MapReduce和Hive实现词频统计

• Hive

 CREATE TABLE t_docs (line string);

 LOAD DATA LOCAL INPATH '/opt/workspace/docs.dat' INTO TABLE t_docs;

 WITH tmp AS (
     SELECT explode(split(line, "\s")) as word FROM t_docs
)
SELECT word, count(1) as cnt
FROM tmp
GROUP BY word
ORDER BY cnt;

 

• MapReduce　

 

package org.shydow.hadoop.mapreduce;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

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

/**
 * @author Rainbow
 * @date 2021/11/20 21:39
 * @desc mapReduce的wordcount
 * @exec ./bin/hadoop jar /opt/workspace/interview-tutorial-1.0-SNAPSHOT.jar org.shydow.hadoop.mapreduce.WordCount /test/data/wordcount.dat /output1
 */
public class WordCount {

    /**
     * LongWritable: 距离首行的offset
     * Text: value, 行记录
     * Text: word
     * IntWritable: word cnt
     */
    public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {

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

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            StringTokenizer tokenizer = new StringTokenizer(line);
            while (tokenizer.hasMoreTokens()) {
                word.set(tokenizer.nextToken());
                context.write(word, one);
            }
        }
    }

    public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            Iterator<IntWritable> iterator = values.iterator();
            while (iterator.hasNext()) {
                int value = iterator.next().get();
                sum += value;
            }
            context.write(key, new IntWritable(sum));
        }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = new Job(conf, "wordcount");
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);

        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        job.waitForCompletion(true);
    }
}