Hadoop 2.4 单词计数并获取最大词频

2014-11-17

这里的“词频”是指单词出现的频数,也就是次数。

Hadoop 2.4 实现单词计数中已经论述了如何进行单词计数,其处理的结果保存在HDFS中的/output目录下,其中有一文件_SUCCESS是空文件(因为是空文件,所以可以忽略),表示这个JOB成功执行了。 另外一个文件是part-r-00000r代表着这个文件是reduce的结果。

现在对/output中的文件进行处理,获取最大词频。创建java文件MaxNum.java,内容如下:

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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class MaxNum {



    public static class MaxNumMapper extends
            Mapper<Object, Text, IntWritable, IntWritable> {

        private final static IntWritable onlyKey = new IntWritable(1);

        public void map(Object key, Text value, Context context)
                throws IOException, InterruptedException {
            String numStr = value.toString().split("\t")[1];
            context.write(onlyKey, new IntWritable(Integer.parseInt(numStr)));
        }
    }

    public static class MaxNumReducer extends
            Reducer<IntWritable, IntWritable, Text, IntWritable> {

        private final static Text onlyKey = new Text("max");
        private IntWritable result = new IntWritable();

        public void reduce(IntWritable key, Iterable<IntWritable> values,
                Context context) throws IOException, InterruptedException {
            int max_num = 0;
            for (IntWritable val : values) {
                if ( max_num < val.get()) {
                    max_num = val.get();
                }
            }
            result.set(max_num);
            context.write(onlyKey, result);
        }
    }

    public static void main(String[] args) throws Exception {

        Configuration conf2 = new Configuration();
        Job job2 = Job.getInstance(conf2, "get max number");

        job2.setJarByClass(WordCountAndMaxNum.class);

        job2.setMapperClass(MaxNumMapper.class);
        job2.setMapOutputKeyClass(IntWritable.class);
        job2.setMapOutputValueClass(IntWritable.class);    


 //     job2.setCombinerClass(MaxNumReducer.class);
        job2.setReducerClass(MaxNumReducer.class);
        job2.setOutputKeyClass(Text.class);
        job2.setOutputValueClass(IntWritable.class);

        FileInputFormat.setInputPaths(job2, "/output");
        FileOutputFormat.setOutputPath(job2, new Path("/output2"));

        job2.waitForCompletion(true);

    }
}

注意,在main()函数中job2.setCombinerClass(MaxNumReducer.class);被注释掉了,如果不注释掉,在运行时会产生这样一个错误:

Error: java.io.IOException: wrong key class: class org.apache.hadoop.io.Text is not class org.apache.hadoop.io.IntWritable

原因是这样的。Combiner过程发生在Map和Reduce之间,它是一个微型的Reduce(一个Combiner Task处理的数据量较小)。在设置Combiner后,意味着这整个JOB有两次Reduce,第一次是Combiner TASK调用MaxNumReducer类,输出的键值类型是<Text, IntWritable>,该输出会作为第二次Reduce的输入;第二次是Reduce TASK调用MaxNumReducer类,要求输入的键值类型为IntWritable, IntWritable,由此便产生了类型的冲突。

如果一定要加上Combiner,有两个方案:
1、修改MaxNumReducer类;
2、再添加一个继承了Reducer的类供Combiner单独使用。

下面我们将单词计数和获取最大词频整合在一起,创建WordCountAndMaxNum.java,内容如下:

import java.io.IOException;
import java.util.StringTokenizer;

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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class WordCountAndMaxNum {

    public static class TokenizerMapper extends
            Mapper<Object, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(Object key, Text value, Context context)
                throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class IntSumReducer extends
            Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();

        public void reduce(Text key, Iterable<IntWritable> values,
                Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }


    public static class MaxNumMapper extends
            Mapper<Object, Text, IntWritable, IntWritable> {

        private final static IntWritable onlyKey = new IntWritable(1);

        public void map(Object key, Text value, Context context)
                throws IOException, InterruptedException {
            String numStr = value.toString().split("\t")[1];
            context.write(onlyKey, new IntWritable(Integer.parseInt(numStr)));
        }
    }

    public static class MaxNumReducer extends
            Reducer<IntWritable, IntWritable, Text, IntWritable> {

        private final static Text onlyKey = new Text("max");
        private IntWritable result = new IntWritable();

        public void reduce(IntWritable key, Iterable<IntWritable> values,
                Context context) throws IOException, InterruptedException {
            int max_num = 0;
            for (IntWritable val : values) {
                if ( max_num < val.get()) {
                    max_num = val.get();
                }
            }
            result.set(max_num);
            context.write(onlyKey, result);
        }
    }

    public static void main(String[] args) throws Exception {

        Configuration conf1 = new Configuration();
        Job job1 = Job.getInstance(conf1, "word count");

        job1.setJarByClass(WordCountAndMaxNum.class);

        job1.setMapperClass(TokenizerMapper.class);
        job1.setMapOutputKeyClass(Text.class);  //!
        job1.setMapOutputValueClass(IntWritable.class); //!

        job1.setCombinerClass(IntSumReducer.class);
        job1.setReducerClass(IntSumReducer.class);
        job1.setOutputKeyClass(Text.class);
        job1.setOutputValueClass(IntWritable.class);

        FileInputFormat.setInputPaths(job1, "/input");
        FileOutputFormat.setOutputPath(job1, new Path("/output"));

        job1.waitForCompletion(true);

        // --

        Configuration conf2 = new Configuration();
        Job job2 = Job.getInstance(conf2, "get max number");

        job2.setJarByClass(WordCountAndMaxNum.class);

        job2.setMapperClass(MaxNumMapper.class);
        job2.setMapOutputKeyClass(IntWritable.class);
        job2.setMapOutputValueClass(IntWritable.class);    


//        job2.setCombinerClass(MaxNumReducer.class);
        job2.setReducerClass(MaxNumReducer.class);
        job2.setOutputKeyClass(Text.class);
        job2.setOutputValueClass(IntWritable.class);

        FileInputFormat.setInputPaths(job2, "/output");
        FileOutputFormat.setOutputPath(job2, new Path("/output2"));

        job2.waitForCompletion(true);

    }
}

仍然处理Hadoop 2.4 实现单词计数中使用的文本,结果如下:

zsh >> $HADOOP_PREFIX/bin/hadoop fs -cat /output2/part-r-00000                 
max    3

我在编码过程中遇到过这样一个问题:

java.io.IOException: Type mismatch in key from map: expected org.apache.hadoop.io.Text, received org.apache.hadoop.io.LongWritable

可以在Type mismatch in key from map: expected org.apache.hadoop.io.Text, recieved org.apache.hadoop.io.LongWritable找到答案。

( 完 )