一、數據準備
1、每天生成隨機一個文本，每小時向文本中追加2次數據，每次10萬條
隨機數據生成：
2,32? * * * *? bash /mnt/jediael/irms/signalGenerator/signalGenerator.sh >> /home/jediael/sg.log 2>&1
類：SignalGenerator

2、每天將前一天生成的數據文本導入HDFS
32 0 * * * bash /mnt/jediael/irms/signalGenerator/copySignalToHdfs.sh >>/home/jediael/sg.log 2>&1


二、數據分析
1、每天執行一次數據分析，將結果輸出到hdfs文本中。
42 0 * * * bash /mnt/jediael/irms/signalparser/signalParser.sh >>/home/jediael/sg.log 2>&1
類：SignalParser

程序文件：

/mnt/jediael/irms/signalGenerator/signalGenerator.sh

#!/bin/bash export JAVA_HOME=/usr/java/jdk1.7.0_51 export PATH=$JAVA_HOME/bin:$PATH export CLASSPATH=$CLASSPATH:/mnt/jediael/irms/signalGenerator/ java SignalGenerator

/mnt/jediael/irms/signalGenerator/copySignalToHdfs.sh

#!/bin/bash export JAVA_HOME=/usr/java/jdk1.7.0_51 PATH=/mnt/jediael/hadoop-1.2.1/bin/:/mnt/jediael/hbase-0.94.26/bin:/mnt/jediael/tomcat-7.0.54/bin:$JAVA_HOME/bin:$PATH hadoop fs -copyFromLocal /mnt/jediael/irms/signalGenerator/`date -d "-1 day" +%Y%m%d`.txt /irms/signal >> sg.log
/mnt/jediael/irms/signalparser/signalParser.sh

#!/bin/bashexport JAVA_HOME=/usr/java/jdk1.7.0_51 PATH=/mnt/jediael/hadoop-1.2.1/bin/:/mnt/jediael/hbase-0.94.26/bin:/mnt/jediael/tomcat-7.0.54/bin:$JAVA_HOME/bin:$PATH hadoop jar signalgenerator.jar /irms/signal/`date -d "-1 day" +%Y%m%d`.txt /irms/result/`date -d "-1 day" +%Y%m%d`

SignalGenerator.java

package com.gmcc.irms.util;import java.io.FileOutputStream; import java.io.IOException; import java.io.OutputStream; import java.text.SimpleDateFormat; import java.util.Random;//此類用于模擬生成信令數據,每次生成100000條public class SignalGenerator {// 業務類型，如呼入、呼出、發短信、收短信、上網、WLAN等private int activeType = 0;private String getNextSign() {String sign = "";Random rand = new Random();activeType = rand.nextInt(6);// 主叫號碼String callNum = "1390222" + rand.nextInt(9) + rand.nextInt(9)+ rand.nextInt(9) + rand.nextInt(9);// 被叫號碼String beCallNum = "1390222" + rand.nextInt(9) + rand.nextInt(9)+ rand.nextInt(9) + rand.nextInt(9);// 時長、或者是流量String callDuration = "";for (int i = 0; i < 16; i++) {callDuration += rand.nextInt(9);}sign = activeType + callNum + beCallNum + callDuration;for (int i = 0; i < 800; i++) {sign += rand.nextInt(9);}return sign;}public static void main(String[] args) throws IOException {SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMdd");long time = System.currentTimeMillis();String fileName = sdf.format(time) + ".txt";OutputStream os = new FileOutputStream(fileName, true);SignalGenerator sg = new SignalGenerator();String newline = System.getProperty("line.separator");for (int i = 0; i < 100000; i++) {os.write((sg.getNextSign() + newline).getBytes());}os.flush();os.close();}}

SignalParser.java

package com.gmcc.irms.signal;import java.io.IOException;import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.LongWritable; 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;public class SignalParser {public static void main(String[] args) throws Exception {Job job = new Job();job.setJarByClass(SignalParser.class);job.setJobName("signal parser");FileInputFormat.addInputPath(job, new Path(args[0]));FileOutputFormat.setOutputPath(job, new Path(args[1]));job.setMapperClass(SignalParserMapper.class);job.setReducerClass(SignalParserReducer.class);job.setOutputKeyClass(Text.class);job.setOutputValueClass(Text.class);System.exit(job.waitForCompletion(true) ? 0 : 1);} }class SignalParserMapper extends Mapper<LongWritable, Text, Text, Text> {@Overridepublic void map(LongWritable key, Text value, Context context)throws IOException, InterruptedException {String line = value.toString();// 業務類型String activeType = line.substring(0, 1);// 主叫電話號碼String customer = line.substring(1, 12);// 通話時長、web時長、wlan時長int duration = Integer.parseInt(line.substring(23, 30));context.write(new Text(customer),new Text(activeType + "," + duration));} }class SignalParserReducer extends Reducer<Text, Text, Text, Text> {@Overridepublic void reduce(Text key, Iterable<Text> values, Context context)throws IOException, InterruptedException {//總通話時長int sumCallDuration = 0;//通話次數int callTimes = 0;//發送短信次數int smsTimes = 0;//上網總時長int sumWebDuration = 0;//上網次數int webTimes = 0;//WLAN總時長int sumWlanDuration = 0;//WLAN次數int wlanTimes = 0;String[] valueArray = null;int activeType = -1;int duration = -1;for (Text value:values){valueArray = value.toString().split(",");System.out.println(valueArray[0]+" a "+valueArray[1]);activeType = Integer.parseInt(valueArray[0]);duration = Integer.parseInt(valueArray[1]);if(activeType == 0){//呼出sumCallDuration += duration;callTimes++;}else if(activeType == 2){//發smssmsTimes++;}else if(activeType == 4){//上網sumWebDuration += duration;webTimes ++;}else if(activeType == 5){//WLANsumWlanDuration += duration;wlanTimes ++;}else{}}context.write(key, new Text(sumCallDuration + "\t" + callTimes + "\t" +smsTimes+"\t" + sumWebDuration+"\t" + webTimes+"\t" + sumWebDuration+"\t" + webTimes));} }

總結

以上是生活随笔為你收集整理的irms模拟数据生成及数据分析的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。