Skip to content

Conversation

@loomlike
Copy link
Collaborator

@loomlike loomlike commented Jan 9, 2023

Description

I found there's a bug in the model result graph at the Fraud Detection sample notebook
Fixes are:

  • to use ML model output probability instead of the prediction class label for precision/recall graph
  • change the chart label to be the correct ML model name

How was this PR tested?

Does this PR introduce any user-facing changes?

  • No. You can skip the rest of this section.
  • Yes. Make sure to clarify your proposed changes.

Signed-off-by: Jun Ki Min <[email protected]>
Signed-off-by: Jun Ki Min <[email protected]>
@loomlike loomlike added the safe to test Tag to execute build pipeline for a PR from forked repo label Jan 9, 2023
xiaoyongzhu
xiaoyongzhu previously approved these changes Jan 10, 2023
blrchen
blrchen previously approved these changes Jan 10, 2023
@loomlike loomlike dismissed stale reviews from blrchen and xiaoyongzhu via 9d322da January 10, 2023 16:52
@blrchen blrchen merged commit a923a9d into feathr-ai:main Jan 11, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

safe to test Tag to execute build pipeline for a PR from forked repo

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants