feat: wire GenAI feature-engineering into AutoML.fit#10
Merged
Conversation
Close the integrity gap where genai.enabled did not change AutoML: the FeatureEngineerPort was a registered bean the facade never consumed. Now AutoML (and AutoML.from_context) resolves a FeatureEngineerPort and, when present, runs propose->execute->measure->gate before model selection, trains on the engineered features, and threads the accepted/rejected audit into result.extras['feature_engineering']. Classical-first stays the default (no engineer -> AutoML unchanged). LLM-free TDD on real breast_cancer data; docs note added.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Increment 2 (integrity gaps). Closes the functional gap where
genai.enabled=truedid not changeAutoML—GenAIFeatureEngineerwas a registered bean the facade never consumed.Change
AutoML(andAutoML.from_context) now resolves aFeatureEngineerPort. When present,fit()runs propose → execute → measure → gate before model selection, trains/refits on the engineered features, and threads the accepted/rejected audit intoresult.extras["feature_engineering"].AutoMLbehaviour is unchanged.Tests (real data, LLM-free)
breast_cancer+ aStaticFeatureProposerwith a permissive gate: the engineered column appears in the winner'sfeature_namesand in the audit trail.feature_engineeringextra and the engineered column is absent.Local gates green: ruff check, ruff format, pyright (0), affected suite (23 passed).
mkdocs build --strictclean. Docs note added togenai-features.md.