-
Notifications
You must be signed in to change notification settings - Fork 1.7k
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
Add PR curves and F1 score to WIT #2264
Conversation
@tolga-b please review |
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.
Looks good to me.
@@ -1808,6 +1840,11 @@ <h2>Show similarity to selected datapoint</h2> | |||
<div class="perf-table-num-entry">[[getAccuracyModelIndex(inferenceStats_, featureValueThreshold.threshold, index, featureValueThreshold)]]</div> | |||
</template> | |||
</div> | |||
<div class="perf-table-f1 perf-table-clickable" on-tap="togglePerfRow"> |
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.
No action required (since we really don't honor this): a div that is clickable is not really accessible. At the very least, we should put tab-index="-1" (and of course role=button)
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.
ack
if (Object.keys(confCounts).length == 0) { | ||
return 0; | ||
} | ||
if (confCounts['Yes']['Yes'] == 0) { |
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.
might be more readable (or more maintainable) to assign this to a variable.
const truePositive = confCoujnts['Yes']['Yes'];
...
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.
done
Per user requests, adding PR curves and F1 score to performance tab of WIT for binary classification models.
Ran binary classification demos (single and multimodel) to visualize change and ensure correctness.