{"id":17263726,"url":"https://github.com/jrzaurin/recotour","last_synced_at":"2025-08-22T22:42:36.677Z","repository":{"id":44392450,"uuid":"134463121","full_name":"jrzaurin/RecoTour","owner":"jrzaurin","description":"A tour through recommendation algorithms in python [IN PROGRESS]","archived":false,"fork":false,"pushed_at":"2024-12-26T18:38:27.000Z","size":6880,"stargazers_count":176,"open_issues_count":0,"forks_count":38,"subscribers_count":21,"default_branch":"master","last_synced_at":"2025-01-27T15:27:30.169Z","etag":null,"topics":["collaborative-filtering","deep-learning","lightgbm","matrix-factorization","python3","recommendation-algorithms"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jrzaurin.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-05-22T19:06:23.000Z","updated_at":"2024-04-24T13:03:54.000Z","dependencies_parsed_at":"2025-02-08T13:09:08.646Z","dependency_job_id":"e9310c2f-5331-484b-8580-c93addc2ab75","html_url":"https://github.com/jrzaurin/RecoTour","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jrzaurin%2FRecoTour","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jrzaurin%2FRecoTour/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jrzaurin%2FRecoTour/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jrzaurin%2FRecoTour/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jrzaurin","download_url":"https://codeload.github.com/jrzaurin/RecoTour/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247190250,"owners_count":20898702,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["collaborative-filtering","deep-learning","lightgbm","matrix-factorization","python3","recommendation-algorithms"],"created_at":"2024-10-15T07:57:21.702Z","updated_at":"2025-04-04T14:07:25.609Z","avatar_url":"https://github.com/jrzaurin.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"450\" src=\"docs/figures/recotour_logo.png\"\u003e\n\u003c/p\u003e\n\n# RecoTour\n\nThis repo intends to be a tour through some recommendation algorithms in\npython using various dataset. Companion posts are:\n\n1. [Recotour: a tour through recommendation algorithms in python](https://medium.com/datadriveninvestor/recotour-a-tour-through-recommendation-algorithms-in-python-52d780628ab9)\n\n2. [RecoTour II: neural recommendation algorithms](https://towardsdatascience.com/recotour-ii-neural-recommendation-algorithms-49733938d56e)\n\n3. [RecoTour III: Variational Autoencoders for Collaborative Filtering with Mxnet and Pytorch](https://jrzaurin.github.io/infinitoml/2020/05/15/mult-vae.html).\n\nThe repo is organised as follows:\n\n1. **recotour**: this is the original \"tour\" through recommendation algorithms\nusing the [Ponpare](https://www.kaggle.com/c/coupon-purchase-prediction)\ncoupon dataset. In particular, the algorithms included in the `recotour`\ndirectory are:\n    1. Data processing, with a deep dive into feature engineering\n    2. Most Popular recommendations (the baseline)\n    3. Item-User similarity based recommendations\n    4. kNN Collaborative Filtering recommendations\n    5. GBM based recommendations using `lightGBM` with a tutorial on how to optimize gbms\n    6. Non-Negative Matrix Factorization recommendations\n    7. Factorization Machines (Steffen Rendle 2010) recommendations using `xlearn`\n    8. Field Aware Factorization Machines (Yuchin Juan, et al, 2016) recommendations using `xlearn`\n    9. Deep Learning based recommendations (Wide and Deep, Heng-Tze Cheng, et al, 2016) using `pytorch`\n\n  I have included a more modular (nicer looking) version of a possible final\n  solution (described in `Chapter16_final_solution_Recommendations.ipynb`) in\n  the directory `final_recommendations`.\n\n  In addition, I have included an illustration of how to use other evaluation\n  metrics apart from the one shown in the notebooks ( the mean average precision\n  or MAP) such as the Normalized Discounted Cumulative Gain\n  ([NDCG](https://en.wikipedia.org/wiki/Discounted_cumulative_gain)). This can\n  be found in `using_ncdg.py` in the directory `py_scripts`.\n\nIn addition, there are other, DL-based recommendation algorithms that use\nmainly the [Amazon Reviews](http://jmcauley.ucsd.edu/data/amazon/) dataset,\nin particular the 5-core Movies and TV reviews. These are:\n\n2. **neural_cf**: Neural Collaborative Filtering (Xiangnan He et al., 2017)\n3. **neural_graph_cf**: Neural Graph Collaborative Filtering (Wang Xiang et al. 2019)\n4. **mult-vae**: Variational Autoencoders for Collaborative Filtering (Dawen Liang et al,. 2018)\n\n**The core of the repo are the notebooks** in each directory. They intend to\nbe self-contained and in consequence, there is some of code repetition. The\ncode is, of course, \"notebook-oriented\". The notebooks have plenty of\nexplanations and references to relevant papers or packages. My intention was\nto focus on the code, but you will also find some math.\n\nI hope the code here is useful to someone. If you have any idea on how to\nimprove the content of the repo, or you want to contribute, let me know.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjrzaurin%2Frecotour","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjrzaurin%2Frecotour","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjrzaurin%2Frecotour/lists"}