1200字范文 > 尚硅谷大数据hadoop教程_mapReduce

尚硅谷大数据hadoop教程_mapReduce

时间：2019-01-20 14:07:51

p67 课程介绍

p68概述

p69 mapreduce核心思想

p70 wordcount源码序列化类型

mapReduce三类进程

p71 编程规范

用户编写的程序分成三个部分：Mapper、Reducer和Driver。

P72 wordcount需求案例分析

p 73 -78 案例环境准备

（1）创建maven工程，MapReduceDemo

（2）在pom.xml文件中添加如下依赖

<dependencies><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-client</artifactId><version>3.1.3</version></dependency><dependency><groupId>junit</groupId><artifactId>junit</artifactId><version>4.12</version></dependency><dependency><groupId>org.slf4j</groupId><artifactId>slf4j-log4j12</artifactId><version>1.7.30</version></dependency></dependencies>

（2）在项目的src/main/resources目录下，新建一个文件，命名为“log4j.properties”，在文件中填入。

log4j.rootLogger=INFO, stdout log4j.appender.stdout=org.apache.log4j.ConsoleAppender log4j.appender.stdout.layout=org.apache.log4j.PatternLayout log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n log4j.appender.logfile=org.apache.log4j.FileAppender log4j.appender.logfile.File=target/spring.log log4j.appender.logfile.layout=org.apache.log4j.PatternLayout log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n

（3）创建包名：com.atguigu.mapreduce.wordcount

4）编写程序

（1）编写Mapper类

package com.atguigu.mapreduce.wordcount;import java.io.IOException;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.LongWritable;import org.apache.hadoop.io.Text;import org.apache.hadoop.mapreduce.Mapper;public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{Text k = new Text();IntWritable v = new IntWritable(1);@Overrideprotected void map(LongWritable key, Text value, Context context)throws IOException, InterruptedException {// 1 获取一行String line = value.toString();// 2 切割String[] words = line.split(" ");// 3 输出for (String word : words) {k.set(word);context.write(k, v);}}}

（2）编写Reducer类

package com.atguigu.mapreduce.wordcount;import java.io.IOException;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.Text;import org.apache.hadoop.mapreduce.Reducer;public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{int sum;IntWritable v = new IntWritable();@Overrideprotected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {// 1 累加求和sum = 0;for (IntWritable count : values) {sum += count.get();}// 2 输出v.set(sum);context.write(key,v);}}

（3）编写Driver驱动类

package com.atguigu.mapreduce.wordcount;import java.io.IOException;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IntWritable;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 WordCountDriver {public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {// 1 获取配置信息以及获取job对象Configuration conf = new Configuration();Job job = Job.getInstance(conf);// 2 关联本Driver程序的jarjob.setJarByClass(WordCountDriver.class);// 3 关联Mapper和Reducer的jarjob.setMapperClass(WordCountMapper.class);job.setReducerClass(WordCountReducer.class);// 4 设置Mapper输出的kv类型job.setMapOutputKeyClass(Text.class);job.setMapOutputValueClass(IntWritable.class);// 5 设置最终输出kv类型job.setOutputKeyClass(Text.class);job.setOutputValueClass(IntWritable.class);// 6 设置输入和输出路径FileInputFormat.setInputPaths(job, new Path(args[0]));FileOutputFormat.setOutputPath(job, new Path(args[1]));// 7 提交jobboolean result = job.waitForCompletion(true);System.exit(result ? 0 : 1);}}

本地测试

（1）需要首先配置好HADOOP_HOME变量以及Windows运行依赖

（2）在IDEA/Eclipse上运行程序

提交到集群测试

集群上测试

（1）用maven打jar包，需要添加的打包插件依赖

<build><plugins><plugin><artifactId>maven-compiler-plugin</artifactId><version>3.6.1</version><configuration><source>1.8</source><target>1.8</target></configuration></plugin><plugin><artifactId>maven-assembly-plugin</artifactId><configuration><descriptorRefs><descriptorRef>jar-with-dependencies</descriptorRef></descriptorRefs></configuration><executions><execution><id>make-assembly</id><phase>package</phase><goals><goal>single</goal></goals></execution></executions></plugin></plugins></build>

（2）将程序打成jar包

（3）修改不带依赖的jar包名称为wc.jar，并拷贝该jar包到Hadoop集群的/opt/module/hadoop-3.1.3路径。

（4）启动Hadoop集群

[atguigu@hadoop102 hadoop-3.1.3]sbin/start-dfs.sh

[atguigu@hadoop103 hadoop-3.1.3]$ sbin/start-yarn.sh

（5）执行WordCount程序

[atguigu@hadoop102 hadoop-3.1.3]$hadoop jar wc.jar

com.atguigu.mapreduce.wordcount.WordCountDriver /user/atguigu/input /user/atguigu/output

p79-86 序列化案例

编写MapReduce程序

package com.atguigu.mapreduce.writable;import org.apache.hadoop.io.Writable;import java.io.DataInput;import java.io.DataOutput;import java.io.IOException;public class FlowBean implements Writable {private long upFlow;private long downFlow;private long sumFlow;public FlowBean() {}public long getUpFlow() {return upFlow;}public void setUpFlow(long upFlow) {this.upFlow = upFlow;}public long getDownFlow() {return downFlow;}public void setDownFlow(long downFlow) {this.downFlow = downFlow;}public long getSumFlow() {return sumFlow;}public void setSumFlow() {sumFlow= upFlow+downFlow;}@Overridepublic void write(DataOutput out) throws IOException {out.writeLong(upFlow);out.writeLong(downFlow);out.writeLong(sumFlow);}@Overridepublic void readFields(DataInput in) throws IOException {upFlow = in.readLong();downFlow = in.readLong();sumFlow = in.readLong();}@Overridepublic String toString() {return upFlow + "\t" + downFlow + "\t" + sumFlow;}}

package com.atguigu.mapreduce.writable;import .apache.bcel.internal.generic.NEW;import org.apache.hadoop.io.LongWritable;import org.apache.hadoop.io.Text;import org.apache.hadoop.mapreduce.Mapper;import javax.sound.sampled.Line;import java.io.IOException;public class FlowMapper extends Mapper<LongWritable, Text,Text,FlowBean> {FlowBean flowBean = new FlowBean();Text keyPhone = new Text();@Overrideprotected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {String line = value.toString();String[] arr = line.split("\t");String phone=arr[1];String up=arr[arr.length-3];String down=arr[arr.length-2];keyPhone.set(phone);flowBean.setUpFlow(Long.parseLong(up));flowBean.setDownFlow(Long.parseLong(down));flowBean.setSumFlow();context.write(keyPhone,flowBean);}}

package com.atguigu.mapreduce.writable;import org.apache.hadoop.io.Text;import org.apache.hadoop.mapreduce.Reducer;import java.io.IOException;public class FlowReducer extends Reducer<Text,FlowBean,Text,FlowBean> {private FlowBean reduceFlowBean=new FlowBean();@Overrideprotected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {long up=0;long down=0;for (FlowBean flowBean: values) {up+=flowBean.getUpFlow();down+=flowBean.getDownFlow();}reduceFlowBean.setUpFlow(up);reduceFlowBean.setDownFlow(down);reduceFlowBean.setSumFlow();context.write(key,reduceFlowBean);}}

package com.atguigu.mapreduce.writable;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.Path;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;import java.io.IOException;public class FlowDriver {public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {Configuration config = new Configuration();Job job = Job.getInstance(config);job.setJarByClass(FlowDriver.class);job.setMapperClass(FlowMapper.class);job.setReducerClass(FlowReducer.class);job.setMapOutputKeyClass(Text.class);job.setMapOutputValueClass(FlowBean.class);job.setOutputKeyClass(Text.class);job.setOutputValueClass(FlowBean.class);FileInputFormat.setInputPaths(job,new Path("D:\\inputFlow"));FileOutputFormat.setOutputPath(job,new Path("D:\\outputFlow"));boolean completion = job.waitForCompletion(true);System.exit(completion?0:1);}}