Repository navigation
Register generic nested prediction scorer - #676
Open
DhavalRepo18 wants to merge 1 commit into
Open
DhavalRepo18 wants to merge 1 commit into
DhavalRepo18 wants to merge 1 commit into
Conversation
Signed-off-by: Dhaval Patel <pateldha@us.ibm.com>
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Register
source_panel_continuous_v1for nested per-episode predictions with integer/string classes or numeric targets. All verifier labels, target names, normalization scales and acceptance limits come from private scenario inputs; none are bundled with the scorer.The continuous
grade()helper reports fixed-class macro-F1 and complete-row accuracy for categorical outputs, or per-target RMSE/MAE and normalized error for numeric outputs. Extra submission fields are ignored; no sensor/program/model matching is performed. Malformed answers score zero; invalid verifier configuration or gold raises a harness error.AOB requires a boolean pass field. The native entry point therefore requires an explicit
acceptanceobject in scenario metadata:metricandthreshold. Supported metrics aremean_component_macro_f1(inclusive lower bound),mean_normalized_rmse(inclusive upper bound), or single-targetrmse(inclusive upper bound). Missing acceptance policy raises a harness error instead of inventing an exact-match pass rule. Uncalibrated research can usegrade()directly and receives no pass decision.Validation: 243 evaluation tests passed, including 48 new synthetic tests. Fixtures use only fictional identifiers/class names, invented large numeric codes/values and artificial scales/limits. No private scenario IDs, asset identifiers, timestamps, ground truth, reference scales or adopted cutoffs are included. Changes are limited to scorer code, registration and synthetic tests.