Hadoop之MapReduces统计单词个数

1、配置Windows环境变量

2、创建maven工程

3、导入相应的依赖坐标&＃43;日志添加

org.apache.hadoophadoop-client3.1.4junitjunit4.12org.slf4jslf4j-log4j121.7.30



重新载入

4、在项目的src/main/resources目录下&＃xff0c;新建一个文件&＃xff0c;命名为“log4j.properties”&＃xff0c;在文件中填入

log4j.rootLogger&＃61;INFO, stdout
log4j.appender.stdout&＃61;org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout&＃61;org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern&＃61;%d %p [%c] - %m%n
log4j.appender.logfile&＃61;org.apache.log4j.FileAppender
log4j.appender.logfile.File&＃61;target/spring.log
log4j.appender.logfile.layout&＃61;org.apache.log4j.PatternLayout
log4j.appender.logfile.layout.ConversionPattern&＃61;%d %p [%c] - %m%n

5、创建三个类

package com.haoedu.wordcount;import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;import java.io.IOException;/*** KEYIN, map阶段输入的key的类型&＃xff1a;LongWritable* VALUEIN,map阶段输入value类型&＃xff1a;Text* KEYOUT,map阶段输出的Key类型&＃xff1a;Text* VALUEOUT,map阶段输出的value类型&＃xff1a;IntWritable*/
public class WordCountMapper extends Mapper {private Text outkey&＃61; new Text();private IntWritable outvalue &＃61; new IntWritable(1);&＃64;Overrideprotected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {//获取一行String line &＃61; value.toString();String[] words &＃61; line.split(",");for (String word : words) {outkey.set(word);context.write(outkey, outvalue);}}
}


package com.haoedu.wordcount;import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;import java.io.IOException;/*** KEYIN, reduce阶段输入的key的类型&＃xff1a;Text* VALUEIN,reduce阶段输入value类型&＃xff1a;IntWritable* KEYOUT,reduce阶段输出的Key类型&＃xff1a;Text* VALUEOUT,reduce阶段输出的value类型&＃xff1a;IntWritable*/
public class WordCountReducer extends Reducer {private IntWritable outvalue &＃61; new IntWritable();&＃64;Overrideprotected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {int sum &＃61; 0;for (IntWritable value : values) {sum &＃43;&＃61; value.get();}outvalue.set(sum);context.write(key,outvalue);}
}


package com.haoedu.wordcount;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;import java.io.IOException;public class WordCountDriver {public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {// 1 获取jobConfiguration conf &＃61; new Configuration();Job job &＃61; Job.getInstance(conf);// 2 设置jar包路径job.setJarByClass(WordCountDriver.class);// 3 关联mapper和reducerjob.setMapperClass(WordCountMapper.class);job.setReducerClass(WordCountReducer.class);// 4 设置map输出的kv类型job.setMapOutputKeyClass(Text.class);job.setMapOutputValueClass(IntWritable.class);// 5 设置最终输出的kV类型job.setOutputKeyClass(Text.class);job.setOutputValueClass(IntWritable.class);// 6 设置输入路径和输出路径FileInputFormat.setInputPaths(job, new Path("D:\\大数据全集资料\\Hadoop3.x\\11_input\\inputword"));FileOutputFormat.setOutputPath(job, new Path("D:\\大数据全集资料\\Hadoop3.x\\output888"));// 7 提交jobboolean result &＃61; job.waitForCompletion(true);System.exit(result ? 0 : 1);}
}


结果如下

 6、运行在Linux系统之上

注入依赖

maven-compiler-plugin3.6.11.81.8maven-assembly-pluginjar-with-dependenciesmake-assemblypackagesingle



在集群上运行的时候需要动态输入,输入输出改成

args[0],args[1]