Github user yogeshg commented on a diff in the pull request:
https://github.com/apache/spark/pull/20829#discussion_r176220684
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/feature/VectorAssemblerSuite.scala ---
@@ -37,24 +37,26 @@ class VectorAssemblerSuite
test("assemble") {
import org.apache.spark.ml.feature.VectorAssembler.assemble
- assert(assemble(0.0) === Vectors.sparse(1, Array.empty, Array.empty))
- assert(assemble(0.0, 1.0) === Vectors.sparse(2, Array(1), Array(1.0)))
+ assert(assemble(Seq(1), true)(0.0) === Vectors.sparse(1, Array.empty,
Array.empty))
+ assert(assemble(Seq(1, 1), true)(0.0, 1.0) === Vectors.sparse(2,
Array(1), Array(1.0)))
val dv = Vectors.dense(2.0, 0.0)
- assert(assemble(0.0, dv, 1.0) === Vectors.sparse(4, Array(1, 3),
Array(2.0, 1.0)))
+ assert(assemble(Seq(1, 2, 1), true)(0.0, dv, 1.0) ===
+ Vectors.sparse(4, Array(1, 3), Array(2.0, 1.0)))
val sv = Vectors.sparse(2, Array(0, 1), Array(3.0, 4.0))
- assert(assemble(0.0, dv, 1.0, sv) ===
+ assert(assemble(Seq(1, 2, 1, 2), true)(0.0, dv, 1.0, sv) ===
Vectors.sparse(6, Array(1, 3, 4, 5), Array(2.0, 1.0, 3.0, 4.0)))
- for (v <- Seq(1, "a", null)) {
- intercept[SparkException](assemble(v))
- intercept[SparkException](assemble(1.0, v))
+ for (v <- Seq(1, "a")) {
+ intercept[SparkException](assemble(Seq(1), true)(v))
+ intercept[SparkException](assemble(Seq(1, 1), true)(1.0, v))
}
}
test("assemble should compress vectors") {
import org.apache.spark.ml.feature.VectorAssembler.assemble
- val v1 = assemble(0.0, 0.0, 0.0, Vectors.dense(4.0))
+ val v1 = assemble(Seq(1, 1, 1, 4), true)(0.0, 0.0, 0.0,
Vectors.dense(4.0))
--- End diff --
that's a typo, Thanks for pointing it out! that number is not used in case
we do not have nulls, which is why the test passes
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
