search

jingw2 / demand_forecast

453 stars 123 forks source link

question for TPA-LSTM source code #16

Open verystrongjoe opened 3 years ago

verystrongjoe commented 3 years ago

https://github.com/jingw2/demand_forecast/blob/1978fef8af5b676f562946b6f58286f688010d4c/tpa_lstm.py#L150

In this line, I think that Xtrain should be used instead of ytrain. Am I wrong? I could not have found any source code for using multi-variate features in TPA-LSTM code.

jingw2 commented 3 years ago

In the paper, TPA-LSTM just uses y{t-w}, y{t-w+1} ... to predict y_{t-1+delta}

2017wxyzwxyz commented 3 years ago

@verystrongjoe，你好！请问你是在windows还是linux环境下跑通这些程序的？若在windows10下跑通，能否发我一份代码，我这里出现非常多的错误，我的邮箱是NewWxy2016@163.com，多谢！

verystrongjoe commented 3 years ago

@2017wxyzwxyz Hi, I will run this source code on my Ubuntu OS. do you want me to send the source code? I think that there is no big difference between original source code and my local code. If you want, I will send a zip file.

2017wxyzwxyz commented 3 years ago

Please send me your code, thank you！

xiaolongwu0713 commented 3 years ago

In the paper, TPA-LSTM just uses y{t-w}, y{t-w+1} ... to predict y_{t-1+delta}

I think they use multivariate model, not single variable.

YachaoDong commented 3 years ago

https://github.com/jingw2/demand_forecast/blob/1978fef8af5b676f562946b6f58286f688010d4c/tpa_lstm.py#L150

In this line, I think that Xtrain should be used instead of ytrain. Am I wrong? I could not have found any source code for using multi-variate features in TPA-LSTM code.

Hi~ Have you finally solved the problem of multivariate forecasting?

jingw2 commented 3 years ago

image

MikhailovichGlushkov commented 2 years ago

TPA-LSTM 是应该考虑多个特征的，请问就这个项目而言需要在哪个地方进行改进

EdoPriyo13 commented 8 months ago

@verystrongjoe Hello! Are you running this program in a windows or linux environment? If it works on Windows 10, could you send me a copy of the code? I have a lot of errors here. My email is edopriyoutomo32@gmail.com Thank You!