We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
我在努力理解算法的逻辑,并做了一些尝试,发现一个非常疑惑的现象 1、使用LSTM训练并测试开盘价,测试曲线相对合理,但训练收盘价时,测试曲线出现滞后现象
开盘价
收盘价
尝试了下列的措施,滞后程度并没有改善,希望各位可以给点意见:
训练并测试开盘价(LSTM,EPOCH=100,SEQ_LEN=60,SHUFFLE=True)
训练并测试收盘价(LSTM,EPOCH=100,SEQ_LEN=60,SHUFFLE=True)
The text was updated successfully, but these errors were encountered:
我想请问下,这个具体操作是怎么样的,首先 1.python getdata.py 2.python data_preprocess.py 3.python predict.py --mode train --model lstm --predict_days 10 为什么第三步出错了,出现code: data_queue, train error: name 'loss' is not defined
Sorry, something went wrong.
我在努力理解算法的逻辑,并做了一些尝试,发现一个非常疑惑的现象 1、使用LSTM训练并测试开盘价,测试曲线相对合理,但训练收盘价时,测试曲线出现滞后现象 尝试了下列的措施,滞后程度并没有改善,希望各位可以给点意见: 独立训练,独立模型 调整收盘价到第一列位置 剔除开盘价,或者剔除最大、最小、交易量等 调整EPOCH=20-50-100,SEQ_LEN=10-20-60-99,SHUFFLE=True/False 训练并测试开盘价(LSTM,EPOCH=100,SEQ_LEN=60,SHUFFLE=True) 训练并测试收盘价(LSTM,EPOCH=100,SEQ_LEN=60,SHUFFLE=True)
这应该是时间窗口引起的问题,等我有时间,会来重新对应时间窗口的
No branches or pull requests
我在努力理解算法的逻辑,并做了一些尝试,发现一个非常疑惑的现象
1、使用LSTM训练并测试
开盘价
,测试曲线相对合理,但训练收盘价
时,测试曲线出现滞后现象尝试了下列的措施,滞后程度并没有改善,希望各位可以给点意见:
收盘价
到第一列位置开盘价
,或者剔除最大、最小、交易量等训练并测试开盘价(LSTM,EPOCH=100,SEQ_LEN=60,SHUFFLE=True)
![m-100-60-shuffle-0-predict](https://private-user-images.githubusercontent.com/16029492/263652806-4b79dc96-717b-4b61-8b1c-de8bc4a1c601.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.SZhY-gqqk8eRt7cj8eJK7-usrBBW5BnIEwzG1liRi24)
![Figure_1](https://private-user-images.githubusercontent.com/16029492/263657261-11ccddca-160b-4742-a41c-eb7e3ea70972.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.0A5KodZx7FOfv60mlFPFmRnQH8LYSi7pSCaYAbMNi4o)
训练并测试收盘价(LSTM,EPOCH=100,SEQ_LEN=60,SHUFFLE=True)
![m-100-60-shuffle-1-predict](https://private-user-images.githubusercontent.com/16029492/263652947-169afa6c-72f5-44fd-80e8-23fc943d3866.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.IvqnjaXeiT3Ewu7Yxl9ryKX_Ehar1ghrCws8OD1XtKk)
![Figure_2](https://private-user-images.githubusercontent.com/16029492/263657704-7bbd371f-a87c-4aa0-9692-4cd2d97470fa.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.2E3aWrCufmZKzhxtvYtg4Xtz5peiweG3R13ziRgC6to)
The text was updated successfully, but these errors were encountered: