Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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
AUC chart #2171
base: main
Are you sure you want to change the base?
AUC chart #2171
Changes from 15 commits
6fb178f
ff63c42
62be4c6
d30c5d4
a280519
861bde5
49537d1
002fe4d
84ef9cf
925d532
f283823
6b4fc7d
6baeba2
03e15b4
7b0d2cc
a05ebc3
41e42cd
17f3682
f197aec
2a3ca4c
File filter
Filter by extension
Conversations
Jump to
There are no files selected for viewing
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.
If you add zeros after the comma to get all the points closer together (0.032, 0.033, 0.034, for example), then it will not do it right, will it?
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.
That's not quite right, is it?
For example, if I have two points within a tick (let's say at 0.001 and 0.004) then none of my thresholds covers the case where they are on opposite sides of the decision boundary. This could very well be the best FPR/TPR combination....
So I would order the values first, and then always take thresholds as the middle between two values, e.g.,
values: [1,5,4,2,3]
ordered: [1,2,3,4,5]
thresholds: [-inf, 1.5, 2.5, 3.5, 4.5, inf]
so total of 6 points for ROC, but then you still need to calculate the convex hull of those points if I'm not mistaken. How are you avoiding hitting points below the convex hull btw?
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.
This should only run for binary classification, right? So we probably need a check somewhere to disable the component otherwise.
For multiclass one could do one vs all but I don't know if anyone wants that.
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.
in the studio, there's an auc chart for multiclass so i assumed we'd want that (binarizeData is supposed to handle this case), but i'll discuss with Minsoo tomorrow
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.
That's probably 1 vs all, so that makes sense.
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.
This is fine, but we'll probably need a little explainer somewhere. Especially because it's an acronym
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.
will discuss with Minsoo!