用MapReduce寫一個wordcount做詞頻統計

需求: 在一堆給定的文本文件中統計輸出每一個單詞出現的總次數

Step 1. 數據格式準備

1.創建一個新的文件

cd /export/servers
vim wordcount.txt

2. 向其中放入以下內容並保存

hello,world,hadoop
hive,sqoop,flume,hello
kitty,tom,jerry,world
hadoop

3. 上傳到 HDFS

hdfs dfs -mkdir /wordcount/
hdfs dfs -put wordcount.txt /wordcount/

Step 2. Mapper

public class WordCountMapper extends
Mapper<LongWritable,Text,Text,LongWritable> {
    @Override
    public void map(LongWritable key, Text value, Context context) throws
IOException, InterruptedException {
        String line = value.toString();
        String[] split = line.split(",");
        for (String word : split) {
            context.write(new Text(word),new LongWritable(1));
       }
   }
}

Step 3. Reducer

public class WordCountReducer extends
Reducer<Text,LongWritable,Text,LongWritable> {
    /**
     * 自定義我們的reduce邏輯
     * 所有的key都是我們的單詞，所有的values都是我們單詞出現的次數
     * @param key
     * @param values
     * @param context
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    protected void reduce(Text key, Iterable<LongWritable> values,
Context context) throws IOException, InterruptedException {
        long count = 0;
        for (LongWritable value : values) {
            count += value.get();
       }
        context.write(key,new LongWritable(count));
   }
}

Step 4. 定義主類, 描述 Job 並提交 Job

public class JobMain extends Configured implements Tool {
    @Override
    public int run(String[] args) throws Exception {
        Job job = Job.getInstance(super.getConf(),
JobMain.class.getSimpleName());
        //打包到集羣上面運行時候，必須要添加以下配置，指定程序的main函數
        job.setJarByClass(JobMain.class);
        //第一步：讀取輸入文件解析成key，value對
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new
Path("hdfs://192.168.52.250:8020/wordcount"));
        //第二步：設置我們的mapper類
        job.setMapperClass(WordCountMapper.class);
        //設置我們map階段完成之後的輸出類型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);
        //第三步，第四步，第五步，第六步，省略
        //第七步：設置我們的reduce類
        job.setReducerClass(WordCountReducer.class);
        //設置我們reduce階段完成之後的輸出類型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);
        //第八步：設置輸出類以及輸出路徑
        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job,new
Path("hdfs://192.168.52.250:8020/wordcount_out"));
        boolean b = job.waitForCompletion(true);
        return b?0:1;
   }
    /**
     * 程序main函數的入口類
     * @param args
     * @throws Exception
     */
    public static void main(String[] args) throws Exception {
        Configuration configuration = new Configuration();
        Tool tool  =  new JobMain();
        int run = ToolRunner.run(configuration, tool, args);
        System.exit(run);
   }
}