Github user srowen commented on a diff in the pull request:
https://github.com/apache/spark/pull/20632#discussion_r168956209
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/tree/impl/RandomForestSuite.scala ---
@@ -640,4 +740,55 @@ private object RandomForestSuite {
val (indices, values) = map.toSeq.sortBy(_._1).unzip
Vectors.sparse(size, indices.toArray, values.toArray)
}
+
+ /** Generate a label. */
+ private def generateLabel(rnd: Random, numClasses: Int): Double = {
+ rnd.nextInt(numClasses)
+ }
+
+ /** Generate a numeric value in the range [numericMin, numericMax]. */
+ private def generateNumericValue(rnd: Random, numericMin: Double,
numericMax: Double) : Double = {
+ rnd.nextDouble() * (numericMax- numericMin) + numericMin
+ }
+
+ /** Generate a binary value. */
+ private def generateBinaryValue(rnd: Random) : Double = if
(rnd.nextBoolean()) 1 else 0
+
+ /** Generate an array of binary values of length numBinary. */
+ private def generateBinaryArray(rnd: Random, numBinary: Int):
Array[Double] = {
+ Range.apply(0, numBinary).map(_ => generateBinaryValue(rnd)).toArray
--- End diff --
`Array.fill(numBinary)(generateBinaryValue(rnd))` is simpler
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
