Apache spark Spark 1.6中的数据集
我正在评估将现有RDD代码替换为Dataset。对于我的一个用例，我无法将数据集映射到另一个用例类 这就是我要做的Apache spark Spark 1.6中的数据集,apache-spark,apache-spark-sql,spark-dataframe,apache-spark-dataset,Apache Spark,Apache Spark Sql,Spark Dataframe,Apache Spark Dataset,我正在评估将现有RDD代码替换为Dataset。对于我的一个用例，我无法将数据集映射到另一个用例类 这就是我要做的 case class MyMap(map: Map[String, String]) case class V1(a: String, b: String){ def toMyMap: MyMap = { MyMap(Map(a->b)) } def toStr: String = { a } } object MyApp extends
case class MyMap(map: Map[String, String])
case class V1(a: String, b: String){
def toMyMap: MyMap = {
MyMap(Map(a->b))
}
def toStr: String = {
a
}
}
object MyApp extends App {
//Get handle to sqlContext and other useful stuff here.
val df1 = sqlContext.createDataset(Seq(V1("2015-05-01", "data1"), V1("2015-05-01", "data2"))).toDF()
df1.as[V1].map(_.toMyMap).show() //Errors out. Added the exception below.
df1.as[V1].map(_.toStr).show() //Works fine.
}