zhengruifeng opened a new pull request, #58277:
URL: https://github.com/apache/spark/pull/58277

   ### What changes were proposed in this pull request?
   
   This PR fixes the prediction column alias in `GBTRegressionModel.transform` 
to use
   `predictionCol` and its output metadata. It also adds a regression test that 
verifies the
   transformed prediction metadata matches `transformSchema`.
   
   ### Why are the changes needed?
   
   The prediction expression was aliased with `featuresCol` and the feature 
column metadata.
   Although `withColumns` assigned the final prediction column name, its outer 
alias inherited the
   feature metadata from the inner alias. As a result, the transformed 
prediction column could carry
   vector feature metadata instead of its expected numeric prediction metadata.
   
   ### Does this PR introduce _any_ user-facing change?
   
   Yes. `GBTRegressionModel.transform` now attaches the correct numeric 
metadata to the prediction
   column. Prediction values, data types, and column names are unchanged.
   
   ### How was this patch tested?
   
   Added a regression test and ran:
   
   `./build/sbt 'mllib/testOnly 
org.apache.spark.ml.regression.GBTRegressorSuite'`
   
   ### Was this patch authored or co-authored using generative AI tooling?
   
   Generated-by: OpenAI Codex (GPT-5)
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to