数据
代码开始
- 按照好友进行分组得到同一个好友下面的用户
- 获取两两用户之间的好友(会排除掉只有一个用户一个好友的数据)
总结

数据

part-r-00000 (1).txt
冒号前面代表用户后面代表用户好友 :::info 需求: 求两两之间共同好友和个数
思路:

:::

代码开始

按照好友进行分组得到同一个好友下面的用户

public static class FirendsMap extends Mapper<LongWritable, Text, Text, Text>{
        @Override
        protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context) throws IOException, InterruptedException {
            // 按照冒号分割
            String[] split = value.toString().split(":");
            // 对好友数据进行，分割
            String[] split1 = split[1].split(" ");
            for (String s : split1) {
                // 好友, 用户key
                context.write(new Text(s), new Text(split[0]));
            }
        }
    }

public static class FirendsReduce extends Reducer<Text, Text, Text, Text>{
        @Override
        protected void reduce(Text key, Iterable<Text> values, Reducer<Text, Text, Text, Text>.Context context) throws IOException, InterruptedException {
            String data = "";
            // 循环用户 并且拼接
            for (Text value : values) {
                data += (value.toString() +"-");
            }
            // 去掉最后面的 -
            data = data.substring(0, data.length()-1);// 包前不包后
            context.write(new Text(data), key);
        }
    }

N-B    A
A    B
N-A-B    C
Z-A-C-B    D
C-A    F
B    G
N-C-Z    K
C-N    L
N-Z    M
Z    N
N-Z    S
Z    W

package mapFirends;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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;
import java.io.IOException;
public class FirendsOne {
    public static void deleteFile(Path s) throws IOException {
        FileSystem fileSystem = FileSystem.get(new Configuration());
        if(fileSystem.exists(s)){
            fileSystem.delete(s, true);
        }
    }
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(FirendsOne.class);
        job.setMapperClass(FirendsOne.FirendsMap.class);
//        job.setCombinerClass(FirendsOne.FirendsReduce.class);
        job.setReducerClass(FirendsOne.FirendsReduce.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(Text.class);
        Path path = new Path("data/result4");
        deleteFile(path);
        FileInputFormat.addInputPath(job,new Path("data/firends.txt"));
        FileOutputFormat.setOutputPath(job,path);
        System.exit(job.waitForCompletion(true)?0:1);
    }
    public static class FirendsMap extends Mapper<LongWritable, Text, Text, Text>{
        @Override
        protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context) throws IOException, InterruptedException {
            // 按照冒号分割
            String[] split = value.toString().split(":");
            // 对好友数据进行，分割
            String[] split1 = split[1].split(" ");
            for (String s : split1) {
                context.write(new Text(s), new Text(split[0]));
            }
        }
    }
    public static class FirendsReduce extends Reducer<Text, Text, Text, Text>{
        @Override
        protected void reduce(Text key, Iterable<Text> values, Reducer<Text, Text, Text, Text>.Context context) throws IOException, InterruptedException {
            String data = "";
            for (Text value : values) {
                data += (value.toString() +"-");
            }
            data = data.substring(0, data.length()-1);// 包前不包后
            context.write(new Text(data), key);
        }
    }
}

获取两两用户之间的好友(会排除掉只有一个用户一个好友的数据)

 public static class FirendsMap extends Mapper<LongWritable, Text, Text, Text>{
        @Override
        protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context) throws IOException, InterruptedException {
          // 按照制表符进行切割
            String[] split = value.toString().split("\t");
            // 对用户进行切分
            String[] split1 = split[0].split("-");
            Arrays.sort(split1);
            // 不要最后一个
            for (int i = 0; i < split1.length-1; i++) {
                // 跳过第一个
                for (int i1 = i+1; i1 < split1.length; i1++) {
                    //  拼接两两用户
                    context.write(new Text(split1[i]+"-"+split1[i1]), new Text(split[1]));
                }
            }
        }
    }

 public static class FirendsReduce extends Reducer<Text, Text, Text, Text>{
        @Override
        protected void reduce(Text key, Iterable<Text> values, Reducer<Text, Text, Text, Text>.Context context) throws IOException, InterruptedException {
            int count = 0;
            String result = "";
            // 拼接共同好友 这里用 \t 拼接
            // 计数共同好友
            for (Text value : values) {
                count +=1;
                result += value+"\t";
            }
            result += count; // result最后一个元素是\t 所以这里直接拼接个数
            context.write(key, new Text(result));
        }
    }

A-B    C    D    2
A-C    D    F    2
A-N    C    1
A-Z    D    1
B-C    D    1
B-N    C    A    2
B-Z    D    1
C-N    K    L    2
C-Z    D    K    2
N-Z    K    M    S    3

package mapFirends;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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;
import java.io.IOException;
import java.util.Arrays;
public class FirendsTwo {
    public static void deleteFile(Path s) throws IOException {
        FileSystem fileSystem = FileSystem.get(new Configuration());
        if(fileSystem.exists(s)){
            fileSystem.delete(s, true);
        }
    }
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(FirendsTwo.class);
        job.setMapperClass(FirendsTwo.FirendsMap.class);
//        job.setCombinerClass(FirendsTwo.FirendsReduce.class);
        job.setReducerClass(FirendsTwo.FirendsReduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        Path path = new Path("data/result5");
        deleteFile(path);
        FileInputFormat.addInputPath(job,new Path("data/result4"));
        FileOutputFormat.setOutputPath(job,path);
        System.exit(job.waitForCompletion(true)?0:1);
    }
    public static class FirendsMap extends Mapper<LongWritable, Text, Text, Text>{
        @Override
        protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context) throws IOException, InterruptedException {
          // 按照制表符进行切割
            String[] split = value.toString().split("\t");
            // 对用户进行切分
            String[] split1 = split[0].split("-");
            Arrays.sort(split1);
            // 不要最后一个
            for (int i = 0; i < split1.length-1; i++) {
                // 跳过第一个
                for (int i1 = i+1; i1 < split1.length; i1++) {
                    //  拼接两两用户
                    context.write(new Text(split1[i]+"-"+split1[i1]), new Text(split[1]));
                }
            }
        }
    }
    public static class FirendsReduce extends Reducer<Text, Text, Text, Text>{
        @Override
        protected void reduce(Text key, Iterable<Text> values, Reducer<Text, Text, Text, Text>.Context context) throws IOException, InterruptedException {
            int count = 0;
            String result = "";
            // 拼接共同好友 这里用 \t 拼接
            // 计数共同好友
            for (Text value : values) {
                count +=1;
                result += value+"\t";
            }
            result += count; // result最后一个元素是\t 所以这里直接拼接个数
            context.write(key, new Text(result));
        }
    }
}

总结

理解逻辑代码不难
注意拼接用户的时候一个不要最后一个一个不要第一个

编程语言

8 共同好友训练题

数据

代码开始

按照好友进行分组得到同一个好友下面的用户

获取两两用户之间的好友(会排除掉只有一个用户一个好友的数据)

总结

8 共同好友训练题

数据

代码开始

按照好友进行分组 得到同一个好友下面的用户

获取两两用户之间的好友(会排除掉只有一个用户一个好友的数据)

总结

按照好友进行分组得到同一个好友下面的用户