Github user yanboliang commented on a diff in the pull request:

    https://github.com/apache/spark/pull/9311#discussion_r43724499
  
    --- Diff: 
mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.scala 
---
    @@ -227,10 +227,10 @@ class AFTSurvivalRegression @Since("1.6.0") 
(@Since("1.6.0") override val uid: S
     
         if (handlePersistence) instances.unpersist()
     
    -    val coefficients = Vectors.dense(weights.slice(2, weights.length))
    -    val intercept = weights(1)
    -    val scale = math.exp(weights(0))
    -    val model = new AFTSurvivalRegressionModel(uid, coefficients, 
intercept, scale)
    +    val regressionCoefficients = Vectors.dense(coefficients.slice(2, 
coefficients.length))
    --- End diff --
    
    Sorry for late attention. I think we should not rename ```coefficients``` 
to ```regressionCoefficients``` and ```weights``` to ```coefficients```, 
because the original ```coefficients``` is correctly used and should not 
renamed.
    When I was writing ```AFTSurvivalRegression```, I have noticed the misusage 
of ```weights``` and use the right name ```coefficients```. But the 
```weights``` is misused and should be renamed, because that it's different 
from other ```weights```, it include three parts : log(sigma), intercept and 
coefficients. I have send #9431 to rename ```weights``` to ```parameters``` or 
other names which will not bring confusion, it's not a public variable. And 
rename ```regressionCoefficients``` back to ```coefficients```.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

Reply via email to