Spark SQL使用简介（2）--UDF（用户自定义函数）

内建的DataFrame函数提供了正常的聚合函数，如count(), countDistinct(), avg(), max(), min()，我们也可以自己定义聚合函数，无类型的用户定义聚合函数按如下方式定义：

import org.apache.spark.sql.{Row, SparkSession}
import org.apache.spark.sql.expressions.MutableAggregationBuffer
import org.apache.spark.sql.expressions.UserDefinedAggregateFunction
import org.apache.spark.sql.types._

object MyAverage extends UserDefinedAggregateFunction {
  // Data types of input arguments of this aggregate function
  //聚合函数的输入参数的类型
  def inputSchema: StructType = StructType(StructField("inputColumn", LongType) :: Nil)
  // Data types of values in the aggregation buffer
  //聚合buffer里的值得数据类型
  def bufferSchema: StructType = {
    StructType(StructField("sum", LongType) :: StructField("count", LongType) :: Nil)
  }
  // The data type of the returned value
  //返回值的数据类型
  def dataType: DataType = DoubleType
  // Whether this function always returns the same output on the identical input
  //对于相同的输入函数是否返回相同的输出
  def deterministic: Boolean = true
  // Initializes the given aggregation buffer. The buffer itself is a `Row` that in addition to
  // standard methods like retrieving a value at an index (e.g., get(), getBoolean()), provides
  // the opportunity to update its values. Note that arrays and maps inside the buffer are still
  // immutable.
  //初始化buffer
  def initialize(buffer: MutableAggregationBuffer): Unit = {
    buffer(0) = 0L
    buffer(1) = 0L
  }
  // Updates the given aggregation buffer `buffer` with new input data from `input`
  def update(buffer: MutableAggregationBuffer, input: Row): Unit = {
    if (!input.isNullAt(0)) {
      buffer(0) = buffer.getLong(0) + input.getLong(0)
      buffer(1) = buffer.getLong(1) + 1
    }
  }
  // Merges two aggregation buffers and stores the updated buffer values back to `buffer1`
  def merge(buffer1: MutableAggregationBuffer, buffer2: Row): Unit = {
    buffer1(0) = buffer1.getLong(0) + buffer2.getLong(0)
    buffer1(1) = buffer1.getLong(1) + buffer2.getLong(1)
  }
  // Calculates the final result
  def evaluate(buffer: Row): Double = buffer.getLong(0).toDouble / buffer.getLong(1)
}

// Register the function to access it
spark.udf.register("myAverage", MyAverage)

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

val result = spark.sql("SELECT myAverage(salary) as average_salary FROM employees")
result.show()
// +--------------+
// |average_salary|
// +--------------+
// |        3750.0|
// +--------------+

下面是类型安全的用户自定义函数： 

import org.apache.spark.sql.{Encoder, Encoders, SparkSession}
import org.apache.spark.sql.expressions.Aggregator

case class Employee(name: String, salary: Long)
case class Average(var sum: Long, var count: Long)

object MyAverage extends Aggregator[Employee, Average, Double] {
  // A zero value for this aggregation. Should satisfy the property that any b + zero = b
  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
  }
  // Merge two intermediate values
  def merge(b1: Average, b2: Average): Average = {
    b1.sum += b2.sum
    b1.count += b2.count
    b1
  }
  // Transform the output of the reduction
  def finish(reduction: Average): Double = reduction.sum.toDouble / reduction.count
  // Specifies the Encoder for the intermediate value type
  def bufferEncoder: Encoder[Average] = Encoders.product
  // Specifies the Encoder for the final output value type
  def outputEncoder: Encoder[Double] = Encoders.scalaDouble
}

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|
// +--------------+