MapReduce+HIVE 课堂练习

本次课堂测试的要求如下:

但是第一次做还不成熟,只能完成带一部分的前两个要求。

 

Result文件数据说明:

Ip:106.39.41.166,(城市)

Date:10/Nov/2016:00:01:02 +0800,(日期)

Day:10,(天数)

Traffic: 54 ,(流量)

Type: video,(类型:视频video或文章article)

Id: 8701(视频或者文章的id)

测试要求:

1、 数据清洗:按照进行数据清洗,并将清洗后的数据导入hive数据库中。

两阶段数据清洗:

(1)第一阶段:把需要的信息从原始日志中提取出来

ip:    199.30.25.88

time:  10/Nov/2016:00:01:03 +0800

traffic:  62

文章: article/11325

视频: video/3235

(2)第二阶段:根据提取出来的信息做精细化操作

ip--->城市 city(IP)

date--> time:2016-11-10 00:01:03

day: 10

traffic:62

type:article/video

id:11325

(3)hive数据库表结构:

create table data(  ip string,  time string , day string, traffic bigint, type string, id   string )

2、数据处理:

·统计最受欢迎的视频/文章的Top10访问次数 (video/article)

·按照地市统计最受欢迎的Top10课程 (ip)

·按照流量统计最受欢迎的Top10课程 (traffic)

3、数据可视化:将统计结果倒入MySql数据库中,通过图形化展示的方式展现出来。

Result.txt文件内容如下:

 源码:

 1 package hivetest;
 2 
 3 import java.io.IOException;
 4 
 5 import org.apache.hadoop.conf.Configuration;
 6 import org.apache.hadoop.fs.Path;
 7 import org.apache.hadoop.io.LongWritable;
 8 import org.apache.hadoop.io.Text;
 9 import org.apache.hadoop.mapreduce.Job;
10 import org.apache.hadoop.mapreduce.Mapper;
11 import org.apache.hadoop.mapreduce.Reducer;
12 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
13 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
14 public class Hivetest1 {
15 
16     //  static ClassService service=new ClassService();
17     public static class MyMapper extends Mapper<LongWritable, Text, Text/*map对应键类型*/, Text/*map对应值类型*/>
18     {
19          protected void map(LongWritable key, Text value,Context context)throws IOException, InterruptedException
20          {
21               String[] strNlist = value.toString().split(",");//如何分隔
22               //LongWritable,IntWritable,Text等
23               
24               context.write(new Text(strNlist[0])/*map对应键类型*/,new Text(strNlist[1]+","+strNlist[2]+","+strNlist[3]+","+strNlist[4]+","+strNlist[5])/*map对应值类型*/);
25          }
26     }
27     public static class MyReducer extends Reducer<Text/*map对应键类型*/, Text/*map对应值类型*/, Text/*reduce对应键类型*/, Text/*reduce对应值类型*/>
28     {
29         // static No1Info info=new No1Info();
30          protected void reduce(Text key, Iterable<Text/*map对应值类型*/> values,Context context)throws IOException, InterruptedException
31          {
32              for (/*map对应值类型*/Text init : values)
33              {
34                  context.write( key/*reduce对应键类型*/, new Text(init)/*reduce对应值类型*/);
35              }
36          }
37     }
38     
39     public static void main(String[] args) throws Exception {
40         Configuration conf = new Configuration();        
41         Job job = Job.getInstance();
42         job.setJarByClass(Hivetest1.class);
43         job.setMapperClass(MyMapper.class);
44         job.setMapOutputKeyClass(/*map对应键类型*/Text.class);
45         job.setMapOutputValueClass( /*map对应值类型*/Text.class);    
46         // TODO: specify a reducer
47         job.setReducerClass(MyReducer.class);
48         job.setOutputKeyClass(/*reduce对应键类型*/Text.class);
49         job.setOutputValueClass(/*reduce对应值类型*/Text.class);
50 
51         // TODO: specify input and output DIRECTORIES (not files)
52         FileInputFormat.setInputPaths(job, new Path("hdfs://localhost:9000/user/hive/warehouse/test/result.txt"));
53         FileOutputFormat.setOutputPath(job, new Path("hdfs://localhost:9000/user/hive/warehouse/result"));
54 
55         boolean flag = job.waitForCompletion(true);
56         System.out.println("完成!");    //任务完成提示
57         System.exit(flag ? 0 : 1);
58         System.out.println();
59     }
60 
61 }

运行结果:

 代码②:

 1 import java.lang.String;
 2 import java.text.SimpleDateFormat;
 3 import java.util.Date;
 4 import java.util.Locale;
 5 import java.io.IOException;
 6 import org.apache.hadoop.conf.Configuration;
 7 import org.apache.hadoop.fs.Path;
 8 import org.apache.hadoop.io.LongWritable;
 9 import org.apache.hadoop.io.Text;
10 import org.apache.hadoop.mapreduce.Job;
11 import org.apache.hadoop.mapreduce.Mapper;
12 import org.apache.hadoop.mapreduce.Reducer;
13 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
14 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
15 public class sjqx {
16      public static final SimpleDateFormat FORMAT = new SimpleDateFormat("d/MMM/yyyy:HH:mm:ss", Locale.ENGLISH); //原时间格式
17      public static final SimpleDateFormat dateformat1 = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");//现时间格式
18    private static Date parseDateFormat(String string) {         //转换时间格式
19         Date parse = null;
20         try {
21             parse = FORMAT.parse(string);
22         } catch (Exception e) {
23             e.printStackTrace();
24         }
25         return parse;
26     }
27     public static class MyMapper extends Mapper<LongWritable, Text, Text/*map对应键类型*/, Text/*map对应值类型*/>
28     {
29          protected void map(LongWritable key, Text value,Context context)throws IOException, InterruptedException
30          {
31               String[] strNlist = value.toString().split(",");//如何分隔
32               //LongWritable,IntWritable,Text等
33               Date date = parseDateFormat(strNlist[1]);
34               context.write(new Text(strNlist[0])/*map对应键类型*/,new Text(dateformat1.format(date)+" "+strNlist[2]+" "+strNlist[3]+" "+strNlist[4]+" "+strNlist[5])/*map对应值类型*/);
35          }
36     }
37     public static class MyReducer extends Reducer<Text/*map对应键类型*/, Text/*map对应值类型*/, Text/*reduce对应键类型*/, Text/*reduce对应值类型*/>
38     {
39 //        static No1Info info=new No1Info();
40          protected void reduce(Text key, Iterable<Text/*map对应值类型*/> values,Context context)throws IOException, InterruptedException
41          {
42              for (/*map对应值类型*/Text init : values)
43              {
44 
45                  context.write( key/*reduce对应键类型*/, new Text(init)/*reduce对应值类型*/);
46              }
47          }
48     }
49     
50     public static void main(String[] args) throws Exception {
51         Configuration conf = new Configuration();    
52         Job job = Job.getInstance();
53         //job.setJar("MapReduceDriver.jar");
54         job.setJarByClass(sjqx.class);
55         // TODO: specify a mapper
56         job.setMapperClass(MyMapper.class);
57         job.setMapOutputKeyClass(/*map对应键类型*/Text.class);
58         job.setMapOutputValueClass( /*map对应值类型*/Text.class);
59         
60         // TODO: specify a reducer
61         job.setReducerClass(MyReducer.class);
62         job.setOutputKeyClass(/*reduce对应键类型*/Text.class);
63         job.setOutputValueClass(/*reduce对应值类型*/Text.class);
64 
65         // TODO: specify input and output DIRECTORIES (not files)
66         FileInputFormat.setInputPaths(job, new Path("hdfs://localhost:9000/test/in/result"));
67         FileOutputFormat.setOutputPath(job, new Path("hdfs://localhost:9000/test/out"));
68 
69         boolean flag = job.waitForCompletion(true);
70         System.out.println("SUCCEED!"+flag);    //任务完成提示
71         System.exit(flag ? 0 : 1);
72         System.out.println();
73     }
74 }

运行结果:

 

原文地址:https://www.cnblogs.com/0518liu/p/11858448.html