spark入門之WordCount

maven配置：

<?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>SparkScalaTest</artifactId>
    <packaging>pom</packaging>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <scala.version>2.11.8</scala.version>
        <java.version>1.8</java.version>
        <spark.version>2.1.0</spark.version>
        <hadoop.version>2.7.3</hadoop.version>
    </properties>

    <url>http://maven.apache.org</url>
    <dependencies>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>2.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-network-common_2.11</artifactId>
            <version>2.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-network-shuffle_2.11</artifactId>
            <version>2.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>2.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql-kafka-0-10_2.11</artifactId>
            <version>2.1.0</version>
        </dependency>
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>6.0.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-hive_2.11</artifactId>
            <version>2.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-metastore</artifactId>
            <version>2.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-service</artifactId>
            <version>2.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>2.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
            <version>2.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>1.2.4</version>
        </dependency>

    </dependencies>
</project>

wordcount：

package com.wc  

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

/** 
  * Created by tan on 2016/8/4. 
  */  
object WordCountScala {  
  def main(args: Array[String]) {  
    val conf = new SparkConf().setAppName("WordCount").setMaster("local")  
    val sc = new SparkContext(conf)  


//    sc.textFile("spark.txt").flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_).sortBy(-_._2).foreach(println(_))  
    //以行讀入  
    val lines = sc.textFile("spark.txt")  
    //扁平化map處理(map後將集合中的數據取出)  
    val words = lines.flatMap(_.split(" "))  
//    val words = lines.flatMap(line => line.split(" "))  
    //將集合中的每個單詞處理，設置爲key-value元組  
    val spair = words.map((_,1))  
//    val spair = words.map(word => (word,1))  
    //以元組的key分組，然後聚合處理，最後以value值降序排序  
    val results = spair.reduceByKey(_+_).sortBy(-_._2)  
//    val results = spair.reduceByKey((x,y) => x+y).sortBy(x => -x._2)  
//    val results = spair.reduceByKey(_+_).map(tuple => (tuple._2,tuple._1)).sortByKey(false).map(tuple => (tuple._2,tuple._1))  
    //循環打印results集合中的數據  
    results.foreach(println(_))  

    val distinctResult = words.distinct().map(_ => 1).reduce(_+_)  

    println("distinctResult: "+distinctResult)  

  }  
}