目录
1.准备工作
启动集群的HDFS与Spark
编辑并上传grades.txt 到hdfs
2.新建Maven项目
将java
目录改成scala
目录
3.添加相关依赖和构建插件
<?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>net.luog.sql</groupId>
<artifactId>CalculateAverage</artifactId>
<version>1.0-SNAPSHOT</version><dependencies>
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>2.11.12</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>2.1.1</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
<version>2.1.1</version>
</dependency>
</dependencies>
<build>
<sourceDirectory>src/main/scala</sourceDirectory>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-assembly-plugin</artifactId>
<version>3.3.0</version>
<configuration>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
</configuration>
<executions>
<execution>
<id>make-assembly</id>
<phase>package</phase>
<goals>
<goal>single</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>3.3.2</version>
<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>
</plugins>
</build></project>
4.创建日志属性文件
log4j.rootLogger=ERROR, stdout, logfile
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n
log4j.appender.logfile=org.apache.log4j.FileAppender
log4j.appender.logfile.File=target/spark.log
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n
5.创建分组排行榜单例对象
package net.luog.rdd
import org.apache.spark.{SparkConf, SparkContext}
/**
* 功能:成绩分组排行榜
*/
object GradeTopN {
def main(args: Array[String]): Unit = {
// 创建Spark配置对象
val conf = new SparkConf()
.setAppName("GradeTopN") // 设置应用名称
.setMaster("local[*]") // 设置主节点位置(目前本地调试)
// 基于Spark配置对象创建Spark容器
val sc = new SparkContext(conf);
// 实现分组排行榜
val top3 = sc.textFile("hdfs://master:9000/input/grades.txt")
.map(line => {
val fields = line.split(" ")
(fields(0), fields(1))
}) // 将每行成绩映射成二元组(name, grade)
.groupByKey() // 按键分组
.map(item => {
val name = item._1
val top3 = item._2.toList.sortWith(_ > _).take(3)
(name, top3)
}) // 值排序,取前三// 输出分组排行榜结果
top3.collect.foreach(line => {
val name = line._1
var scores = ""
for (score <- line._2)
scores = scores + " " + score
println(name + ":" + scores)
})// 停止Spark容器,结束任务
sc.stop()
}
}