search

piEsposito / blitz-bayesian-deep-learning

A simple and extensible library to create Bayesian Neural Network layers on PyTorch.
GNU General Public License v3.0
916 stars 107 forks source link

stocks-blstm.ipynb #93

Open waudinio27 opened 2 years ago

waudinio27 commented 2 years ago

This program is amazing!

I am reproducing the stocks-blstm.ipynb example - as a beginner I would be interested to train and test a model with data up to now and then make predictions directly after this.

Or is there something that I got wrong and did not understand properly?

Could somebody show me how to do so? ..... I would appreciate it a lot.

Thanks a lot and keep up the good work :-D

TerenceLiu98 commented 2 years ago

You mean, you want to predict the next day's price? You can just modify the future_length = 7 to future_length = 1

waudinio27 commented 2 years ago

Thank you, Terence! I think what is actually missing is a function for the prediction after training and fitting the model. I will try to write one and make a pull request once I am done :-D

Greetings

TerenceLiu98 commented 2 years ago

@waudinio27 I think the code block No.14 (in stocks-blstm.ipynb, def pred_stock_future) is the prediction function

waudinio27 commented 2 years ago

Thank you so much Terence!