用户定义的聚合函数 (UDAF)
适用于: Databricks Runtime
用户定义聚合函数 (UDAF) 是一次作用于多个行的用户可编程例程,它返回单个聚合值作为结果。 此文档列出了创建和注册 UDAF 所需的类。 它还包含演示了如何在 Scala 中定义和注册 UDAF 以及如何在 Spark SQL 中调用它们的示例。
聚合器
语法 Aggregator[-IN, BUF, OUT]
用户定义的聚合的基类,可在数据集操作中使用,以获取组的所有元素并将其缩减为单个值。
IN:聚合的输入类型。
BUF:约简的中间值的类型。
OUT:最终输出结果的类型。
bufferEncoder:Encoder[BUF]
中间值类型的编码器。
finish(reduction:BUF):OUT
转换约减的输出。
merge(b1:BUF, b2:BUF):BUF
合并两个中间值。
outputEncoder:Encoder[OUT]
最终输出值类型的编码器。
reduce(b:BUF, a:IN):BUF
将输入值
a
聚合为当前中间值。 为了提高性能,函数可以修改b
并返回它,而不是为b
构造新的对象。zero:BUF
此聚合的中间结果的初始值。
示例
类型安全的用户定义聚合函数
强类型化数据集的用户定义聚合围绕 Aggregator
抽象类进行。
例如,类型安全的用户定义平均值可以如下所示:
Scala
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
// The Encoder for the intermediate value type
val bufferEncoder: Encoder[Average] = Encoders.product
// The Encoder for the final output value type
val outputEncoder: Encoder[Double] = Encoders.scalaDouble
}
Java
import java.io.Serializable;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoder;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.TypedColumn;
import org.apache.spark.sql.expressions.Aggregator;
public static class Employee implements Serializable {
private String name;
private long salary;
// Constructors, getters, setters...
}
public static class Average implements Serializable {
private long sum;
private long count;
// Constructors, getters, setters...
}
public static class MyAverage extends Aggregator<Employee, Average, Double> {
// A zero value for this aggregation. Should satisfy the property that any b + zero = b
public Average zero() {
return new 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
public Average reduce(Average buffer, Employee employee) {
long newSum = buffer.getSum() + employee.getSalary();
long newCount = buffer.getCount() + 1;
buffer.setSum(newSum);
buffer.setCount(newCount);
return buffer;
}
// Merge two intermediate values
public Average merge(Average b1, Average b2) {
long mergedSum = b1.getSum() + b2.getSum();
long mergedCount = b1.getCount() + b2.getCount();
b1.setSum(mergedSum);
b1.setCount(mergedCount);
return b1;
}
// Transform the output of the reduction
public Double finish(Average reduction) {
return ((double) reduction.getSum()) / reduction.getCount();
}
// The Encoder for the intermediate value type
public Encoder<Average> bufferEncoder() {
return Encoders.bean(Average.class);
}
// The Encoder for the final output value type
public Encoder<Double> outputEncoder() {
return Encoders.DOUBLE();
}
}
Encoder<Employee> employeeEncoder = Encoders.bean(Employee.class);
String path = "examples/src/main/resources/employees.json";
Dataset<Employee> ds = spark.read().format("json").load(path).as(employeeEncoder);
ds.show();
// +-------+------+
// | name|salary|
// +-------+------+
// |Michael| 3000|
// | Andy| 4500|
// | Justin| 3500|
// | Berta| 4000|
// +-------+------+
MyAverage myAverage = new MyAverage();
// Convert the function to a `TypedColumn` and give it a name
TypedColumn<Employee, Double> averageSalary = myAverage.toColumn().name("average_salary");
Dataset<Double> result = ds.select(averageSalary);
result.show();
// +--------------+
// |average_salary|
// +--------------+
// | 3750.0|
// +--------------+
非类型化的用户定义聚合函数
如上所述,类型化的聚合也可以注册为与数据帧配合使用的非类型化聚合 UDF。 例如,针对非类型化数据帧的用户定义平均值可能如下所示:
Scala
import org.apache.spark.sql.{Encoder, Encoders, SparkSession}
import org.apache.spark.sql.expressions.Aggregator
import org.apache.spark.sql.functions
case class Average(var sum: Long, var count: Long)
object MyAverage extends Aggregator[Long, 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, data: Long): Average = {
buffer.sum += data
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
// The Encoder for the intermediate value type
val bufferEncoder: Encoder[Average] = Encoders.product
// The Encoder for the final output value type
val outputEncoder: Encoder[Double] = Encoders.scalaDouble
}
// Register the function to access it
spark.udf.register("myAverage", functions.udaf(MyAverage))
val df = spark.read.format("json").load("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|
// +--------------+
Java
import java.io.Serializable;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoder;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.expressions.Aggregator;
import org.apache.spark.sql.functions;
public static class Average implements Serializable {
private long sum;
private long count;
// Constructors, getters, setters...
}
public static class MyAverage extends Aggregator<Long, Average, Double> {
// A zero value for this aggregation. Should satisfy the property that any b + zero = b
public Average zero() {
return new 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
public Average reduce(Average buffer, Long data) {
long newSum = buffer.getSum() + data;
long newCount = buffer.getCount() + 1;
buffer.setSum(newSum);
buffer.setCount(newCount);
return buffer;
}
// Merge two intermediate values
public Average merge(Average b1, Average b2) {
long mergedSum = b1.getSum() + b2.getSum();
long mergedCount = b1.getCount() + b2.getCount();
b1.setSum(mergedSum);
b1.setCount(mergedCount);
return b1;
}
// Transform the output of the reduction
public Double finish(Average reduction) {
return ((double) reduction.getSum()) / reduction.getCount();
}
// The Encoder for the intermediate value type
public Encoder<Average> bufferEncoder() {
return Encoders.bean(Average.class);
}
// The Encoder for the final output value type
public Encoder<Double> outputEncoder() {
return Encoders.DOUBLE();
}
}
// Register the function to access it
spark.udf().register("myAverage", functions.udaf(new MyAverage(), Encoders.LONG()));
Dataset<Row> df = spark.read().format("json").load("examples/src/main/resources/employees.json");
df.createOrReplaceTempView("employees");
df.show();
// +-------+------+
// | name|salary|
// +-------+------+
// |Michael| 3000|
// | Andy| 4500|
// | Justin| 3500|
// | Berta| 4000|
// +-------+------+
Dataset<Row> result = spark.sql("SELECT myAverage(salary) as average_salary FROM employees");
result.show();
// +--------------+
// |average_salary|
// +--------------+
// | 3750.0|
// +--------------+
SQL
-- Compile and place UDAF MyAverage in a JAR file called `MyAverage.jar` in /tmp.
CREATE FUNCTION myAverage AS 'MyAverage' USING JAR '/tmp/MyAverage.jar';
SHOW USER FUNCTIONS;
+------------------+
| function|
+------------------+
| default.myAverage|
+------------------+
CREATE TEMPORARY VIEW employees
USING org.apache.spark.sql.json
OPTIONS (
path "examples/src/main/resources/employees.json"
);
SELECT * FROM employees;
+-------+------+
| name|salary|
+-------+------+
|Michael| 3000|
| Andy| 4500|
| Justin| 3500|
| Berta| 4000|
+-------+------+
SELECT myAverage(salary) as average_salary FROM employees;
+--------------+
|average_salary|
+--------------+
| 3750.0|
+--------------+