我的第一个wordcount程序

关注

原创最新推荐文章于 2023-04-23 10:44:29 发布 425 阅读 AI 写同款· GEO 优化 ›

什么是WordCount?WordCount如何实现编程? 上述代码中，word_count函数接受一个文本字符串作为参数，并返回一个字典，其中键是每个单词，值是对应的出现次数。在函数内部，首先将文本转换为小写，并将标点符号替换为空格，以便正确地分割单词。然后，使用split方法将文本分割成单词列表。接下来，通过遍历单词列表，统计每个单词的出现次数，并将结果存储在word_count字典中。WordCount是一种常见的文本处理任务，用于计算给定文本中单词的数量。我们可以根据需要进一步处理这个字典，例如按照出现次数进行排序或输出频率最高的单词。阅读详情

环境：hadoop 版本2.6.0 jdk版本1.7.0 伪分布式环境下运行wordcount程序

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;
import org.apache.hadoop.util.GenericOptionsParser;
public class WordCount {

  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 void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    conf.set("mapred.job.tracker", "ip地址:9001");
    conf.set("fs.default.name", "hdfs://ip地址:9000");
    //conf.set("mapred.jar", "C:\\Users\\Administrator\\Desktop\\wordcount.jar");
    String[] otherArgs = {"/user/input","/user/output/1.txt"};
    if (otherArgs.length != 2) {
      System.err.println("Usage: wordcount <in> <out>");
      System.exit(2);
    }
    Job job = new Job(conf, "WordCount");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

第一次运行并没有成功，出现下列问题

于是