Spark-Shell交互式客户端

启动spark集群

[root@hdp-104 sbin]# ./start-all.sh 

启动交互shell

[root@hdp-104 bin]# ./spark-shell --master spark://hdp-104:7077 --executor-memory 500m --total-executor-cores 1

运行wordcount程序

sc.textFile("/spark/hi.txt").flatMap(.split(",")).map((,1)).reduceByKey(+).saveAsTextFile("/spark/out")

textFile("/spark/hi.txt")是hdfs中读取数据

flatMap(_.split(" "))先map再压平

map((_,1))将单词和1构成元组

reduceByKey(+)按照key进行reduce，并将value累加

saveAsTextFile("/spark/out")将结果写入到hdfs中

提交到yarn集群上运行

spark-shell --master yarn --deploy-mode client

scala> val array = Array(1,2,3,4,5)
 
array: Array[Int] = Array(1, 2, 3, 4, 5)
 
scala> val rdd = sc.makeRDD(array)
 
rdd: org.apache.spark.rdd.RDD[Int] = ParallelCollectionRDD[0] at makeRDD at <console>:26
 
scala> rdd.count
 
res0: Long = 5   

scala编写WordCount程序打包到集群上运行

1.依赖

<properties>
        <maven.compiler.source>1.8</maven.compiler.source>
        <maven.compiler.target>1.8</maven.compiler.target>
        <scala.version>2.11.8</scala.version>
        <spark.version>2.2.0</spark.version>
        <hadoop.version>2.6.5</hadoop.version>
        <encoding>UTF-8</encoding>
    </properties>
 
    <dependencies>
        <!-- 导入scala的依赖 -->
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
 
        <!-- 导入spark的依赖 -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
 
        <!-- 指定hadoop-client API的版本 -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</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>

2.代码

import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}
 
 
object ScalaWordCount {
 
  def main(args: Array[String]): Unit = {
    //创建spark配置，设置应用程序名字
    //val conf = new SparkConf().setAppName("ScalaWordCount")
    val conf = new SparkConf().setAppName("ScalaWordCount").setMaster("local[4]")
    //创建spark执行的入口
    val sc = new SparkContext(conf)
    //指定以后从哪里读取数据创建RDD（弹性分布式数据集）
    //sc.textFile(args(0)).flatMap(_.split(" ")).map((_, 1)).reduceByKey(_+_).sortBy(_._2, false).saveAsTextFile(args(1))
 
    val lines: RDD[String] = sc.textFile(args(0))
    //切分压平 _代表一行内容
    val words: RDD[String] = lines.flatMap(_.split(","))
    //将单词和一组合，形成一个元组
    val wordAndOne: RDD[(String, Int)] = words.map((_, 1))
    //按key进行聚合
    val reduced:RDD[(String, Int)] = wordAndOne.reduceByKey(_+_)
    //排序
    val sorted: RDD[(String, Int)] = reduced.sortBy(_._2, false)
    //将结果保存到HDFS中
    sorted.saveAsTextFile(args(1))
    //释放资源
    sc.stop()
 
  }

3、打成jar包提交到集群运行

./spark-submit --master spark://hdp-104:7077 --class com.zpark.wc.ScalaWordCount /root/apps/original-sparkwctwo-1.0-SNAPSHOT.jar hdfs://hdp-101:9000/spark/hi.txt hdfs://hdp-101:9000/spark/out