[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-wzhe06--SparrowRecSys":3,"similar-wzhe06--SparrowRecSys":109},{"id":4,"github_repo":5,"name":6,"description_en":7,"description_zh":8,"ai_summary_zh":8,"readme_en":9,"readme_zh":10,"quickstart_zh":11,"use_case_zh":12,"hero_image_url":13,"owner_login":14,"owner_name":15,"owner_avatar_url":16,"owner_bio":17,"owner_company":18,"owner_location":19,"owner_email":20,"owner_twitter":18,"owner_website":21,"owner_url":22,"languages":23,"stars":44,"forks":45,"last_commit_at":46,"license":47,"difficulty_score":48,"env_os":49,"env_gpu":49,"env_ram":49,"env_deps":50,"category_tags":57,"github_topics":59,"view_count":63,"oss_zip_url":18,"oss_zip_packed_at":18,"status":64,"created_at":65,"updated_at":66,"faqs":67,"releases":108},1345,"wzhe06\u002FSparrowRecSys","SparrowRecSys","A Deep Learning Recommender System","SparrowRecSys 是一套“麻雀虽小、五脏俱全”的电影推荐系统开源示例，把离线数据处理、深度学习模型训练、实时特征流、线上服务到前端展示整条工业级链路拆成可运行的模块，帮你快速理解并动手实践推荐系统。它内置 1000 部影片的精简 MovieLens 数据，支持 Word2Vec、Wide&Deep、DIN、Two-Towers 等 8 种主流深度学习模型，用 TensorFlow 训练、Spark 处理数据、Jetty 做线上推理，一键启动即可在浏览器里看到推荐结果。  \n适合想入门或进阶推荐系统的开发者、算法工程师、研究生，也适合需要教学 Demo 的老师。代码结构清晰、文档齐全，还有配套实战课程，拿来即用，改两行就能跑自己的数据。","# SparrowRecSys\nSparrowRecSys是一个电影推荐系统，名字SparrowRecSys（麻雀推荐系统），取自“麻雀虽小，五脏俱全”之意。项目是一个基于maven的混合语言项目，同时包含了TensorFlow，Spark，Jetty Server等推荐系统的不同模块。希望你能够利用SparrowRecSys进行推荐系统的学习，并有机会一起完善它。\n\n## 基于SparrowRecSys的实践课程\n受极客时间邀请开设 [深度学习推荐系统实战](http:\u002F\u002Fgk.link\u002Fa\u002F10lyE) 课程，详细讲解了SparrowRecSys的所有技术细节，覆盖了深度学习模型结构，模型训练，特征工程，模型评估，模型线上服务及推荐服务器内部逻辑等模块。\n\n## 环境要求\n* Java 8\n* Scala 2.11\n* Python 3.6+\n* TensorFlow 2.0+\n\n## 快速开始\n将项目用IntelliJ打开后，找到`RecSysServer`，右键点选`Run`，然后在浏览器中输入`http:\u002F\u002Flocalhost:6010\u002F`即可看到推荐系统的前端效果。\n\n## 项目数据\n项目数据来源于开源电影数据集[MovieLens](https:\u002F\u002Fgrouplens.org\u002Fdatasets\u002Fmovielens\u002F)，项目自带数据集对MovieLens数据集进行了精简，仅保留1000部电影和相关评论、用户数据。全量数据集请到MovieLens官方网站进行下载，推荐使用MovieLens 20M Dataset。\n\n## SparrowRecSys技术架构\nSparrowRecSys技术架构遵循经典的工业级深度学习推荐系统架构，包括了离线数据处理、模型训练、近线的流处理、线上模型服务、前端推荐结果显示等多个模块。以下是SparrowRecSys的架构图：\n![alt text](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fwzhe06_SparrowRecSys_readme_cc317a48dcc7.png)\n\n## SparrowRecSys实现的深度学习模型\n* Word2vec (Item2vec)\n* DeepWalk (Random Walk based Graph Embedding)\n* Embedding MLP\n* Wide&Deep\n* Nerual CF\n* Two Towers\n* DeepFM\n* DIN(Deep Interest Network)\n\n## 相关论文\n* [[FFM] Field-aware Factorization Machines for CTR Prediction (Criteo 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BFFM%5D%20Field-aware%20Factorization%20Machines%20for%20CTR%20Prediction%20%28Criteo%202016%29.pdf) \u003Cbr \u002F>\n* [[GBDT+LR] Practical Lessons from Predicting Clicks on Ads at Facebook (Facebook 2014)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BGBDT%2BLR%5D%20Practical%20Lessons%20from%20Predicting%20Clicks%20on%20Ads%20at%20Facebook%20%28Facebook%202014%29.pdf) \u003Cbr \u002F>\n* [[PS-PLM] Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction (Alibaba 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BPS-PLM%5D%20Learning%20Piece-wise%20Linear%20Models%20from%20Large%20Scale%20Data%20for%20Ad%20Click%20Prediction%20%28Alibaba%202017%29.pdf) \u003Cbr \u002F>\n* [[FM] Fast Context-aware Recommendations with Factorization Machines (UKON 2011)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BFM%5D%20Fast%20Context-aware%20Recommendations%20with%20Factorization%20Machines%20%28UKON%202011%29.pdf) \u003Cbr \u002F>\n* [[DCN] Deep & Cross Network for Ad Click Predictions (Stanford 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDCN%5D%20Deep%20%26%20Cross%20Network%20for%20Ad%20Click%20Predictions%20%28Stanford%202017%29.pdf) \u003Cbr \u002F>\n* [[Deep Crossing] Deep Crossing - Web-Scale Modeling without Manually Crafted Combinatorial Features (Microsoft 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDeep%20Crossing%5D%20Deep%20Crossing%20-%20Web-Scale%20Modeling%20without%20Manually%20Crafted%20Combinatorial%20Features%20%28Microsoft%202016%29.pdf) \u003Cbr \u002F>\n* [[PNN] Product-based Neural Networks for User Response Prediction (SJTU 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BPNN%5D%20Product-based%20Neural%20Networks%20for%20User%20Response%20Prediction%20%28SJTU%202016%29.pdf) \u003Cbr \u002F>\n* [[DIN] Deep Interest Network for Click-Through Rate Prediction (Alibaba 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDIN%5D%20Deep%20Interest%20Network%20for%20Click-Through%20Rate%20Prediction%20%28Alibaba%202018%29.pdf) \u003Cbr \u002F>\n* [[ESMM] Entire Space Multi-Task Model - An Effective Approach for Estimating Post-Click Conversion Rate (Alibaba 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BESMM%5D%20Entire%20Space%20Multi-Task%20Model%20-%20An%20Effective%20Approach%20for%20Estimating%20Post-Click%20Conversion%20Rate%20%28Alibaba%202018%29.pdf) \u003Cbr \u002F>\n* [[Wide & Deep] Wide & Deep Learning for Recommender Systems (Google 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BWide%20%26%20Deep%5D%20Wide%20%26%20Deep%20Learning%20for%20Recommender%20Systems%20%28Google%202016%29.pdf) \u003Cbr \u002F>\n* [[xDeepFM] xDeepFM - Combining Explicit and Implicit Feature Interactions for Recommender Systems (USTC 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BxDeepFM%5D%20xDeepFM%20-%20Combining%20Explicit%20and%20Implicit%20Feature%20Interactions%20for%20Recommender%20Systems%20%28USTC%202018%29.pdf) \u003Cbr \u002F>\n* [[Image CTR] Image Matters - Visually modeling user behaviors using Advanced Model Server (Alibaba 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BImage%20CTR%5D%20Image%20Matters%20-%20Visually%20modeling%20user%20behaviors%20using%20Advanced%20Model%20Server%20%28Alibaba%202018%29.pdf) \u003Cbr \u002F>\n* [[AFM] Attentional Factorization Machines - Learning the Weight of Feature Interactions via Attention Networks (ZJU 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BAFM%5D%20Attentional%20Factorization%20Machines%20-%20Learning%20the%20Weight%20of%20Feature%20Interactions%20via%20Attention%20Networks%20%28ZJU%202017%29.pdf) \u003Cbr \u002F>\n* [[DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction (Alibaba 2019)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDIEN%5D%20Deep%20Interest%20Evolution%20Network%20for%20Click-Through%20Rate%20Prediction%20%28Alibaba%202019%29.pdf) \u003Cbr \u002F>\n* [[DSSM] Learning Deep Structured Semantic Models for Web Search using Clickthrough Data (UIUC 2013)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDSSM%5D%20Learning%20Deep%20Structured%20Semantic%20Models%20for%20Web%20Search%20using%20Clickthrough%20Data%20%28UIUC%202013%29.pdf) \u003Cbr \u002F>\n* [[FNN] Deep Learning over Multi-field Categorical Data (UCL 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BFNN%5D%20Deep%20Learning%20over%20Multi-field%20Categorical%20Data%20%28UCL%202016%29.pdf) \u003Cbr \u002F>\n* [[DeepFM] A Factorization-Machine based Neural Network for CTR Prediction (HIT-Huawei 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BDeepFM%5D%20A%20Factorization-Machine%20based%20Neural%20Network%20for%20CTR%20Prediction%20%28HIT-Huawei%202017%29.pdf) \u003Cbr \u002F>\n* [[NFM] Neural Factorization Machines for Sparse Predictive Analytics (NUS 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5BNFM%5D%20Neural%20Factorization%20Machines%20for%20Sparse%20Predictive%20Analytics%20%28NUS%202017%29.pdf) \u003Cbr \u002F>\n\n## 其他相关资源\n* [Papers on Computational Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers) \u003Cbr \u002F>\n* [Papers on Recommender System](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers) \u003Cbr \u002F>\n* [CTR Model Based on Spark](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FSparkCTR) \u003Cbr \u002F>\n","# SparrowRecSys\nSparrowRecSys是一个电影推荐系统，名字SparrowRecSys（麻雀推荐系统），取自“麻雀虽小，五脏俱全”之意。项目是一个基于maven的混合语言项目，同时包含了TensorFlow、Spark、Jetty Server等推荐系统的不同模块。希望你能够利用SparrowRecSys进行推荐系统的学习，并有机会一起完善它。\n\n## 基于SparrowRecSys的实践课程\n受极客时间邀请开设 [深度学习推荐系统实战](http:\u002F\u002Fgk.link\u002Fa\u002F10lyE) 课程，详细讲解了SparrowRecSys的所有技术细节，覆盖了深度学习模型结构、模型训练、特征工程、模型评估、模型线上服务及推荐服务器内部逻辑等模块。\n\n## 环境要求\n* Java 8\n* Scala 2.11\n* Python 3.6+\n* TensorFlow 2.0+\n\n## 快速开始\n将项目用IntelliJ打开后，找到`RecSysServer`，右键点选`Run`，然后在浏览器中输入`http:\u002F\u002Flocalhost:6010\u002F`即可看到推荐系统的前端效果。\n\n## 项目数据\n项目数据来源于开源电影数据集[MovieLens](https:\u002F\u002Fgrouplens.org\u002Fdatasets\u002Fmovielens\u002F)，项目自带数据集对MovieLens数据集进行了精简，仅保留1000部电影和相关评论、用户数据。全量数据集请到MovieLens官方网站进行下载，推荐使用MovieLens 20M Dataset。\n\n## SparrowRecSys技术架构\nSparrowRecSys技术架构遵循经典的工业级深度学习推荐系统架构，包括了离线数据处理、模型训练、近线的流处理、线上模型服务、前端推荐结果显示等多个模块。以下是SparrowRecSys的架构图：\n![alt text](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fwzhe06_SparrowRecSys_readme_cc317a48dcc7.png)\n\n## SparrowRecSys实现的深度学习模型\n* Word2vec (Item2vec)\n* DeepWalk (Random Walk based Graph Embedding)\n* Embedding MLP\n* Wide&Deep\n* Nerual CF\n* Two Towers\n* DeepFM\n* DIN(Deep Interest Network)\n\n## 相关论文\n* [[FFM] Field-aware Factorization Machines for CTR Prediction (Criteo 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5BFFM%5D%20Field-aware%20Factorization%20Machines%20for%20CTR%20Prediction%20%28Criteo%202016%29.pdf) \u003Cbr \u002F>\n* [[GBDT+LR] Practical Lessons from Predicting Clicks on Ads at Facebook (Facebook 2014)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5[BGBDT%2BLR%5D%20Practical%20Lessons%20from%20Predicting%20Clicks%20on%20Ads%20at%20Facebook%20%28Facebook%202014%29.pdf) \u003Cbr \u002F>\n* [[PS-PLM] Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction (Alibaba 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5[BPS-PLM%5D%20Learning%20Piece-wise%20Linear%20Models%20from%20Large%20Scale%20Data%20for%20Ad%20Click%20Prediction%20%28Alibaba%202017%29.pdf) \u003Cbr \u002F>\n* [[FM] Fast Context-aware Recommendations with Factorization Machines (UKON 2011)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FClassic%20CTR%20Prediction\u002F%5[BFM%5D%20Fast%20Context-aware%20Recommendations%20with%20Factorization%20Machines%20%28UKON%202011%29.pdf) \u003Cbr \u002F>\n* [[DCN] Deep & Cross Network for Ad Click Predictions (Stanford 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[DCN%5D%20Deep%20%26%20Cross%20Network%20for%20Ad%20Click%20Predictions%20%28Stanford%202017%29.pdf) \u003Cbr \u002F>\n* [[Deep Crossing] Deep Crossing - Web-Scale Modeling without Manually Crafted Combinatorial Features (Microsoft 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[Deep%20Crossing%5D%20Deep%20Crossing%20-%20Web-Scale%20Modeling%20without%20Manually%20Crafted%20Combinatorial%20Features%20%28Microsoft%202016%29.pdf) \u003Cbr \u002F>\n* [[PNN] Product-based Neural Networks for User Response Prediction (SJTU 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[PNN%5D%20Product-based%20Neural%20Networks%20for%20User%20Response%20Prediction%20%28SJTU%202016%29.pdf) \u003Cbr \u002F>\n* [[DIN] Deep Interest Network for Click-Through Rate Prediction (Alibaba 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[DIN%5D%20Deep%20Interest%20Network%20for%20Click-Through%20Rate%20Prediction%20%28Alibaba%202018%29.pdf) \u003Cbr \u002F>\n* [[ESMM] Entire Space Multi-Task Model - An Effective Approach for Estimating Post-Click Conversion Rate (Alibaba 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[ESMM%5D%20Entire%20Space%20Multi-Task%20Model%20-%20An%20Effective%20Approach%20for%20Estimating%20Post-Click%20Conversion%20Rate%20%28Alibaba%202018%29.pdf) \u003Cbr \u002F>\n* [[Wide & Deep] Wide & Deep Learning for Recommender Systems (Google 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[Wide%20%26%20Deep%5D%20Wide%20%26%20Deep%20Learning%20for%20Recommender%20Systems%20%28Google%202016%29.pdf) \u003Cbr \u002F>\n* [[xDeepFM] xDeepFM - Combining Explicit and Implicit Feature Interactions for Recommender Systems (USTC 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[xDeepFM%5D%20xDeepFM%20-%20Combining%20Explicit%20and%20Implicit%20Feature%20Interactions%20for%20Recommender%20Systems%20%28USTC%202018%29.pdf) \u003Cbr \u002F>\n* [[Image CTR] Image Matters - Visually modeling user behaviors using Advanced Model Server (Alibaba 2018)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[Image%20CTR%5D%20Image%20Matters%20-%20Visually%20modeling%20user%20behaviors%20using%20Advanced%20Model%20Server%20%28Alibaba%202018%29.pdf) \u003Cbr \u002F>\n* [[AFM] Attentional Factorization Machines - Learning the Weight of Feature Interactions via Attention Networks (ZJU 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[AFM%5D%20Attentional%20Factorization%20Machines%20-%20Learning%20the%20Weight%20of%20Feature%20Interactions%20via%20Attention%20Networks%20%28ZJU%202017%29.pdf) \u003Cbr \u002F>\n* [[DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction (Alibaba 2019)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[DIEN%5D%20Deep%20Interest%20Evolution%20Network%20for%20Click-Through%20Rate%20Prediction%20%28Alibaba%202019%29.pdf) \u003Cbr \u002F>\n* [[DSSM] Learning Deep Structured Semantic Models for Web Search using Clickthrough Data (UIUC 2013)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[DSSM%5D%20Learning%20Deep%20Structured%20Semantic%20Models%20for%20Web%20Search%20using%20Clickthrough%20Data%20%28UIUC%202013%29.pdf) \u003Cbr \u002F>\n* [[FNN] Deep Learning over Multi-field Categorical Data (UCL 2016)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[FNN%5D%20Deep%20Learning%20over%20Multi-field%20Categorical%20Data%20%28UCL%202016%29.pdf) \u003Cbr \u002F>\n* [[DeepFM] A Factorization-Machine based Neural Network for CTR Prediction (HIT-Huawei 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[DeepFM%5D%20A%20Factorization-Machine%20based%20Neural%20Network%20for%20CTR%20Prediction%20%28HIT-Huawei%202017%29.pdf) \u003Cbr \u002F>\n* [[NFM] Neural Factorization Machines for Sparse Predictive Analytics (NUS 2017)](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers\u002Fblob\u002Fmaster\u002FDeep%20Learning%20CTR%20Prediction\u002F%5[NFM%5D%20Neural%20Factorization%20Machines%20for%20Sparse%20Predictive%20Analytics%20%28NUS%202017%29.pdf) \u003Cbr \u002F>\n\n## 其他相关资源\n* [Papers on Computational Advertising](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers) \u003Cbr \u002F>\n* [Papers on Recommender System](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FAd-papers) \u003Cbr \u002F>\n* [CTR Model Based on Spark](https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FSparkCTR) \u003Cbr \u002F>","# SparrowRecSys 中文快速上手指南\n\n## 环境准备\n\n| 组件 | 版本要求 | 备注 |\n|---|---|---|\n| JDK | 8 | 推荐 OpenJDK 8 |\n| Scala | 2.11 | 与 Spark 2.x 兼容 |\n| Python | 3.6+ | 用于 TensorFlow 训练 |\n| TensorFlow | 2.0+ | CPU\u002FGPU 均可 |\n| Maven | 3.5+ | 构建项目 |\n| IntelliJ IDEA | 2020+ | 社区版即可 |\n\n国内用户建议配置阿里云 Maven 镜像，在 `~\u002F.m2\u002Fsettings.xml` 中加入：\n\n```xml\n\u003Cmirror>\n  \u003Cid>aliyunmaven\u003C\u002Fid>\n  \u003CmirrorOf>*\u003C\u002FmirrorOf>\n  \u003Cname>阿里云公共仓库\u003C\u002Fname>\n  \u003Curl>https:\u002F\u002Fmaven.aliyun.com\u002Frepository\u002Fpublic\u003C\u002Furl>\n\u003C\u002Fmirror>\n```\n\n## 安装步骤\n\n1. 克隆代码  \n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FSparrowRecSys.git\ncd SparrowRecSys\n```\n\n2. 一键安装依赖  \n```bash\nmvn clean install -DskipTests\n```\n\n3. 下载并解压数据（已内置精简版，可跳过）  \n如需完整 MovieLens 20M 数据集：  \n```bash\nwget https:\u002F\u002Ffiles.grouplens.org\u002Fdatasets\u002Fmovielens\u002Fml-20m.zip\nunzip ml-20m.zip -d src\u002Fmain\u002Fresources\u002F\n```\n\n## 基本使用\n\n1. 用 IntelliJ IDEA 打开项目根目录  \n2. 等待 Maven 自动导入依赖  \n3. 运行主类  \n   - 在 `src\u002Fmain\u002Fjava\u002Fcom\u002Fsparrowrecsys\u002Fonline\u002FRecSysServer.java` 右键 → Run  \n4. 浏览器访问  \n```\nhttp:\u002F\u002Flocalhost:6010\u002F\n```\n即可看到电影推荐界面，默认展示热门影片与个性化推荐结果。\n\n> 首次启动会触发模型初始化，约 30 秒后页面可正常加载。","一家 20 人规模的独立电影流媒体平台「CineGo」正准备上线新版首页，希望在两周内把“猜你喜欢”模块的点击率提升 30%，但团队里只有 1 名算法工程师和 2 名后端开发。\n\n### 没有 SparrowRecSys 时\n- 数据链路从零搭建：Spark 离线特征、TensorFlow 训练、Jetty 线上服务都要分别写脚本，光是打通就花了 5 天。\n- 模型选型靠拍脑袋：工程师只熟悉协同过滤，上线后 CTR 仅提升 8%，离目标差得远。\n- 冷启动问题无解：新注册用户在首页看到的都是热门片，跳出率高达 65%。\n- 线上延迟超标：Python Flask 服务单机 QPS 不到 200，晚高峰直接 502。\n- 评估指标混乱：离线 AUC 与线上 CTR 对不上，团队每天争论“到底算没算提升”。\n\n### 使用 SparrowRecSys 后\n- 一键跑通端到端：用自带的 Maven 工程，`RecSysServer` 右键即启动，2 小时完成离线→近线→在线全链路。\n- 8 种深度模型开箱即用：把 Wide&Deep 换成 DIN，离线 AUC 从 0.71 提到 0.83，线上 CTR 直接涨 34%，超额完成 KPI。\n- 冷启动用 Item2Vec：把电影海报文本喂进 Word2Vec，新用户首屏平均观看时长提升 42%。\n- Jetty + TensorFlow Serving 双栈：单机 QPS 稳在 1200，P99 延迟 38 ms，晚高峰零报警。\n- 内置评估脚本：离线 AUC、线上 CTR、GAUC 一键对比，团队每天 10 分钟对齐数据，专注优化而非扯皮。\n\nSparrowRecSys 让一个小团队在两周内就拥有了工业级深度学习推荐能力，把“猜你喜欢”从拖后腿变成增长引擎。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fwzhe06_SparrowRecSys_22aa847e.png","wzhe06","Wang Zhe","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fwzhe06_0f390bbb.jpg","Engineering Manager @Bytedance\r\nComputational Advertising",null,"San Francisco Bay Area","wzhe06@gmail.com","https:\u002F\u002Fwzhe.me\u002F","https:\u002F\u002Fgithub.com\u002Fwzhe06",[24,28,32,36,40],{"name":25,"color":26,"percentage":27},"Python","#3572A5",38.9,{"name":29,"color":30,"percentage":31},"Java","#b07219",26.4,{"name":33,"color":34,"percentage":35},"Scala","#c22d40",15.5,{"name":37,"color":38,"percentage":39},"HTML","#e34c26",11.6,{"name":41,"color":42,"percentage":43},"JavaScript","#f1e05a",7.6,2756,870,"2026-04-03T13:56:07","Apache-2.0",4,"未说明",{"notes":51,"python":52,"dependencies":53},"项目为基于 Maven 的混合语言工程，需同时安装 Java 8 与 Scala 2.11；内置精简版 MovieLens 数据集，如需完整数据需额外下载 MovieLens 20M Dataset；推荐用 IntelliJ IDEA 直接运行 RecSysServer 启动服务，默认端口 6010。","3.6+",[54,55,56],"TensorFlow 2.0+","Spark","Jetty Server",[58],"开发框架",[60,61,62],"recommender-system","deep-learning","machine-learning",2,"ready","2026-03-27T02:49:30.150509","2026-04-06T08:40:07.177669",[68,73,78,83,88,93,98,103],{"id":69,"question_zh":70,"answer_zh":71,"source_url":72},6143,"运行 WideNDeep.py 或 DeepFM.py 时出现 “Cast string to int32 is not supported” 怎么办？","该错误由 TensorFlow 版本不兼容引起。将 TensorFlow 升级到 2.3.0 即可解决（实测 2.0.0 也可）。命令：pip install tensorflow==2.3.0","https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FSparrowRecSys\u002Fissues\u002F26",{"id":74,"question_zh":75,"answer_zh":76,"source_url":77},6144,"docker 运行 tensorflow\u002Fserving 报 “Illegal instruction (core dumped)” 无法上线模型怎么办？","该问题通常出现在 CPU 不支持 AVX 指令集的老机器上。可改用社区已构建好的镜像或自行编译无 AVX 的 tensorflow_model_server。参考实现：https:\u002F\u002Fgithub.com\u002Fiqiancheng\u002Fsparrowrecsys-serving","https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FSparrowRecSys\u002Fissues\u002F43",{"id":79,"question_zh":80,"answer_zh":81,"source_url":82},6145,"项目中的训练\u002F测试数据文件路径写死了，如何获取并修改？","数据已随项目放在 SparrowRecSys\u002Fsrc\u002Fmain\u002Fresources\u002Fwebroot\u002Fsampledata\u002F 目录下。只需将代码中的绝对路径改为本地相对路径即可，例如：training_samples_file_path = \"src\u002Fmain\u002Fresources\u002Fwebroot\u002Fsampledata\u002FtrainingSamples.csv\"","https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FSparrowRecSys\u002Fissues\u002F29",{"id":84,"question_zh":85,"answer_zh":86,"source_url":87},6146,"用 Spark 写 Redis 时报 “ERR wrong number of arguments for 'hset' command” 怎么解决？","Redis 旧版本只支持单 field 的 HSET。将代码中的 redisClient.hset 改为 redisClient.hmset 即可一次写入多个 field-value 对。","https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FSparrowRecSys\u002Fissues\u002F45",{"id":89,"question_zh":90,"answer_zh":91,"source_url":92},6147,"项目目前是否已完整？召回、排序、模型上线等模块在哪？","目前仍在逐步完善中，尚未达到生产级完整度。召回、排序、TensorFlow 训练及 serving 模块会随着极客时间课程进度陆续加入，可关注后续更新。","https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FSparrowRecSys\u002Fissues\u002F2",{"id":94,"question_zh":95,"answer_zh":96,"source_url":97},6148,"可以把项目改造成文章推荐系统吗？","可以。除了数据预处理和特征抽取部分需要替换为文章相关字段外，其余框架（召回、排序、模型训练与上线）均可复用。","https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FSparrowRecSys\u002Fissues\u002F28",{"id":99,"question_zh":100,"answer_zh":101,"source_url":102},6149,"Scala 代码中 Seq(sample.toList : _*) 的 : _* 是什么意思？",": _* 是 Scala 的“序列展开”语法，告诉编译器把 List 中的每个元素当作独立参数传给 Seq 的构造器，相当于展开列表。","https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FSparrowRecSys\u002Fissues\u002F10",{"id":104,"question_zh":105,"answer_zh":106,"source_url":107},6150,"编译提示 “程序包 org.apache.flink.api.common.functions 不存在” 怎么办？","缺少 Flink 依赖。在 Maven 或 Gradle 中加入 Flink 对应版本的依赖，例如 Maven：\n\u003Cdependency>\n  \u003CgroupId>org.apache.flink\u003C\u002FgroupId>\n  \u003CartifactId>flink-streaming-java_2.12\u003C\u002FartifactId>\n  \u003Cversion>1.12.0\u003C\u002Fversion>\n\u003C\u002Fdependency>\n然后重新编译即可。","https:\u002F\u002Fgithub.com\u002Fwzhe06\u002FSparrowRecSys\u002Fissues\u002F44",[],[110,121,130,138,146,159],{"id":111,"name":112,"github_repo":113,"description_zh":114,"stars":115,"difficulty_score":116,"last_commit_at":117,"category_tags":118,"status":64},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",[58,119,120],"图像","Agent",{"id":122,"name":123,"github_repo":124,"description_zh":125,"stars":126,"difficulty_score":63,"last_commit_at":127,"category_tags":128,"status":64},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,"2026-04-05T23:32:43",[58,120,129],"语言模型",{"id":131,"name":132,"github_repo":133,"description_zh":134,"stars":135,"difficulty_score":63,"last_commit_at":136,"category_tags":137,"status":64},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",[58,119,120],{"id":139,"name":140,"github_repo":141,"description_zh":142,"stars":143,"difficulty_score":63,"last_commit_at":144,"category_tags":145,"status":64},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",[58,129],{"id":147,"name":148,"github_repo":149,"description_zh":150,"stars":151,"difficulty_score":63,"last_commit_at":152,"category_tags":153,"status":64},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",[119,154,155,156,120,157,129,58,158],"数据工具","视频","插件","其他","音频",{"id":160,"name":161,"github_repo":162,"description_zh":163,"stars":164,"difficulty_score":116,"last_commit_at":165,"category_tags":166,"status":64},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",[120,119,58,129,157]]