{"id":18430667,"url":"https://github.com/trivago/recsys-challenge-2019-benchmarks","last_synced_at":"2025-04-07T17:33:46.803Z","repository":{"id":66086178,"uuid":"224626500","full_name":"trivago/recsys-challenge-2019-benchmarks","owner":"trivago","description":"Run benchmark algorithms on the data sets of the RecSys Challenge 2019. https://recsys.trivago.cloud/","archived":true,"fork":false,"pushed_at":"2020-04-29T15:29:33.000Z","size":17,"stargazers_count":4,"open_issues_count":0,"forks_count":2,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-02T06:28:59.903Z","etag":null,"topics":["data-science","recsys","recsys2019"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/trivago.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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":"2019-11-28T10:18:27.000Z","updated_at":"2023-09-06T12:11:09.000Z","dependencies_parsed_at":"2023-02-22T06:00:49.092Z","dependency_job_id":null,"html_url":"https://github.com/trivago/recsys-challenge-2019-benchmarks","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/trivago%2Frecsys-challenge-2019-benchmarks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/trivago%2Frecsys-challenge-2019-benchmarks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/trivago%2Frecsys-challenge-2019-benchmarks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/trivago%2Frecsys-challenge-2019-benchmarks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/trivago","download_url":"https://codeload.github.com/trivago/recsys-challenge-2019-benchmarks/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247698171,"owners_count":20981312,"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":["data-science","recsys","recsys2019"],"created_at":"2024-11-06T05:21:54.482Z","updated_at":"2025-04-07T17:33:46.798Z","avatar_url":"https://github.com/trivago.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RecSys Challenge 2019 - benchmark models\n\nThis repository contains code to reproduce the benchmarks calculated for the data from the [ACM RecSys Challenge 2019](http://www.recsyschallenge.com/2019/) organized by trivago, TU Wien, Politecnico di Milano, and Karlsruhe Institute of Technology.\n\n## Installation and usage\n\n[Optional] Before installing the code, you can create a virtual environment so\nthe installed packages don't get mixed with the ones in your system. To do it,\nexecute the following commands in your terminal:\n\n    python3 -m venv trvrecsys2019benchmarks\n    source trvrecsys2019benchmarks/bin/activate\n\nThis will create a folder in the current directory which will contain the Python executable files.\n\nTo install the package and its dependencies use:\n\n    pip install git+https://github.com/trivago/recsys-challenge-2019-benchmarks.git#egg=trvrecsys2019benchmarks\n\nThis will install all Python packages that are needed. Note that in order to run the code on a Mac, the used version of the lightgbm library requires the installation of the OpenMP library, which is required for running LightGBM on the system with the Apple Clang compiler. This can be installed via:\n\n    brew install libomp\n\n\n### Producing example data\nBefore running any models you can create a small example data set to test the execution of the models before running them with the bigger RecSysChallenge data sets.\n\n    produce-example-data --data-path \u003ctarget-location-for-csv-files\u003e\n\n### Running a single model\nTo run an individual model, run:\n\n    run-single-model --data-path \u003cpath-to-csv-files-directory\u003e --train-file \u003ctraining-data-file\u003e --test-file \u003ctest-data-file\u003e --subm-file \u003csubmission-file-to-be-created\u003e --model-name \u003cname-of-model\u003e\n\nTo see what models are available, run:\n\n    run-single-model --help\n\nNote, that some models need a different set of training data. For example, the nn-item model relies on the item_metadata.csv as input.\n\n### Running all models\nYou can run all models at once. This might take a while and the name of the submission files will be inferred from the model names. To do so, run:\n\n    run-all-models --data-path \u003cpath-to-csv-files-directory\u003e --train-file \u003ctraining-data-file\u003e --test-file \u003ctest-data-file\u003e --meta-file \u003citem-metadata-file\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrivago%2Frecsys-challenge-2019-benchmarks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftrivago%2Frecsys-challenge-2019-benchmarks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrivago%2Frecsys-challenge-2019-benchmarks/lists"}