1. 创建maven 工程
2. 相关依赖和插件
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>2.1.1</version>
</dependency>
</dependencies>
<build>
<finalName>wordCount</finalName>
<plugins>
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>4.2.0</version>
<executions>
<execution>
<goals>
<goal>compile</goal>
<goal>testCompile</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-assembly-plugin</artifactId>
<version>3.1.0</version>
<configuration>
<archive>
<manifest>
<mainClass>wordCount</mainClass>
</manifest>
</archive>
<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>
</plugins>
</build>
3. wordCount 案例
package com.atgu.bigdata.spark
import org.apache.spark._
import org.apache.spark.rdd.RDD
object wordCount extends App {
// local模式
// 1.创建sparkConf 对象
val conf: SparkConf = new SparkConf().setMaster("local[*]").setAppName("wordCount")
// 2. 创建spark 上下文对象
val sc:SparkContext=new SparkContext(config = conf)
// 3. 读取文件
val lines: RDD[String] = sc.textFile("file:///opt/data/1.txt")
// 4. 切割单词
val words: RDD[String] = lines.flatMap(_.split(" "))
// words.collect().foreach(println)
// map
private val keycounts: RDD[(String, Int)] = words.map((_, 1))
//
private val results: RDD[(String, Int)] = keycounts.reduceByKey(_ + _)
private val res: Array[(String, Int)] = results.collect
res.foreach(println)
}
4. 项目目录结构
