wordCount

<?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_yarn</groupId>
    <artifactId>yarn</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <scala.version>2.11</scala.version>
        <scala.compat.version>2.11</scala.compat.version>
        <spark.version>2.2.0</spark.version>
        <hadoop.version>2.7.2</hadoop.version>
        <hbase.version>1.0</hbase.version>
    </properties>
    <!--<properties>-->
    <!--<scala.version>2.11</scala.version>-->
    <!--<scala.compat.version>2.11</scala.compat.version>-->
    <!--<spark.version>1.6.1</spark.version>-->
    <!--<hadoop.version>2.7.2</hadoop.version>-->
    <!--</properties>-->
    <repositories>
        <repository>
            <id>nexus-aliyun</id>
            <name>Nexus aliyun</name>
            <url>http://maven.aliyun.com/nexus/content/groups/public</url>
        </repository>
    </repositories>

    <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_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>


        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-yarn_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-launcher_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>com.databricks</groupId>
            <artifactId>spark-csv_${scala.version}</artifactId>
            <version>1.4.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <!-- hadoop的客户端,用于访问HDFS -->
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-auth</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-yarn-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-yarn-api</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-yarn-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-yarn-server-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-yarn-server-web-proxy</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>com.typesafe</groupId>
            <artifactId>config</artifactId>
            <version>1.3.3</version>
        </dependency>

    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.scala-tools</groupId>
                <artifactId>maven-scala-plugin</artifactId>
                <version>2.15.2</version>
                <executions>
                    <execution>
                        <id>scala-compile-first</id>
                        <goals>
                            <goal>compile</goal>
                        </goals>
                        <configuration>
                            <includes>
                                <include>**/*.scala</include>
                            </includes>
                        </configuration>
                    </execution>
                    <execution>
                        <id>scala-test-compile</id>
                        <goals>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>






</project>

 

package atguigu
import org.apache.spark.SparkContext
import org.apache.spark.SparkConf
object WordCount {


  //定义主方法
  def main(args: Array[String]): Unit = {


    //创建SparkConf对象
    //如果Master是local，表示运行在本地模式上，即可以在开发工具中直接运行
    //如果要提交到集群中运行，不需要设置Master
//本地模式
    val conf = new SparkConf().setAppName("My Scala Word Count").setMaster("local")

    //创建SparkContext对象
    val sc = new SparkContext(conf)

    //本地模式

//        val result = sc.textFile(args(0))
//          .flatMap(_.split(" "))
//          .map((_, 1))
//          .reduceByKey(_ + _).saveAsTextFile(args(1))

    val result = sc.textFile("in")
      .flatMap(_.split(" "))
      .map((_, 1))
      .reduceByKey(_ + _).saveAsTextFile("out")
    sc.stop()

  }
}

 

package atguigu

import org.apache.spark.sql.SparkSession

object WordCount2 {


  //定义主方法
  def main(args: Array[String]): Unit = {

    //集群模式

    val spark: SparkSession = SparkSession.builder().appName("My Scala Word Count").getOrCreate()

    //创建SparkContext对象

        val result = spark.sparkContext.textFile(args(0))
          .flatMap(_.split(" "))
          .map((_, 1))
          .reduceByKey(_ + _).saveAsTextFile(args(1))

    spark.sparkContext.stop()

  }
}

bin/spark-submit --class atguigu.WordCount --master yarn --deploy-mode cluster session.jar in out2