{"id":16972234,"url":"https://github.com/anastasia/minhash","last_synced_at":"2025-03-21T20:25:22.342Z","repository":{"id":74336984,"uuid":"90172275","full_name":"anastasia/minhash","owner":"anastasia","description":null,"archived":false,"fork":false,"pushed_at":"2019-01-23T17:43:26.000Z","size":17,"stargazers_count":2,"open_issues_count":1,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-26T15:14:18.568Z","etag":null,"topics":["minhash"],"latest_commit_sha":null,"homepage":null,"language":"Python","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/anastasia.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":"2017-05-03T16:52:05.000Z","updated_at":"2019-01-23T17:43:28.000Z","dependencies_parsed_at":null,"dependency_job_id":"08cde9af-7d6c-4d60-8294-479ae792f679","html_url":"https://github.com/anastasia/minhash","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/anastasia%2Fminhash","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anastasia%2Fminhash/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anastasia%2Fminhash/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anastasia%2Fminhash/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/anastasia","download_url":"https://codeload.github.com/anastasia/minhash/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244862480,"owners_count":20522806,"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":["minhash"],"created_at":"2024-10-14T00:58:17.181Z","updated_at":"2025-03-21T20:25:22.285Z","avatar_url":"https://github.com/anastasia.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"### MinHash\nMinHash explanation: http://infolab.stanford.edu/~ullman/mmds/book.pdf\n(chapter 3, also archived here: https://perma.cc/K9B4-QTX3)\nA simple take here: https://moz.com/devblog/near-duplicate-detection/\n\nThis implementation borrows from Chris McCormick's MinHash tutorial.\nhttps://github.com/chrisjmccormick/MinHash\n\n#### To install (for now):\n`pip install -e \"git+git://github.com/anastasia/minhash.git@master#egg=minhash\"`\n\n#### To run in CLI:\n`python minhash.py doc1 doc2`\n\n#### To run in python:\n```\nimport minhash\nminhash.calculate(string_a, string_b)\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanastasia%2Fminhash","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fanastasia%2Fminhash","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanastasia%2Fminhash/lists"}