[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-LastAncientOne--Deep_Learning_Machine_Learning_Stock":3,"tool-LastAncientOne--Deep_Learning_Machine_Learning_Stock":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":76,"owner_location":79,"owner_email":80,"owner_twitter":76,"owner_website":81,"owner_url":82,"languages":83,"stars":92,"forks":93,"last_commit_at":94,"license":95,"difficulty_score":96,"env_os":97,"env_gpu":98,"env_ram":98,"env_deps":99,"category_tags":107,"github_topics":108,"view_count":23,"oss_zip_url":76,"oss_zip_packed_at":76,"status":16,"created_at":129,"updated_at":130,"faqs":131,"releases":159},4091,"LastAncientOne\u002FDeep_Learning_Machine_Learning_Stock","Deep_Learning_Machine_Learning_Stock","Deep Learning and Machine Learning stocks represent promising opportunities for both long-term and short-term investors and traders.","Deep_Learning_Machine_Learning_Stock 是一个专注于利用人工智能技术进行股票预测的开源研究项目。它通过整合深度学习（DL）与机器学习（ML）算法，对股票市场数据进行全方位的分析与建模，旨在帮助投资者和交易者探索股价波动的规律，从而辅助长短期投资决策。\n\n该项目主要解决了传统金融分析中难以处理海量复杂数据、以及人工判断主观性强等痛点。它不仅仅是一个简单的预测工具，更是一个实验平台，致力于深入探究不同 AI 模型在股市中的有效性及其局限性。项目独特之处在于同时融合了技术分析（如价格趋势）与基本面分析（如公司财务数据），并利用模拟人脑神经网络结构的深度学习方法，对连续变量进行高精度回归预测，以捕捉市场细微变化。\n\nDeep_Learning_Machine_Learning_Stock 非常适合数据科学家、AI 研究人员、量化交易开发者以及对金融科技感兴趣的学习者使用。对于希望深入理解如何将前沿 AI 算法应用于金融领域的专业人士，该项目提供了从数据收集、清洗预处理到模型选择与训练的完整流程参考，是学习构建智能投研系统的优质资源。","\n[![Contributors][contributors-shield]][contributors-url]\n[![Forks][forks-shield]][forks-url]\n[![Stargazers][stars-shield]][stars-url]\n[![Issues][issues-shield]][issues-url]\n[![MIT License][license-shield]][license-url]\n[![LinkedIn][linkedin-shield]][linkedin-url]\n\n\u003Ca href=\"https:\u002F\u002Fwww.buymeacoffee.com\u002Flastancientone\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fcdn.buymeacoffee.com\u002Fbuttons\u002Fv2\u002Fdefault-yellow.png\" alt=\"Buy Me A Coffee\" style=\"height: 60px !important;width: 217px !important;\" >\u003C\u002Fa>\n\n\u003C!-- MARKDOWN LINKS & IMAGES -->\n\u003C!-- https:\u002F\u002Fwww.markdownguide.org\u002Fbasic-syntax\u002F#reference-style-links -->\n[contributors-shield]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcontributors\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock.svg?style=for-the-badge\n[contributors-url]: https:\u002F\u002Fgithub.com\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock\u002Fgraphs\u002Fcontributors\n[forks-shield]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock.svg?style=for-the-badge\n[forks-url]: https:\u002F\u002Fgithub.com\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock\u002Fnetwork\u002Fmembers\n[stars-shield]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock.svg?style=for-the-badge\n[stars-url]: https:\u002F\u002Fgithub.com\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock\u002Fstargazers\n[issues-shield]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock.svg?style=for-the-badge\n[issues-url]: https:\u002F\u002Fgithub.com\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock\u002Fissues\n[license-shield]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock.svg?style=for-the-badge\n[license-url]: LICENSE\n[linkedin-shield]: https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-LinkedIn-black.svg?style=for-the-badge&logo=linkedin&colorB=555\n[linkedin-url]: https:\u002F\u002Flinkedin.com\u002Fin\u002Ftin-hang\n\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FLastAncientOne_Deep_Learning_Machine_Learning_Stock_readme_a1f039533f9d.png\">  \n\n\u003Ch1 align=\"center\">Deep Learning and Machine Learning for Stock Predictions\u003C\u002Fh1>  \n\nDescription: This is a comprehensive study and analysis of stocks using deep learning (DL) and machine learning (ML) techniques. Both machine learning and deep learning are types of artificial intelligence (AI). The objective is to predict stock behavior by employing various machine learning and deep learning algorithms. The focus is on experimenting with stock data to understand how and why certain methods are effective, as well as identifying reasons for their potential limitations. Different stock strategies are explored within the context of machine learning and deep learning. Technical Analysis and Fundamental Analysis are utilized to predict future stock prices using these AI techniques, encompassing both long-term and short-term predictions.  \n\nMachine learning is a branch of artificial intelligence that involves the development of algorithms capable of automatically adapting and generating outputs by processing structured data. On the other hand, deep learning is a subset of machine learning that employs similar algorithms but with additional layers of complexity, enabling different interpretations of the data. The network of algorithms used in deep learning is known as artificial neural networks, which mimic the interconnectedness of neural pathways in the human brain.   \n\nDeep learning and machine learning are powerful approaches that have revolutionized the AI landscape. Understanding the fundamentals of these techniques and the commonly used algorithms is essential for aspiring data scientists and AI enthusiasts. Regression, as a fundamental concept in predictive modeling, plays a crucial role in analyzing and predicting continuous variables. By harnessing the capabilities of these algorithms and techniques, we can unlock incredible potential in various domains, leading to advancements and improvements in numerous industries.  \n\n### Machine Learning Step-by-Step  \n1. Collecting\u002FGathering Data.\n2. Preparing the Data - load data and prepare it for the machine learning training.\n3. Choosing a Model.  \n4. Training the Model.  \n5. Evaluating the Model.  \n6. Parameter Tuning.  \n7. Make a Predictions.\n\n### Deep Learning Model Step-by-Step  \n1. Define the Model.  \n2. Complie the Model.  \n3. Fit the Model with training dataset.  \n4. Make a Predictions.  \n\n\u003Ch3 align=\"left\">Programming Languages and Tools:\u003C\u002Fh3>\n\u003Cp align=\"left\"> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fwww.python.org\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fdevicons\u002Fdevicon\u002Fmaster\u002Ficons\u002Fpython\u002Fpython-original.svg\" alt=\"python\" width=\"50\" height=\"50\"\u002F>  \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fnteract.io\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FLastAncientOne_Deep_Learning_Machine_Learning_Stock_readme_542fbf04dac8.png\" alt=\"Nteract\" width=\"50\" height=\"50\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fanaconda.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FLastAncientOne_Deep_Learning_Machine_Learning_Stock_readme_bac345d62a19.png\" alt=\"Anaconda\" width=\"50\" height=\"50\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fwww.spyder-ide.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FLastAncientOne_Deep_Learning_Machine_Learning_Stock_readme_025db2d7e8fc.png\" alt=\"Spyder\" width=\"50\" height=\"50\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fjupyter.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Fupload.wikimedia.org\u002Fwikipedia\u002Fcommons\u002F3\u002F38\u002FJupyter_logo.svg\" alt=\"Jupyter Notebook\" width=\"50\" height=\"50\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fnotepad-plus-plus.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FLastAncientOne_Deep_Learning_Machine_Learning_Stock_readme_ce3ac06d0e9b.png\" alt=\"Notepad++\" width=\"50\" height=\"50\"\u002F> \u003C\u002Fa> \u003C\u002Fp>\n\n### Three main types of data: Categorical, Discrete, and Continuous variables\n  1. Categorical variable(Qualitative): Label data or distinct groups.    \n    Example: location, gender, material type, payment, highest level of education  \n  2. Discrete variable (Class Data): Numerica variables but the data is countable number of values between any two values.  \n    Example: customer complaints or number of flaws or defects, Children per Household, age (number of years)  \n  3. Continuous variable (Quantitative): Numeric variables that have an infinite number of values between any two values.\n    Example: length of a part or the date and time a payment is received, running distance, age (infinitly accurate and use an infinite number of decimal places)  \n\n### Data Use  \n  1. For 'Quantitative data' is used with all three centre measures (mean, median and mode) and all spread measures.  \n  2. For 'Class data' is used with median and mode.  \n  3. For 'Qualitative data' is for only with mode.  \n\n### Two types of problems: \n  1. Classification (predict label)  \n  2. Regression (predict values)  \n\n### Bias-Variance Tradeoff  \n#### Bias  \n- Bias is the difference between our actual and predicted values.  \n- Bias is the simple assumptions that our model makes about our data to be able to predict new data.  \n- Assumptions made by a model to make a function easier to learn.   \n#### Variance  \n- Variance is opposite of bias.  \n- Variance is variability of model prediction for a given data point or a value that tells us the spread of our data.  \n- If you train your data on training data and obtain a very low error, upon changing the data and then training the same.   \n\n### Overfitting, Underfitting, and the bias-variance tradeoff  \nOverfitted is when the model memorizes the noise and fits too closely to the training set. Good fit is a model that learns the training dataset and genernalizes well with the old out dataset. Underfitting is when it cannot establish the dominant trend within the data; as a result, in training errors and poor performance of the model. \n\n#### Overfitting:   \nOverfitting model is a good model with the training data that fit or at lease with near each observation; however, the model mist the point and random noise is capture inside the model. The model have low training error and high CV error, low in-sample error and high out-of-sample error, and high variance.  \n  1. High Train Accuracy   \n  2. Low Test Accuracy\n#### Avoiding Overfitting:  \n  1. Early stopping - stop the training before the model starts learning the noise within the model.   \n  2. Training with more data - adding more data will increase the accuracy of the modelor can help algorithms detect the signal better.     \n  3. Data augmentation - add clean and relevant data into training data.  \n  4. Feature selection - Use important features within the data. Remove features. \n  5. Regularization - reduce features by using regularization methods such as L1 regularization, Lasso regularization, and dropout.  \n  6. Ensemble methods - combine predictions from multiple separate models such as bagging and boosting.       \n  7. Increase training data.  \n#### Good fit:  \n  1. High Train Accuracy   \n  2. High Test Accuracy   \n#### Underfitting:  \nUnderfitting model is not perfect, so it does not capture the underlying logic of the data. Therefore, the model does not have strong predictive power with low accuracy. The model have large training set error, large in-sample error, and high bias.  \n  1. Low Train Accuracy  \n  2. Low Test Accuracy   \n#### Avoiding Underfitting:  \n  1. Decrease regularization - reduce the variance with a model by applying a penalty to the input parameters with the larger coefficients such as L1 regularization, Lasso regularization, dropout, etc.   \n  2. Increase the duration of training - extending the duration of training because stopping the training early will cause underfit model.  \n  3. Feature selection - not enough predictive features present, then adding more features or features with greater importance would improve the model.  \n  4. Increase the number of features - performing feature engineering  \n  5. Remove noise from the data    \n\n\n## Python Reviews\nStep 1 through step 8 is a review on python.  \nAfter step 8, everything you need to know is relates to data analysis, data engineering, data science, machine learning, and deep learning.   \nHere the link to python tutorial:  \n[Python Tutorial for Stock Analysis](https:\u002F\u002Fgithub.com\u002FLastAncientOne\u002FSimpleStockAnalysisPython)\n\n\n## List of Machine Learning Algorithms for Stock Trading  \n### Most Common Regression Algorithms  \n1. Linear Regression Model  \n2. Logistic Regression  \n3. Lasso Regression    \n4. Support Vector Machines  \n5. Polynomial Regression  \n6. Stepwise Regression  \n7. Ridge Regression  \n8. Multivariate Regression Algorithm    \n9. Multiple Regression Algorithm  \n10. K Means Clustering Algorithm  \n11. Naïve Bayes Classifier Algorithm  \n12. Random Forests  \n13. Decision Trees  \n14. Nearest Neighbours   \n15. Lasso Regression  \n16. ElasticNet Regression  \n17. Reinforcement Learning  \n18. Artificial Intelligence    \n19. MultiModal Network  \n20. Biologic Intelligence  \n\n### Different Types of Machine Learning Algorithms and Models  \nAlgorithms are processes and sets of instructions used to solve a class of problems. Additionally, algorithms perform computations such as calculations, data processing, automated reasoning, and other tasks. A machine learning algorithm is a method that enables systems to learn and improve automatically from experience, without the need for explicit formulation.  \n\n# Prerequistes  \nPython 3.5+  \nJupyter Notebook Python 3    \nWindows 7 or Windows 10  \n\n### Download Software  \nhttps:\u002F\u002Fwww.python.org\u002F  \n\n\u003Ch3 align=\"left\"> Programming Language:\u003C\u002Fh3>\n\u003Cp align=\"left\"> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fwww.python.org\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fdevicons\u002Fdevicon\u002Fmaster\u002Ficons\u002Fpython\u002Fpython-original.svg\" alt=\"python\" width=\"80\" height=\"80\"\u002F> \u003C\u002Fa>  \n\n\u003Ch3 align=\"left\">Tools:\u003C\u002Fh3>\n\u003Cp align=\"left\"> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fanaconda.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FLastAncientOne_Deep_Learning_Machine_Learning_Stock_readme_bac345d62a19.png\" alt=\"Anaconda\" width=\"80\" height=\"80\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fwww.spyder-ide.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Fwww.kindpng.com\u002Fpicc\u002Fm\u002F86-862450_spyder-python-logo-png-transparent-png.png\" alt=\"Spyder\" width=\"80\" height=\"80\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fjupyter.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Fupload.wikimedia.org\u002Fwikipedia\u002Fcommons\u002F3\u002F38\u002FJupyter_logo.svg\" alt=\"Jupyter Notebook\" width=\"80\" height=\"80\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fnotepad-plus-plus.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FLastAncientOne_Deep_Learning_Machine_Learning_Stock_readme_ce3ac06d0e9b.png\" alt=\"Notepad++\" width=\"80\" height=\"80\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fwww.jetbrains.com\u002Fpycharm\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Fbrandeps.com\u002Flogo-download\u002FP\u002FPycharm-logo-vector-01.svg\" alt=\"Notepad++\" width=\"80\" height=\"80\"\u002F> \u003C\u002Fa> \u003C\u002Fp>  \n\n\u003Ca href=\"https:\u002F\u002Fwww.buymeacoffee.com\u002Flastancientone\">\u003Cimg src=\"https:\u002F\u002Fimg.buymeacoffee.com\u002Fbutton-api\u002F?text=Buy me a Book&emoji=📚&slug=lastancientone&button_colour=000000&font_colour=ffffff&font_family=Lato&outline_colour=ffffff&coffee_colour=FFDD00\" \u002F>\u003C\u002Fa>  \n\n## Authors  \n### Tin Hang\n\n## Disclaimer  \n🔻 Do not use this code for investing or trading in the stock market. However, if you are interest in the stock market, you should read :books: books that relate to stock market, investment, or finance. On the other hand, if you into quant or machine learning, read books about 📘 machine trading, algorithmic trading, and quantitative trading. You should read 📗 about Machine Learning and Deep Learning to understand the concept, theory, and the mathematics. On the other hand, you should read academic paper and do research online about machine learning and deep learning on :computer:  \n\n### Certain portions of the code may encounter issues stemming from updates or obsolescence within specific library packages. Consequently, adjustments will be necessary, contingent upon the Python package library employed. It may be imperative to either upgrade or downgrade certain libraries accordingly.  \n\n## 🔴 Warning: This is not financial advice; it should not be relied upon for investment or trading decisions, as it is for educational purposes only.  \n","[![贡献者][contributors-shield]][contributors-url]\n[![复刻数][forks-shield]][forks-url]\n[![星标数][stars-shield]][stars-url]\n[![问题数][issues-shield]][issues-url]\n[![MIT许可证][license-shield]][license-url]\n[![LinkedIn][linkedin-shield]][linkedin-url]\n\n\u003Ca href=\"https:\u002F\u002Fwww.buymeacoffee.com\u002Flastancientone\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fcdn.buymeacoffee.com\u002Fbuttons\u002Fv2\u002Fdefault-yellow.png\" alt=\"Buy Me A Coffee\" style=\"height: 60px !important;width: 217px !important;\" >\u003C\u002Fa>\n\n\u003C!-- MARKDOWN LINKS & IMAGES -->\n\u003C!-- https:\u002F\u002Fwww.markdownguide.org\u002Fbasic-syntax\u002F#reference-style-links -->\n[contributors-shield]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcontributors\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock.svg?style=for-the-badge\n[contributors-url]: https:\u002F\u002Fgithub.com\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock\u002Fgraphs\u002Fcontributors\n[forks-shield]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock.svg?style=for-the-badge\n[forks-url]: https:\u002F\u002Fgithub.com\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock\u002Fnetwork\u002Fmembers\n[stars-shield]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock.svg?style=for-the-badge\n[stars-url]: https:\u002F\u002Fgithub.com\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock\u002Fstargazers\n[issues-shield]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock.svg?style=for-the-badge\n[issues-url]: https:\u002F\u002Fgithub.com\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock\u002Fissues\n[license-shield]: https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002FLastAncientOne\u002FDeep-Learning-Machine-Learning-Stock.svg?style=for-the-badge\n[license-url]: LICENSE\n[linkedin-shield]: https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-LinkedIn-black.svg?style=for-the-badge&logo=linkedin&colorB=555\n[linkedin-url]: https:\u002F\u002Flinkedin.com\u002Fin\u002Ftin-hang\n\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FLastAncientOne_Deep_Learning_Machine_Learning_Stock_readme_a1f039533f9d.png\">  \n\n\u003Ch1 align=\"center\">基于深度学习和机器学习的股票预测\u003C\u002Fh1>  \n\n描述：本项目采用深度学习（DL）和机器学习（ML）技术对股票进行全面的研究与分析。机器学习和深度学习均属于人工智能（AI）的范畴。其目标是通过运用多种机器学习和深度学习算法来预测股票走势。重点在于利用股票数据进行实验，以理解某些方法为何有效，并识别其潜在局限性的原因。同时，在机器学习和深度学习的框架下探索不同的股票策略。借助这些AI技术，结合技术分析和基本面分析，实现对股票未来价格的长期及短期预测。  \n\n机器学习是人工智能的一个分支，它涉及开发能够通过处理结构化数据自动适应并生成输出的算法。而深度学习则是机器学习的一个子集，它使用类似的算法，但增加了更多的复杂层次，从而能够对数据进行不同角度的解读。深度学习中所使用的算法网络被称为人工神经网络，其模拟了人脑中神经通路之间的相互连接。   \n\n深度学习和机器学习是强大的方法，它们彻底改变了人工智能领域。对于有志于成为数据科学家或人工智能爱好者的人来说，掌握这些技术的基础知识以及常用算法至关重要。回归作为预测建模中的基本概念，在分析和预测连续变量方面起着关键作用。通过充分利用这些算法和技术，我们可以在各个领域释放巨大的潜力，推动众多行业的进步与发展。  \n\n### 机器学习步骤  \n1. 数据收集\u002F获取。  \n2. 数据准备 - 加载数据并为机器学习训练做好准备。  \n3. 选择模型。  \n4. 训练模型。  \n5. 模型评估。  \n6. 参数调优。  \n7. 进行预测。\n\n### 德普学习模型步骤  \n1. 定义模型。  \n2. 编译模型。  \n3. 使用训练数据集拟合模型。  \n4. 进行预测。  \n\n\u003Ch3 align=\"left\">编程语言和工具：\u003C\u002Fh3>\n\u003Cp align=\"left\"> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fwww.python.org\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fdevicons\u002Fdevicon\u002Fmaster\u002Ficons\u002Fpython\u002Fpython-original.svg\" alt=\"python\" width=\"50\" height=\"50\"\u002F>  \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fnteract.io\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FLastAncientOne_Deep_Learning_Machine_Learning_Stock_readme_542fbf04dac8.png\" alt=\"Nteract\" width=\"50\" height=\"50\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fanaconda.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FLastAncientOne_Deep_Learning_Machine_Learning_Stock_readme_bac345d62a19.png\" alt=\"Anaconda\" width=\"50\" height=\"50\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fwww.spyder-ide.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FLastAncientOne_Deep_Learning_Machine_Learning_Stock_readme_025db2d7e8fc.png\" alt=\"Spyder\" width=\"50\" height=\"50\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fjupyter.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Fupload.wikimedia.org\u002Fwikipedia\u002Fcommons\u002F3\u002F38\u002FJupyter_logo.svg\" alt=\"Jupyter Notebook\" width=\"50\" height=\"50\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fnotepad-plus-plus.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FLastAncientOne_Deep_Learning_Machine_Learning_Stock_readme_ce3ac06d0e9b.png\" alt=\"Notepad++\" width=\"50\" height=\"50\"\u002F> \u003C\u002Fa> \u003C\u002Fp>\n\n### 数据的三种主要类型：分类变量、离散变量和连续变量\n  1. 分类变量（定性）：标签数据或不同类别。    \n    例子：地点、性别、材料类型、支付方式、最高学历  \n  2. 离散变量（分组数据）：数值变量，但在任意两个值之间只有可数个取值。  \n    例子：客户投诉数量、缺陷数量、每户儿童数、年龄（以年为单位）  \n  3. 连续变量（定量）：在任意两个值之间有无限多个取值的数值变量。\n    例子：零件长度、收到付款的日期和时间、跑步距离、年龄（精确到无限小数位）  \n\n### 数据用途  \n  1. 对“定量数据”可使用所有三种集中趋势度量（均值、中位数和众数）以及所有离散程度度量。  \n  2. 对“分组数据”可使用中位数和众数。  \n  3. 对“定性数据”仅可使用众数。  \n\n### 两类问题：  \n  1. 分类问题（预测标签）  \n  2. 回归问题（预测数值）\n\n### 偏差-方差权衡  \n#### 偏差  \n- 偏差是我们实际值与预测值之间的差异。  \n- 偏差是模型为了能够预测新数据而对数据所做的简单假设。  \n- 模型为了使函数更容易学习而做出的假设。   \n#### 方差  \n- 方差与偏差相反。  \n- 方差是指模型对给定数据点的预测变化程度，或者说是衡量数据分散程度的一个指标。  \n- 如果你在训练数据上训练模型并得到非常低的误差，但当你更换数据并再次训练同一模型时……  \n\n### 过拟合、欠拟合以及偏差-方差权衡  \n过拟合是指模型记住了噪声，并且过于紧密地拟合了训练集。良好的拟合是指模型能够学习训练数据，并在新的测试数据上表现良好。欠拟合则是指模型无法捕捉数据中的主要趋势，从而导致训练误差大、模型性能差。\n\n#### 过拟合：  \n过拟合模型在训练数据上表现很好，几乎能完美拟合每一个观测点；然而，它也会将随机噪声纳入模型中。这种模型具有较低的训练误差和较高的交叉验证误差，较低的样本内误差和较高的样本外误差，以及较高的方差。  \n  1. 训练准确率高  \n  2. 测试准确率低  \n#### 避免过拟合：  \n  1. 提前停止——在模型开始学习噪声之前就停止训练。  \n  2. 使用更多数据进行训练——增加数据可以提高模型的准确性，或帮助算法更好地识别信号。  \n  3. 数据增强——向训练数据中添加干净且相关的新数据。  \n  4. 特征选择——仅使用数据中重要的特征，去除不相关的特征。  \n  5. 正则化——通过L1正则化、Lasso正则化和丢弃法等方法减少特征数量。  \n  6. 集成方法——结合多个独立模型的预测结果，例如Bagging和Boosting。  \n  7. 增加训练数据量。  \n#### 良好拟合：  \n  1. 训练准确率高  \n  2. 测试准确率高  \n#### 欠拟合：  \n欠拟合模型并不完美，因此无法捕捉数据的本质规律。这导致模型的预测能力较弱，准确性较低。这种模型具有较大的训练误差、较大的样本内误差，以及较高的偏差。  \n  1. 训练准确率低  \n  2. 测试准确率低  \n#### 避免欠拟合：  \n  1. 减少正则化——通过降低较大系数的输入参数惩罚来减少模型的方差，例如使用L1正则化、Lasso正则化或丢弃法等。  \n  2. 延长训练时间——如果过早停止训练，会导致模型欠拟合。  \n  3. 特征选择——如果现有特征不足以提供足够的预测能力，则应增加特征或引入更重要的特征。  \n  4. 增加特征数量——进行特征工程。  \n  5. 清除数据中的噪声。  \n\n\n## Python 复习\n步骤1至步骤8是对Python的复习。  \n完成步骤8后，你所需要了解的内容都与数据分析、数据工程、数据科学、机器学习和深度学习相关。   \n以下是Python教程的链接：  \n[股票分析Python教程](https:\u002F\u002Fgithub.com\u002FLastAncientOne\u002FSimpleStockAnalysisPython)\n\n\n## 用于股票交易的机器学习算法列表  \n### 最常见的回归算法  \n1. 线性回归模型  \n2. 逻辑回归  \n3. Lasso回归    \n4. 支持向量机  \n5. 多项式回归  \n6. 逐步回归  \n7. 岭回归  \n8. 多元回归算法    \n9. 多重回归算法  \n10. K均值聚类算法  \n11. 朴素贝叶斯分类器算法  \n12. 随机森林  \n13. 决策树  \n14. 最近邻算法   \n15. Lasso回归  \n16. ElasticNet回归  \n17. 强化学习  \n18. 人工智能    \n19. 多模态网络  \n20. 生物智能  \n\n### 不同类型的机器学习算法和模型  \n算法是一系列用于解决某一类问题的过程和指令。此外，算法还执行计算、数据处理、自动推理等任务。机器学习算法是一种方法，使系统能够从经验中自动学习和改进，而无需显式地进行编程。  \n\n# 先决条件  \nPython 3.5及以上版本  \nJupyter Notebook Python 3  \nWindows 7或Windows 10  \n\n### 软件下载  \nhttps:\u002F\u002Fwww.python.org\u002F  \n\n\u003Ch3 align=\"left\"> 编程语言：\u003C\u002Fh3>\n\u003Cp align=\"left\"> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fwww.python.org\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fdevicons\u002Fdevicon\u002Fmaster\u002Ficons\u002Fpython\u002Fpython-original.svg\" alt=\"python\" width=\"80\" height=\"80\"\u002F> \u003C\u002Fa>  \n\n\u003Ch3 align=\"left\">工具：\u003C\u002Fh3>\n\u003Cp align=\"left\"> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fanaconda.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FLastAncientOne_Deep_Learning_Machine_Learning_Stock_readme_bac345d62a19.png\" alt=\"Anaconda\" width=\"80\" height=\"80\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fwww.spyder-ide.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Fwww.kindpng.com\u002Fpicc\u002Fm\u002F86-862450_spyder-python-logo-png-transparent-png.png\" alt=\"Spyder\" width=\"80\" height=\"80\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fjupyter.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Fupload.wikimedia.org\u002Fwikipedia\u002Fcommons\u002F3\u002F38\u002FJupyter_logo.svg\" alt=\"Jupyter Notebook\" width=\"80\" height=\"80\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fnotepad-plus-plus.org\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FLastAncientOne_Deep_Learning_Machine_Learning_Stock_readme_ce3ac06d0e9b.png\" alt=\"Notepad++\" width=\"80\" height=\"80\"\u002F> \u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fwww.jetbrains.com\u002Fpycharm\u002F\" target=\"_blank\"> \u003Cimg src=\"https:\u002F\u002Fbrandeps.com\u002Flogo-download\u002FP\u002FPycharm-logo-vector-01.svg\" alt=\"Notepad++\" width=\"80\" height=\"80\"\u002F> \u003C\u002Fa> \u003C\u002Fp>  \n\n\u003Ca href=\"https:\u002F\u002Fwww.buymeacoffee.com\u002Flastancientone\">\u003Cimg src=\"https:\u002F\u002Fimg.buymeacoffee.com\u002Fbutton-api\u002F?text=Buy me a Book&emoji=📚&slug=lastancientone&button_colour=000000&font_colour=ffffff&font_family=Lato&outline_colour=ffffff&coffee_colour=FFDD00\" \u002F>\u003C\u002Fa>  \n\n## 作者  \n### Tin Hang\n\n## 免责声明  \n🔻 请勿将此代码用于股票市场的投资或交易。然而，如果你对股票市场感兴趣，建议阅读与股票市场、投资或金融相关的书籍。另一方面，如果你对量化或机器学习感兴趣，则应阅读关于机器交易、算法交易和量化交易的书籍。同时，你也应该阅读有关机器学习和深度学习的资料，以理解其概念、理论和数学原理。此外，还可以查阅学术论文并在网上研究机器学习和深度学习的相关内容。\n\n### 代码中的某些部分可能会因特定库包的更新或过时而出现问题。因此，需要根据所使用的 Python 包库进行相应调整。有时可能必须升级或降级某些库以解决问题。\n\n## 🔴 注意：本内容不构成投资建议；请勿将其作为投资或交易决策的依据，仅供教育目的使用。","# Deep_Learning_Machine_Learning_Stock 快速上手指南\n\n本项目旨在利用深度学习（DL）和机器学习（ML）技术对股票行为进行预测分析，涵盖技术指标与基本面分析，适用于长短期股价预测研究。\n\n## 1. 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**: Windows 7 \u002F Windows 10 (或更高版本)，Linux, macOS\n*   **Python 版本**: Python 3.5 或更高版本 (推荐 Python 3.8+)\n*   **核心工具**:\n    *   Jupyter Notebook (用于交互式数据分析)\n    *   Anaconda (推荐安装，包含大部分数据科学依赖包)\n    *   Spyder IDE (可选，用于代码编辑)\n\n> **国内加速建议**：\n> 推荐使用 [清华大学开源软件镜像站](https:\u002F\u002Fmirrors.tuna.tsinghua.edu.cn\u002Fhelp\u002Fanaconda\u002F) 下载 Anaconda，并在安装后配置 `conda` 和 `pip` 使用国内源以提升下载速度。\n\n## 2. 安装步骤\n\n### 方案 A：使用 Anaconda (推荐)\n\n如果您已安装 Anaconda，可以直接创建环境并安装必要库：\n\n```bash\n# 创建名为 stock_dl 的虚拟环境\nconda create -n stock_dl python=3.8\n\n# 激活环境\nconda activate stock_dl\n\n# 安装常用数据科学与深度学习库\nconda install numpy pandas matplotlib scikit-learn tensorflow keras jupyter notebook\n```\n\n### 方案 B：使用原生 Python + pip\n\n如果未安装 Anaconda，请确保已安装 Python，然后执行以下命令：\n\n```bash\n# 升级 pip (可选，建议使用国内源)\npython -m pip install --upgrade pip -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n\n# 安装项目所需依赖\npip install numpy pandas matplotlib scikit-learn tensorflow keras jupyter notebook -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n## 3. 基本使用\n\n本项目主要通过 Jupyter Notebook 进行实验和分析。\n\n### 启动项目\n\n1.  克隆或下载本仓库到本地。\n2.  在终端中进入项目目录。\n3.  启动 Jupyter Notebook：\n\n```bash\njupyter notebook\n```\n\n### 运行示例\n\n在浏览器打开的 Jupyter 界面中，找到现有的 `.ipynb` 文件（通常包含数据收集、预处理、模型训练等步骤）。\n\n以下是一个基于该项目逻辑的**最小化代码示例**，展示如何加载数据并构建一个简单的机器学习流程：\n\n```python\nimport pandas as pd\nimport numpy as np\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import LinearRegression\nfrom sklearn.metrics import mean_squared_error\n\n# 1. 收集\u002F加载数据 (此处以模拟数据为例，实际使用时请替换为真实股票 CSV 文件)\n# 假设数据包含 'Date', 'Open', 'High', 'Low', 'Close', 'Volume'\ndata = pd.read_csv('your_stock_data.csv') \n\n# 2. 数据准备\n# 例如：使用收盘价作为预测目标，使用前一日收盘价作为特征\ndata['Prediction'] = data[['Close']].shift(-1)\nfeatures = data[['Close']]\nfeatures = features[:-1] # 去掉最后一行因为它是空值\ntarget = data['Prediction']\ntarget = target[:-1]\n\n# 分割数据集\nx_train, x_test, y_train, y_test = train_test_split(features, target, test_size=0.2)\n\n# 3. 选择并训练模型 (线性回归)\nmodel = LinearRegression()\nmodel.fit(x_train, y_train)\n\n# 4. 评估模型\npredictions = model.predict(x_test)\nrmse = np.sqrt(mean_squared_error(y_test, predictions))\nprint(f\"Root Mean Squared Error: {rmse}\")\n\n# 5. 进行预测\nfuture_prediction = model.predict([[data['Close'].iloc[-1]]])\nprint(f\"Next Day Predicted Price: {future_prediction[0]}\")\n```\n\n### 核心流程说明\n\n根据项目文档，完整的分析与建模遵循以下步骤：\n\n**机器学习流程：**\n1.  **Collecting\u002FGathering Data**: 收集股票历史数据。\n2.  **Preparing the Data**: 清洗数据，处理缺失值，特征工程。\n3.  **Choosing a Model**: 选择合适的算法（如线性回归、随机森林、SVM 等）。\n4.  **Training the Model**: 使用训练集拟合模型。\n5.  **Evaluating the Model**: 使用测试集评估性能（关注过拟合与欠拟合）。\n6.  **Parameter Tuning**: 调整超参数以优化结果。\n7.  **Make Predictions**: 对未来股价进行预测。\n\n**深度学习流程：**\n1.  **Define the Model**: 定义神经网络结构（如 LSTM, CNN）。\n2.  **Compile the Model**: 配置损失函数和优化器。\n3.  **Fit the Model**: 使用训练数据集训练模型。\n4.  **Make Predictions**: 输出预测结果。","一位量化交易研究员正试图构建一个能同时捕捉短期波动与长期趋势的个股预测模型，以优化投资组合策略。\n\n### 没有 Deep_Learning_Machine_Learning_Stock 时\n- **数据整合困难**：需要手动收集并清洗分散的技术指标与基本面数据，耗时且容易出错，难以形成结构化训练集。\n- **模型选择盲目**：面对回归、神经网络等多种算法，缺乏系统的对比实验框架，难以判断哪种模型更适合当前股票特性。\n- **预测维度单一**：传统方法往往只能侧重短线投机或长线价值之一，无法在同一框架下有效兼顾长短期股价行为预测。\n- **黑盒难解释**：自行搭建的深度学习模型缺乏可解释性分析，无法理解为何某些策略有效或在特定市场环境下失效。\n\n### 使用 Deep_Learning_Machine_Learning_Stock 后\n- **流程标准化**：直接利用其内置的数据采集与预处理模块，快速将多源股票数据转化为适配机器学习的高质量结构化输入。\n- **策略系统化验证**：依托项目提供的完整实验流程，高效对比不同深度学习与机器学习算法在特定股票上的表现，科学选定最优模型。\n- **双周期精准覆盖**：结合技术分析与基本面分析的双重驱动，成功构建出既能响应日内波动又能预判季度趋势的综合预测模型。\n- **深度归因分析**：通过项目中的案例研究，清晰识别出模型在不同市场情境下的局限性，从而针对性地调整特征工程与参数配置。\n\nDeep_Learning_Machine_Learning_Stock 将复杂的 AI 选股过程转化为可复现、可解释的系统工程，显著提升了量化策略的研发效率与预测可靠性。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FLastAncientOne_Deep_Learning_Machine_Learning_Stock_a1f03953.png","LastAncientOne",null,"https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FLastAncientOne_a3add8be.png","Programming Language: Python, R, & Matlab\r\nDatabase: NoSQL, SQL & Access\r\nSoftware: Excel\r\nFinance, Stock Market, Mathematics, Machine Learning & Deep Learning","USA","lastancientone@gmail.com","https:\u002F\u002Flastancientone.github.io\u002F","https:\u002F\u002Fgithub.com\u002FLastAncientOne",[84,88],{"name":85,"color":86,"percentage":87},"Jupyter Notebook","#DA5B0B",99.9,{"name":89,"color":90,"percentage":91},"Python","#3572A5",0.1,1730,367,"2026-04-03T21:50:46","MIT",4,"Windows 7, Windows 10","未说明",{"notes":100,"python":101,"dependencies":102},"该项目主要侧重于股票预测的机器学习与深度学习算法教学与研究。官方明确列出的运行环境为 Windows 7 或 Windows 10，未提及 Linux 或 macOS 支持。虽然项目涉及深度学习（人工神经网络），但 README 中未具体说明 GPU、显存或 CUDA 版本需求，也未列出具体的 Python 第三方库（如 TensorFlow 或 PyTorch）及其版本号，仅提到了开发工具和编程语言版本。建议参考其提供的 Python 教程链接获取更详细的依赖信息。","3.5+",[85,103,104,105,106],"Anaconda","Spyder IDE","Nteract","Notepad++",[51,13,54],[109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128],"deep-learning","machine-learning","stock-price-prediction","features-extraction","financial-engineering","prediction","feature-engineering","feature-extraction","feature-selection","stock-data","stock-trading","stock-analysis","stock-prices","stock-market","stock-prediction","algorithms","data-science","trading","technical-analysis","neural-network","2026-03-27T02:49:30.150509","2026-04-06T09:01:51.283198",[132,137,141,146,151,155],{"id":133,"question_zh":134,"answer_zh":135,"source_url":136},18634,"运行机器学习预测笔记本时需要安装哪些依赖包？","项目主要依赖以下包及其版本：numpy (1.19.5), pandas (1.1.5), sklearn (0.24.2), yfinance (0.1.63)。维护者主要在 Python 3.5 和 3.6 版本（特别是 3.6.13 Anaconda 环境）下测试通过，在新版本 Python 上可能未进行测试。","https:\u002F\u002Fgithub.com\u002FLastAncientOne\u002FDeep_Learning_Machine_Learning_Stock\u002Fissues\u002F8",{"id":138,"question_zh":139,"answer_zh":140,"source_url":136},18635,"在 Ubuntu 18.04 (Python 3.6.9) 上无法安装指定版本的 numpy 怎么办？","如果在 Python 3.6.9 环境下使用 pip 安装 numpy==1.19.5 失败（提示找不到匹配版本），建议尝试使用 Anaconda 环境（如 Python 3.6.13），因为维护者确认该配置下可以正常运行。直接使用系统自带的 pip 可能因源或编译问题导致特定版本安装失败。",{"id":142,"question_zh":143,"answer_zh":144,"source_url":145},18636,"运行 stocks_app.py 输入股票名称时报错 'module yahoo_finance has no attribute download' 如何解决？","该错误是由于代码库更新导致的兼容性问题。维护者已对代码进行了修复和更新，请拉取最新的代码版本即可解决此问题。","https:\u002F\u002Fgithub.com\u002FLastAncientOne\u002FDeep_Learning_Machine_Learning_Stock\u002Fissues\u002F6",{"id":147,"question_zh":148,"answer_zh":149,"source_url":150},18637,"在 '001_Pandas.ipynb' 的第 16 单元格中移动列代码报错如何修正？","原代码 `cols = list(new_df)` 在某些 Pandas 版本中可能无效。请将代码修改为：`cols = new_df.columns.to_list()`，然后再执行后续的插入操作 `cols.insert(0, cols.pop(cols.index('Date')))`。维护者已确认此修正并会更新仓库。","https:\u002F\u002Fgithub.com\u002FLastAncientOne\u002FDeep_Learning_Machine_Learning_Stock\u002Fissues\u002F5",{"id":152,"question_zh":153,"answer_zh":154,"source_url":136},18638,"该项目推荐使用的操作系统和 Python 环境是什么？","维护者主要在 Windows 平台配合 Anaconda (Python 3.6.13) 环境下开发和测试。虽然有人在 Ubuntu 上尝试，但可能会遇到特定包（如 numpy）的版本兼容问题，因此推荐优先使用 Windows + Anaconda Python 3.6 环境以确保稳定性。",{"id":156,"question_zh":157,"answer_zh":158,"source_url":136},18639,"遇到代码运行错误时，应该检查哪些基本信息？","遇到错误时，应首先检查 Python 版本（项目基于 3.5\u002F3.6）、操作系统类型以及关键依赖包的具体版本号（如 numpy, pandas, yfinance）。版本不匹配（例如在新版 Python 上使用旧版代码或包）是常见报错原因。",[]]