Conversation
…ermodules e tolto dal push gitmodules,IGNORARE COMMIT PRECEDENTE
…ro che il test non e' valido'
ErTucano
left a comment
ErTucano
left a comment
There was a problem hiding this comment.
Apart for the comment I added it looks all good to me. I'm not approving because I'm waiting for feedback from Giulia about the changes in .gitignore and .gitmodules.
|
|
||
| train_dataset = timeseries_dataset_from_array( | ||
| data=data[:train_size], | ||
| targets=data[input_sequence_length:train_size + input_sequence_length, 0], |
There was a problem hiding this comment.
Are you sure input_sequence_length:train_size + input_sequence_length stays in the bounds of the data DataFrame?
… a fare il test non lineare
There was a problem hiding this comment.
For when you do the granger_analysis in granger.ipynb can you modify the function so that it doesn't print the correlation between the same tickers (like SIRI and SIRI or CTSH and CTSH).
About the ipynb file you have recently added can you also put all the import in a single cell? I noticed you repeated them every time. It shouldn't be necessary; in case someone where to copy the code on vscode it would look bad having multiple imports all around.
There are also some errors in the code, as you see from the exceptions (the red text in the output), if you can please resolve it.
Can you answer me about the question I asked on the previous comment on models/lstm.py?
As a refernce look at the ipynb files uploaded by Riccardo, they are well organised and tidy.
3 participants
No description provided.