Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/21493#discussion_r192910578
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/clustering/PowerIterationClusteringSuite.scala
---
@@ -222,17 +167,13 @@ object PowerIterationClusteringSuite {
val n = n1 + n2
val points = genCircle(r1, n1) ++ genCircle(r2, n2)
- val rows = for (i <- 1 until n) yield {
- val neighbors = for (j <- 0 until i) yield {
- j.toLong
+ val rows = (for (i <- 1 until n) yield {
+ for (j <- 0 until i) yield {
+ (i.toLong, j.toLong, sim(points(i), points(j)))
}
- val similarities = for (j <- 0 until i) yield {
- sim(points(i), points(j))
- }
- (i.toLong, neighbors.toArray, similarities.toArray)
- }
+ }).flatMap(_.iterator)
- spark.createDataFrame(rows).toDF("id", "neighbors", "similarities")
+ spark.createDataFrame(rows).toDF("src", "dst", "weight")
}
}
--- End diff --
Should test default weight.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
