Skip to content
New issue

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

original forms of data issue #1

Open
Liu-200106 opened this issue Jun 17, 2024 · 0 comments
Open

original forms of data issue #1

Liu-200106 opened this issue Jun 17, 2024 · 0 comments

Comments

@Liu-200106
Copy link

Liu-200106 commented Jun 17, 2024

I use 32 columns of dummy variable to indicate industry, and concat with 10 factors I've got from the model. I use SecuCode and TradingDay as multiindex.

However during the training it keeps erroring like this:
in calc_factor_ret
cap_w = stock_cap.values @ X[:, slc]
~~~~~~~~~~~~~~~~~^~~~~~~~~~~
ValueError: matmul: Input operand 1 has a mismatch in its core dimension 0, with gufunc signature (n?,k),(k,m?)->(n?,m?) (size 3461 is different from 1)

If i fix this by adding a .T to stock_cap, there will still be other errors. I guess it's because the forms of data we use are different. Could you please share me with your data's form?

@Liu-200106 Liu-200106 changed the title torch.inverse Error: Singular Matrix during Training original forms of data issue Jun 21, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant