zhengruifeng commented on a change in pull request #25802: [SPARK-29095][ML]
add extractInstances
URL: https://github.com/apache/spark/pull/25802#discussion_r327031113
##########
File path: mllib/src/main/scala/org/apache/spark/ml/Predictor.scala
##########
@@ -62,6 +62,40 @@ private[ml] trait PredictorParams extends Params
}
SchemaUtils.appendColumn(schema, $(predictionCol), DoubleType)
}
+
+ /**
+ * Extract [[labelCol]], weightCol(if any) and [[featuresCol]] from the
given dataset,
+ * and put it in an RDD with strong types.
+ */
+ protected def extractInstances(dataset: Dataset[_]): RDD[Instance] = {
+ val w = this match {
+ case p: HasWeightCol =>
+ if (isDefined(p.weightCol) && $(p.weightCol).nonEmpty) {
+ col($(p.weightCol)).cast(DoubleType)
+ } else {
+ lit(1.0)
+ }
+ case _ => lit(1.0)
Review comment:
OK, I will remove this line. Impls that do not support weighting call this
method should fail.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
