SparkSQL编程之自定义聚合函数（强类型）

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/m0_37294838/article/details/90199348

 强类型用户自定义聚合函数：通过继承Aggregator来实现强类型自定义聚合函数，

import org.apache.spark.sql.expressions.Aggregator
import org.apache.spark.sql.Encoder
import org.apache.spark.sql.Encoders
import org.apache.spark.sql.SparkSession
// 既然是强类型，可能有case类
case class Employee(name: String, salary: Long)
case class Average(var sum: Long, var count: Long)

object MyAverage extends Aggregator[Employee, Average, Double] {
// 定义一个数据结构，保存工资总数和工资总个数，初始都为0
def zero: Average = Average(0L, 0L)
// Combine two values to produce a new value. For performance, the function may modify `buffer`
// and return it instead of constructing a new object
def reduce(buffer: Average, employee: Employee): Average = {
buffer.sum += employee.salary
buffer.count += 1
buffer
}
// 聚合不同execute的结果
def merge(b1: Average, b2: Average): Average = {
b1.sum += b2.sum
b1.count += b2.count
b1
}
// 计算输出
def finish(reduction: Average): Double = reduction.sum.toDouble / reduction.count
// 设定之间值类型的编码器，要转换成case类
// Encoders.product是进行scala元组和case类转换的编码器 
def bufferEncoder: Encoder[Average] = Encoders.product
// 设定最终输出值的编码器
def outputEncoder: Encoder[Double] = Encoders.scalaDouble
}

import spark.implicits._

val ds = spark.read.json("examples/src/main/resources/employees.json").as[Employee]
ds.show()
// +-------+------+
// |   name|salary|
// +-------+------+
// |Michael|  3000|
// |   Andy|  4500|
// | Justin|  3500|
// |  Berta|  4000|
// +-------+------+

// Convert the function to a `TypedColumn` and give it a name
val averageSalary = MyAverage.toColumn.name("average_salary")
val result = ds.select(averageSalary)
result.show()
// +--------------+
// |average_salary|
// +--------------+
// |        3750.0|
// +--------------+