Spark批处理WordCount

我们在工作中最长见的问题就是词频统计了，下面给大家一个模板，希望可以帮到大家，scala版本为2.11

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>sparkt</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>

代码如下

package com.wy.sparkcore

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

object WordCount {
    
    
  def main(args: Array[String]): Unit = {
    
    
    //Spark的容器SparkConext
    val conf: SparkConf = new SparkConf().setMaster("local").setAppName("WordCount")
    val sc = new SparkContext(conf)
    //读取文件创建RDD:(弹性分布式数据集)
    //拿到文件的行集(行的RDD)
    val dataRDD: RDD[String] = sc.textFile("a.txt")
    //对每行进行切分：按照空格切分 => 切分之后的字符串RDD
    val wordRDD: RDD[String] = dataRDD.flatMap(_.split(" "))
    //对上面处理的字符串RDD做转换：每个字符串记1  ("hello",1) ("hello",1)
    val wordnumRDD: RDD[(String, Int)] = wordRDD.map((_,1))
    //对上面的到的元组按照key进行reduce
    //val resultRDD: RDD[(String, Int)] = wordnumRDD.reduceByKey(_+_)
    val resultRDD: RDD[(String, Int)] = wordnumRDD.reduceByKey((num1:Int,num2:Int)=>num1+num2)
    //触发任务提交执行，打印输出结果
    resultRDD.foreach(println(_))

    //sc.textFile("a.txt").flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_).foreach(println(_))
  }
}