All Projects → zepen → predict_Lottery_ticket

zepen / predict_Lottery_ticket

Licence: other
双色球+大乐透彩票AI预测

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to predict Lottery ticket

embedding study
中文预训练模型生成字向量学习,测试BERT,ELMO的中文效果
Stars: ✭ 94 (-72.43%)
Mutual labels:  chinese
leetspeek
Open and collaborative content from leet hackers!
Stars: ✭ 11 (-96.77%)
Mutual labels:  ml
lm-scorer
📃Language Model based sentences scoring library
Stars: ✭ 264 (-22.58%)
Mutual labels:  ml
pypmml
Python PMML scoring library
Stars: ✭ 65 (-80.94%)
Mutual labels:  ml
revisiting rainbow
Revisiting Rainbow
Stars: ✭ 71 (-79.18%)
Mutual labels:  ml
Vanhiupun.github.io
🏖️ Vanhiupun's Awesome Site ==> another theme for elegant writers with modern flat style and beautiful night/dark mode.
Stars: ✭ 57 (-83.28%)
Mutual labels:  chinese
SENet-for-Weakly-Supervised-Relation-Extraction
No description or website provided.
Stars: ✭ 39 (-88.56%)
Mutual labels:  ml
BERT-chinese-text-classification-pytorch
This repo contains a PyTorch implementation of a pretrained BERT model for text classification.
Stars: ✭ 92 (-73.02%)
Mutual labels:  chinese
community
README for Rekcurd projects
Stars: ✭ 16 (-95.31%)
Mutual labels:  ml
card-scanner-flutter
A flutter package for Fast, Accurate and Secure Credit card & Debit card scanning
Stars: ✭ 82 (-75.95%)
Mutual labels:  ml
word2vec-movies
Bag of words meets bags of popcorn in Python 3 中文教程
Stars: ✭ 54 (-84.16%)
Mutual labels:  chinese
ime.vim
A Vim input method engine
Stars: ✭ 74 (-78.3%)
Mutual labels:  chinese
CustomVisionMicrosoftToCoreMLDemoApp
This app recognises 3 hand signs - fist, high five and victory hand [ rock, paper, scissors basically :) ] with live feed camera. It uses a HandSigns.mlmodel which has been trained using Custom Vision from Microsoft.
Stars: ✭ 25 (-92.67%)
Mutual labels:  ml
TrackMania AI
Racing game AI
Stars: ✭ 65 (-80.94%)
Mutual labels:  ml
RE-VERB
speaker diarization system using an LSTM
Stars: ✭ 22 (-93.55%)
Mutual labels:  ml
eslint-config-mingelz
A shared ESLint configuration with Chinese comments. 一份带有完整中文注释的 ESLint 规则。
Stars: ✭ 15 (-95.6%)
Mutual labels:  chinese
DevSoc21
Official website for DEVSOC 21, our annual flagship hackathon.
Stars: ✭ 15 (-95.6%)
Mutual labels:  ml
Hacktoberfest-2k19
Just add pull requests to this repo and stand a chance to win a limited edition Hacktoberfest T-shirt.
Stars: ✭ 33 (-90.32%)
Mutual labels:  ml
dask-sql
Distributed SQL Engine in Python using Dask
Stars: ✭ 271 (-20.53%)
Mutual labels:  ml
chinese-tokenizer
Tokenizes Chinese texts into words.
Stars: ✭ 72 (-78.89%)
Mutual labels:  chinese

双色球+大乐透彩票AI预测

介于越来越多的盆友关心本项目,本人将预测系统制作成了小程序,供大家娱乐使用,再不用担心程序调试出bug啦! 后续会不断优化迭代,也欢迎在issue中提出宝贵建议!

avatar

有问题,欢迎联系我(QQ: 270393749,客服群号:246714623)

公众号

avatar

Installing

  • step1,安装anaconda(可参考https://zhuanlan.zhihu.com/p/32925500);

  • step2,创建一个conda环境,conda create -n your_env_name python=3.6;

  • step3,进入创建conda的环境 conda activate your_env_name,然后执行pip install -r requirements.txt;

  • step4,按照Getting Started执行即可,推荐使用PyCharm

Getting Started

python get_data.py  --name ssq  # 执行获取双色球训练数据

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 若要大乐透,替换参数 --name dlt 即可

python run_train_model.py --name ssq  # 执行训练双色球模型

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 具体训练时间消耗与模型参数和超参数相关。

python run_predict.py  --name ssq # 执行双色球模型预测

预测结果会打印在控制台

Update

  • 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。

  • 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。

  • 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, 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。

  • 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, 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, 在 2.x 的tensorflow中 tf.compat.v1.XXX 保留了 1.x 的接口方式。

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].