Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/21183#discussion_r185049467
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAOptimizer.scala ---
@@ -605,14 +609,16 @@ private[clustering] object OnlineLDAOptimizer {
expElogbeta: BDM[Double],
alpha: breeze.linalg.Vector[Double],
gammaShape: Double,
- k: Int): (BDV[Double], BDM[Double], List[Int]) = {
+ k: Int,
+ seed: Long): (BDV[Double], BDM[Double], List[Int]) = {
val (ids: List[Int], cts: Array[Double]) = termCounts match {
case v: DenseVector => ((0 until v.size).toList, v.values)
case v: SparseVector => (v.indices.toList, v.values)
}
// Initialize the variational distribution q(theta|gamma) for the
mini-batch
+ val randBasis = new RandBasis(new
org.apache.commons.math3.random.MersenneTwister(seed))
val gammad: BDV[Double] =
- new Gamma(gammaShape, 1.0 / gammaShape).samplesVector(k)
// K
+ new Gamma(gammaShape, 1.0 / gammaShape)(randBasis).samplesVector(k)
// K
--- End diff --
nit: Note that the original spacing with the comment was intentional to
match lines below.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
