sparksql agg用法

sparkSql agg用法，样例代码

 def main(args: Array[String]): Unit = {
    val spark = SparkSession.builder().appName("JoinCoreApiTest").master("local").getOrCreate()
    val sc = spark.sparkContext

    sc.setLogLevel("ERROR")

    import spark.implicits._

    val caseIdr = sc.makeRDD(Array(("1", "a1"),("1", "a4"), ("2", "a2"), ("3", "a3"))).toDF("caseId", "r")
    caseIdr.show(false)

    val trans = sc.makeRDD(Array(("a1","x1"),("a2","x2"),("a3","x3"),("a4", "x4"))).toDF("r","x")
    trans.show(false)

    val joinRdd = caseIdr.join(trans,Seq("r"),"inner")
      joinRdd.show(false)

    import org.apache.spark.sql.functions._

    val value = joinRdd.groupBy("caseId").agg(count("r").as("cou"),collect_list("r").as("rs"),collect_list("x").as("xs"))
      .show(false)


  }

运行结果展示：

+------+---+
|caseId|r  |
+------+---+
|1     |a1 |
|1     |a4 |
|2     |a2 |
|3     |a3 |
+------+---+

+---+---+
|r  |x  |
+---+---+
|a1 |x1 |
|a2 |x2 |
|a3 |x3 |
|a4 |x4 |
+---+---+

+---+------+---+
|r  |caseId|x  |
+---+------+---+
|a3 |3     |x3 |
|a4 |1     |x4 |
|a2 |2     |x2 |
|a1 |1     |x1 |
+---+------+---+

+------+---+--------+--------+
|caseId|cou|rs      |xs      |
+------+---+--------+--------+
|3     |1  |[a3]    |[x3]    |
|1     |2  |[a4, a1]|[x4, x1]|
|2     |1  |[a2]    |[x2]    |
+------+---+--------+--------+