{"id":13901176,"url":"https://github.com/zepen/predict_Lottery_ticket","last_synced_at":"2025-07-17T21:32:32.857Z","repository":{"id":38354497,"uuid":"130827252","full_name":"zepen/predict_Lottery_ticket","owner":"zepen","description":"双色球+大乐透彩票AI预测","archived":false,"fork":false,"pushed_at":"2023-05-31T16:12:22.000Z","size":2779,"stargazers_count":725,"open_issues_count":15,"forks_count":373,"subscribers_count":31,"default_branch":"master","last_synced_at":"2024-08-06T21:40:33.694Z","etag":null,"topics":["chinese","deep-learning","ml","python"],"latest_commit_sha":null,"homepage":"","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/zepen.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}},"created_at":"2018-04-24T09:09:39.000Z","updated_at":"2024-08-06T16:07:33.000Z","dependencies_parsed_at":"2024-01-16T22:21:49.114Z","dependency_job_id":"547ffefc-7281-4fc6-9a43-64388abb1dc7","html_url":"https://github.com/zepen/predict_Lottery_ticket","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/zepen%2Fpredict_Lottery_ticket","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zepen%2Fpredict_Lottery_ticket/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zepen%2Fpredict_Lottery_ticket/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zepen%2Fpredict_Lottery_ticket/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zepen","download_url":"https://codeload.github.com/zepen/predict_Lottery_ticket/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226305242,"owners_count":17603773,"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":["chinese","deep-learning","ml","python"],"created_at":"2024-08-06T21:00:58.380Z","updated_at":"2025-07-17T21:32:32.846Z","avatar_url":"https://github.com/zepen.png","language":"Python","readme":"# 双色球+大乐透彩票AI预测\n\n有问题，请联系客服（客服1群：246714623（满员请加2群），客服2群：980203303）\n\n公众号\n\n![avatar](img/gzh.png)\n\n\n## Installing\n        \n* step1，安装anaconda(可参考https://zhuanlan.zhihu.com/p/32925500)；\n\n* step2，创建一个conda环境，conda create -n your_env_name python=3.6；\n       \n* step3，进入创建conda的环境 conda activate your_env_name，然后执行pip install -r requirements.txt；\n       \n* step4，按照Getting Started执行即可，推荐使用PyCharm\n\n## Getting Started\n\n```python\npython get_data.py  --name ssq  # 执行获取双色球训练数据\n```\n如果出现解析错误，应该看看网页 http://datachart.500.com/ssq/history/newinc/history.php 是否可以正常访问\n若要大乐透，替换参数 --name dlt 即可\n\n```python\npython run_train_model.py --name ssq  # 执行训练双色球模型\n``` \n开始模型训练，先训练红球模型，再训练蓝球模型，模型参数和超参数在 config.py 文件中自行配置\n具体训练时间消耗与模型参数和超参数相关。\n\n```python\npython run_predict.py  --name ssq # 执行双色球模型预测\n```\n预测结果会打印在控制台\n\n## Update\n\n* 新增模型预测评估，可以自行调整训练集和测试集比例，建议训练集采样比例高于0.5\n\n* 修复大乐透蓝球号码预测超出取值范围问题，修复训练传参数导致数据维度不匹配问题\n\n* 有盆友反馈想要个大乐透的预测玩法，加入对大乐透的数据爬取，模型训练，模型预测等功能，通过传入执行参数 --name dlt即可。\n\n* 为了降低本项目的使用门槛，废弃docker模式和微服务，按照Getting Started执行脚本，即可获取预测结果。\n\n* 非常开心有更多的同志们关注项目，并且提出了很多宝贵的问题，但是由于工作较忙，没有给大家比较完善的解答，再次说句抱歉，\n大部分问题都是安装依赖问题，我更新了requirements.txt中相关库版本，应该可以解决。\n\n* 之前有issue反应，因为不同红球模型预测会有重复号码出现，所以将红球序列整体作为一个序列模型看待，推翻之前红球之间相互独立设定，\n因为序列模型预测要引入crf层，相关API必须在 tf.compat.v1.disable_eager_execution()下，故整个模型采用 1.x 构建和训练模式，\n在 2.x 的tensorflow中 tf.compat.v1.XXX 保留了 1.x 的接口方式。\n","funding_links":[],"categories":["Python"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzepen%2Fpredict_Lottery_ticket","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzepen%2Fpredict_Lottery_ticket","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzepen%2Fpredict_Lottery_ticket/lists"}