Spark聚合函数agg

agg的作用

• 正常情况下，当我们使用了聚合算子，后面就无法在使用其他聚合算子
• 而agg可以使我们同时获取多个聚合运算结果

示例

object InnerFunctionDemo {

  def main(args: Array[String]): Unit = {
    val spark = SparkSession.builder().master("local[*]").appName("function").getOrCreate()
    import spark.implicits._
    val sc = spark.sparkContext
    val stuDF: DataFrame = Seq(
      Student(1001, "zhangsan", "F", 20),
      Student(1002, "lisi", "M", 16),
      Student(1003, "wangwu", "M", 21),
      Student(1004, "zhaoliu", "F", 21),
      Student(1005, "zhouqi", "M", 22),
      Student(1006, "qianba", "M", 19),
      Student(1007, "liuliu", "F", 23)
    ).toDF()

    import org.apache.spark.sql.functions._
    //同样也可以这样写
    //stuDF.groupBy("gender").agg(max("age"),min("age"),avg("age"),count("id")).show()
    stuDF.groupBy("gender").agg("age"->"max","age"->"min","age"->"avg","id"->"count").show()
    /*
    +------+--------+--------+------------------+---------+
	|gender|max(age)|min(age)|          avg(age)|count(id)|
	+------+--------+--------+------------------+---------+
	|     F|      23|      20|21.333333333333332|        3|
	|     M|      22|      16|              19.5|        4|
	+------+--------+--------+------------------+---------+
    */
    }
}