方法一

需要先配置好eclipse，關於eclipse上Hadoop的配置請參考：
大數據入門（七）win10上eclipse使用Hadoop的配置

上傳文件到hdfs

可以直接右擊upload也可以參考：大數據入門（六）win10對Hadoop hdfs的基本操作（傳送門）

java project

新建java project：

其中WordCount.java【這個是參考了windows10上使用Eclipse配置Hadoop開發環境詳細步驟+WordCount示例】:

package word_count_pag;

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();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length != 2) {
            System.err.println("Usage: wordcount <in> <out>");
            System.exit(2);
        }
        @SuppressWarnings("deprecation")
		Job job = new Job(conf, "word count");
        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);
    }
}

log4j.properties（在src下）【這個是參考了windows10上使用Eclipse配置Hadoop開發環境詳細步驟+WordCount示例】：

# Configure logging for testing:optionally with log file 
#log4j.rootLogger=debug,appender 
log4j.rootLogger=info,appender 
#log4j.rootLogger=error,appender 
#\u8F93\u51FA\u5230\u63A7\u5236\u53F0 
log4j.appender.appender=org.apache.log4j.ConsoleAppender 
#\u6837\u5F0F\u4E3ATTCCLayout 
log4j.appender.appender.layout=org.apache.log4j.TTCCLayout