本地MapReduce案例分享

没有接触的时候,以为MapReduce只能通过远程Hadoop虚拟机才能运行,学习了相关课程之后,发现这种计算也可以在本地运行,只是在部署的时候需要部署到远程服务器上就行了
引入的pom.xml

  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <maven.compiler.source>1.7</maven.compiler.source>
    <maven.compiler.target>1.7</maven.compiler.target>
    <hadoop.version>2.6.0-cdh5.15.1</hadoop.version>
  </properties>

  <repositories>
    <repository>
      <id>cloudera</id>
      <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
    </repository>
  </repositories>
  <dependencies>
    <dependency>
      <groupId>org.apache.hadoop</groupId>
      <artifactId>hadoop-client</artifactId>
      <version>${hadoop.version}</version>
    </dependency>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>4.10</version>
      <scope>test</scope>
    </dependency>
  </dependencies>

WordCount词频统计案例

wordcount是最经典的案例,实现如下

Mapper

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;

public class WordCountMapper extends Mapper<LongWritable, Text,Text, IntWritable>{

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //super.map(key, value, context);
        String[] words = value.toString().split("\t");
        for (String word:words){
            context.write(new Text(word),new IntWritable(1));
        }
    }
}

Reducer

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

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        //super.reduce(key, values, context);
        int count=0;
        Iterator<IntWritable> iterator = values.iterator();
        while(iterator.hasNext()){
            IntWritable value = iterator.next();
            count+=value.get();
        }
        context.write(key,new IntWritable(count));
    }
}

Driver

    public  static  void  main (String[] args) throws Exception {
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        job.setJarByClass(WordCountDriver.class);

        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        FileInputFormat.setInputPaths(job,new Path("input"));
        FileOutputFormat.setOutputPath(job,new Path("output"));

        boolean result = job.waitForCompletion(true);
        System.exit(result?0:1);

    }

在项目目录下创建input文件,并使用词频文件

hello	world	welcome
Hello	Welcome

运行之后,可以得到结果

在这里插入图片描述

流量统计分析

自定义类

import org.apache.hadoop.io.Writable;

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

public class Access  implements Writable {
    private   String phone;
    private long up;
    private  long down;
    private  long sum;

    public String getPhone() {
        return phone;
    }

    public void setPhone(String phone) {
        this.phone = phone;
    }

    public Access() {
    }

    public Access(String phone, long up, long down) {
        this.phone = phone;
        this.up = up;
        this.down = down;
        this.sum = up+down;
    }

    @Override
    public void write(DataOutput dataOutput) throws IOException {

        dataOutput.writeUTF(phone);
        dataOutput.writeLong(up);
        dataOutput.writeLong(down);
        dataOutput.writeLong(sum);
    }

    @Override
    public String toString() {
        return  phone  +
                "," + up +
                "," + down +
                "," + sum ;
    }

    @Override
    public void readFields(DataInput in) throws IOException {
        //注意与write方法的顺序匹配
        this.phone = in.readUTF();
        this.up = in.readLong();
        this.down = in.readLong();
        this.sum = in.readLong();

    }

    public long getUp() {
        return up;
    }

    public void setUp(long up) {
        this.up = up;
    }

    public long getDown() {
        return down;
    }

    public void setDown(long down) {
        this.down = down;
    }

    public long getSum() {
        return sum;
    }

    public void setSum(long sum) {
        this.sum = sum;
    }
}

Mapper

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class AccessMapper extends Mapper<LongWritable, Text,Text,Access> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] lines =value.toString().split("\t");
        String phone = lines[1];
        long up = Long.parseLong(lines[lines.length-3]);
        long down =Long.parseLong(lines[lines.length-2]);
        context.write(new Text(phone),new Access(phone,up,down));

    }
}

Reducer

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

import java.io.IOException;

public class AccessReducer extends Reducer<Text,Access,Text,Access> {
    @Override
    protected void reduce(Text key, Iterable<Access> values, Context context) throws IOException, InterruptedException {

        long ups = 0;
        long downs = 0;
        for (Access access:values){
            ups+= access.getUp();
            downs+= access.getDown();
        }
        context.write(key,new Access(key.toString(),ups,downs));
    }
}

Driver

public class AccessDriver {
    public static void main(String[] args) throws  Exception{
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        job.setJarByClass(AccessDriver.class);

        job.setMapperClass(AccessMapper.class);
        job.setReducerClass(AccessReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Access.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Access.class);

        FileInputFormat.setInputPaths(job,new Path("access/input"));
        FileOutputFormat.setOutputPath(job,new Path("access/output"));

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

输入的文件内容

1363157985066 	13726230503	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com		24	27	2481	24681	200
1363157995052 	13826544101	5C-0E-8B-C7-F1-E0:CMCC	120.197.40.4			4	0	264	0	200
1363157991076 	13926435656	20-10-7A-28-CC-0A:CMCC	120.196.100.99			2	4	132	1512	200
1363154400022 	13926251106	5C-0E-8B-8B-B1-50:CMCC	120.197.40.4			4	0	240	0	200
1363157993044 	18211575961	94-71-AC-CD-E6-18:CMCC-EASY	120.196.100.99	iface.qiyi.com	视频网站	15	12	1527	2106	200
1363157995074 	84138413	5C-0E-8B-8C-E8-20:7DaysInn	120.197.40.4	122.72.52.12		20	16	4116	1432	200
1363157993055 	13560439658	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			18	15	1116	954	200
1363157995033 	15920133257	5C-0E-8B-C7-BA-20:CMCC	120.197.40.4	sug.so.360.cn	信息安全	20	20	3156	2936	200
1363157983019 	13719199419	68-A1-B7-03-07-B1:CMCC-EASY	120.196.100.82			4	0	240	0	200
1363157984041 	13660577991	5C-0E-8B-92-5C-20:CMCC-EASY	120.197.40.4	s19.cnzz.com	站点统计	24	9	6960	690	200
1363157973098 	15013685858	5C-0E-8B-C7-F7-90:CMCC	120.197.40.4	rank.ie.sogou.com	搜索引擎	28	27	3659	3538	200
1363157986029 	15989002119	E8-99-C4-4E-93-E0:CMCC-EASY	120.196.100.99	www.umeng.com	站点统计	3	3	1938	180	200
1363157992093 	13560439658	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			15	9	918	4938	200
1363157986041 	13480253104	5C-0E-8B-C7-FC-80:CMCC-EASY	120.197.40.4			3	3	180	180	200
1363157984040 	13602846565	5C-0E-8B-8B-B6-00:CMCC	120.197.40.4	2052.flash2-http.qq.com	综合门户	15	12	1938	2910	200
1363157995093 	13922314466	00-FD-07-A2-EC-BA:CMCC	120.196.100.82	img.qfc.cn		12	12	3008	3720	200
1363157982040 	13502468823	5C-0A-5B-6A-0B-D4:CMCC-EASY	120.196.100.99	y0.ifengimg.com	综合门户	57	102	7335	110349	200
1363157986072 	18320173382	84-25-DB-4F-10-1A:CMCC-EASY	120.196.100.99	input.shouji.sogou.com	搜索引擎	21	18	9531	2412	200
1363157990043 	13925057413	00-1F-64-E1-E6-9A:CMCC	120.196.100.55	t3.baidu.com	搜索引擎	69	63	11058	48243	200
1363157988072 	13760778710	00-FD-07-A4-7B-08:CMCC	120.196.100.82			2	2	120	120	200
1363157985066 	13726238888	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com		24	27	2481	24681	200
1363157993055 	13560436666	C4-17-FE-BA-DE-D9:CMCC	120.196.100.99			18	15	1116	954	200
1363157985066 	13726238888	00-FD-07-A4-72-B8:CMCC	120.196.100.82	i02.c.aliimg.com		24	27	10000	20000	200

输出内容

在这里插入图片描述

本文参考
Hadoop基础与电商行为日志分析 新手入门大数据

已标记关键词 清除标记
©️2020 CSDN 皮肤主题: 博客之星2020 设计师:CY__0809 返回首页