我在听教程http://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/mapreducetutorial.html 这是我的密码
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
import java.util.StringTokenizer;
import java.util.Iterator;
public class WordCount {
public static class WordCountMapper extends Mapper<Object, Text, Text, IntWritable> {
private Text word = new Text();
private final IntWritable one = new IntWritable(1);
@Override
public void map(Object key, Text val, Context context) throws IOException, InterruptedException {
String line = val.toString();
StringTokenizer tokenizer = new StringTokenizer(line.toLowerCase());
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
context.write(word, one);
}
}
}
public static class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterator<IntWritable> value, Context context) throws IOException, InterruptedException {
int sum = 0;
while (value.hasNext()) {
IntWritable val = (IntWritable) value.next();
sum += val.get();
}
context.write(key, new IntWritable(sum));
}
}
public static void main(String[] args) throws Exception {
Configuration config = new Configuration();
Job job = Job.getInstance(config, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(WordCountMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setCombinerClass(WordCountReducer.class);
job.setReducerClass(WordCountReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path("/user/Icarus/words.txt"));
FileOutputFormat.setOutputPath(job, new Path("/user/Icarus/words.out"));
job.waitForCompletion(true);
}
}
但是当我运行它而不是计算词频时,我得到了:
bye 1
goodbye 1
hadoop 1
hadoop 1
hello 1
hello 1
hello 1
world 1
我一定错过了一些非常琐碎的事情,但我不知道是什么。救命啊。。
1条答案
按热度按时间bnlyeluc1#
这个问题的根本原因是,您没有调用
reduce()
用精确的Signature
按要求呼叫Hadoop
. 签名如下(此处参考)自从你的
reduce()
不符合Signature
,Hadoop
将调用默认的identityreducer,它输出相同的输入。因此,只有您得到的map输出与reduce输出相同。
对于这个问题,我可以给你两个建议,
首先:尝试下面的代码
第二:第二个解决方案很简单,
不用手动定义reduce类,只需将reducer类设置为
IntSumReducer
或者LongSumReducer
它将执行与上述代码相同的操作。所以不要定义
WordCountReducer
类并添加以下代码,基于你想要的计数类型。
希望有帮助!