头歌:旅游网站之数据分析

第1关 统计每个城市的宾馆平均价格

java 复制代码
package com.processdata;

import java.io.IOException;
import java.util.Scanner;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import com.util.HBaseUtil;

/**
 * 使用MapReduce程序处理HBase中的数据并将最终结果存入到另一张表 1中
 */
public class HBaseMapReduce extends Configured implements Tool {

    public static class MyMapper extends TableMapper<Text, DoubleWritable> {
        public static final byte[] column = "price".getBytes();
        public static final byte[] family = "hotel_info".getBytes();

        @Override
        protected void map(ImmutableBytesWritable rowKey, Result result, Context context)
                throws IOException, InterruptedException {
            /********** Begin *********/
		//获取酒店价格
        String cityId = Bytes.toString(result.getValue("cityIdInfo".getBytes(),"cityId".getBytes()));
        byte[] value = result.getValue(family,column);
        //将价格转换为double 
		Double hotel = Double.parseDouble(Bytes.toString(value));
        //将价格转化成()类型
        DoubleWritable i = new DoubleWritable(hotel);
		String key = cityId; 
		//写出城市(id,酒店价格)
        context.write(new Text(key),i);

            // String cityId = Bytes.toString(result.getValue("cityInfo".getBytes(), "cityId".getBytes())); 
            // byte[] value = result.getValue(family, column);
            
            // //获取酒店价格
            // //String cityId1 = Bytes.toString(result.getValue("hotel_info".getBytes(), "price".getBytes())); 
            
            // //将价格转换为double
            // Double ho =Double.parseDouble(Bytes.toString(value));
            // //将价格转换成()类型
            // DoubleWritable i = new DoubleWritable(ho);
            // String key = cityId;
            // //写出(城市id,酒店价格)
            // context.write(new  Text(key),i);
		  	/********** End *********/
        }
    }

    public static class MyTableReducer extends TableReducer<Text, DoubleWritable, ImmutableBytesWritable> {
        @Override
        public void reduce(Text key, Iterable<DoubleWritable> values, Context context) throws IOException, InterruptedException {
            /********** Begin *********/
		 
		 
		double sum = 0;
        int count = 0;  
        for (DoubleWritable num:values){ 
            count++; 
            sum += num.get();  
        }
        double avePrice = sum / count;  
        Put put = new Put(Bytes.toBytes(key.toString()));  
        put.addColumn("average_infos".getBytes(),"price".getBytes(),Bytes.toBytes(String.valueOf(avePrice)));  
        context.write(null,put);//initTableReducerJob 设置了表名所以在这里无需设置了

            // double sum=0;
            // int count=0;
            // for(DoubleWritable value:values){
            //     count++;
            //     sum+=value.get();
            // }
            // double avePrice=sum/count;
            // //创建pit对象
            // Put put =new Put(Bytes.toBytes(key.toString()));
            // put.addColumn("average_infos".getBytes(),"price".getBytes(),Bytes.toBytes(String.valueOf(avePrice)));
            
            // context.write(null,put);        
		 
			/********** End *********/
        }

    }

    
    
    
    
    
    public int run(String[] args) throws Exception {
        //配置Job
        Configuration conf = HBaseConfiguration.create(getConf());
        conf.set("hbase.zookeeper.quorum", "127.0.0.1");  //hbase 服务地址
        conf.set("hbase.zookeeper.property.clientPort", "2181"); //端口号
        Scanner sc = new Scanner(System.in);
        String arg1 = sc.next();
        String arg2 = sc.next();
        //String arg1 = "t_city_hotels_info";
        //String arg2 = "average_table";
        try {
			HBaseUtil.createTable("average_table", new String[] {"average_infos"});
		} catch (Exception e) {
			// 创建表失败
			e.printStackTrace();
		}
        Job job = configureJob(conf,new String[]{arg1,arg2});
        return job.waitForCompletion(true) ? 0 : 1;
    }

    private Job configureJob(Configuration conf, String[] args) throws IOException {
        String tablename = args[0];
        String targetTable = args[1];
        Job job = new Job(conf,tablename);
        Scan scan = new Scan();
        scan.setCaching(300);
        scan.setCacheBlocks(false);//在mapreduce程序中千万不要设置允许缓存
        //初始化Mapreduce程序
        TableMapReduceUtil.initTableMapperJob(tablename,scan,MyMapper.class, Text.class, DoubleWritable.class,job);
        //初始化Reduce
        TableMapReduceUtil.initTableReducerJob(
                targetTable,        // output table
                MyTableReducer.class,    // reducer class
                job);
        job.setNumReduceTasks(1);
        return job;
    }
}

第2关 统计酒店评论中词频较高的词

java 复制代码
package com.processdata;
import java.io.IOException;
import java.util.List;
import java.util.Scanner;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apdplat.word.WordSegmenter;
import org.apdplat.word.segmentation.Word;
import com.util.HBaseUtil;
import com.vdurmont.emoji.EmojiParser;

/**
 * 词频统计
 *
 */
public class WorldCountMapReduce extends Configured implements Tool {
    

    public static class MyMapper extends TableMapper<Text, IntWritable> {
        private static byte[] family = "comment_info".getBytes();
    	private static byte[] column = "content".getBytes();
        
        @Override
        protected void map(ImmutableBytesWritable rowKey, Result result, Context context)
                throws IOException, InterruptedException {
            /********** Begin *********/
		// String content = Bytes.toString(result.getValue("comment_info".getBytes(),"content".getBytes()));
        // byte[] content = result.getValue(family,column);
		// if(content != null && content.isEmpty()){
        //     content=EmojiParser.removeAllEmojis(content);
        //     List<Word> words = WordSegmenter.seg(content);
        //     IntWritable intWritable = new IntWritable(1);
        //     for (Word word : words) {
        //         Text text = new Text(word.getText());
        //         //5、写入到context
        //         context.write(text,intWritable);
        //     } 
        // }
		 
		    byte[] value = result.getValue(family, column);
            String word = new String(value,"utf-8");
            if(!word.isEmpty()){
                String filter = EmojiParser.removeAllEmojis(word);
                List<Word> segs = WordSegmenter.seg(filter);
                for(Word cont : segs) {
                    Text text = new Text(cont.getText());
                    IntWritable v = new IntWritable(1);
                    context.write(text,v);
                }
            }
		 
			/********** End *********/
    	}
    }

    public static class MyReducer extends TableReducer<Text, IntWritable, ImmutableBytesWritable> {
        private static byte[] family =  "word_info".getBytes();
        private static byte[] column = "count".getBytes();
        
        @Override
        public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            /********** Begin *********/
		        //1.统计每一个分词的次数
                // int count = 0;
                // for (IntWritable value:values){
                //     count +=value.get();
                // }
                // //2.构建一个v3 是put  RowKey: 分词
                // Put put = new Put(Bytes.toBytes(key.toString()));
                // //添加列
                // put.addColumn(family,column,Bytes.toBytes(coumt));
                // //3.把k3,v3 写入到context
                // context.write(null,put);

            int sum = 0;
            for (IntWritable value : values) {
                sum += value.get();
            }
            Put put = new Put(Bytes.toBytes(key.toString()));
            put.addColumn(family,column,Bytes.toBytes(sum));
            context.write(null,put);
		  	/********** End *********/
        }

    }

    
    
    
    
    
    public int run(String[] args) throws Exception {
        //配置Job
        Configuration conf = HBaseConfiguration.create(getConf());
        conf.set("hbase.zookeeper.quorum", "127.0.0.1");  //hbase 服务地址
        conf.set("hbase.zookeeper.property.clientPort", "2181"); //端口号
        Scanner sc = new Scanner(System.in);
        String arg1 = sc.next();
        String arg2 = sc.next();
        try {
			HBaseUtil.createTable("comment_word_count", new String[] {"word_info"});
		} catch (Exception e) {
			// 创建表失败
			e.printStackTrace();
		}
        Job job = configureJob(conf,new String[]{arg1,arg2});
        return job.waitForCompletion(true) ? 0 : 1;
    }

    private Job configureJob(Configuration conf, String[] args) throws IOException {
        String tablename = args[0];
        String targetTable = args[1];
        Job job = new Job(conf,tablename);
        Scan scan = new Scan();
        scan.setCaching(300);
        scan.setCacheBlocks(false);//在mapreduce程序中千万不要设置允许缓存
        //初始化Mapper Reduce程序
        TableMapReduceUtil.initTableMapperJob(tablename,scan,MyMapper.class, Text.class, IntWritable.class,job);
        TableMapReduceUtil.initTableReducerJob(targetTable,MyReducer.class,job);
        job.setNumReduceTasks(1);
        return job;
    }

}
相关推荐
2402_857589368 分钟前
SpringBoot框架:作业管理技术新解
java·spring boot·后端
HBryce2412 分钟前
缓存-基础概念
java·缓存
一只爱打拳的程序猿27 分钟前
【Spring】更加简单的将对象存入Spring中并使用
java·后端·spring
杨荧28 分钟前
【JAVA毕业设计】基于Vue和SpringBoot的服装商城系统学科竞赛管理系统
java·开发语言·vue.js·spring boot·spring cloud·java-ee·kafka
minDuck30 分钟前
ruoyi-vue集成tianai-captcha验证码
java·前端·vue.js
为将者,自当识天晓地。1 小时前
c++多线程
java·开发语言
daqinzl1 小时前
java获取机器ip、mac
java·mac·ip
激流丶1 小时前
【Kafka 实战】如何解决Kafka Topic数量过多带来的性能问题?
java·大数据·kafka·topic
Themberfue1 小时前
Java多线程详解⑤(全程干货!!!)线程安全问题 || 锁 || synchronized
java·开发语言·线程·多线程·synchronized·