Mapreduce 案例3 -------SortByCount

案例需求还是案例2的网站登录日志的数据需要实现：

（1）要统计每个用户访问网站的次数

（2）按用户访问的次数排序
本次案例的键值对的流程：

以下是实现需求的流程：

1、创建新的Maven项目，如下:

（2）修改pom.xml文件，添加以下代码，添加成功之后在右侧的Maven可以看见dependencies

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>3.1.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>3.1.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>3.1.4</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-mapreduce-examples -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-examples</artifactId>
            <version>3.1.4</version>
            <scope>test</scope>
        </dependency>
    </dependencies>

 （3）添加main函数，创建demo 并新建两个java文件---SortByDateFirst和SortByDateSecond，如图：

----------------------------------------------SortByDateFirst.java代码--------------------------------------------

package demo;

        import org.apache.hadoop.conf.Configuration;
        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.Mapper;
        import org.apache.hadoop.mapreduce.Reducer;
        import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
        import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
        import org.apache.hadoop.util.GenericOptionsParser;

        import java.io.IOException;
        import java.util.StringTokenizer;

public class SortByDateFirst {
    public static class SplitMapper
            extends Mapper<Object, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();
        //value email | date
        public void map(Object key, Text value, Context context
        ) throws IOException, InterruptedException {
            String data[] = value.toString().split("\\|", -1);
            word.set(data[0]);
            context.write(word, one);
        }
    }
    public static class IntSumReducer
            extends Reducer<Text,IntWritable,Text,IntWritable> {
        private IntWritable result = new IntWritable();

        public void reduce(Text key, Iterable<IntWritable> values,
                           Context context
        ) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
        }
    }
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length < 2) {
            System.err.println("Usage: SortByCountFirst <in> [<in>...] <out>");
            System.exit(2);
        }
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(SortByDateFirst.class);
        job.setMapperClass(SplitMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        for (int i = 0; i < otherArgs.length - 1; ++i) {
            FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
        }
        FileOutputFormat.setOutputPath(job,
                new Path(otherArgs[otherArgs.length - 1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

 ---------------------------------------------SortByDateSecond.java----------------------------------------------

package demo;

        import org.apache.hadoop.conf.Configuration;
        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.Mapper;
        import org.apache.hadoop.mapreduce.Reducer;
        import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
        import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
        import org.apache.hadoop.util.GenericOptionsParser;

        import java.io.IOException;
        import java.util.StringTokenizer;

public class SortByDateSecond {
    public static class SplitMapper
            extends Mapper<Object, Text, IntWritable ,Text> {

        private IntWritable count = new IntWritable(1);
        private Text word = new Text();
        //value email_address \t count
        public void map(Object key, Text value, Context context
        ) throws IOException, InterruptedException {
            String data[] = value.toString().split("\t", -1);
            word.set(data[0]);
            count.set(Integer.parseInt(data[1]));
            context.write(count, word);
        }
    }
    public static class ReverseReducer
            extends Reducer<IntWritable,Text,Text,IntWritable> {
        private IntWritable result = new IntWritable();

        public void reduce(IntWritable key, Iterable<Text> values,
                           Context context
        ) throws IOException, InterruptedException {
            for (Text val : values) {
                context.write(val,key);
            }
        }
    }
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length < 2) {
            System.err.println("Usage: SortByCountFirst <in> [<in>...] <out>");
            System.exit(2);
        }
        Job job = Job.getInstance(conf, "word count");
        job.setJarByClass(SortByDateSecond.class);
        job.setMapperClass(SplitMapper.class);

        job.setReducerClass(ReverseReducer.class);
        job.setMapOutputKeyClass(IntWritable.class);
        job.setMapOutputValueClass(Text.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        for (int i = 0; i < otherArgs.length - 1; ++i) {
            FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
        }
        FileOutputFormat.setOutputPath(job,
                new Path(otherArgs[otherArgs.length - 1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

2、编译和打包

（1）file-->project Structure-->artifacts中添加一个jar包

（2） 添加Build-->build artifacts-->countbydate-->build，将jar包放在out文件里面。

3、 上传Jar包，上传数据

在上传jar包之前我重新创建了一个文件夹用来存放此次MapReduce的数据以及jar包

命令： mkdir ~/sc00

4、运行程序

（1）启动Hadoop集群

（2）创建一个文件并将此次的数据上传到分布式文件系统中。运行第一步：

命令：hdfs dfs -mkdir /scinput

命令：  hdfs dfs -put email_log_with_date.txt /scinput

命令：  yarn jar SortByCount.jar demo.SortByCountFirst /scinput /scresultsFirst

 第一步结果如下：

（3） 第二步统计次数

命令： yarn jar SortByCount.jar demo.SortByDateSecond /scresultsFirst /scresultsSecond

结果：

可参考MapReduce案例二的实现流程：

(5条消息) MapReduce案例2_Countbydate_仄言2997的博客-优快云博客