Spark 程序 WordCount实现 Scala、Python

单词统计程序

Scala实现

---

idea 安装scala插件

创建maven项目，引入scala sdk



pom.xml<?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>spark-learn</groupId>
<artifactId>cn.spark.learn</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>2.10.6</scala.version>
<scala.compat.version>2.10</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_2.10</artifactId>
<version>1.5.2</version>
</dependency>

<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.10</artifactId>
<version>1.5.2</version>
</dependency>

<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.6.2</version>
</dependency>
</dependencies>

<build>
<sourceDirectory>src/main/scala</sourceDirectory>
<testSourceDirectory>src/test/scala</testSourceDirectory>
<plugins>
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>3.2.0</version>
<executions>
<execution>
<goals>
<goal>compile</goal>
<goal>testCompile</goal>
</goals>
<configuration>
<args>
<arg>-make:transitive</arg>
<arg>-dependencyfile</arg>
<arg>${project.build.directory}/.scala_dependencies</arg>
</args>
</configuration>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.18.1</version>
<configuration>
<useFile>false</useFile>
<disableXmlReport>true</disableXmlReport>
<includes>
<include>**/*Test.*</include>
<include>**/*Suite.*</include>
</includes>
</configuration>
</plugin>

<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>2.3</version>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<filters>
<filter>

b4b0
<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.ManifestResourceTransformer">
<mainClass>cn.itcast.spark.WordCount</mainClass>
</transformer>
</transformers>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>     3. 代码实现object WordCount {

def main(args: Array[String]): Unit = {
// 创建conf，设置应用程序的名字和运行的方式，local[2]表示本地模式运行两个线程，产生两个文件结果
val conf = new SparkConf().setAppName("wordcount").setMaster("local[2]")
// 创建sparkcontext
val sc = new SparkContext(conf)
// 开始计算代码
// textfile从hdfs中读取代码
val file: RDD[String] = sc.textFile("hdfs://mini1:9000/words.txt")
// 压平，分割每一行数据为每个单词
val words: RDD[String] = file.flatMap(_.split(" "))
val tuple: RDD[(String, Int)] = words.map((_, 1))
val result: RDD[(String, Int)] = tuple.reduceByKey(_ + _)
val resultBy: RDD[(String, Int)] = result.sortBy(_._2, false)

// 打印结果
resultBy.foreach(println)
}

}以上程序的输出结果 从控制台打印上来看可能没有排序，原因是local[2]启动了两个线程执行，产生了两个结果文件，local[1]相当于全局排序。
4. 提交到集群执行
import org.apache.spark.SparkContext
import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD

object WordCount {

def main(args: Array[String]): Unit = {
// 创建conf，设置应用程序的名字和运行的方式，local[2]表示本地模式运行两个线程，产生两个文件结果
// val conf = new SparkConf().setAppName("wordcount").setMaster("local[2]")
// 提交到集群执行
val conf = new SparkConf().setAppName("wordcount")
// 创建sparkcontext
val sc = new SparkContext(conf)
// 开始计算代码
// textfile从hdfs中读取代码
val file: RDD[String] = sc.textFile(args(0))
// 压平，分割每一行数据为每个单词
val words: RDD[String] = file.flatMap(_.split(" "))
val tuple: RDD[(String, Int)] = words.map((_, 1))
val result: RDD[(String, Int)] = tuple.reduceByKey(_ + _)
val resultBy: RDD[(String, Int)] = result.sortBy(_._2, false)

// 打印结果
// resultBy.foreach(println)
resultBy.saveAsTextFile(args(1))
}

}使用idea打包，上传至集群中的任意台机器。
提交任务spark-submit --master spark://mini1:7077 --class cn.itcast.spark.WordCount original-spark-learn-1.0-SNAPSHOT.jar hdfs://mini1:9000/words.txt hdfs://mini1:9000/ceshi-scala/

Python实现

---#!/usr/bin/python

from pyspark import SparkContext, SparkConf

conf = SparkConf().setAppName("pywordCount").setMaster("spark://mini1:7077")
sc = SparkContext(conf = conf)

sc.textFile("hdfs://mini1:9000/words.txt").flatMap(lambda a:a.split(" ")).map(lambda x:(x,1)).reduceByKey(lambda x,y:x+y).saveAsTextFile("hdfs://mini1:9000/wordcount/ceshi/")

spark-submit wordcount.py