-
Notifications
You must be signed in to change notification settings - Fork 46
Dev/multitask - STAMP extended for regression and survival analysis (v2.4 update) #132
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
Conversation
|
I found that regression and survival heatmaps are meaningless without determining gradient range. |
|
I’ve added both slide-level and patient-level support for regression and survival tasks (only mlp can be trained). Just a few more steps are needed to add tests. |
s1787956
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I am very happy, great job Duc! I think we can merge tomorrow.
| # Sample count for training | ||
| log_total_class_summary(patient_to_data, categories) | ||
|
|
||
| # Stratified split |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The stratified split is also needed for survival, the variable for the StratifiedKFold should be the event marker. I did not see it in the code, make sure that the stratification variable for survival is set
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for pointing it out. I have just added it and also strengthened event labels handling.
|
Can we merge it today? I will release it as 2.4 :) |
Stamp v2.4