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.

Sign up for GitHub

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

Jump to bottom

Updating docs, fixing CSDI&LOCF&MRNN, and adding the strategy to save all models #284

Merged
merged 11 commits into from
Dec 25, 2023
Merged

Updating docs, fixing CSDI&LOCF&MRNN, and adding the strategy to save all models #284

merged 11 commits into from
Dec 25, 2023

Conversation

WenjieDu
Copy link
Owner

@WenjieDu WenjieDu commented Dec 25, 2023 •
edited

What does this PR do?

  1. updating docs;
  2. GP-VAE should return multiple sampling results #276;
  3. fixing CSDI Fixing CSDI, adding placeholder for epoch num in logging #280;
  4. fixing LOCF Infinite loop in LOCF when whole feature missing #281;
  5. fixing some issues in MRNN;
  6. making PyPOTS able to save all models during training;

Before submitting

  • This PR is made to fix a typo or improve the docs (you can dismiss the other checks if this is the case).
  • Was this discussed/approved via a GitHub issue? Please add a link to it if that's the case.
  • I have commented my code, particularly in hard-to-understand areas.
  • I have written necessary tests and already run them locally.

@WenjieDu
docs: update docs and some text in code;
5dc5ba3
@WenjieDu
Adding _check_inputs() for error calculation functions (#279)
9c5c380 
* feat: add _check_inputs() for all error metric calculation functions;

* fix: use corresponding lib to detect NaN, otherwise loss calculation during torch training will raise error...

RuntimeError: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead.

* fix: don't check shapes for CRPS calc funcs;
@WenjieDu
fix: error indicating_mask in DatasetForBRITS;
508edb8
@WenjieDu
Fixing CSDI, adding placeholder for epoch num in logging (#280)
4e3fbb0 
* feat: add assertion for CSDI and GP-VAE to ensure n_sampling_times>0 in predict();

* fix: val_set for CSDI should return X_ori for model validation;

* refactor: add placeholder for epoch number in logging;
@WenjieDu
Fixing the infinite loop in LOCF (#282)
1ff5b7e 
* fix: apply zero filling if missing values still exist after applying first_step_imputation;

* refactor: adjust some logging info;

* fix: set a default value for first_step_imputation in _locf();
@WenjieDu
feat: create the parent dir for saving data in pickle_dump();
59421af
@WenjieDu
refactor: print epoch number start from 1 in training log;
a798baf
@WenjieDu
fix: remove unused module;
50a0a99
@WenjieDu
feat: enable to save every model after each epoch training;
83132df
@WenjieDu
fix: apply additional activation functions to FCN_Regression module a…
04d67a0 
…nd correct the reconstruction loss on its output;
@WenjieDu
Update docs (#285)
5ba8ac3 
* feat: let pytest print detail logs during testing;

* docs: update the docs;

* docs: add doc text for customized_loss_func in SAITS;
@WenjieDu WenjieDu merged commit bae6dd4 into main Dec 25, 2023
4 of 10 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
1 participant
@WenjieDu