n**2. Feature Cleaning**\n\n  -    2.1 Missing Values  \n       -  Missing Value Check   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#214-how-to-handle-missing-data)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)  \n       -  Listwise Deletion   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#214-how-to-handle-missing-data)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)  \n       -  Mean\u002FMedian\u002FMode Imputation   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#214-how-to-handle-missing-data)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)  \n       -  End of distribution Imputation   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#214-how-to-handle-missing-data)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)  \n       -  Random Imputation   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#214-how-to-handle-missing-data)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)  \n       -  Arbitrary Value Imputation   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#214-how-to-handle-missing-data)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)  \n       -  Add a variable to denote NA   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#214-how-to-handle-missing-data)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)\n  -    2.2 Outliers  \n       -  Detect by Arbitrary Boundary   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#222-outlier-detection)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)  \n       -  Detect by Mean & Standard Deviation   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#222-outlier-detection)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)  \n       -  Detect by IQR    [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#222-outlier-detection)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)  \n       -  Detect by MAD      [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#222-outlier-detection)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)  \n       -  Mean\u002FMedian\u002FMode Imputation   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#223-how-to-handle-outliers)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)  \n       -  Discretization   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#223-how-to-handle-outliers)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.2_Demo_Discretisation.ipynb)  \n       -  Imputation with Arbitrary Value   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#223-how-to-handle-outliers)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)  \n       -  Windsorization   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#223-how-to-handle-outliers)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)  \n       -  Discard Outliers   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#223-how-to-handle-outliers)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)\n  -    2.3 Rare Values  \n       -  Mode Imputation     [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#23-rare-values)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.3_Demo_Rare_Values.ipynb)  \n       -  Grouping into One New Category   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#23-rare-values)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.3_Demo_Rare_Values.ipynb)\n  -    2.4 High Cardinality  \n       -  Grouping Labels with Business Understanding    [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#24-high-cardinality)   \n       -  Grouping Labels with Rare Occurrence into One Category   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#24-high-cardinality)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.3_Demo_Rare_Values.ipynb)  \n       -  Grouping Labels with Decision Tree   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#24-high-cardinality)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.2_Demo_Discretisation.ipynb)\n\n**3. Feature Engineering**\n  -    3.1 Feature Scaling    \n       -  Normalization - Standardization    [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#31-feature-scaling)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.1_Demo_Feature_Scaling.ipynb)  \n       -  Min-Max Scaling   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#31-feature-scaling)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.1_Demo_Feature_Scaling.ipynb)  \n       -  Robust Scaling   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#31-feature-scaling)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.1_Demo_Feature_Scaling.ipynb)\n  -    3.2 Discretize     \n       -  Equal Width Binning   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#32-discretize)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.2_Demo_Discretisation.ipynb)  \n       -  Equal Frequency Binning   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#32-discretize)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.2_Demo_Discretisation.ipynb)  \n       -  K-means Binning      [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#32-discretize)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.2_Demo_Discretisation.ipynb)  \n       -  Discretization by Decision Trees   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#32-discretize)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.2_Demo_Discretisation.ipynb)  \n       -  ChiMerge   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#32-discretize)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.2_Demo_Discretisation.ipynb)\n  -    3.3 Feature Encoding  \n       -  One-hot Encoding   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#33-feature-encoding)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.3_Demo_Feature_Encoding.ipynb)  \n       -  Ordinal-Encoding   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#33-feature-encoding)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.3_Demo_Feature_Encoding.ipynb)  \n       -  Count\u002Ffrequency Encoding    [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#33-feature-encoding)   \n       -  Mean Encoding   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#33-feature-encoding)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.3_Demo_Feature_Encoding.ipynb)  \n       -  WOE Encoding   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#33-feature-encoding)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.3_Demo_Feature_Encoding.ipynb)  \n       -  Target Encoding   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#33-feature-encoding)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.3_Demo_Feature_Encoding.ipynb)\n  -    3.4 Feature Transformation  \n       -  Logarithmic Transformation   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#34-feature-transformation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.4_Demo_Feature_Transformation.ipynb)  \n       -  Reciprocal Transformation   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#34-feature-transformation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.4_Demo_Feature_Transformation.ipynb)  \n       -  Square Root Transformation   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#34-feature-transformation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.4_Demo_Feature_Transformation.ipynb)  \n       -  Exponential Transformation   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#34-feature-transformation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.4_Demo_Feature_Transformation.ipynb)  \n       -  Box-cox Transformation   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#34-feature-transformation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.4_Demo_Feature_Transformation.ipynb)  \n       -  Quantile Transformation   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#34-feature-transformation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.4_Demo_Feature_Transformation.ipynb)\n  -    3.5 Feature Generation  \n       -  Missing Data Derived   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)  \n       -  Simple Stats   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)   \n       -  Crossing   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)   \n       -  Ratio & Proportion   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)   \n       -  Cross Product   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)   \n       -  Polynomial   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)  [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.5_Demo_Feature_Generation.ipynb)  \n       -  Feature Learning by Tree   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.5_Demo_Feature_Generation.ipynb)  \n       -  Feature Learning by Deep Network   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)  \n\n**4. Feature Selection**\n\n  -    4.1 Filter Method  \n       -  Variance   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#41-filter-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.1_Demo_Feature_Selection_Filter.ipynb)  \n       -  Correlation   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#41-filter-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.1_Demo_Feature_Selection_Filter.ipynb)  \n       -  Chi-Square   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#41-filter-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.1_Demo_Feature_Selection_Filter.ipynb)  \n       -  Mutual Information Filter   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#41-filter-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.1_Demo_Feature_Selection_Filter.ipynb)  \n       -  Information Value (IV)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#41-filter-method) \n  -    4.2 Wrapper Method  \n       -  Forward Selection   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#42-wrapper-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.2_Demo_Feature_Selection_Wrapper.ipynb)  \n       -  Backward Elimination   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#42-wrapper-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.2_Demo_Feature_Selection_Wrapper.ipynb)  \n       -  Exhaustive Feature Selection   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#42-wrapper-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.2_Demo_Feature_Selection_Wrapper.ipynb)  \n       -  Genetic Algorithm   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#42-wrapper-method) \n  -    4.3 Embedded Method  \n       -  Lasso (L1)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#43-embedded-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.3_Demo_Feature_Selection_Embedded.ipynb)  \n       -  Random Forest Importance   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#43-embedded-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.3_Demo_Feature_Selection_Embedded.ipynb)  \n       -  Gradient Boosted Trees Importance   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#43-embedded-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.3_Demo_Feature_Selection_Embedded.ipynb)\n  -    4.4 Feature Shuffling  \n       -  Random Shuffling   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#44-feature-shuffling)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.4_Demo_Feature_Selection_Feature_Shuffling.ipynb)\n  -    4.5 Hybrid Method  \n       -  Recursive Feature Selection    [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#451-recursive-feature-elimination)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.5_Demo_Feature_Selection_Hybrid_method.ipynb)  \n       -  Recursive Feature Addition   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#452-recursive-feature-addition)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.5_Demo_Feature_Selection_Hybrid_method.ipynb)\n\n\n\n## Key Links and Resources\n\n- Udemy's Feature Engineering online course\n\nhttps:\u002F\u002Fwww.udemy.com\u002Ffeature-engineering-for-machine-learning\u002F\n\n- Udemy's Feature Selection online course\n\nhttps:\u002F\u002Fwww.udemy.com\u002Ffeature-selection-for-machine-learning\n\n- JMLR Special Issue on Variable and Feature Selection\n\nhttp:\u002F\u002Fjmlr.org\u002Fpapers\u002Fspecial\u002Ffeature03.html\n\n- Data Analysis Using Regression and Multilevel\u002FHierarchical Models, Chapter 25: Missing data\n\nhttp:\u002F\u002Fwww.stat.columbia.edu\u002F~gelman\u002Farm\u002Fmissing.pdf\n\n- Data mining and the impact of missing data\n\nhttp:\u002F\u002Fcore.ecu.edu\u002Fomgt\u002Fkrosj\u002FIMDSDataMining2003.pdf\n\n- PyOD: A Python Toolkit for Scalable Outlier Detection\n\nhttps:\u002F\u002Fgithub.com\u002Fyzhao062\u002Fpyod\n\n- Weight of Evidence (WoE) Introductory Overview\n\nhttp:\u002F\u002Fdocumentation.statsoft.com\u002FStatisticaHelp.aspx?path=WeightofEvidence\u002FWeightofEvidenceWoEIntroductoryOverview\n\n- About Feature Scaling and Normalization\n\nhttp:\u002F\u002Fsebastianraschka.com\u002FArticles\u002F2014_about_feature_scaling.html\n\n- Feature Generation with RF, GBDT and Xgboost\n\nhttps:\u002F\u002Fblog.csdn.net\u002Fanshuai_aw1\u002Farticle\u002Fdetails\u002F82983997\n\n- A review of feature selection methods with applications\n\nhttps:\u002F\u002Fieeexplore.ieee.org\u002Fiel7\u002F7153596\u002F7160221\u002F07160458.pdf\n\n\n","# 特征工程与特征选择\n\n一份关于**特征工程 (Feature Engineering)** 和**特征选择 (Feature Selection)** 的综合指南 [[pdf]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.pdf) [[markdown]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md)，包含 Python 实现与示例。\n\n## 动机\n\n尽管如今涌现出数百种前沿的机器学习算法，如深度学习 (Deep Learning) 和迁移学习 (Transfer Learning)，但特征工程与特征选择仍然是构建实用机器学习 (Machine Learning) 项目中最关键的部分。事实上，正如《终极算法》(The Master Algorithm) 的作者 Domingos 教授所言：\n\n> “归根结底，有些机器学习项目成功了，有些则失败了。区别在哪里？最重要的因素无疑是所使用的特征。”\n>\n> — Pedro Domingos 教授\n\n![001](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FYimeng-Zhang_feature-engineering-and-feature-selection_readme_ff333afca999.png)\n\n数据和特征对机器学习项目的影响最大，并决定了我们能做到的极限，而模型和算法只是在不断逼近这个极限。然而，目前很少有资料能系统地介绍特征工程的艺术，能解释其背后原理的更是寥寥无几。本仓库是我在学习机器学习过程中的个人笔记，旨在作为特征工程与特征选择的参考资料。\n\n## 下载\n\n在此下载 PDF：\n\n- https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.pdf\n\n同样的内容，Markdown 版本：\n\n- https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md\n\nPDF 的格式更具可读性，而 Markdown 拥有自动生成的锚点链接，便于从外部源导航。GitHub 在显示语法复杂的 Markdown 时效果不佳，因此建议阅读 PDF，或者下载本仓库并使用 [Typora](https:\u002F\u002Ftypora.io\u002F) 阅读 Markdown。\n\n## 你将学到什么\n\n这不仅是实用函数的集合，更解释了在数据挖掘中**为什么**、**如何**以及**何时**采用**哪种**特征工程技术。\n\n- 我们常遇到的数据问题的本质与风险\n- 各种特征工程与特征选择技术的解释\n- 使用原理\n- 每种方法的优缺点\n- 代码与示例\n\n## 快速开始\n\n本仓库主要供进行特征工程的人员作为参考，大部分模块通过 scikit-learn 或其社区实现。\n\n要运行演示或使用自定义函数，请从仓库下载 ZIP 文件，或者直接复制粘贴您觉得有帮助的任何代码部分。它们应该都非常易于理解。\n\n**所需依赖**：\n\n- Python 3.5, 3.6 or 3.7\n- numpy>=1.15\n- pandas>=0.23\n- scipy>=1.1.0\n- scikit_learn>=0.20.1\n- seaborn>=0.9.0\n\n## 目录与代码示例\n\n以下是本仓库中目前已实现的方法列表。\n\n**1. 数据探索**\n\n  -    1.1 变量\n  -    1.2 变量识别\n       -  检查数据类型   [[指南]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#12-variable-identification)  [[演示]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)\n  -    1.3 单变量分析\n       -  描述性分析   [[指南]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#13-univariate-analysis)   [[演示]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)\n       -  离散变量条形图 (Barplot)   [[指南]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#13-univariate-analysis)   [[演示]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)\n       -  离散变量计数图 (Countplot)   [[指南]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#13-univariate-analysis)   [[演示]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)\n       -  离散变量箱线图 (Boxplot)   [[指南]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#13-univariate-analysis)   [[演示]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)\n       -  连续变量分布图 (Distplot)   [[指南]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#13-univariate-analysis)   [[演示]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)\n  -    1.4 双变量分析\n       -  散点图   [[指南]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#14-bi-variate-analysis)   [[演示]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)\n       -  相关性图   [[指南]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#14-bi-variate-analysis)   [[演示]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)\n       -  热力图   [[指南]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#14-bi-variate-analysis)   [[演示]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F1_Demo_Data_Explore.ipynb)\n\n**2. 特征清洗**\n\n-    2.1 缺失值  \n       -  缺失值检查   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#214-how-to-handle-missing-data)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)  \n       -  列表删除   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#214-how-to-handle-missing-data)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)  \n       -  均值\u002F中位数\u002F众数填充   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#214-how-to-handle-missing-data)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)  \n       -  分布末端填充   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#214-how-to-handle-missing-data)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)  \n       -  随机填充   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#214-how-to-handle-missing-data)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)  \n       -  任意值填充   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#214-how-to-handle-missing-data)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)  \n       -  添加变量以标记 NA   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#214-how-to-handle-missing-data)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)\n  -    2.2 异常值  \n       -  通过任意边界检测   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#222-outlier-detection)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)  \n       -  通过均值和标准差检测   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#222-outlier-detection)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)  \n       -  通过 IQR (四分位距) 检测    [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#222-outlier-detection)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)  \n       -  通过 MAD (中位数绝对偏差) 检测      [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#222-outlier-detection)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)  \n       -  均值\u002F中位数\u002F众数填充   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#223-how-to-handle-outliers)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)  \n       -  离散化   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#223-how-to-handle-outliers)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.2_Demo_Discretisation.ipynb)  \n       -  任意值填充   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#223-how-to-handle-outliers)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)  \n       -  缩尾处理   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#223-how-to-handle-outliers)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)  \n       -  丢弃异常值   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#223-how-to-handle-outliers)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.2_Demo_Outlier.ipynb)\n  -    2.3 稀有值  \n       -  众数填充     [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#23-rare-values)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.3_Demo_Rare_Values.ipynb)  \n       -  合并为一个新类别   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#23-rare-values)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.3_Demo_Rare_Values.ipynb)\n  -    2.4 高基数  \n       -  结合业务理解对标签分组    [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#24-high-cardinality)   \n       -  将稀有出现的标签合并为一类   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#24-high-cardinality)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.3_Demo_Rare_Values.ipynb)  \n       -  使用决策树对标签分组   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#24-high-cardinality)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.2_Demo_Discretisation.ipynb)\n\n**3. 特征工程**\n  -    3.1 特征缩放    \n       -  归一化 - 标准化    [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#31-feature-scaling)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.1_Demo_Feature_Scaling.ipynb)  \n       -  Min-Max 缩放   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#31-feature-scaling)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.1_Demo_Feature_Scaling.ipynb)  \n       -  鲁棒缩放   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#31-feature-scaling)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.1_Demo_Feature_Scaling.ipynb)\n  -    3.2 离散化     \n       -  等宽分箱   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#32-discretize)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.2_Demo_Discretisation.ipynb)  \n       -  等频分箱   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#32-discretize)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.2_Demo_Discretisation.ipynb)  \n       -  K-means 分箱      [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#32-discretize)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.2_Demo_Discretisation.ipynb)  \n       -  决策树离散化   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#32-discretize)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.2_Demo_Discretisation.ipynb)  \n       -  ChiMerge (卡方分箱)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#32-discretize)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.2_Demo_Discretisation.ipynb)\n  -    3.3 特征编码  \n       -  One-hot 编码 (独热编码)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#33-feature-encoding)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.3_Demo_Feature_Encoding.ipynb)  \n       -  序数编码   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#33-feature-encoding)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.3_Demo_Feature_Encoding.ipynb)  \n       -  计数\u002F频率编码    [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#33-feature-encoding)   \n       -  均值编码   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#33-feature-encoding)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.3_Demo_Feature_Encoding.ipynb)  \n       -  WOE 编码   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#33-feature-encoding)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.3_Demo_Feature_Encoding.ipynb)  \n       -  目标编码   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#33-feature-encoding)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.3_Demo_Feature_Encoding.ipynb)\n  -    3.4 特征变换  \n       -  对数变换   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#34-feature-transformation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.4_Demo_Feature_Transformation.ipynb)  \n       -  倒数变换   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#34-feature-transformation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.4_Demo_Feature_Transformation.ipynb)  \n       -  平方根变换   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#34-feature-transformation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.4_Demo_Feature_Transformation.ipynb)  \n       -  指数变换   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#34-feature-transformation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.4_Demo_Feature_Transformation.ipynb)  \n       -  Box-cox 变换   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#34-feature-transformation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.4_Demo_Feature_Transformation.ipynb)  \n       -  分位数变换   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#34-feature-transformation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.4_Demo_Feature_Transformation.ipynb)\n  -    3.5 特征生成  \n       -  缺失数据衍生   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F2.1_Demo_Missing_Data.ipynb)  \n       -  简单统计   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)   \n       -  特征交叉   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)   \n       -  比率与比例   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)   \n       -  交叉积   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)   \n       -  多项式特征   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)  [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.5_Demo_Feature_Generation.ipynb)  \n       -  基于树的特征学习   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F3.5_Demo_Feature_Generation.ipynb)  \n       -  基于深度网络的特征学习   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#35-feature-generation)\n\n**4. 特征选择**\n\n  -    4.1 Filter Method (过滤法)\n       -  Variance (方差)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#41-filter-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.1_Demo_Feature_Selection_Filter.ipynb)  \n       -  Correlation (相关性)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#41-filter-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.1_Demo_Feature_Selection_Filter.ipynb)  \n       -  Chi-Square (卡方检验)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#41-filter-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.1_Demo_Feature_Selection_Filter.ipynb)  \n       -  Mutual Information Filter (互信息过滤)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#41-filter-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.1_Demo_Feature_Selection_Filter.ipynb)  \n       -  Information Value (IV) (信息价值)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#41-filter-method) \n  -    4.2 Wrapper Method (包装法)\n       -  Forward Selection (前向选择)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#42-wrapper-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.2_Demo_Feature_Selection_Wrapper.ipynb)  \n       -  Backward Elimination (后向消除)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#42-wrapper-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.2_Demo_Feature_Selection_Wrapper.ipynb)  \n       -  Exhaustive Feature Selection (穷举特征选择)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#42-wrapper-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.2_Demo_Feature_Selection_Wrapper.ipynb)  \n       -  Genetic Algorithm (遗传算法)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#42-wrapper-method) \n  -    4.3 Embedded Method (嵌入法)\n       -  Lasso (L1 正则化)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#43-embedded-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.3_Demo_Feature_Selection_Embedded.ipynb)  \n       -  Random Forest Importance (随机森林重要性)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#43-embedded-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.3_Demo_Feature_Selection_Embedded.ipynb)  \n       -  Gradient Boosted Trees Importance (梯度提升树重要性)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#43-embedded-method)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.3_Demo_Feature_Selection_Embedded.ipynb)\n  -    4.4 Feature Shuffling (特征混洗)\n       -  Random Shuffling (随机混洗)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#44-feature-shuffling)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.4_Demo_Feature_Selection_Feature_Shuffling.ipynb)\n  -    4.5 Hybrid Method (混合法)\n       -  Recursive Feature Selection (递归特征选择)    [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#451-recursive-feature-elimination)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.5_Demo_Feature_Selection_Hybrid_method.ipynb)  \n       -  Recursive Feature Addition (递归特征添加)   [[guide]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002FA%20Short%20Guide%20for%20Feature%20Engineering%20and%20Feature%20Selection.md#452-recursive-feature-addition)   [[demo]](https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fblob\u002Fmaster\u002F4.5_Demo_Feature_Selection_Hybrid_method.ipynb)\n\n\n\n\n\n## 关键链接与资源\n\n- Udemy 的特征工程在线课程\n\nhttps:\u002F\u002Fwww.udemy.com\u002Ffeature-engineering-for-machine-learning\u002F\n\n- Udemy 的特征选择在线课程\n\nhttps:\u002F\u002Fwww.udemy.com\u002Ffeature-selection-for-machine-learning\n\n- JMLR 关于变量与特征选择的特刊\n\nhttp:\u002F\u002Fjmlr.org\u002Fpapers\u002Fspecial\u002Ffeature03.html\n\n- 《回归与多层\u002F分层模型数据分析》，第 25 章：缺失数据\n\nhttp:\u002F\u002Fwww.stat.columbia.edu\u002F~gelman\u002Farm\u002Fmissing.pdf\n\n- 数据挖掘与缺失数据的影响\n\nhttp:\u002F\u002Fcore.ecu.edu\u002Fomgt\u002Fkrosj\u002FIMDSDataMining2003.pdf\n\n- PyOD：用于可扩展异常值检测的 Python 工具包\n\nhttps:\u002F\u002Fgithub.com\u002Fyzhao062\u002Fpyod\n\n- Weight of Evidence (WoE) (证据权重) 介绍概览\n\nhttp:\u002F\u002Fdocumentation.statsoft.com\u002FStatisticaHelp.aspx?path=WeightofEvidence\u002FWeightofEvidenceWoEIntroductoryOverview\n\n- 关于特征缩放与归一化\n\nhttp:\u002F\u002Fsebastianraschka.com\u002FArticles\u002F2014_about_feature_scaling.html\n\n- 使用 RF、GBDT 和 Xgboost 进行特征生成\n\nhttps:\u002F\u002Fblog.csdn.net\u002Fanshuai_aw1\u002Farticle\u002Fdetails\u002F82983997\n\n- 特征选择方法及其应用综述\n\nhttps:\u002F\u002Fieeexplore.ieee.org\u002Fiel7\u002F7153596\u002F7160221\u002F07160458.pdf","# Feature Engineering & Feature Selection 快速上手指南\n\n本指南旨在帮助开发者快速搭建环境并使用 `feature-engineering-and-feature-selection` 项目。该项目提供了特征工程与特征选择的完整教程及 Python 代码示例。\n\n## 1. 环境准备\n\n在开始之前，请确保您的系统满足以下要求：\n\n**系统要求：**\n*   Python 3.5, 3.6 或 3.7\n\n**前置依赖库：**\n*   numpy >= 1.15\n*   pandas >= 0.23\n*   scipy >= 1.1.0\n*   scikit_learn >= 0.20.1\n*   seaborn >= 0.9.0\n\n## 2. 安装步骤\n\n该项目主要作为参考手册和代码库使用，无需通过 pip 安装特定包，只需下载源码并配置依赖即可。\n\n**步骤 1：获取源码**\n\n选择以下任一方式下载项目：\n\n```bash\n# 方式一：使用 Git 克隆（推荐）\ngit clone https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection.git\n\n# 方式二：直接下载 ZIP 压缩包\n# 访问 GitHub 页面下载并解压\n```\n\n**步骤 2：安装依赖库**\n\n建议在虚拟环境中安装所需依赖。为提高国内下载速度，推荐使用国内镜像源：\n\n```bash\npip install numpy pandas scipy scikit-learn seaborn -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n## 3. 基本使用\n\n本项目包含详细的教程文档和可运行的代码示例。\n\n### 阅读教程文档\n\n项目提供了 PDF 和 Markdown 两种格式的指南，建议优先阅读 PDF 版本以获得最佳排版体验。\n\n*   **PDF 版本**：`A Short Guide for Feature Engineering and Feature Selection.pdf`\n*   **Markdown 版本**：建议使用 [Typora](https:\u002F\u002Ftypora.io\u002F) 等编辑器打开 `.md` 文件，以获得更好的阅读体验。\n\n### 运行代码示例\n\n项目提供了 Jupyter Notebook 格式的演示代码。您可以根据需要运行特定的模块：\n\n**启动 Jupyter Notebook：**\n\n```bash\ncd feature-engineering-and-feature-selection\njupyter notebook\n```\n\n**示例模块列表：**\n\n以下是项目中包含的核心演示文件，可直接在 Jupyter 中打开运行：\n\n*   **数据探索**：`1_Demo_Data_Explore.ipynb`\n    *   包含变量识别、单变量分析（直方图、计数图、箱线图）、双变量分析（散点图、热力图）等。\n*   **缺失值处理**：`2.1_Demo_Missing_Data.ipynb`\n    *   演示了列表删除、均值\u002F中位数\u002F众数填充、随机填充等多种缺失值处理技术。\n*   **异常值处理**：`2.2_Demo_Outlier.ipynb`\n    *   演示了基于标准差、IQR、MAD 等方法的异常值检测与处理。\n\n您可以直接复制代码片段到您的项目中使用，或修改参数以适应您的数据集。","小李是一名初级数据科学家，正在负责构建一个二手房价格预测模型，虽然尝试了 XGBoost 等多种复杂算法，但模型的预测误差始终居高不下。\n\n### 没有 feature-engineering-and-feature-selection 时\n\n- **缺乏系统性思路**：面对几十个原始字段（如房屋朝向、经纬度、装修情况），不知道该优先处理哪些，只能盲目尝试，导致特征工程环节混乱无序。\n- **知其然不知其所以然**：虽然通过网络搜索复制了一些特征处理的代码片段，但不理解背后的数学原理，例如不清楚为何要对长尾分布做对数转换，导致特征转换效果不佳。\n- **特征选择盲目**：在筛选特征时，要么保留了过多冗余特征导致模型过拟合，要么误删了关键信息，模型泛化能力极差，线上表现不如预期。\n- **代码实现碎片化**：处理不同类型特征时，代码风格各异且缺乏注释，不仅复用困难，在团队协作时也难以解释处理逻辑。\n\n### 使用 feature-engineering-and-feature-selection 后\n\n- **建立标准化流程**：参考指南中的“数据探索 -> 变量识别 -> 特征构建”路径，小李能够有条不紊地制定特征处理计划，不再盲目试错。\n- **深入理解底层逻辑**：通过文档中对“Why, How, When”的详细讲解，小李明白了不同特征工程技术的适用场景，针对性地处理了房屋年龄等非线性特征，显著提升了数据质量。\n- **科学筛选特征**：利用仓库中提供的特征选择方法与示例，小李掌握了如何根据模型表现精准剔除噪声特征，有效降低了模型复杂度并提升了预测准确率。\n- **代码规范统一**：直接参考仓库中基于 scikit-learn 的标准化 Python 实现和 Jupyter Notebook 示例，小李的代码变得整洁规范，易于维护和向团队汇报。\n\nfeature-engineering-and-feature-selection 不仅提供了即插即用的代码库，更通过系统化的理论讲解与实战案例，帮助开发者打通了从原始数据到高质量特征的“最后一公里”。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FYimeng-Zhang_feature-engineering-and-feature-selection_fb0ad2b6.png","Yimeng-Zhang","Yimeng.Zhang","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FYimeng-Zhang_bdf403a0.jpg","I'm a lovely machine learning learner~",null,"https:\u002F\u002Fgithub.com\u002FYimeng-Zhang",[82,86],{"name":83,"color":84,"percentage":85},"Jupyter Notebook","#DA5B0B",91.8,{"name":87,"color":88,"percentage":89},"Python","#3572A5",8.2,1644,425,"2026-04-04T21:16:25",1,"未说明",{"notes":96,"python":97,"dependencies":98},"主要基于 scikit-learn 实现；建议使用 Typora 阅读 Markdown 文件，或直接阅读 PDF；运行示例需下载代码库 ZIP 文件。","3.5, 3.6 or 3.7",[99,100,101,102,103],"numpy>=1.15","pandas>=0.23","scipy>=1.1.0","scikit_learn>=0.20.1","seaborn>=0.9.0",[51,13],[106,107,108,109,110,111],"python","machine-learning","feature-engineering","feature-selection","feature-extraction","data-mining",4,"2026-03-27T02:49:30.150509","2026-04-06T08:46:05.543147",[116],{"id":117,"question_zh":118,"answer_zh":119,"source_url":120},1745,"仓库中的三角形图表来源于哪里？","该图表来源于 'Dive into Machine Learning' 项目，遵循 Creative Commons Attribution 4.0 License 协议。维护者已确认会在仓库中添加来源说明，以便用户能够找到更多相关的学习资源。","https:\u002F\u002Fgithub.com\u002FYimeng-Zhang\u002Ffeature-engineering-and-feature-selection\u002Fissues\u002F1",[]]