Hadoop詞頻統計（一）之叢集模式執行

阿新 • • 發佈：2019-02-10

maven pom.xml：

<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>HadoopStu</groupId>
	<artifactId>HadoopStu</artifactId>
	<version>0.0.1-SNAPSHOT</version>
	<build>
		<sourceDirectory>src</sourceDirectory>
		<resources>
			<resource>
				<directory>src</directory>
				<excludes>
					<exclude>**/*.java</exclude>
				</excludes>
			</resource>
		</resources>
		<plugins>
			<plugin>
				<artifactId>maven-compiler-plugin</artifactId>
				<version>3.3</version>
				<configuration>
					<source>1.8</source>
					<target>1.8</target>
				</configuration>
			</plugin>
		</plugins>
	</build>
	<dependencies>
		<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-common -->
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-common</artifactId>
			<version>2.6.0</version>
		</dependency>
		<!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-core -->
		<dependency>
			<groupId>org.apache.hadoop</groupId>
			<artifactId>hadoop-core</artifactId>
			<version>1.2.1</version>
		</dependency>
		<!-- https://mvnrepository.com/artifact/junit/junit -->
		<dependency>
			<groupId>junit</groupId>
			<artifactId>junit</artifactId>
			<version>4.11</version>
		</dependency>

	</dependencies>
</project>

map:

package cn.hadoop.mr;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.util.StringUtils;

public class WCMapper extends Mapper<LongWritable, Text, Text, LongWritable>{

	@Override
	protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, LongWritable>.Context context)
			throws IOException, InterruptedException {
		// TODO Auto-generated method stub
		String line = value.toString();
		
		String[] words = StringUtils.split(line,' ');
		
		for(String word : words) {
			context.write(new Text(word), new LongWritable(1));
		}
	}
}

reduce:

package cn.hadoop.mr;

import java.io.IOException;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WCReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
	@Override
	protected void reduce(Text key, Iterable<LongWritable> values,
			Reducer<Text, LongWritable, Text, LongWritable>.Context context) throws IOException, InterruptedException {
		long count = 0;
		for(LongWritable value : values) {
			count += value.get();
		}
		context.write(key, new LongWritable(count));
	}
}

run:

package cn.hadoop.mr;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;


public class WCRunner {
	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
		
		Configuration conf = new Configuration();
		Job wcjob = Job.getInstance(conf);
		
		wcjob.setJarByClass(WCRunner.class);
		
		wcjob.setMapperClass(WCMapper.class);
		wcjob.setReducerClass(WCReducer.class);
		
		wcjob.setOutputKeyClass(Text.class);
		wcjob.setOutputValueClass(LongWritable.class);
		
		wcjob.setMapOutputKeyClass(Text.class);
		wcjob.setMapOutputValueClass(LongWritable.class);
		
		FileInputFormat.setInputPaths(wcjob, "/wc/inputdata/");
		FileOutputFormat.setOutputPath(wcjob, new Path("/output/"));
		
		wcjob.waitForCompletion(true);
	}
}

生成輸入資料：

[[email protected] ~]$ cat in.dat
haha lalala
hehe heiheihei
heiheihei lololo
lololo haha
haha haha
hehe lololo

在HDFS上建立相應路徑：
[[email protected] ~]$ hadoop fs -mkdir -p /wc/inputdata

將in.dat文字檔案上傳到HDFS上的相應路徑下：

[[email protected] ~]$ hadoop fs -put in.dat /wc/inputdata/

將上面的java程式打成jar包上傳伺服器，然後通過Hadoop呼叫：

hadoop jar mr.jar cn.hadoop.mr.WCRunner

[[email protected] ~]$ hadoop jar wc.jar  cn.hadoop.mr.WCRunner
16/07/25 15:25:05 INFO client.RMProxy: Connecting to ResourceManager at hadoop01/192.168.56.200:8032
16/07/25 15:25:06 WARN mapreduce.JobSubmitter: Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
16/07/25 15:25:06 INFO input.FileInputFormat: Total input paths to process : 1
16/07/25 15:25:06 INFO mapreduce.JobSubmitter: number of splits:1
16/07/25 15:25:07 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1469431467769_0001
16/07/25 15:25:07 INFO impl.YarnClientImpl: Submitted application application_1469431467769_0001
16/07/25 15:25:07 INFO mapreduce.Job: The url to track the job: http://hadoop01:8088/proxy/application_1469431467769_0001/
16/07/25 15:25:07 INFO mapreduce.Job: Running job: job_1469431467769_0001
16/07/25 15:25:16 INFO mapreduce.Job: Job job_1469431467769_0001 running in uber mode : false
16/07/25 15:25:16 INFO mapreduce.Job:  map 0% reduce 0%
16/07/25 15:25:23 INFO mapreduce.Job:  map 100% reduce 0%
16/07/25 15:25:30 INFO mapreduce.Job:  map 100% reduce 100%
16/07/25 15:25:31 INFO mapreduce.Job: Job job_1469431467769_0001 completed successfully
16/07/25 15:25:31 INFO mapreduce.Job: Counters: 49
	File System Counters
		FILE: Number of bytes read=204
		FILE: Number of bytes written=211397
		FILE: Number of read operations=0
		FILE: Number of large read operations=0
		FILE: Number of write operations=0
		HDFS: Number of bytes read=183
		HDFS: Number of bytes written=44
		HDFS: Number of read operations=6
		HDFS: Number of large read operations=0
		HDFS: Number of write operations=2
	Job Counters 
		Launched map tasks=1
		Launched reduce tasks=1
		Data-local map tasks=1
		Total time spent by all maps in occupied slots (ms)=4219
		Total time spent by all reduces in occupied slots (ms)=4519
		Total time spent by all map tasks (ms)=4219
		Total time spent by all reduce tasks (ms)=4519
		Total vcore-seconds taken by all map tasks=4219
		Total vcore-seconds taken by all reduce tasks=4519
		Total megabyte-seconds taken by all map tasks=4320256
		Total megabyte-seconds taken by all reduce tasks=4627456
	Map-Reduce Framework
		Map input records=6
		Map output records=12
		Map output bytes=174
		Map output materialized bytes=204
		Input split bytes=105
		Combine input records=0
		Combine output records=0
		Reduce input groups=5
		Reduce shuffle bytes=204
		Reduce input records=12
		Reduce output records=5
		Spilled Records=24
		Shuffled Maps =1
		Failed Shuffles=0
		Merged Map outputs=1
		GC time elapsed (ms)=93
		CPU time spent (ms)=1100
		Physical memory (bytes) snapshot=348495872
		Virtual memory (bytes) snapshot=1864597504
		Total committed heap usage (bytes)=219480064
	Shuffle Errors
		BAD_ID=0
		CONNECTION=0
		IO_ERROR=0
		WRONG_LENGTH=0
		WRONG_MAP=0
		WRONG_REDUCE=0
	File Input Format Counters 
		Bytes Read=78
	File Output Format Counters 
		Bytes Written=44

輸出結果如下：

haha   4
hehe   2
heiheihei   2
lalala   1
lololo   3

Hadoop詞頻統計（一）之叢集模式執行

maven pom.xml： <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLo

Hadoop離線計算（一）之安裝並配置Hadoop

一、準備linux環境 1.0 配置好各虛擬機器的網路（採用NAT聯網模式）第一種：通過Linux圖形介面進行修改(桌面版本Centos)進入Linux圖形介面 -> 右鍵點選右上方的兩個小電腦 -> 點選Edit connections->

Java進階 ——— Java多執行緒（一）之程序和執行緒

引言講到執行緒，不可避免的提到程序。而因為執行緒無法脫離程序單獨存在，那什麼是程序？延伸閱讀,Java多執行緒系列文章什麼是程序？程序：具有一定獨立功能的程式關於某個資料集合上的一次執行活動,程序是系統進行資源分配和排程的最小單位。例如手機執行的眾多

Struts2 入門（一）之控制器與執行步驟

Struts2是什麼？是一個MVC框架。框架都是半成品。藉助框架可以提高開發效率。 Filter VS Servlet 過濾器要比Servlet要強大，開發中經常用Servlet作為控制器，Filter也可以作為控制器來使用。 public class ServletDemo implements Serv

python自然語言處理（一）之中文分詞預處理、統計詞頻

一個小的嘗試。。資料來源資料集一共200條關於手機的中文評論，以XML格式儲存。分詞工具 python-jieba預處理包括去停用詞、去標點符號和數字去停用詞：使用的是他人總結的停用詞表去標點符號和數字：用正則表示式。原本打算的是中文標點符號從網上覆制，英文標點符號用st

Hadoop基礎學習（一）分析、編寫並執行WordCount詞頻統計程序

Hadoop（一）之初識大數據與Hadoop

hive 程序員 http 關系型數據庫 .com 邏輯使用 alt clu 前言　　從今天起，我將一步一步的分享大數據相關的知識，其實很多程序員感覺大數據很難學，其實並不是你想象的這樣，只要自己想學，還有什麽難得呢？　　學習Hadoop有一個8020原則，80%

Hadoop（一）之初識大數據與Hadoop【轉載】

hba 無效理解組織鼠標掌握能夠 through 2.3 原文地址：http://www.cnblogs.com/zhangyinhua/p/7647334.html 閱讀目錄(Content) 一、引言（大數據時代） 1.1、從數據中得到信息 1.2、大數據

7天hadoop學習（一）之虛擬機器的網路連線方式及linux的靜態ip設定

學習hadoop需要用到linux,所以視訊中講解了一些用到的linux知識。如果通過虛擬機器進去linux系統一直讀進度條就是進不去主機頁面，有可能是網絡卡原因，那麼在虛擬機器設定選項選擇高階，重新生成MAC地址。 http://www.cnblogs.com/xi

【統計】SQL之case when then else end用法(用於分類統計)（一）

case具有兩種格式。簡單case函式和case搜尋函式。--簡單case函式 case sex when '1' then '男' when '2' then '女’ else '其他' end --case搜尋函式 case when sex = '1' th

地址映象和變換（一）之主存虛存

規則根據 pan 命中率實現 -s tro 分享使用地址映象：是將每一個虛存單元按某種規則裝入實存，即建立多用戶虛地址與實存地址之間的相應關系。地址變換：是程序依照這樣的映象關系裝入實存後。在運行時，多用戶虛地址怎樣變換成相應的實存地址。頁面爭用（實頁沖突

Hadoop自學筆記（一）常見Hadoop相關項目一覽

-a https class Lucene 百萬 data fcm you 轉換本自學筆記來自於Yutube上的視頻Hadoop系列。網址： https://www.youtube.com/watch?v=-TaAVaAwZTs（當中一個）以後不再贅述自學筆

web框架（一）之基礎簡介

-a 程序我想 pos 客戶創建當前自動 art http的請求聲明周期：域名----DNS服務器---IP地址---基於tcp協議的http協議發送請求協議，服務端返回響應頭+響應體（我們所看到的頁面(是經過js渲染的，接收的是字符串)）服務端（web服務）根據我

android深入之設計模式（一）托付模式

-h listen back != new 聚合 string static data- （一）托付模式簡單介紹托付模式是主要的設計模式之中的一個。托付。即是讓還有一個對象幫你做事情。更多的模式，如狀態模式、策略模式、訪問者模式本質上是在更特殊的場合採用了托

數據庫中間件 Sharding-JDBC 源碼分析 —— SQL 解析（一）之語法解析

sharding-jdbc關註微信公眾號：【芋艿的後端小屋】有福利：RocketMQ / MyCAT / Sharding-JDBC 所有源碼分析文章列表RocketMQ / MyCAT / Sharding-JDBC 中文註釋源碼 GitHub 地址您對於源碼的疑問每條留言都將得到認真回復。甚至不知道如何讀