zhengruifeng commented on code in PR #50106:
URL: https://github.com/apache/spark/pull/50106#discussion_r1982392072
##########
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala:
##########
@@ -1041,6 +1041,24 @@ class LogisticRegression @Since("1.2.0") (
(solution, arrayBuilder.result())
}
+ private[spark] override def estimateModelSize(dataset: Dataset[_]): Long = {
+ // TODO: get numClasses and numFeatures together from dataset
+ val numClasses = DatasetUtils.getNumClasses(dataset, $(labelCol))
+ val numFeatures = DatasetUtils.getNumFeatures(dataset, $(featuresCol))
+
+ var size = this.estimateMatadataSize
+ if (checkMultinomial(numClasses)) {
+ size += Matrices.getDenseSize(numFeatures, numClasses) //
coefficientMatrix
+ size += Vectors.getDenseSize(numClasses) // interceptVector
+ } else {
+ size += Matrices.getDenseSize(numFeatures, 1) // coefficientMatrix
+ size += Vectors.getDenseSize(1) // interceptVector
+ }
+ size += java.lang.Integer.BYTES // numClasses
+ size += 1 // isMultinomial
Review Comment:
i am fine if we only focus on larger ones like vector/matrix/array
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
