Hadoop WordCount按单词出现次序排序 [英] Hadoop WordCount sorted by word occurrences
本文介绍了Hadoop WordCount按单词出现次序排序的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！
问题描述
我需要运行 WordCount ，它会给我所有的单词和他们的事件，但按事件排序，而不是按字母排序。我知道我需要创建两个工作为此并运行一个接一个
我使用了mapper和reducer从使用Hadoop MapReduce对字数进行排序
package org.myorg;
import java.io.IOException;
import java.util。*;
导入org.apache.hadoop.fs.Path;
import org.apache.hadoop.io。*;
import org.apache.hadoop.mapred。*;
import org.apache.hadoop.mapreduce.Job;
public class WordCount {
public static class Map扩展MapReduceBase实现Mapper< LongWritable，Text，Text，IntWritable> {
private static static IntWritable one = new IntWritable（1）;
私人文字=新文字（）;
$ b $ public void map（LongWritable key，Text value，OutputCollector< Text，IntWritable> output，Reporter reporter）throws IOException {
String line = value.toString（）;
StringTokenizer tokenizer = new StringTokenizer（line）;
while（tokenizer.hasMoreTokens（））{
word.set（tokenizer.nextToken（））;
output.collect（word，one）;
$ b public static class Reduce extends MapReduceBase implements Reducer< Text，IntWritable，Text，IntWritable> {
$ b $ public void reduce（Text key，Iterator< IntWritable> values，OutputCollector< Text，IntWritable> output，Reporter reporter）throws IOException {
int sum = 0;
while（values.hasNext（））{
sum + = values.next（）。get（）;
}
output.collect（key，new IntWritable（sum））;
}
}
类Map1扩展MapReduceBase实现Mapper< Object，Text，IntWritable，Text> {
$ b $ public void map（Object key，Text value，OutputCollector< IntWritable，Text> collector，Reporter arg3）throws IOException {
String line = value.toString（）;
StringTokenizer stringTokenizer = new StringTokenizer（line）;
{
int number = 999;
String word =empty;
if（stringTokenizer.hasMoreTokens（））{
String str0 = stringTokenizer.nextToken（）;
word = str0.trim（）;
if（stringTokenizer.hasMoreElements（））{
String str1 = stringTokenizer.nextToken（）;
number = Integer.parseInt（str1.trim（））;
}
collector.collect（new IntWritable（number），new Text（word））;
}
}
}
class Reduce1扩展MapReduceBase实现Reducer< IntWritable，Text，IntWritable，Text> {
$ b $ public void reduce（IntWritable key，Iterator< Text> values，OutputCollector< IntWritable，Text> arg2，Reporter arg3）抛出IOException {
while（（values.hasNext（））） {
arg2.collect（key，values.next（））;
$ b public static void main（String [] args）throws Exception {
JobConf conf = new JobConf（ WordCount.class）;
conf.setJobName（wordCount）;
conf.setOutputKeyClass（Text.class）;
conf.setOutputValueClass（IntWritable.class）;
conf.setMapperClass（Map.class）;
conf.setCombinerClass（Reduce.class）;
conf.setReducerClass（Reduce.class）;
conf.setInputFormat（TextInputFormat.class）;
conf.setOutputFormat（TextOutputFormat.class）;
FileInputFormat.setInputPaths（conf，new Path（args [0]））;
FileOutputFormat.setOutputPath（conf，new Path（/ tmp / temp））;
//JobClient.runJob(conf）;
// -------------------------------------------- ----------------------
JobConf conf2 = new JobConf（WordCount.class）;
conf2.setJobName（WordCount1）;
conf2.setOutputKeyClass（Text.class）;
conf2.setOutputValueClass（IntWritable.class）;
conf2.setMapperClass（Map1.class）;
conf2.setCombinerClass（Reduce1.class）;
conf2.setReducerClass（Reduce1.class）;
conf2.setInputFormat（TextInputFormat.class）;
conf2.setOutputFormat（TextOutputFormat.class）;
FileInputFormat.setInputPaths（conf2，new Path（/ tmp / temp / part-00000））;
FileOutputFormat.setOutputPath（conf2，new Path（args [1]））;
工作job1 =新工作（conf）;
工作job2 =新工作（conf2）;
job1.submit（）;
if（job1.waitForCompletion（true））{
job2.submit（）;
job1.waitForCompletion（true）;
}
}
}
这不是工作，我应该改变什么，或者为什么它不工作???如果程序运行到：
INFO input.FileInputFormat：要输入的总输入路径：1
然后问题在于你的最后一行：
$ $ $ $ $ $ $ $ $ $> job2.submit（） ;
作业已提交但未排入队列进行处理。试试这个：
job1.submit（）;
if（job1.waitForCompletion（true））{
job2.submit（）;
job2.waitForCompletion（true）;
}
来处理您的分拣机MR作业。我已经用MR和流程工程的新API试过了你的代码。
只需添加最后一行即可。
I need to run WordCount which will give me all the words and their occurrences but sorted by the occurrences and not by the alphabet
I understand that I need to create two jobs for this and run one after the other I used the mapper and the reducer from Sorted word count using Hadoop MapReduce
package org.myorg;
import java.io.IOException;
import java.util.*;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.mapreduce.Job;
public class WordCount {
public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
output.collect(word, one);
}
}
}
public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
int sum = 0;
while (values.hasNext()) {
sum += values.next().get();
}
output.collect(key, new IntWritable(sum));
}
}
class Map1 extends MapReduceBase implements Mapper<Object, Text, IntWritable, Text> {
public void map(Object key, Text value, OutputCollector<IntWritable, Text> collector, Reporter arg3) throws IOException {
String line = value.toString();
StringTokenizer stringTokenizer = new StringTokenizer(line);
{
int number = 999;
String word = "empty";
if (stringTokenizer.hasMoreTokens()) {
String str0 = stringTokenizer.nextToken();
word = str0.trim();
}
if (stringTokenizer.hasMoreElements()) {
String str1 = stringTokenizer.nextToken();
number = Integer.parseInt(str1.trim());
}
collector.collect(new IntWritable(number), new Text(word));
}
}
}
class Reduce1 extends MapReduceBase implements Reducer<IntWritable, Text, IntWritable, Text> {
public void reduce(IntWritable key, Iterator<Text> values, OutputCollector<IntWritable, Text> arg2, Reporter arg3) throws IOException {
while ((values.hasNext())) {
arg2.collect(key, values.next());
}
}
}
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(WordCount.class);
conf.setJobName("wordCount");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(Map.class);
conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path("/tmp/temp"));
//JobClient.runJob(conf);
//------------------------------------------------------------------
JobConf conf2 = new JobConf(WordCount.class);
conf2.setJobName("WordCount1");
conf2.setOutputKeyClass(Text.class);
conf2.setOutputValueClass(IntWritable.class);
conf2.setMapperClass(Map1.class);
conf2.setCombinerClass(Reduce1.class);
conf2.setReducerClass(Reduce1.class);
conf2.setInputFormat(TextInputFormat.class);
conf2.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf2, new Path("/tmp/temp/part-00000"));
FileOutputFormat.setOutputPath(conf2, new Path(args[1]));
Job job1 = new Job(conf);
Job job2 = new Job(conf2);
job1.submit();
if (job1.waitForCompletion(true)) {
job2.submit();
job1.waitForCompletion(true);
}
}
}
It's not working, what should I change here, or why it's not working ???
解决方案
If the program runs until:
INFO input.FileInputFormat: Total input paths to process : 1
then the problem lies in your last line:
job2.submit();
the job has been submitted but not queued to be processed. Try this:
job1.submit();
if (job1.waitForCompletion(true)) {
job2.submit();
job2.waitForCompletion(true);
}
to process your sorter MR job. I've tried your code with the new API for MR and the flow works.
Just add the last line.
这篇关于Hadoop WordCount按单词出现次序排序的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
查看全文
