{"id":26192923,"url":"https://github.com/vinch1/wechatdatasetprocess","last_synced_at":"2026-03-05T08:02:13.762Z","repository":{"id":281871867,"uuid":"946704711","full_name":"Vinch1/WechatDatasetProcess","owner":"Vinch1","description":"Feature engineering Wechat video channel for multi-task model ","archived":false,"fork":false,"pushed_at":"2025-03-11T15:06:57.000Z","size":18,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-05T23:31:49.421Z","etag":null,"topics":["feature-engineering","mmoe","python3","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/Vinch1.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2025-03-11T14:50:53.000Z","updated_at":"2025-06-02T04:15:53.000Z","dependencies_parsed_at":"2025-03-11T16:22:48.931Z","dependency_job_id":"54ef5ef7-7478-40bc-932b-0147385567f2","html_url":"https://github.com/Vinch1/WechatDatasetProcess","commit_stats":null,"previous_names":["vinch1/wechatdatasetprocess"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Vinch1/WechatDatasetProcess","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vinch1%2FWechatDatasetProcess","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vinch1%2FWechatDatasetProcess/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vinch1%2FWechatDatasetProcess/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vinch1%2FWechatDatasetProcess/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Vinch1","download_url":"https://codeload.github.com/Vinch1/WechatDatasetProcess/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vinch1%2FWechatDatasetProcess/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30115662,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-05T03:40:26.266Z","status":"ssl_error","status_checked_at":"2026-03-05T03:39:15.902Z","response_time":93,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["feature-engineering","mmoe","python3","tensorflow"],"created_at":"2025-03-12T01:25:13.403Z","updated_at":"2026-03-05T08:02:13.739Z","avatar_url":"https://github.com/Vinch1.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# WechatDatasetProcess\n### What's it about?\nThis repository contains a .ipynb file that manipulate Wechat video channel data, giving a lesser but denser matrix for model training.\n### Description\nIt logic is to get all samples that have at least one positive target among four tagets and randomly add the rest samples to amount of samples. They are \"read_comment\", \"like\", \"click_avatar\" and \"forward\".\nAnd that reduces its scale from 700k lines of data to 50k, which is suitable for a single machine with 16G RAM to train with.\n### Credit\nIf you want to see the whole project, please leave a star and head to https://github.com/ShowMeAI-Hub/multi-task-learning/blob/main/1.data-preprocessing-and-feature-engineering.ipynb for more~\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvinch1%2Fwechatdatasetprocess","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvinch1%2Fwechatdatasetprocess","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvinch1%2Fwechatdatasetprocess/lists"}