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

Typos and other Errata #88

Open
casras111 opened this issue Jan 13, 2021 · 6 comments
Open

Typos and other Errata #88

casras111 opened this issue Jan 13, 2021 · 6 comments

Comments

@casras111
Copy link

From reading the book below what seem like typos:

In chapter 4 repeated passage
image

In chapter 5 calculations of std and variance mixed:

chptr5_2
chprt5_1

@stefan-jansen stefan-jansen changed the title book typos Typos and other Errata Jan 21, 2021
@stefan-jansen
Copy link
Owner

Thank you! I'll keep this open in the hope that others will also contribute any errors they come across so I can fix them in the next edition.

@drsxr
Copy link

drsxr commented Jun 1, 2021

On algoseek_minute_data.ipynb Section 4 Nasdaq 100 constituents, the field date_time is incorrect and should be date_timebarstart
errata1

@stefan-jansen
Copy link
Owner

stefan-jansen commented Jun 7, 2021

@drsx the issue was a missing inplace=True when renaming the index to date_time, which I have fixed.

@hxyue1
Copy link

hxyue1 commented Oct 20, 2021

Not sure if this is a typo or actually intended, but it looks like there are some inconsistencies in the TimeGAN notebook with regards to indexing for the supervisor inputs and outputs:

Screenshot from 2021-10-20 14-41-51

Screenshot from 2021-10-20 14-42-27

Screenshot from 2021-10-20 14-42-40

When training the supervisor, the mse calculation is mse(h[:, 1:, :], h_hat_supervised[:, :-1, :]), but the other two times it is mse(h[:, 1:, :], h_hat_supervised[:, 1:, :]). Is this intentional?

@dama0418
Copy link

dama0418 commented Feb 8, 2022

It looks like in the script: 08_ml4t_workflow/02_vectorized_backtest.ipynb
the conditions (">") applied after .rank for selecting the best long_signals and short_signals
must be inverted ("<=").

image

@CDLim0906
Copy link

image

sample perhaps?

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

6 participants