Spark简单使用案例-WordCount

一、基本步骤

1.观察数据集

2.编写代码测试数据集

3.固化代码、提交集群运行上线

二、编写代码方式

1.spark-shell

　　·数据集的探索

　　·测试

2.独立应用

　　·上线，放在集群运行

三、WordCount案例

步骤：1.读取文件

　　    2.差分单词

　　    3.给与每个单词词频为1

　　    4.按照单词进行词频聚合

相关代码：

<?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>groupId</groupId>
    <artifactId>spark</artifactId>
    <version>1.0-SNAPSHOT</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>${scala.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.7</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.7</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>jcl-over-slf4j</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-api</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>${log4j.version}</version>
        </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.alchem31.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>${project.build.directory}/.scala_dependencies</arg>
                            </args>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>3.1.1</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.$F</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META_INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

package cn.itcasr.spark

import java.util
import org.apache.spark.{SparkConf,SparkContext}
object WordCount {
  def main(args:util.Arrays[String]):Unit={
    //1.创建SparkContext
    val conf=new SparkConf().setMaster("local[6]").setAppName("word_count")
    val sc=new SparkContext(conf)
    //2.加载数据文件
        //2.1准备文件
        //2.2读取文件
    val rdd1=sc.textFile(path="dataset/wordcount.txt");
    //3.处理
      //3.1把整句话拆分成多个单词
    val rdd2=rdd1.flatMap(item=>item.split(""))
      //3.2把每个单词指定一个词频
    val rdd3=rdd2.map(item=>(item,1))
      //3.3整合
    val rdd4=rdd3.reduceByKey(curr,agg)=>curr+agg)
    //4.得到结果
    val result=rdd4.collect()
    println(result)
  }
}