-
Notifications
You must be signed in to change notification settings - Fork 12
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
Integrate tgcca #76
base: main
Are you sure you want to change the base?
Integrate tgcca #76
Conversation
* Instead of dividing by std which might be null, we divide by the max between std and machine precision for floats * Since some variables may be null, we always divide by the frobenius norm and not by the number of variables once scaled
Since we do not remove constant variables anymore we do no longer need a specific strategy for sampling bootstrap samples.
I chose to scale arrays by unfolding them, scaling the resulting matrices and fold them back. It may not be the adapted way to scale a tensor. It will be interesting to have a string argument for the scale parameter to allow choosing the best strategy.
comp_orth = TRUE yields orthogonal canonical components but comp_orth = FALSE does not lead yet to orthogonal canonical vectors
* Important change in this version: tau and sparsity are converted to matrices directly in select_analysis
Codecov ReportAttention:
❗ Your organization needs to install the Codecov GitHub app to enable full functionality. Additional details and impacted files@@ Coverage Diff @@
## main #76 +/- ##
==========================================
- Coverage 94.39% 90.56% -3.83%
==========================================
Files 83 82 -1
Lines 3319 3212 -107
==========================================
- Hits 3133 2909 -224
- Misses 186 303 +117 ☔ View full report in Codecov by Sentry. |
No description provided.