Github user attilapiros commented on a diff in the pull request:
https://github.com/apache/spark/pull/20686#discussion_r171764043
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/feature/RFormulaSuite.scala ---
@@ -313,13 +306,14 @@ class RFormulaSuite extends MLTest with
DefaultReadWriteTest {
Seq(("male", "foo", 4), ("female", "bar", 4), ("female", "bar", 5),
("male", "baz", 5))
.toDF("id", "a", "b")
val model = formula.fit(original)
+ val attr = NominalAttribute.defaultAttr
val expected = Seq(
("male", "foo", 4, Vectors.dense(0.0, 1.0, 4.0), 1.0),
("female", "bar", 4, Vectors.dense(1.0, 0.0, 4.0), 0.0),
("female", "bar", 5, Vectors.dense(1.0, 0.0, 5.0), 0.0),
("male", "baz", 5, Vectors.dense(0.0, 0.0, 5.0), 1.0)
).toDF("id", "a", "b", "features", "label")
- // assert(result.schema.toString == resultSchema.toString)
+ .select($"id", $"a", $"b", $"features", $"label".as("label",
attr.toMetadata()))
--- End diff --
It was at the level of val +2 extra spaces. Should I indent the dots to the
same row?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
