Hadoop-02 基于Hadoop的JavaEE数据可视化简易案例

需求

1.统计音乐点播次数

2.使用echarts柱状图显示每首音乐的点播次数

 

项目结构

创建JavaEE项目

 

统计播放次数Job关键代码

package com.etc.mc;

import java.io.IOException;
import java.util.HashMap;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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;

/** 歌曲点播统计 */
public class MusicCount {

	//定义保存统计数据结果的map集合
	public static HashMap<String, Integer> map=new HashMap<String, Integer>();
	
	
	public static class MusicMapper extends Mapper<Object, Text, Text, IntWritable> {

		public void map(Object key, Text value, Context context) throws IOException, InterruptedException {

			IntWritable valueOut = new IntWritable(1);
			String keyInStr = value.toString();
			String[] keyInStrArr = keyInStr.split("\t");// 使用\t将输入 文本行转换为字符串
			String keyOut = keyInStrArr[0];// 获取歌曲名称
			context.write(new Text(keyOut), valueOut);
		}
	}

	public static class MusicReducer 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);//统计数据保存到hdfs文件
			map.put(key.toString(), sum);//将统计结果保存到map集合
		}
	}

	
	public static HashMap<String, Integer> main() throws Exception {
		Configuration conf = new Configuration();
		conf.addResource("core-site.xml");// 读取项目中hdfs配置信息
		conf.addResource("mapred-site.xml");// 读取项目中mapreduce配置信息		
		// 实例化作业
		Job job = Job.getInstance(conf, "music_count");
		// 指定jar的class
		job.setJarByClass(MusicCount.class);
		// 指定Mapper
		job.setMapperClass(MusicMapper.class);
		// 压缩数据
		job.setCombinerClass(MusicReducer.class);// 减少datanode，TaskTracker之间数据传输
		// 指定reducer
		job.setReducerClass(MusicReducer.class);
		// 设置输出key数据类型
		job.setOutputKeyClass(Text.class);
		// 设置输出Value数据类型
		job.setOutputValueClass(IntWritable.class);
		// 设置输入文件路径
		FileInputFormat.addInputPath(job, new Path("hdfs://192.168.137.131:9000/music/music1.txt"));
		FileInputFormat.addInputPath(job, new Path("hdfs://192.168.137.131:9000/music/music2.txt"));
		FileInputFormat.addInputPath(job, new Path("hdfs://192.168.137.131:9000/music/music3.txt"));
		FileInputFormat.addInputPath(job, new Path("hdfs://192.168.137.131:9000/music/music4.txt"));		
		//设置输出文件路径
		FileSystem fs=FileSystem.get(conf);
		Path path=new Path("hdfs://192.168.137.131:9000/musicout");
		if(fs.exists(path)) {
			fs.delete(path,true);
		}
		FileOutputFormat.setOutputPath(job, new Path("hdfs://192.168.137.131:9000/musicout"));		
		if(job.waitForCompletion(true)) {
			return map;
		}else {
			return null;
		}

	}
}

　　

Servlet关键代码

package com.etc.action;

import java.io.IOException;
import java.io.PrintWriter;
import java.util.HashMap;

import javax.servlet.ServletException;
import javax.servlet.annotation.WebServlet;
import javax.servlet.http.HttpServlet;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;

import com.alibaba.fastjson.JSON;
import com.etc.mc.MusicCount;

/**向客户端提供json数据*/
@WebServlet("/CountServlet")
public class CountServlet extends HttpServlet {
	private static final long serialVersionUID = 1L;
	

	protected void doGet(HttpServletRequest request, HttpServletResponse response)
			throws ServletException, IOException {
		//post乱码处理	
		request.setCharacterEncoding("utf-8");	
		// 设置响应数据类型
		response.setContentType("text/html");
		// 设置响应编码格式
		response.setCharacterEncoding("utf-8");
		// 获取out对象
		PrintWriter out = response.getWriter();		
		//组织json数据
		HashMap<String, Integer> map=null;
		
		try {
			map=MusicCount.main();
		} catch (Exception e) {
			System.out.println("获取数据出错");
		}
		
		//通过构建map集合转换为嵌套json格式数据
		HashMap jsonmap = new HashMap();
		jsonmap.put("mytitle","歌词播放统计");
		jsonmap.put("mylegend", "点播");
		jsonmap.put("prolist", map);
		
		String str =JSON.toJSONString(jsonmap);			

		out.print(str);
		out.flush();
		out.close();

	}

	protected void doPost(HttpServletRequest request, HttpServletResponse response)
			throws ServletException, IOException {
		doGet(request, response);
	}

}

　　

视图index.jsp关键代码

<%@ page language="java" contentType="text/html; charset=UTF-8"
	pageEncoding="UTF-8"%>
<!DOCTYPE html>
<html lang="en">

<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<meta http-equiv="X-UA-Compatible" content="ie=edge">
<title>金融大数据解析</title>
<!-- 引入 echarts.js -->
<script src="script/echarts.min.js"></script>
<!-- 引入 jquery.js -->
<script src="script/jquery-1.8.3.min.js"></script>
</head>

<body>
	<!-- 为ECharts准备一个具备大小（宽高）的Dom -->
	<div id="main" style="width: 600px; height: 400px;"></div>

	<script type="text/javascript">
		//显示柱状图函数
		function showdata(mytitle, mylegend, xdata, ydata) {
			// 基于准备好的dom，初始化echarts实例
			var myChart = echarts.init(document.getElementById('main'));
			// 指定图表的配置项和数据
			var option = {
				title : {
					text : mytitle
				},
				tooltip : {},
				legend : {
					data : mylegend
				},
				xAxis : {
					data : xdata
				},
				yAxis : {},
				series : [ {
					name : '点播',
					type : 'bar',
					data : ydata
				} ]
			};
			// 使用刚指定的配置项和数据显示图表。
			myChart.setOption(option);
		}



		$(function() {			
			var mytitle;
			var mylegend;
			var xdata=new Array();
			var ydata=new Array();		
			
			$.getJSON("CountServlet", function(data) {
				mytitle = data.mytitle;
				mylegend = data.mylegend;
				//获取x轴数据
				$.each(data.prolist, function(i, n) {
					xdata.push(i);
				});
				//获取y轴数据
				$.each(data.prolist, function(i, n) {
					ydata.push(n);
				});
				
				//执行函数
				showdata(mytitle, [ mylegend ], xdata, ydata);
			});
	
		});
	</script>
</body>

</html>

　　

运行结果

 

项目所需jar列表

 

总结

1.该案例的缺点是什么？每次访问数据需要提交job到hadoop集群运行，性能低。

2.数据分析结果保存在HDFS和集合中，不适合分析结果为大数据集合。

3.如何改进？使用HBase存储解析后的数据集，构建离线分析和即时查询大数据分析平台。