{"id":13934780,"url":"https://github.com/nlpjoe/daguan-classify-2018","last_synced_at":"2025-07-19T19:31:38.643Z","repository":{"id":206158155,"uuid":"148303992","full_name":"nlpjoe/daguan-classify-2018","owner":"nlpjoe","description":"2018达观杯长文本分类智能处理挑战赛 18解决方案","archived":false,"fork":false,"pushed_at":"2019-06-10T01:38:11.000Z","size":120,"stargazers_count":152,"open_issues_count":2,"forks_count":60,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-07-10T23:44:31.523Z","etag":null,"topics":["competition-code","keras","python"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/nlpjoe.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2018-09-11T11:03:15.000Z","updated_at":"2024-09-11T06:14:50.000Z","dependencies_parsed_at":"2023-11-08T10:32:05.058Z","dependency_job_id":null,"html_url":"https://github.com/nlpjoe/daguan-classify-2018","commit_stats":null,"previous_names":["nlpjoe/daguan-classify-2018"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/nlpjoe/daguan-classify-2018","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nlpjoe%2Fdaguan-classify-2018","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nlpjoe%2Fdaguan-classify-2018/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nlpjoe%2Fdaguan-classify-2018/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nlpjoe%2Fdaguan-classify-2018/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nlpjoe","download_url":"https://codeload.github.com/nlpjoe/daguan-classify-2018/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nlpjoe%2Fdaguan-classify-2018/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265973519,"owners_count":23858248,"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":["competition-code","keras","python"],"created_at":"2024-08-07T23:01:13.821Z","updated_at":"2025-07-19T19:31:38.196Z","avatar_url":"https://github.com/nlpjoe.png","language":"Jupyter Notebook","funding_links":["https://opencollective.com/daguan-2018"],"categories":["Jupyter Notebook"],"sub_categories":[],"readme":"# 达观杯2018\n[![Backers on Open Collective](https://opencollective.com/daguan-2018/backers/badge.svg)](#backers)\n [![Sponsors on Open Collective](https://opencollective.com/daguan-2018/sponsors/badge.svg)](#sponsors) \n\n参数没调好，仓促比赛，单模型线上没测过，线下0.784，最终得分0.791，排名18/3462，排名不高就不多写了，等着前排分享。思路如同代码所写，很简单。\n\n数据请在[达观数据](http://www.dcjingsai.com/common/cmpt/%E2%80%9C%E8%BE%BE%E8%A7%82%E6%9D%AF%E2%80%9D%E6%96%87%E6%9C%AC%E6%99%BA%E8%83%BD%E5%A4%84%E7%90%86%E6%8C%91%E6%88%98%E8%B5%9B_%E8%B5%9B%E4%BD%93%E4%B8%8E%E6%95%B0%E6%8D%AE.html)处下载，放在data目录下。\n\n### 一、环境\n\n|环境/库|版本|\n|:---------:|----------|\n|Ubuntu|14.04.5 LTS|\n|python|3.6|\n|jupyter notebook|4.2.3|\n|tensorflow-gpu|1.10.1|\n|numpy|1.14.1|\n|pandas|0.23.0|\n|matplotlib|2.2.2|\n|gensim|3.5.0|\n|tqdm|4.24.0|\n\n\n### 二、数据预处理\n\n都写在`jupyter`里了。运行`src/preprocess/EDA.ipynb`生成各种文件。\n\n### 三、baseline模型训练\n\n在`src/preprocess/`中运行：\n\n```\npython baseline-x-cv.py\n```\n\n### 四、深度模型训练\n\n然后直接train模型，单GPU运行，模型自选：\n\n```\npython train_predict.py --gpu 4 --option 5 --model convlstm --feature char\n```\n\n多GPU训练示例：\n\n```\npython train_predict.py --gpu 4,5,6,7 --option 5 --model convlstm --feature char\n```\n\n### 五、模型融合输出\n\n```\npython stacking.py --gpu 1 --tfidf True --option 5\n```\n\n这里是stacking和伪标签一起做了，请修改代码自选是否用伪标签。\n\n\n\n\n## Contributors\n\nThis project exists thanks to all the people who contribute. [[Contribute](CONTRIBUTING.md)].\n\u003ca href=\"https://github.com/nlpjoe/daguan-classify-2018/graphs/contributors\"\u003e\u003cimg src=\"https://opencollective.com/daguan-2018/contributors.svg?width=890\u0026button=false\" /\u003e\u003c/a\u003e\n\n\n## Backers\n\nThank you to all our backers! 🙏 [[Become a backer](https://opencollective.com/daguan-2018#backer)]\n\n\u003ca href=\"https://opencollective.com/daguan-2018#backers\" target=\"_blank\"\u003e\u003cimg src=\"https://opencollective.com/daguan-2018/backers.svg?width=890\"\u003e\u003c/a\u003e\n\n\n## Sponsors\n\nSupport this project by becoming a sponsor. Your logo will show up here with a link to your website. [[Become a sponsor](https://opencollective.com/daguan-2018#sponsor)]\n\n\u003ca href=\"https://opencollective.com/daguan-2018/sponsor/0/website\" target=\"_blank\"\u003e\u003cimg src=\"https://opencollective.com/daguan-2018/sponsor/0/avatar.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://opencollective.com/daguan-2018/sponsor/1/website\" target=\"_blank\"\u003e\u003cimg src=\"https://opencollective.com/daguan-2018/sponsor/1/avatar.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://opencollective.com/daguan-2018/sponsor/2/website\" target=\"_blank\"\u003e\u003cimg src=\"https://opencollective.com/daguan-2018/sponsor/2/avatar.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://opencollective.com/daguan-2018/sponsor/3/website\" target=\"_blank\"\u003e\u003cimg src=\"https://opencollective.com/daguan-2018/sponsor/3/avatar.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://opencollective.com/daguan-2018/sponsor/4/website\" target=\"_blank\"\u003e\u003cimg src=\"https://opencollective.com/daguan-2018/sponsor/4/avatar.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://opencollective.com/daguan-2018/sponsor/5/website\" target=\"_blank\"\u003e\u003cimg src=\"https://opencollective.com/daguan-2018/sponsor/5/avatar.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://opencollective.com/daguan-2018/sponsor/6/website\" target=\"_blank\"\u003e\u003cimg src=\"https://opencollective.com/daguan-2018/sponsor/6/avatar.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://opencollective.com/daguan-2018/sponsor/7/website\" target=\"_blank\"\u003e\u003cimg src=\"https://opencollective.com/daguan-2018/sponsor/7/avatar.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://opencollective.com/daguan-2018/sponsor/8/website\" target=\"_blank\"\u003e\u003cimg src=\"https://opencollective.com/daguan-2018/sponsor/8/avatar.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://opencollective.com/daguan-2018/sponsor/9/website\" target=\"_blank\"\u003e\u003cimg src=\"https://opencollective.com/daguan-2018/sponsor/9/avatar.svg\"\u003e\u003c/a\u003e\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnlpjoe%2Fdaguan-classify-2018","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnlpjoe%2Fdaguan-classify-2018","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnlpjoe%2Fdaguan-classify-2018/lists"}