Repository navigation
Register metadata-driven batch classification scorer - #675
Open
DhavalRepo18 wants to merge 2 commits into
Open
DhavalRepo18 wants to merge 2 commits into
DhavalRepo18 wants to merge 2 commits into
Conversation
Signed-off-by: Dhaval Patel <pateldha@us.ibm.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
batch_classification_macro_f1_v1so native evaluation can score a batch of categorical episode predictions usingallowed_codesandmacro_f1_thresholdfrom private scenario metadata.The checker requires exact episode coverage and integer class codes, reports continuous macro-F1 over all configured classes (zero division gives zero), and passes at the inclusive metadata cutoff. Duplicate JSON keys and malformed predictions fail. Invalid gold or verifier configuration raises a harness error.
Scoring uses only predictions. Additional submission fields are ignored; there are no sensor/feature matching, sensor-budget, program-presence, code-execution or model-matching checks.
Validation: 230 evaluation tests passed, including 35 batch-classification tests. All new fixtures are invented: large artificial class codes, fictional identifiers and artificial thresholds. No private scenario data, ground-truth values, labels or cutoffs are included. Only scorer code, registration and synthetic tests are changed.