Github user smurakozi commented on a diff in the pull request:
https://github.com/apache/spark/pull/20362#discussion_r165308129
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala ---
@@ -628,18 +635,24 @@ class ALSSuite
}
withClue("transform should fail when ids exceed integer range. ") {
val model = als.fit(df)
- assert(intercept[SparkException] {
- model.transform(df.select(df("user_big").as("user"),
df("item"))).first
- }.getMessage.contains(msg))
- assert(intercept[SparkException] {
- model.transform(df.select(df("user_small").as("user"),
df("item"))).first
- }.getMessage.contains(msg))
- assert(intercept[SparkException] {
- model.transform(df.select(df("item_big").as("item"),
df("user"))).first
- }.getMessage.contains(msg))
- assert(intercept[SparkException] {
- model.transform(df.select(df("item_small").as("item"),
df("user"))).first
- }.getMessage.contains(msg))
+ def testTransformIdExceedsIntRange[A : Encoder](dataFrame:
DataFrame): Unit = {
+ assert(intercept[SparkException] {
+ model.transform(dataFrame).first
+ }.getMessage.contains(msg))
+ assert(intercept[StreamingQueryException] {
+ testTransformer[A](dataFrame, model, "prediction") {
+ case _ =>
--- End diff --
No need for a partial function here, you can simplify it to `{ _ => }`.
I would also add a small comment to make it explicit that we intentionally
do not check anything.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
