{"id":65,"date":"2013-12-13T09:43:36","date_gmt":"2013-12-13T01:43:36","guid":{"rendered":"http:\/\/www.lixiaodong.com\/?p=65"},"modified":"2014-02-03T07:42:39","modified_gmt":"2014-02-02T23:42:39","slug":"mapreduce%e5%a4%84%e7%90%86%e7%a4%be%e4%ba%a4%e5%85%b3%e7%b3%bb%e7%9a%84%e4%b8%80%e9%81%93%e9%97%ae%e9%a2%98","status":"publish","type":"post","link":"https:\/\/www.lixiaodong.com\/?p=65","title":{"rendered":"MapReduce\u5904\u7406\u793e\u4ea4\u5173\u7cfb\u7684\u4e00\u9053\u95ee\u9898"},"content":{"rendered":"<p>\u7ed9\u5b9a\u4e00\u4e2a\u793e\u4ea4\u5173\u7cfb\uff08A,B\uff09\uff0cA\u548cB\u5206\u522b\u4ee3\u88682\u4e2a\u4eba\u7684id\u6216\u540d\u5b57\uff08\u5982\u679c\u662f\u540d\u5b57\uff0c\u8981\u6c42\u540d\u5b57\u4e0d\u80fd\u6709\u91cd\u590d\uff09\u3002\u8981\u6c42\u53ea\u4f7f\u7528\u4e00\u6b21MapReduce\uff0c\u8fc7\u6ee4\u6389\u91cc\u9762\u7684\u53cc\u5411\u5173\u7cfb\uff0c\u53ea\u4fdd\u7559\u5355\u5411\u5173\u7cfb\u3002\u6bd4\u5982\u73b0\u5728\u8fd9\u4e2a\u5173\u7cfb\u91cc\u5305\u542b\u5982\u4e0b\u5185\u5bb9\uff1a<\/p>\n<p>\uff08\u5f20\u4e09\uff0c\u674e\u56db\uff09<\/p>\n<p>\uff08\u5f20\u4e09\uff0c\u738b\u4e94\uff09<\/p>\n<p>\uff08\u5f20\u4e09\uff0c\u8d75\u516d\uff09<\/p>\n<p>\uff08\u674e\u56db\uff0c\u5f20\u4e09\uff09<\/p>\n<p>\u91cc\u9762\u7684\u7b2c1\u6761\u548c\u7b2c4\u6761\u6784\u6210\u4e86\u53cc\u5411\u5173\u7cfb\uff0c\u8981\u8fc7\u6ee4\u6389\uff0c\u5269\u4e0b\u7b2c2\u548c\u7b2c3\u6761\u3002<\/p>\n<p>\u601d\u8def1\uff1a\u5bf9\u6bcf\u4e00\u6761\u5173\u7cfb(A, B)\uff0c\u5728map\u9636\u6bb5\u751f\u6210(A, B) \u548c(B, A) \u3002\u5982\u679cA\u548cB\u662f\u53cc\u5411\u7684\uff0c\u4f1a\u751f\u62104\u6761\u8bb0\u5f55\uff0c\u5206\u522b\u662f\uff08A, B), \u00a0(B, A),\u00a0(B, A), (A,B)\u3002<\/p>\n<p>\u5728reduce\u9636\u6bb5\uff0c\u6211\u4eec\u53d1\u73b0key A\u5bf9\u5e94\u7684values\u91cc\uff0cB\u67092\u6761\u3002\u6211\u4eec\u77e5\u9053\u8fd9\u662f\u7531\u53cc\u5411\u5173\u7cfb\u4ea7\u751f\u7684\uff0c\u6211\u4eec\u4e0d\u5e94\u8be5\u6709\u4efb\u4f55\u8f93\u51fa\u3002\u6211\u4eec\u53ea\u8f93\u51fa\u5728values\u91cc\u53ea\u67091\u4e2a\u7684\u3002\u5047\u5982C\u5728values\u91cc\u53ea\u67091\u4e2a\u3002\u5219reduce\u9636\u6bb5\uff0c\u6211\u4eec\u8f93\u51fa(A,C)\u3002<\/p>\n<p>\u5e26\u6765\u7684\u95ee\u9898\uff1a\u4ee5\u4e0a\u7684\u529e\u6cd5\u80fd\u8fc7\u6ee4\u6389\u53cc\u5411\u5173\u7cfb\uff0c\u4f46\u662f\u4f1a\u8f93\u51fa\u591a\u4f59\u7684\u5185\u5bb9\u3002\u6bd4\u5982\u4e00\u4e2a\u5355\u9879\u5173\u7cfb (A, B)\u3002\u6309\u7167\u4ee5\u4e0a\u65b9\u6cd5\uff0c reduce\u9636\u6bb5\u6700\u540e\u4f1a\u8f93\u51fa(A,B)\u548c(B,A)\u3002\u5b9e\u9645\u4e0a\u4e0d\u5e94\u8be5\u8f93\u51fa(B, A)\u3002\u8fd9\u4e2a(B,A)\u662f\u6211\u4eec\u4eba\u4e3a\u52a0\u8fdb\u53bb\u7684\u3002<\/p>\n<p>\u601d\u8def2\uff1a\u5728\u601d\u8def1\u7684\u57fa\u7840\u4e0a\uff0cmap \u9636\u6bb5\u52a0\u5165\u6807\u8bb0\u3002\u5bf9\u6bcf\u4e00\u6761\u5173\u7cfb(A, B)\uff0c\u5728map\u9636\u6bb5\u751f\u6210(A, B|1) \u548c(B, A|0)\u30021\u4ee3\u8868\u771f\u5b9e\u5b58\u5728\u7684\u5173\u7cfb\uff0c0\u4ee3\u8868\u4e3a\u4e86\u89e3\u51b3\u95ee\u9898\u52a0\u5165\u7684\u865a\u6784\u5173\u7cfb\u3002\u5728reduce\u9636\u6bb5\uff0c\u6211\u4eec\u6309\u7167\u601d\u8def1\u8fc7\u6ee4\u6389\u67092\u4e2a\u503c\u7684\uff0c\u7136\u540e\u770b\u6807\u8bb0\u662f\u4e0d\u662f1\uff0c\u5982\u679c\u662f1\u5219\u8f93\u51fa\uff1b\u5982\u679c\u662f0\uff0c\u4e0d\u8f93\u51fa\u3002<\/p>\n<p>Hadoop MapReduce\u4ee3\u7801\u5982\u4e0b\uff1a<br \/>\n[code lang=&#8221;java&#8221;]<br \/>\nimport java.io.IOException;<\/p>\n<p>import org.apache.hadoop.io.LongWritable;<br \/>\nimport org.apache.hadoop.io.Text;<br \/>\nimport org.apache.hadoop.mapred.MapReduceBase;<br \/>\nimport org.apache.hadoop.mapred.Mapper;<br \/>\nimport org.apache.hadoop.mapred.OutputCollector;<br \/>\nimport org.apache.hadoop.mapred.Reporter;<\/p>\n<p>public class SingleRelationshipMapper extends MapReduceBase implements<br \/>\nMapper&lt;LongWritable, Text, Text, Text&gt;{<\/p>\n<p>    @Override<br \/>\n    public void map(LongWritable key, Text value, OutputCollector&lt;Text, Text&gt; output, Reporter arg3)<br \/>\n        throws IOException {<br \/>\n        String line = value.toString();<br \/>\n        String[] names = line.split(&quot; &quot;);<br \/>\n        Text text1 = new Text(names[0]);<br \/>\n        Text text2 = new Text(names[1]);<br \/>\n        output.collect(new Text(text1), new Text(text2+&quot;|1&quot;)); \/\/1\u4ee3\u8868\u771f\u5b9e\u5173\u7cfb<br \/>\n        output.collect(new Text(text2), new Text(text1+&quot;|0&quot;)); \/\/0\u4ee3\u8868\u865a\u6784\u5173\u7cfb<br \/>\n    }<br \/>\n}<br \/>\n[\/code]<\/p>\n<p>[code lang=&#8221;java&#8221;]<\/p>\n<p>import java.io.IOException;<br \/>\nimport java.util.ArrayList;<br \/>\nimport java.util.Iterator;<br \/>\nimport java.util.List;<\/p>\n<p>import org.apache.hadoop.io.Text;<br \/>\nimport org.apache.hadoop.mapred.MapReduceBase;<br \/>\nimport org.apache.hadoop.mapred.OutputCollector;<br \/>\nimport org.apache.hadoop.mapred.Reducer;<br \/>\nimport org.apache.hadoop.mapred.Reporter;<\/p>\n<p>public class SingleRelationshipReducer extends MapReduceBase implements<br \/>\n    Reducer&lt;Text, Text, Text, Text&gt;{<\/p>\n<p>    @Override<br \/>\n    public void reduce(Text key, Iterator&lt;Text&gt; values, OutputCollector&lt;Text, Text&gt; output, Reporter arg3) throws IOException {<br \/>\n        List&lt;String&gt; list = new ArrayList&lt;String&gt;();<br \/>\n        while (values.hasNext()) {<br \/>\n            list.add(values.next().toString());<br \/>\n       }<br \/>\n       for(String item:list){<br \/>\n           String[] array = item.split(&quot;\\\\|&quot;);<br \/>\n           if(onlyOne(array[0], list)){<br \/>\n               if(array[1].equals(&quot;1&quot;)){<br \/>\n                   output.collect(key, new Text(array[0]));<br \/>\n               }<br \/>\n           }<br \/>\n       }<br \/>\n    }<\/p>\n<p>    private boolean onlyOne(String str, List&lt;String&gt; list){<br \/>\n        int count=0;<br \/>\n        for(String item: list){<br \/>\n            String array[] = item.split(&quot;\\\\|&quot;);<br \/>\n            if(array[0].equals(str)){<br \/>\n                count++;<br \/>\n            }<br \/>\n        }<br \/>\n        return count==1;<br \/>\n     }<br \/>\n}<br \/>\n[\/code]<\/p>\n<p>[code lang=&#8221;java&#8221;]<br \/>\nimport org.apache.hadoop.conf.Configured;<br \/>\nimport org.apache.hadoop.fs.Path;<br \/>\nimport org.apache.hadoop.io.Text;<br \/>\nimport org.apache.hadoop.mapred.FileInputFormat;<br \/>\nimport org.apache.hadoop.mapred.FileOutputFormat;<br \/>\nimport org.apache.hadoop.mapred.JobClient;<br \/>\nimport org.apache.hadoop.mapred.JobConf;<br \/>\nimport org.apache.hadoop.util.Tool;<br \/>\nimport org.apache.hadoop.util.ToolRunner;<\/p>\n<p>public class SingleRelationshipDriver extends Configured implements Tool{<\/p>\n<p>    \/**<br \/>\n    * @param args<br \/>\n    * @throws Exception<br \/>\n    *\/<br \/>\n    public static void main(String[] args) throws Exception {<br \/>\n        int exitCode = ToolRunner.run(new SingleRelationshipDriver(), args);<br \/>\n        System.exit(exitCode);<br \/>\n    }<\/p>\n<p>    @Override<br \/>\n    public int run(String[] arg) throws Exception {<\/p>\n<p>        JobConf conf = new JobConf();<br \/>\n        conf.setJobName(&quot;singleRelation&quot;);<br \/>\n        conf.setJarByClass(SingleRelationshipDriver.class);<br \/>\n        conf.setMapperClass(SingleRelationshipMapper.class);<br \/>\n        conf.setReducerClass(SingleRelationshipReducer.class);<br \/>\n        conf.setOutputKeyClass(Text.class);<br \/>\n        conf.setOutputValueClass(Text.class);<br \/>\n        FileInputFormat.addInputPaths(conf, arg[0]);<br \/>\n        FileOutputFormat.setOutputPath(conf, new Path(arg[1]));<br \/>\n        JobClient.runJob(conf);<br \/>\n        return 0;<br \/>\n    }<\/p>\n<p>}<\/p>\n<p>[\/code]<\/p>\n<p>\u8f93\u5165\uff1a<\/p>\n<p>John Tom<br \/>\nJohn Amily<br \/>\nJohn\u00a0George<br \/>\nAmily John<\/p>\n<p>\u8f93\u51fa\uff1a<\/p>\n<p>John Tom<br \/>\nJohn\u00a0George<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u7ed9\u5b9a\u4e00\u4e2a\u793e\u4ea4\u5173\u7cfb\uff08A,B\uff09\uff0cA\u548cB\u5206\u522b\u4ee3\u88682\u4e2a\u4eba\u7684id\u6216\u540d\u5b57\uff08\u5982\u679c\u662f\u540d\u5b57\uff0c\u8981\u6c42\u540d\u5b57\u4e0d\u80fd\u6709\u91cd\u590d\uff09\u3002\u8981\u6c42\u53ea\u4f7f\u7528\u4e00\u6b21 [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[21],"tags":[22,47,23],"class_list":["post-65","post","type-post","status-publish","format-standard","hentry","category-mapreduce","tag-hadoop","tag-mapreduce","tag-23"],"_links":{"self":[{"href":"https:\/\/www.lixiaodong.com\/index.php?rest_route=\/wp\/v2\/posts\/65","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.lixiaodong.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.lixiaodong.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.lixiaodong.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.lixiaodong.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=65"}],"version-history":[{"count":7,"href":"https:\/\/www.lixiaodong.com\/index.php?rest_route=\/wp\/v2\/posts\/65\/revisions"}],"predecessor-version":[{"id":136,"href":"https:\/\/www.lixiaodong.com\/index.php?rest_route=\/wp\/v2\/posts\/65\/revisions\/136"}],"wp:attachment":[{"href":"https:\/\/www.lixiaodong.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=65"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.lixiaodong.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=65"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.lixiaodong.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=65"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}