{"id":18757408,"url":"https://github.com/pacospace/cluster-data-science-packages","last_synced_at":"2025-07-08T07:39:38.489Z","repository":{"id":39882244,"uuid":"274706368","full_name":"pacospace/cluster-data-science-packages","owner":"pacospace","description":"Cluster data science packages.","archived":false,"fork":false,"pushed_at":"2022-12-08T07:50:59.000Z","size":977,"stargazers_count":0,"open_issues_count":5,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-12-29T02:52:10.788Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/pacospace.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":null,"support":null}},"created_at":"2020-06-24T15:40:09.000Z","updated_at":"2021-01-31T20:40:47.000Z","dependencies_parsed_at":"2023-01-25T09:01:18.324Z","dependency_job_id":null,"html_url":"https://github.com/pacospace/cluster-data-science-packages","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":"thoth-station/template-project","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pacospace%2Fcluster-data-science-packages","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pacospace%2Fcluster-data-science-packages/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pacospace%2Fcluster-data-science-packages/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pacospace%2Fcluster-data-science-packages/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pacospace","download_url":"https://codeload.github.com/pacospace/cluster-data-science-packages/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239646684,"owners_count":19674065,"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":[],"created_at":"2024-11-07T17:42:28.513Z","updated_at":"2025-02-19T11:26:41.196Z","avatar_url":"https://github.com/pacospace.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Data Science packages categorization\n\nThis project aims at clustering Python Packages for Data Science under specific categories.\n\nThe initial list of Python packages for data science that are used for this experiment can be found\nin [100 Data Science Python Packages](https://github.com/pacospace/cluster-data-science-packages/blob/master/data/raw/hundreds_data_science_packages_initial_dataset.json).\nThis preliminary list has been selected with collegues from Red Hat AICoE and other departments at Red Hat.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpacospace%2Fcluster-data-science-packages","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpacospace%2Fcluster-data-science-packages","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpacospace%2Fcluster-data-science-packages/lists"}