设为首页 收藏本站
查看: 715|回复: 0

[经验分享] Hadoop Netflix数据统计分析1(转)

[复制链接]

尚未签到

发表于 2015-7-14 07:45:27 | 显示全部楼层 |阅读模式
DSC0000.jpg
DSC0001.jpg
  1map阶段
  输入:MovieID,UserID,Rating,Date
  输出:
  import java.io.*;
  import java.util.*;
  import org.apache.hadoop.io.LongWritable;
  import org.apache.hadoop.io.Text;
  import org.apache.hadoop.mapred.*;
  public class MyMapper {
  public static class MapClass extends MapReduceBase
  implements Mapper {
  private Text word = new Text();
  public void map(LongWritable key, Text value,
  OutputCollector output,
  Reporter reporter) throws IOException {
  //将Text value 转化为string
  String line = value.toString();
  //每行的电影评分数据 "movieID,userID,rating,date"
  //字段之间用 ","分隔
  StringTokenizer itr = new StringTokenizer(line, ",");
  String name = itr.nextToken();
  //设置 movieID作为 Key
  word.set(name);
  // ratingAndDate 保存每部电影的 rating and date
  String ratingAndDate = "";
  //跳过 userID
  itr.nextToken();
  ratingAndDate = itr.nextToken();
  ratingAndDate += "," + itr.nextToken();
  //输出 到reducer
  output.collect(word, new Text(ratingAndDate));
  }
  }
  }
  2reduce阶段
  import java.io.IOException;
  import java.io.BufferedReader;
  import java.io.FileReader;
  import java.util.HashMap;
  import java.util.Iterator;
  import java.util.StringTokenizer;
  import org.apache.hadoop.filecache.DistributedCache;
  import org.apache.hadoop.io.Text;
  import org.apache.hadoop.mapred.MapReduceBase;
  import org.apache.hadoop.mapred.OutputCollector;
  import org.apache.hadoop.mapred.Reducer;
  import org.apache.hadoop.mapred.Reporter;
  import org.apache.hadoop.mapred.JobConf;
  import org.apache.hadoop.fs.Path;
  import org.apache.hadoop.util.StringUtils;
  //Reducer格式
  //
  public class MyReducer{
  public static class Reduce extends MapReduceBase
  implements Reducer {
  // Distributed Cache分布式缓存中文件路径
  Path[] localFiles = new Path[0];
  //HashMap movieTitles 保存 movie_titles.txt中电影信息
  HashMap movieTitles = new HashMap();
  public void configure(JobConf job) {
  if(job.getBoolean("netflixDriver.distributedCacheFile", false)) {
  //获取分布式缓存文件的路径
  try {
  localFiles = DistributedCache.getLocalCacheFiles(job);
  }
  catch (IOException ioe) {
  System.err.println("Caught exception while getting cached files " + StringUtils.stringifyException(ioe));
  }
  //如果分布式缓存中已有文件
  if(localFiles[0].toString() != null) {
  try {
  // movie_titles.txt作为分布式缓存中文件
  BufferedReader reader = new BufferedReader(new FileReader(localFiles[0].toString()));
  //保存缓存文件中的行
  String cachedLine = "";
  while ((cachedLine = reader.readLine()) != null) {
  StringTokenizer cachedIterator = new StringTokenizer(cachedLine, ",");
  //获取movie_id
  String movieID = cachedIterator.nextToken();
  //获取该行剩下的内容
  String dateAndTitle = cachedIterator.nextToken();
  while(cachedIterator.hasMoreTokens())
  {
  dateAndTitle += "," + cachedIterator.nextToken();
  }
  movieTitles.put(movieID, dateAndTitle);
  }
  } catch (IOException ioe) {
  System.err.println("Caught Exception while parsing the cached file " + StringUtils.stringifyException(ioe));
  }
  }
  }
  }
  public void reduce(Text key, Iterator values,
  OutputCollector output,
  Reporter reporter) throws IOException {
  int firstDate = 0;
  int lastDate = 0;
  double rating = 0.0;
  int ratingCount = 0;
  String line;
  String dateStr = "";
  while(values.hasNext()) {
  line = values.next().toString();
  StringTokenizer itr = new StringTokenizer(line, ",");
  rating += Integer.parseInt(itr.nextToken());
  dateStr = itr.nextToken();
  dateStr = dateStr.replaceAll("-","");
  if(firstDate == 0) {
  firstDate = Integer.parseInt(dateStr);
  lastDate = firstDate;
  ratingCount++;
  }
  if(Integer.parseInt(dateStr) > lastDate) {
  lastDate = Integer.parseInt(dateStr);
  }
  if(Integer.parseInt(dateStr) < firstDate) {
  firstDate = Integer.parseInt(dateStr);
  }
  ratingCount++;
  }
  String movieInfo = movieTitles.get(key.toString());
  StringTokenizer tokenizer = new StringTokenizer(movieInfo, ",");
  String prodDate = tokenizer.nextToken();
  String movieTitle = tokenizer.nextToken();
  while(tokenizer.hasMoreTokens())
  {
  movieTitle += "," + tokenizer.nextToken();
  }
  //计算每部电影的平均评分
  rating = rating/ratingCount;
  String dateRange = Integer.toString(firstDate) + "," + Integer.toString(lastDate);
  dateRange += "," + prodDate;
  dateRange += "," + ratingCount;
  dateRange += "," + rating;
  dateRange += "," + movieTitle;
  Text dateRangeText = new Text(dateRange);
  //输出
  output.collect(key, dateRangeText);
  }
  }
  }
  3主程序
  import java.io.IOException;
  import java.util.ArrayList;
  import java.util.List;
  import com.taobao.MyMapper;
  import com.taobao.MyReducer;
  import org.apache.hadoop.conf.Configuration;
  import org.apache.hadoop.conf.Configured;
  import org.apache.hadoop.fs.Path;
  import org.apache.hadoop.io.Text;
  import org.apache.hadoop.mapred.FileInputFormat;
  import org.apache.hadoop.mapred.FileOutputFormat;
  import org.apache.hadoop.mapred.JobClient;
  import org.apache.hadoop.mapred.JobConf;
  import org.apache.hadoop.util.Tool;
  import org.apache.hadoop.util.ToolRunner;
  import org.apache.hadoop.filecache.DistributedCache;
  public class netflixDriver extends Configured implements Tool {
  static int printUsage() {
  System.out.println("netflixDriver [-m ] [-r ]  ");
  ToolRunner.printGenericCommandUsage(System.out);
  return -1;
  }
  public int run(String[] args) throws Exception {
  JobConf conf = new JobConf(getConf(), MyMapper.class);
  conf.setJobName("netflixDriver");
  conf.setOutputKeyClass(Text.class);
  conf.setOutputValueClass(Text.class);
  conf.setMapperClass(MyMapper.MapClass.class);
  conf.setReducerClass(MyReducer.Reduce.class);
  List other_args = new ArrayList();
  for(int i=0; i < args.length; ++i) {
  try {
  if ("-m".equals(args)) {
  conf.setNumMapTasks(Integer.parseInt(args[++i]));
  } else if ("-r".equals(args)) {
  conf.setNumReduceTasks(Integer.parseInt(args[++i]));
  } else if ("-d".equals(args)) {
  DistributedCache.addCacheFile(new Path(args[++i]).toUri(), conf);
  conf.setBoolean("netflixDriver.distributedCacheFile", true);
  } else {
  other_args.add(args);
  }
  } catch (NumberFormatException except) {
  System.out.println("ERROR: Integer expected instead of " + args);
  return printUsage();
  } catch (ArrayIndexOutOfBoundsException except) {
  System.out.println("ERROR: Required parameter missing from " +
  args[i-1]);
  return printUsage();
  }
  }
  if (other_args.size() != 2) {
  System.out.println("ERROR: Wrong number of parameters: " +
  other_args.size() + " instead of 2.");
  return printUsage();
  }
  FileInputFormat.setInputPaths(conf, other_args.get(0));
  FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));
  JobClient.runJob(conf);
  return 0;
  }
  public static void main(String[] args) throws Exception {
  int res = ToolRunner.run(new Configuration(), new netflixDriver(), args);
  System.exit(res);
  }
  }

运维网声明 1、欢迎大家加入本站运维交流群:群②:261659950 群⑤:202807635 群⑦870801961 群⑧679858003
2、本站所有主题由该帖子作者发表,该帖子作者与运维网享有帖子相关版权
3、所有作品的著作权均归原作者享有,请您和我们一样尊重他人的著作权等合法权益。如果您对作品感到满意,请购买正版
4、禁止制作、复制、发布和传播具有反动、淫秽、色情、暴力、凶杀等内容的信息,一经发现立即删除。若您因此触犯法律,一切后果自负,我们对此不承担任何责任
5、所有资源均系网友上传或者通过网络收集,我们仅提供一个展示、介绍、观摩学习的平台,我们不对其内容的准确性、可靠性、正当性、安全性、合法性等负责,亦不承担任何法律责任
6、所有作品仅供您个人学习、研究或欣赏,不得用于商业或者其他用途,否则,一切后果均由您自己承担,我们对此不承担任何法律责任
7、如涉及侵犯版权等问题,请您及时通知我们,我们将立即采取措施予以解决
8、联系人Email:admin@iyunv.com 网址:www.yunweiku.com

所有资源均系网友上传或者通过网络收集,我们仅提供一个展示、介绍、观摩学习的平台,我们不对其承担任何法律责任,如涉及侵犯版权等问题,请您及时通知我们,我们将立即处理,联系人Email:kefu@iyunv.com,QQ:1061981298 本贴地址:https://www.yunweiku.com/thread-86347-1-1.html 上篇帖子: 错误 :(hadoop)could only be replicated to 0 nodes, instead of 1 下篇帖子: hadoop配置错误
您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

扫码加入运维网微信交流群X

扫码加入运维网微信交流群

扫描二维码加入运维网微信交流群,最新一手资源尽在官方微信交流群!快快加入我们吧...

扫描微信二维码查看详情

客服E-mail:kefu@iyunv.com 客服QQ:1061981298


QQ群⑦:运维网交流群⑦ QQ群⑧:运维网交流群⑧ k8s群:运维网kubernetes交流群


提醒:禁止发布任何违反国家法律、法规的言论与图片等内容;本站内容均来自个人观点与网络等信息,非本站认同之观点.


本站大部分资源是网友从网上搜集分享而来,其版权均归原作者及其网站所有,我们尊重他人的合法权益,如有内容侵犯您的合法权益,请及时与我们联系进行核实删除!



合作伙伴: 青云cloud

快速回复 返回顶部 返回列表