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

22.11 fb bilinear regression fit #637

Closed
wants to merge 5 commits into from

Conversation

nickshulman
Copy link
Collaborator

Need to be fixed before merging: the calibration curve graph always draws as a straight line, even though the line for "Bilinear" is supposed to be two straight lines with a turn in it, and "Linear in log space" produces a line which is curved when plotted on a linear graph.
image

Rationale

Issue 43922: Add support for "Linear in Log Space" and "Bilinear" regression fit options

Related Pull Requests

Changes

Add support for "Bilinear" and "Linear in Log Space" regression fit values.

Nicholas Shulman added 3 commits November 2, 2022 14:20
@github-actions
Copy link

github-actions bot commented Nov 5, 2022

ERROR: A pull request from 22.11_fb_bilinear_regression_fit is expected to target release22.11-SNAPSHOT, not develop

WARNING: This PR appears to have the default title generated by GitHub. Please use something more descriptive.

@labkey-jeckels
Copy link
Contributor

@nickshulman let me know if you want help on updating the plots

@labkey-jeckels
Copy link
Contributor

@nickshulman what are the next steps on this PR. Do you want us to handle anything on the LabKey side?

@nickshulman
Copy link
Collaborator Author

I think we should wait a month before committing this fix.
I have to change the implementation of the bilinear regression in Skyline 23.1. After I implement the changes in Skyline I will change this pull request so that it uses the new algorithm.
(The new algorithm puts the bend in the curve at the location which is the mean of the data points below that curve. The algorithm in this pull request uses a Nelder Mead Simplex to find the value which would result in the lowest R-squared.)

@labkey-jeckels
Copy link
Contributor

Sounds good. Thanks for the update.

@labkey-jeckels
Copy link
Contributor

@nickshulman Any updates on your schedule here? Have you had a chance to make the Skyline updates yet?

@labkey-jeckels
Copy link
Contributor

@nickshulman any updates on the timing for this? @brendanx67

@nickshulman
Copy link
Collaborator Author

@nickshulman any updates on the timing for this? @brendanx67

Probably beginning of May.
Skyline code complete is scheduled for end of April, so it will have the new bilinear curve fit algorithm by then, and I will then be able to implement that algorithm in Panorama shortly after that.

@labkey-jeckels
Copy link
Contributor

@nickshulman any updates on this? Brendan mentioned this may be at risk for 23.1.

@labkey-jeckels
Copy link
Contributor

@nickshulman is this the PR on the Skyline side that we can follow the progress and not need to nag you periodically?

ProteoWizard/pwiz#2572

@nickshulman
Copy link
Collaborator Author

@nickshulman is this the PR on the Skyline side that we can follow the progress and not need to nag you periodically?

ProteoWizard/pwiz#2572

Yes, that's the PR on the Skyline side.

@nickshulman
Copy link
Collaborator Author

Need to re-create this pull request with a different branch name targeting develop.

@labkey-jeckels
Copy link
Contributor

@nickshulman we already branched for 23.7, so you may want to use 23.7_fb_ so we can get it out before 23.11 in November.

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

Successfully merging this pull request may close these issues.

2 participants