hadoop-MapReduce案例流量统计+分区

step1:建立Partion

package flow_count_partion_demo03;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;

public class FlowCountPartion extends Partitioner<Text,FlowBean> {
    /*该方法指定分区规则
    * 135  号码分区
    * 136
    * 137
    * */
    @Override
    public int getPartition(Text text, FlowBean flowBean, int i) {
        //1.获取手机号

        String phonenum=text.toString();
        //2.判断手机号开头，分区
        if (phonenum.startsWith("135")){
            return 0;
        }else if (phonenum.startsWith("137")){
            return 1;
        }else if (phonenum.startsWith("137")){
            return 2;
        }else {
            return 3;
        }
    }
}

step2:配置JobMain

package flow_count_partion_demo03;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class JobMain extends Configured implements Tool {
    @Override
    public int run(String[] args) throws Exception {
        Job job = Job.getInstance(super.getConf(), "mapreduce_flow_partition");
        //打包到集群上面运行时候，必须要添加以下配置，指定程序的main函数
        job.setJarByClass(JobMain.class);
        //第一步：读取输入文件解析成key，value对
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("file:///D:\\input\\flow_partition_input"));


        //第二步：设置我们的mapper类
        job.setMapperClass(FlowCountMapper.class);
        //设置我们map阶段完成之后的输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);
        //第三步分区，第四步排序，第六步分组，都默认
        job.setPartitionerClass(FlowCountPartion.class);

        //第七步：设置我们的reduce类
        job.setReducerClass(FlowCountReducer.class);
        //设置我们reduce阶段完成之后的输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);

        //设置reduecer个数
        job.setNumReduceTasks(4);
        //第八步：设置输出类以及输出路径
        job.setOutputFormatClass(TextOutputFormat.class);
        TextOutputFormat.setOutputPath(job,new Path("file:///D:\\out\\flowcount_out"));
        boolean b = job.waitForCompletion(true);
        return b?0:1;
    }

    /**
     * 程序main函数的入口类
     * @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);
    }
}