大数据-经典案例统计求和

3. 流量统计

需求一: 统计求和
统计每个手机号的上行流量总和，下行流量总和，上行总流量之和，下行总流量之和 分析：以手机号码作为key值，上行流量，下行流量，上行总流量，下行总流量四个字段作 为value值，然后以这个key，和value作为map阶段的输出，reduce阶段的输入

Step 1: 自定义map的输出value对象FlowBean

public class FlowBean implements Writable {
    private Integer upFlow;
    private Integer downFlow;
    private Integer upCountFlow;
    private Integer downCountFlow;

    @Override
    public void write(DataOutput out) throws IOException {
        out.writeInt(upFlow);
        out.writeInt(downFlow);
        out.writeInt(upCountFlow);
        out.writeInt(downCountFlow);
    }

    @Override
    public void readFields(DataInput in) throws IOException {
        this.upFlow = in.readInt();
        this.downFlow = in.readInt();
        this.upCountFlow = in.readInt();
        this.downCountFlow = in.readInt();
    }

    public FlowBean() {
    }

    public FlowBean(Integer upFlow, Integer downFlow, Integer upCountFlow, Integer downCountFlow) {
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        this.upCountFlow = upCountFlow;
        this.downCountFlow = downCountFlow;
    }

    public Integer getUpFlow() {
        return upFlow;
    }

    public void setUpFlow(Integer upFlow) {
        this.upFlow = upFlow;
    }

    public Integer getDownFlow() {
        return downFlow;
    }

    public void setDownFlow(Integer downFlow) {
        this.downFlow = downFlow;
    }

    public Integer getUpCountFlow() {
        return upCountFlow;
    }

    public void setUpCountFlow(Integer upCountFlow) {
        this.upCountFlow = upCountFlow;
    }

    public Integer getDownCountFlow() {
        return downCountFlow;
    }

    public void setDownCountFlow(Integer downCountFlow) {
        this.downCountFlow = downCountFlow;
    }

    @Override
    public String toString() {
        return "FlowBean{" + "upFlow=" + upFlow + ", downFlow=" + downFlow + ", upCountFlow=" + upCountFlow + ", downCountFlow=" + downCountFlow + '}';
    }
}

Step 2: 定义FlowMapper类

public class FlowCountMapper extends Mapper<LongWritable, Text, Text, FlowBean> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //1:拆分手机号 
        String[] split = value.toString().split("\t");
        String phoneNum = split[1];
        //2:获取四个流量字段 
        FlowBean flowBean = new FlowBean();
        flowBean.setUpFlow(Integer.parseInt(split[6]));
        flowBean.setDownFlow(Integer.parseInt(split[7]));
        flowBean.setUpCountFlow(Integer.parseInt(split[8]));
        flowBean.setDownCountFlow(Integer.parseInt(split[9]));
        //3:将k2和v2写入上下文中 
        context.write(new Text(phoneNum), flowBean);
    }
}

Step 3: 定义FlowReducer类

public class FlowCountReducer extends Reducer<Text, FlowBean, Text, FlowBean> {
    @Override
    protected void reduce(Text key, Iterable<FlowBean> values, Context context) throws IOException, InterruptedException {
        //封装新的FlowBean 
        FlowBean flowBean = new FlowBean();
        Integer upFlow = 0;
        Integer downFlow = 0;
        Integer upCountFlow = 0;
        Integer downCountFlow = 0;
        for (FlowBean value : values) {
            upFlow += value.getUpFlow();
            downFlow += value.getDownFlow();
            upCountFlow += value.getUpCountFlow();
            downCountFlow += value.getDownCountFlow();
        }
        flowBean.setUpFlow(upFlow);
        flowBean.setDownFlow(downFlow);
        flowBean.setUpCountFlow(upCountFlow);
        flowBean.setDownCountFlow(downCountFlow);
        //将K3和V3写入上下文中 
        context.write(key, flowBean);
    }
}

Step 4: 程序main函数入口FlowMain

public class JobMain extends Configured implements Tool {
    @Override
    public int run(String[] strings) throws Exception {
        //创建一个任务对象
        Job job = Job.getInstance(super.getConf(), "mapreduce_flowcount");
        //打包放在集群运行时，需要做一个配置
        job.setJarByClass(JobMain.class);
        //第一步:设置读取文件的类: K1 和V1
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job, new Path("hdfs://node01:8020/input/flowcount"));
        //第二步：设置Mapper类
        job.setMapperClass(FlowCountMapper.class);
        //设置Map阶段的输出类型: k2 和V2的类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(FlowBean.class);
        //第三,四，五，六步采用默认方式(分区，排序，规约，分组)
        // 第七步 ：设置文的Reducer类
        job.setReducerClass(FlowCountReducer.class);
        //设置Reduce阶段的输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(FlowBean.class);
        //设置Reduce的个数
        // 第八步:设置输出类
        job.setOutputFormatClass(TextOutputFormat.class);
        //设置输出的路径
        TextOutputFormat.setOutputPath(job, new Path("hdfs://node01:8020/out/flowcount_out"));
        boolean b = job.waitForCompletion(true);
        return b ? 0 : 1;
    }

    public static void main(String[] args) throws Exception {
        Configuration configuration = new Configuration();
        //启动一个任务 
        int run = ToolRunner.run(configuration, new JobMain(), args);
        System.exit(run);
    }
}