这个方法是window系列方法中的一个,Window系列的方法,作用就是在当前窗口的时间下再次重新开窗,用的不是很多,毕竟一个总的开窗就满足多数的数据分析需求了,大家有兴趣可以去查查这个系列的其他方法,用途都是一个意思,这里用这个方法,给大家做一个主窗口时间为5秒的基础上做每10秒统计前5秒的抽样词频操作
package com.sparkstream
import org.apache.spark.SparkConf
import org.apache.spark.streaming.dstream.{DStream, ReceiverInputDStream}
import org.apache.spark.streaming.{Seconds, StreamingContext}
object StreamWordCount {
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setMaster("local[2]").setAppName("NetworkWordCount")
val ssc = new StreamingContext(conf, Seconds(5))//滚动窗口,批次大小,处理间隔 => 窗口时间,滑动时间
//每5秒统计一次单词数(滑动时间),每次统计5秒内的数据(窗口大小)
ssc.sparkContext.setLogLevel("ERROR")
val dataDS: ReceiverInputDStream[String] = ssc.socketTextStream("192.168.182.147",9999)
val wordDS: DStream[String] = dataDS.flatMap(_.split(" "))
val tupleDS: DStream[(String, Int)] = wordDS.map((_,1))
//tupleDS.reduceByKey(_+_).print()
//每10秒统计一次单词数,每次统计前5秒的数据
//处理函数,窗口时间,滑动时间
tupleDS.reduceByKeyAndWindow((a:Int,b:Int)=>{a+b},Seconds(10),Seconds(5)).print()
//countByKeyAndWindow
ssc.start()
ssc.awaitTermination()
}
}
pom如下
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.wy</groupId>
<artifactId>zoukao2</artifactId>
<version>1.0-SNAPSHOT</version>
<dependencies>
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>2.11.8</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>2.0.2</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
<version>2.0.2</version>
</dependency>
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.6</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_2.11</artifactId>
<version>2.0.2</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.11</artifactId>
<version>2.0.2</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
<version>2.0.2</version>
</dependency>
</dependencies>
<build>
<pluginManagement>
<plugins>
<!-- 编译scala的插件 -->
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>3.2.2</version>
</plugin>
<!-- 编译java的插件 -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.5.1</version>
</plugin>
</plugins>
</pluginManagement>
<plugins>
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<executions>
<execution>
<id>scala-compile-first</id>
<phase>process-resources</phase>
<goals>
<goal>add-source</goal>
<goal>compile</goal>
</goals>
</execution>
<execution>
<id>scala-test-compile</id>
<phase>process-test-resources</phase>
<goals>
<goal>testCompile</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<executions>
<execution>
<phase>compile</phase>
<goals>
<goal>compile</goal>
</goals>
</execution>
</executions>
</plugin>
<!-- 打jar插件 -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>2.4.3</version>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<filters>
<filter>
<artifact>*:*</artifact>
<excludes>
<exclude>META-INF/*.SF</exclude>
<exclude>META-INF/*.DSA</exclude>
<exclude>META-INF/*.RSA</exclude>
</excludes>
</filter>
</filters>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>