imatiach-msft commented on a change in pull request #21632: [SPARK-19591][ML][MLlib] Add sample weights to decision trees URL: https://github.com/apache/spark/pull/21632#discussion_r249638142
########## File path: mllib/src/test/scala/org/apache/spark/ml/tree/impl/TreeTests.scala ########## @@ -18,37 +18,46 @@ package org.apache.spark.ml.tree.impl import scala.collection.JavaConverters._ +import scala.util.Random import org.apache.spark.{SparkContext, SparkFunSuite} import org.apache.spark.api.java.JavaRDD import org.apache.spark.ml.attribute.{AttributeGroup, NominalAttribute, NumericAttribute} -import org.apache.spark.ml.feature.LabeledPoint +import org.apache.spark.ml.feature.{Instance, LabeledPoint} import org.apache.spark.ml.linalg.Vectors import org.apache.spark.ml.tree._ +import org.apache.spark.mllib.util.TestingUtils._ import org.apache.spark.rdd.RDD import org.apache.spark.sql.{DataFrame, SparkSession} private[ml] object TreeTests extends SparkFunSuite { /** * Convert the given data to a DataFrame, and set the features and label metadata. + * * @param data Dataset. Categorical features and labels must already have 0-based indices. * This must be non-empty. * @param categoricalFeatures Map: categorical feature index to number of distinct values * @param numClasses Number of classes label can take. If 0, mark as continuous. * @return DataFrame with metadata */ def setMetadata( - data: RDD[LabeledPoint], + data: RDD[_], Review comment: oh ok, thanks ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org