Hadoop-02 基於Hadoop的JavaEE數據可視化簡易案例

需求

1.統計音樂點播次數

2.使用echarts柱狀圖顯示每首音樂的點播次數

 

項目結構

創建JavaEE項目

 

統計播放次數Job關鍵代碼

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;

/** 歌曲點播統計 */
public class MusicCount {

	//定義保存統計數據結果的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將輸入 文本行轉換為字符串
			String keyOut = keyInStrArr[0];// 獲取歌曲名稱
			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);//統計數據保存到hdfs文件
			map.put(key.toString(), sum);//將統計結果保存到map集合
		}
	}

	
	public static HashMap<String, Integer> main() throws Exception {
		Configuration conf = new Configuration();
		conf.addResource("core-site.xml");// 讀取項目中hdfs配置信息
		conf.addResource("mapred-site.xml");// 讀取項目中mapreduce配置信息		
		// 實例化作業
		Job job = Job.getInstance(conf, "music_count");
		// 指定jar的class
		job.setJarByClass(MusicCount.class);
		// 指定Mapper
		job.setMapperClass(MusicMapper.class);
		// 壓縮數據
		job.setCombinerClass(MusicReducer.class);// 減少datanode，TaskTracker之間數據傳輸
		// 指定reducer
		job.setReducerClass(MusicReducer.class);
		// 設置輸出key數據類型
		job.setOutputKeyClass(Text.class);
		// 設置輸出Value數據類型
		job.setOutputValueClass(IntWritable.class);
		// 設置輸入文件路徑
		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"));		
		//設置輸出文件路徑
		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關鍵代碼

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;

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

	protected void doGet(HttpServletRequest request, HttpServletResponse response)
			throws ServletException, IOException {
		//post亂碼處理	
		request.setCharacterEncoding("utf-8");	
		// 設置響應數據類型
		response.setContentType("text/html");
		// 設置響應編碼格式
		response.setCharacterEncoding("utf-8");
		// 獲取out對象
		PrintWriter out = response.getWriter();		
		//組織json數據
		HashMap<String, Integer> map=null;
		
		try {
			map=MusicCount.main();
		} catch (Exception e) {
			System.out.println("獲取數據出錯");
		}
		
		//通過構建map集合轉換為嵌套json格式數據
		HashMap jsonmap = new HashMap();
		jsonmap.put("mytitle","歌詞播放統計");
		jsonmap.put("mylegend", "點播");
		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);
	}

}

　　

視圖index.jsp關鍵代碼

<%@ 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>金融大數據解析</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>
	<!-- 為ECharts准備一個具備大小（寬高）的Dom -->
	<div id="main" style="width: 600px; height: 400px;"></div>

	<script type="text/javascript">
		//顯示柱狀圖函數
		function showdata(mytitle, mylegend, xdata, ydata) {
			// 基於准備好的dom，初始化echarts實例
			var myChart = echarts.init(document.getElementById('main'));
			// 指定圖表的配置項和數據
			var option = {
				title : {
					text : mytitle
				},
				tooltip : {},
				legend : {
					data : mylegend
				},
				xAxis : {
					data : xdata
				},
				yAxis : {},
				series : [ {
					name : '點播',
					type : 'bar',
					data : ydata
				} ]
			};
			// 使用剛指定的配置項和數據顯示圖表。
			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;
				//獲取x軸數據
				$.each(data.prolist, function(i, n) {
					xdata.push(i);
				});
				//獲取y軸數據
				$.each(data.prolist, function(i, n) {
					ydata.push(n);
				});
				
				//執行函數
				showdata(mytitle, [ mylegend ], xdata, ydata);
			});
	
		});
	</script>
</body>

</html>

　　

運行結果

 

項目所需jar列表

 

總結

1.該案例的缺點是什么？每次訪問數據需要提交job到hadoop集群運行，性能低。

2.數據分析結果保存在HDFS和集合中，不適合分析結果為大數據集合。

3.如何改進？使用HBase存儲解析后的數據集，構建離線分析和即時查詢大數據分析平台。