SparkSQL自定义聚类函数

数据：

user.json
{"id":1,"name":"zhangsan","age":10}
{"id":2,"name":"lisi","age":30}
{"id":3,"name":"wangwu","age":20}
{"id":4,"name":"liuliu","age":40}

需求：统计以上文件的平均年龄

工具：idea

语言：Scala

代码：

package com.test

import org.apache.spark.SparkConf
import org.apache.spark.sql.{Row, SparkSession}
import org.apache.spark.sql.expressions.{MutableAggregationBuffer, UserDefinedAggregateFunction}
import org.apache.spark.sql.types.{DataType, DoubleType, LongType, StructType}

object SparkUDAF {
  def main(args: Array[String]): Unit = {
    val conf  = new SparkConf().setAppName("SparkUDAF").setMaster("local[*]")
    val sparkSession = SparkSession.builder().config(conf).getOrCreate()
    // 创建dataFrame
    val dataFrame = sparkSession.r