Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/20686#discussion_r173554643
--- Diff: mllib/src/test/scala/org/apache/spark/ml/feature/NGramSuite.scala
---
@@ -19,61 +19,59 @@ package org.apache.spark.ml.feature
import scala.beans.BeanInfo
-import org.apache.spark.SparkFunSuite
-import org.apache.spark.ml.util.DefaultReadWriteTest
-import org.apache.spark.mllib.util.MLlibTestSparkContext
-import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.ml.util.{DefaultReadWriteTest, MLTest}
+import org.apache.spark.sql.{DataFrame, Row}
+
@BeanInfo
case class NGramTestData(inputTokens: Array[String], wantedNGrams:
Array[String])
-class NGramSuite extends SparkFunSuite with MLlibTestSparkContext with
DefaultReadWriteTest {
+class NGramSuite extends MLTest with DefaultReadWriteTest {
- import org.apache.spark.ml.feature.NGramSuite._
import testImplicits._
test("default behavior yields bigram features") {
val nGram = new NGram()
.setInputCol("inputTokens")
.setOutputCol("nGrams")
- val dataset = Seq(NGramTestData(
+ val dataFrame = Seq(NGramTestData(
--- End diff --
These kinds of changes are not necessary and make the PR a lot longer.
Would you mind reverting them?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
