生产实习——Day3

手机流量统计（部分代码）

FlowHDFSApp.java

// An highlighted block
package org.bigdata.wc;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.net.URI;

public class FlowHDFSApp {
    public static void main(String[] args) throws Exception{

        System.setProperty("HADOOP_USER_NAME", "root");

        Configuration configuration = new Configuration();
        configuration.set("fs.defaultFS","hdfs://192.168.88.104:9000");


        // 创建一个Job
        Job job = Job.getInstance(configuration);

        // 设置Job对应的参数: 主类
        job.setJarByClass(FlowHDFSApp.class);

        // 设置Job对应的参数: 设置自定义的Mapper和Reducer处理类
        job.setMapperClass(WCMapper.class);
        job.setReducerClass(WCReducer.class);

        // 添加Combiner的设置即可
        job.setCombinerClass(WCReducer.class);

        // 设置Job对应的参数: Mapper输出key和value的类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 设置Job对应的参数: Reduce输出key和value的类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        // 如果输出目录已经存在，则先删除
        FileSystem fileSystem = FileSystem.get(new URI("hdfs://192.168.10.131:9000"),configuration, "root");
        Path outputPath = new Path("/wordcount/output");
        if(fileSystem.exists(outputPath)) {
            fileSystem.delete(outputPath,true);
        }

        // 设置Job对应的参数: Mapper输出key和value的类型：作业输入和输出的路径
        FileInputFormat.setInputPaths(job, new Path("/wordcount/input"));
        FileOutputFormat.setOutputPath(job, outputPath);

        // 提交job
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : -1);

    }
}

WCMapper.java

package org.bigdata.wc;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
import java.util.Locale;

/*
KEYIN: Mapper输入的键类型，偏移量(LongWritable)
VALUEIN：Mapper输入的值类型，一行内容，字符串类型（Text）
KEYOUT：Mapper输出的键类型，单词，字符串类型（Text）
VALUEOUT：Mapper输出的值类型，1(IntWritable)
这些类型都实现了Writable接口
*/
public class WCMapper extends Mapper<LongWritable, Text,Text, IntWritable> {

    @Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        String[] words = value.toString().split("\t");
        for (String word: words){
            context.write(new Text(word.toLowerCase()),new IntWritable(1));
        }
    }
}

WCReducer.java

package org.bigdata.wc;

import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
/**
 11
 * Reducer接收到形如：hello==>(1,1,1)  如果存在Combiner，则形如：hello==>(2,3,1)
 12
 * KEYIN：shuffle输出的key的类型（在本例中是单词字符串类型Text）
 13
 * VALUEIN：迭代集合中每个元素的类型（在本例中是IntWritable类型）
 14
 * KEYOUT：Reducer的输出键类型（在本例中是单词字符串类型Text）
 15
 * VALUEOUT：Reducer的输出值类型（在本例中是每个单词出现的次数，IntWritable类型）
 16
 */

public class WCReducer extends Reducer<Text, IntWritable,Text,IntWritable> {

    @Override

    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {

        int count=0;

        for(IntWritable value:values){

            count += value.get();  // 累加某个单词出现的次数

        }

        context.write(new Text(key),new IntWritable(count));  // 将Reducer统计的某个单词出现的频率输出

    }

}

mapreduce/Access.java

// An highlighted block
package org.mapreduce;

import org.apache.hadoop.io.Writable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

//1实现writable方法
public class Access implements Writable{

    private long upflow;
    private long downflow;
    private long sumflow;

    //必须要有空参构造，为了以后反射用
    public Access() {
        super();
    }


    public Access(long upflow, long downflow) {
        super();
        this.upflow = upflow;
        this.downflow = downflow;
        this.sumflow = upflow+downflow;
    }

    public void set(long upflow, long downflow) {
        this.upflow = upflow;
        this.downflow = downflow;
        this.sumflow = upflow+downflow;
    }
    //序列化的方法
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeLong(upflow);
        out.writeLong(downflow);
        out.writeLong(sumflow);

        //反序列化方法
        //注意序列化方法和反序列化方法顺序必须保持一致
    }
    @Override
    public void readFields(DataInput in) throws IOException {
        this.upflow=in.readLong();
        this.downflow=in.readLong();
        this.sumflow=in.readLong();
    }


    @Override
    public String toString() {
        return  upflow + "\t" + downflow + "\t" + sumflow;
    }



    public void setUpflow(long upflow) {
        this.upflow = upflow;
    }

    public long getUpflow() {
        return upflow;
    }

    public long getDownflow() {
        return downflow;
    }


    public void setDownflow(long downflow) {
        this.downflow = downflow;
    }


    public long getSumflow() {
        return sumflow;
    }


    public void setSumflow(long sumflow) {
        this.sumflow = sumflow;
    }


}