SparkSQL-聚合函数

SparkSQL中提供了一些DataFramas常用的聚合函数，比如count()，countDistinct()，avg()，max()，min()等等。但是，使用者除了使用这些已经提供的函数外，可以自定义聚合函数。

一、Untyped UDAF

定义一个类集成UserDefinedAggregateFunction并实现其中的方法。

import java.util.ArrayList;
import java.util.List;

import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.expressions.MutableAggregationBuffer;
import org.apache.spark.sql.expressions.UserDefinedAggregateFunction;
import org.apache.spark.sql.types.DataType;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;

public static class MyAverage extends UserDefinedAggregateFunction {

  private StructType inputSchema;
  private StructType bufferSchema;

  public MyAverage() {
    List inputFields = new ArrayList<>();
    inputFields.add(DataTypes.createStructField("inputColumn", DataTypes.LongType, true));
    inputSchema = DataTypes.createStructType(inputFields);

    List bufferFields = new ArrayList<>();
    bufferFields.add(DataTypes.createStructField("sum", DataTypes.LongType, true));
    bufferFields.add(DataTypes.createStructField("count", DataTypes.LongType, true));
    bufferSchema = DataTypes.createStructType(bufferFields);
  }
  // Data types of input arguments of this aggregate function(输入数据类型)
  public StructType inputSchema() {
    return inputSchema;
  }
  // Data types of values in the aggregation buffer(中间进行聚合时，所处理的数据类型)
  public StructType bufferSchema() {
    return bufferSchema;
  }
  // The data type of the returned value(函数返回值类型)
  public DataType dataType() {
    return DataTypes.DoubleType;
  }
  // Whether this function always returns the same output on the identical input
  public boolean deterministic() {
    return 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.(为每个分组的数据执行初始化操作)
  public void initialize(MutableAggregationBuffer buffer) {
    buffer.update(0, 0L);
    buffer.update(1, 0L);
  }
  // Updates the given aggregation buffer `buffer` with new input data from `input`(每个分组有新的值进来的时候，如何进行分组对应的聚合值计算)
  public void update(MutableAggregationBuffer buffer, Row input) {
    if (!input.isNullAt(0)) {
      long updatedSum = buffer.getLong(0) + input.getLong(0);
      long updatedCount = buffer.getLong(1) + 1;
      buffer.update(0, updatedSum);
      buffer.update(1, updatedCount);
    }
  }
  // Merges two aggregation buffers and stores the updated buffer values back to `buffer1`(Spark是分布式的，所以一个分组的数据，可能会在不同的节点上进行局部聚合，就是update。但是，最后一个分组，在各个节点上的聚合值要进行merge，也就是合并。)
  public void merge(MutableAggregationBuffer buffer1, Row buffer2) {
    long mergedSum = buffer1.getLong(0) + buffer2.getLong(0);
    long mergedCount = buffer1.getLong(1) + buffer2.getLong(1);
    buffer1.update(0, mergedSum);
    buffer1.update(1, mergedCount);
  }
  // Calculates the final result(一个分组的聚合值，如何通过中间的缓存聚合值，最后返回值)
  public Double evaluate(Row buffer) {
    return ((double) buffer.getLong(0)) / buffer.getLong(1);
  }
}

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

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

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

二、Type-Safe UDAF

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 {
  // 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();
  }
  // Specifies the Encoder for the intermediate value type
  public Encoder bufferEncoder() {
    return Encoders.bean(Average.class);
  }
  // Specifies the Encoder for the final output value type
  public Encoder outputEncoder() {
    return Encoders.DOUBLE();
  }
}

Encoder employeeEncoder = Encoders.bean(Employee.class);
String path = "examples/src/main/resources/employees.json";
Dataset ds = spark.read().json(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 averageSalary = myAverage.toColumn().name("average_salary");
Dataset result = ds.select(averageSalary);
result.show();
// +--------------+
// |average_salary|
// +--------------+
// |        3750.0|
// +--------------+