{"id":13628226,"url":"https://github.com/opringle/gluonrank","last_synced_at":"2025-04-17T00:33:42.526Z","repository":{"id":119618525,"uuid":"159099409","full_name":"opringle/gluonrank","owner":"opringle","description":"Ranking made easy","archived":false,"fork":false,"pushed_at":"2019-01-09T18:28:18.000Z","size":64,"stargazers_count":36,"open_issues_count":1,"forks_count":4,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-05-22T04:21:23.875Z","etag":null,"topics":["collaborative-filtering","gluon","mxnet","ranking"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/opringle.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}},"created_at":"2018-11-26T02:37:37.000Z","updated_at":"2024-02-06T09:56:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"dea38ca0-8d98-40f4-9ba2-d6d026f40a0f","html_url":"https://github.com/opringle/gluonrank","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/opringle%2Fgluonrank","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opringle%2Fgluonrank/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opringle%2Fgluonrank/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opringle%2Fgluonrank/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/opringle","download_url":"https://codeload.github.com/opringle/gluonrank/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223735342,"owners_count":17194081,"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","gluon","mxnet","ranking"],"created_at":"2024-08-01T22:00:48.704Z","updated_at":"2024-11-08T18:31:37.115Z","avatar_url":"https://github.com/opringle.png","language":"Python","funding_links":[],"categories":["\u003ca name=\"CTR\"\u003e\u003c/a\u003e7. CTR"],"sub_categories":["2.14 Misc"],"readme":"### GluonRank: Your Choice of Deep Learning for Ranking\n\nGluonRank is a toolkit that enables easy implementation of collaborative filtering models using neural networks, to help your prototyping of state of the art ranking systems.\n\n## Installation\n\n\n### Pip\n\nMake sure you are using Python 3.6. You can install `MXNet` and `GluonRank` using pip:\n\n```bash\npip install --index-url https://test.pypi.org/simple/ gluonrank\n```\n\n### Uploading to pypi for testing\n\nBuild distribution\n\n`python setup.py sdist bdist_wheel`bash\n\nUpload to pypi test index\n\n`twine upload --repository-url https://test.pypi.org/legacy/ dist/*`bash\n\n## Docs\n\nComing soon... (it might be a while actually...)\n\n\n## ToDo\n\n- [ ] Categorical features\n    - [ ] Get running with multiple categorical features, maintain performance when reducing to a single one\n    - [ ] Gracefully handle missing continuous embedding or categorical variables \u0026 user/item biases\n    - [ ] Do not require user to index their embedding values for a single matrix \n- [ ] Continuous features\n    - [ ] Get running with 1 continous feature, maintain performance when excluded\n    - [ ] Get running with several continuous features\n- [ ] Increase the efficiency of the evaluation function\n- [ ] Speed up negative sampling... Negative sampling without collisions results in 5X training time.\n\n(answer)[https://stackoverflow.com/questions/53576915/sample-n-zeros-from-a-sparse-coo-matrix/53577344#53577344]\n\n- [x] Match spotlight performance with implicit interaction model on movielense data\n- [x] Build ranking function as network method\n- [ ] Create python package\n    - \n- [ ] Create hosted docs\n\n## Features\n\n- [ ] Allow for sampling more than one negative per interaction\n- [ ] Allow for feedback that can be in the form of 0, 1 or -1. (eg swiping data)\n\n## Ideas\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopringle%2Fgluonrank","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fopringle%2Fgluonrank","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopringle%2Fgluonrank/lists"}