Mapper Reducer计算每日的访客量JAVA代码

在Hadoop MapReduce框架下，想要计算每天的访客量，通常涉及到三个步骤：Map阶段、Shuffle阶段和Reduce阶段。这里是一个简单的Java示例：

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 VisitorCount {

    static class VisitMapper extends Mapper<Object, Text, Text, IntWritable> {
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        @Override
        protected void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String[] fields = value.toString().split(",");
            word.set(fields[0]); // 假设日期字段是第一个
            context.write(word, one);
        }
    }

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

        @Override
        protected 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();
        Job job = Job.getInstance(conf, "visitor count");
        job.setJarByClass(VisitorCount.class);
        job.setMapperClass(VisitMapper.class);
        job.setCombinerClass(VisitReducer.class);
        job.setReducerClass(VisitReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.addInputPath(job, new Path(args[0])); // 输入文件路径
        FileOutputFormat.setOutputPath(job, new Path(args[1])); // 输出结果路径

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

在这个例子中，`VisitMapper`将每个访问记录解析为日期和一条访问，然后生成键值对（日期，1）。`VisitReducer`会累加每日的访问次数，并将结果保存到指定的输出路径。