MapReduce Single-Table Association learning ~

The first consideration is the self-connection of the table, followed by the setting of the column, and finally the result collation.

File contents:

Importorg.apache.hadoop.conf.Configuration;Importorg.apache.hadoop.conf.Configured;ImportOrg.apache.hadoop.fs.Path;Importorg.apache.hadoop.io.IntWritable;ImportOrg.apache.hadoop.io.Text;ImportOrg.apache.hadoop.mapreduce.Job;ImportOrg.apache.hadoop.mapreduce.Mapper;ImportOrg.apache.hadoop.mapreduce.Reducer;ImportOrg.apache.hadoop.mapreduce.lib.input.FileInputFormat;ImportOrg.apache.hadoop.mapreduce.lib.input.TextInputFormat;ImportOrg.apache.hadoop.mapreduce.lib.output.FileOutputFormat;ImportOrg.apache.hadoop.util.Tool;ImportOrg.apache.hadoop.util.ToolRunner;Importjava.io.IOException;ImportJava.util.Iterator;Importjava.util.Objects; Public classStjoinextendsConfiguredImplementsTool { Public Static intTime = 0; Map splits the input into child and parent, and then the positive sequence output is once as the right table, and the reverse output is once as the left table
It is important to note that the left and right table difference flags must be added to the output value
     Public Static classMapextendsMapper<object,text,text,text>{         Public voidMap (Object key,text value,context Context)throwsIOException, interruptedexception{String childname=NewString (); String ParentName=NewString (); String Relationtype=NewString (); String Line=value.tostring (); inti = 0;
Files are separated by spaces while(Line.charat (i)! = ") {i++; }
Split child and parent string[] values= {line.substring (0,i), line.substring (i+1)}; if(Values[0].compareto ("child")! = 0) {ChildName= Values[0]; ParentName= Values[1];
Left and right table distinguishing mark Relationtype= "1"; Context.write (NewText (Values[1]),NewText (Relationtype + "+" + childname + "+" +parentname)); Relationtype= "2"; Context.write (NewText (Values[0]),NewText (Relationtype + "+" + childname + "+" +parentname)); }        }    }     Public Static classReduceextendsReducer<text,text,text,text>{         Public voidReduce (Text key,iterable<text> values,context Context)throwsioexception,interruptedexception{
Output table Headerif(Time = = 0) {Context.write (NewText ("grandchild"),NewText ("Grandparent")); time++; }            intGrandchildnum = 0; String grandchild[]=NewString[10]; intGrandparentnum = 0; String grandparent[]=NewString[10]; Iterator ite=Values.iterator ();  while(Ite.hasnext ()) {String record=Ite.next (). toString (); intLen =record.length (); inti = 2; if(len = = 0){                    Continue; }                CharRelationtype = Record.charat (0); String ChildName=NewString (); String ParentName=NewString ();  while(Record.charat (i)! = ' + ') {ChildName= ChildName +Record.charat (i); I++; } I= I+1;  while(i<Len) {ParentName= ParentName +Record.charat (i); I++; }                if(Relationtype = = ' 1 ') {Grandchild[grandchildnum]=ChildName;                    ; Grandchildnum++; }Else{Grandparent[grandparentnum]=ParentName; Grandparentnum++; }            }            if(Grandparentnum! = 0 && Grandchildnum! = 0){                     for(intm = 0;m<grandchildnum;m++){                         for(intn = 0;n<grandparentnum;n++) {System.out.println (Grandchild[m]+ "  " +Grandparent[n]); Context.write (NewText (Grandchild[m]),NewText (Grandparent[n])); }                    }            }        }    }     Public  intRun (string[] args)throwsexception{Configuration AAA=NewConfiguration (); Job Job=job.getinstance (AAA); String inputpaths= "/usr/local/idea-ic-139.1117.1/hadoop/out/datainput/child-parent.txt"; String OutputPath= "/usr/local/idea-ic-139.1117.1/hadoop/out/dataout/"; Job.setjarbyclass (Sort.class); Job.setjobname ("Sort"); Job.setmapperclass (Map.class); Job.setreducerclass (Reduce.class); Fileinputformat.setinputpaths (Job,NewPath (inputpaths)); Fileoutputformat.setoutputpath (Job,NewPath (OutputPath)); Job.setoutputkeyclass (Text.class); Job.setoutputvalueclass (Text.class); Job.setinputformatclass (Textinputformat.class); Job.setoutputformatclass (Org.apache.hadoop.mapreduce.lib.output.TextOutputFormat.class); BooleanSuccess = Job.waitforcompletion (true); returnSuccess? 0:1; }     Public Static voidMain (string[] args)throwsexception{intret = Toolrunner.run (Newstjoin (), args);    System.exit (ret); }}

Output Result:

Reference: "Hadoop combat"

MapReduce Single-Table Association learning ~