用IDEA编写spark的WordCount

Posted 2020-12-29 xiaocan66

我习惯用Maven项目 所以用IDEA新建一个Maven项目 

　　　　　　　　　　　　

    下面是pom文件 我粘上来吧

 

<?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</groupId>
    <artifactId>ScalaMavenTest2</artifactId>
    <version>1.0-SNAPSHOT</version>
    <properties>
        <maven.compiler.source>1.7</maven.compiler.source>
        <maven.compiler.target>1.7</maven.compiler.target>
        <encoding>UTF-8</encoding>
        <scala.version>2.11.8</scala.version>
        <scala.compat.version>2.11</scala.compat.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>2.2.2</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>2.2.2</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.5</version>
        </dependency>
    </dependencies>


    <!-- 指定插件-->
    <build>
        <plugins>
            <!--编译java的插件-->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.5.1</version>
            </plugin>
            <!-- 指定编译scala的插件 -->
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.2</version>
            </plugin>

            <!-- maven打包的插件 -->
            <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>
                            <transformers>
                                <transformer
                                        implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
                                    <resource>reference.conf</resource>
                                </transformer>
                                <!-- 指定main方法 -->
                                <transformer
                                        implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <mainClass></mainClass>
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>

　　代码如下

import org.apache.spark.{SparkConf, SparkContext}

object WordCount {

  def main(args: Array[String]): Unit = {
    //设置配置文件和名字
    val conf = new SparkConf().setAppName("wordConut")
    //生成Spark的上下文
    val sc = new SparkContext(conf)
    //传入文件
    val rdd = sc.textFile(args(0))
    //先用split()按照空格进行分词 在通过flatMap对分割的单词进行展评,展评完毕后  使用map(x=>(x,1))对每个单词
    //计数1最后使用ReduceByKey(_+_) 根据Key也就是单词进行计数 这是一个Shuffer过程
    val wordcount = rdd.flatMap(_.split(" ")).map(x=>(x,1)).reduceByKey(_+_)
    //先使用map(x=>(x._2,x._1))对单词结果的k V 进行转换然后通过sortByKey(false)根据K V也就是词频进行排序 false要求
    //按照倒序进行排列,最后再次通过map(x=>(x._2,x._1))让 K V 再次进行互换 形成最后结果
    val wordsort = wordcount.map(x=>(x._2,x._1)).sortByKey(false).map(x=>(x._2,x._1))
    //写出路径
    wordsort.saveAsTextFile(args(1))
    sc.stop()
  }


}

之后设置参数 指定master 和文件所在目录  和输出目录

成功之后的结果