【Spark】第一个代码（WordCount）

工程的创建

添加pom

<?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>cn.itcast</groupId>
    <artifactId>spark</artifactId>
    <version>0.1.0</version>

    <properties>
        <scala.version>2.11.8</scala.version>
        <spark.version>2.2.0</spark.version>
        <slf4j.version>1.7.16</slf4j.version>
        <log4j.version>1.2.17</log4j.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.0</version>
        </dependency>

        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>jcl-over-slf4j</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-api</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>${log4j.version}</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.10</version>
            <scope>provided</scope>
        </dependency>
    </dependencies>

    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        <plugins>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.0</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>UTF-8</encoding>
                </configuration>
            </plugin>

            <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>-dependencyfile</arg>
                                <arg>${project.build.directory}/.scala_dependencies</arg>
                            </args>
                        </configuration>
                    </execution>
                </executions>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>3.1.1</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>
                            <transformers>
                                <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <mainClass></mainClass>
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

整个代码

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

object Spark_WordCount {
  def main(args: Array[String]): Unit = {
    //todo 建立和spark框架的连接
    val sparkConf = new SparkConf().setMaster("local").setAppName("WordCount")
    val sc = new SparkContext(sparkConf);
    //todo 执行业务操作

    //1、读取文件,读取一行一行的数据
    //hello world
    var lines: RDD[String] = sc.textFile("datas")

    //2、将一行数据进行拆分
    //"hello world" =>hello,world,hello,world
    //扁平化:将整体拆分成个体
    val word: RDD[String] = lines.flatMap(_.split(" "))

    //3、将数据进行分组
    //(hello,hello,hello)
    val wordGroup: RDD[(String, Iterable[String])] = word.groupBy(word => word)

    //4、对分组后的数据进行转换
    //(hello,3)
    val wordToCount = wordGroup.map {
      case (word, list) => {
        (word,list.size)
      }
    }

    //将结果转换到控制台打印出来
    val array: Array[(String,Int)] = wordToCount.collect()
    array.foreach(println)

    //todo 关闭连接
    sc.stop()
  }
}

业务执行操作的简化

    val rdd1 = sc.textFile("datas")
    //文件拆分
    val rdd2 = rdd1.flatMap(item=>item.split(" "))
    //赋词频
    val rdd3 = rdd2.map(item=>(item,1))
    //以key为区分，词频相加
    val rdd4 = rdd3.reduceByKey((curr,agg)=>curr+agg)
    //收集数据并且输出
    rdd4.collect().foreach(println)