[
https://issues.apache.org/jira/browse/SPARK-17163?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15437531#comment-15437531
]
DB Tsai commented on SPARK-17163:
---------------------------------
Why do we need `_intercept`? Also, for intercept, we may need to do the
following so the MLOR and BLOR have the same model format, and thus only single
implementation of score is required.
{code}
def intercept: Double = {
if (isMultinomial) {
throw new Exception
}
intercepts(1) - intercepts(0)
}
def coefficients: Vector = if (!isMultinomial) {
val temp = coefficientMatrix(1) - coefficientMatrix(0)
Vectors.dense()
} else {
throw new Exception
}
{code}
> Merge MLOR into a single LOR interface
> --------------------------------------
>
> Key: SPARK-17163
> URL: https://issues.apache.org/jira/browse/SPARK-17163
> Project: Spark
> Issue Type: Sub-task
> Components: ML, MLlib
> Reporter: Seth Hendrickson
>
> Before the 2.1 release, we should finalize the API for logistic regression.
> After SPARK-7159, we have both LogisticRegression and
> MultinomialLogisticRegression models. This may be confusing to users and, is
> a bit superfluous since MLOR can do basically all of what BLOR does. We
> should decide if it needs to be changed and implement those changes before 2.1
> *Update*: Seems we have decided to merge the two estimators. I changed the
> title to reflect that.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
