Mahout Series: Minhash cluster

 map:vector featurevector = Features.get ();
    if (Featurevector.size () < minvectorsize) {return; }//Initialize the Minhash values to highest for (int i = 0; i < numhashfunctions; i++) {minhashvalues[
    I] = Integer.max_value;
        for (int i = 0; i < numhashfunctions i++) {for (vector.element ele:featureVector.nonZeroes ()) { int value = HashValue?
        (int) Ele.get (): Ele.index ();
        Bytestohash[0] = (byte) (value >> 24);
        BYTESTOHASH[1] = (byte) (value >> 16);
        BYTESTOHASH[2] = (byte) (value >> 8);
        BYTESTOHASH[3] = (byte) value;
        int hashindex = Hashfunction[i].hash (Bytestohash);
          If we are new hash value is less than the "old one," replace the old one if (Minhashvalues[i] > Hashindex) {
        Minhashvalues[i] = Hashindex; }}//output the cluster information for (int i = 0; i < numhashfunctions; i++) {StRingbuilder Clusteridbuilder = new StringBuilder (); for (int j = 0; J < keygroups J + +) {clusteridbuilder.append (minhashvalues[(i + j)% numhashfunctions]). Append
      ('-');
    
      }//remove the last dash Clusteridbuilder.deletecharat (Clusteridbuilder.length ()-1);
    
      Cluster.set (Clusteridbuilder.tostring ());
        if (debugoutput) {vector.set (featurevector);
      Context.write (cluster, vector);
      else {context.write (cluster, item); }
    }

protected void reduce (Text cluster, iterable<writable> points, context context)
   throws IOException, interruptedexception {
   collection<writable> pointlist = Lists.newarraylist ();
   for (writable point:points) {
     if (debugoutput) {
       Vector pointvector = ((vectorwritable) point). Get (). Clone (); 
  writable writablepointvector = new vectorwritable (pointvector);
       Pointlist.add (Writablepointvector);
     } else {
       writable pointtext = new Text (point.tostring ());
       Pointlist.add (Pointtext);
     }
   if (Pointlist.size () >= minclustersize) {
     context.getcounter (clusters.accepted). Increment (1);
     for (writable point:pointlist) {
       context.write (cluster, point);
     }
   } else {
     context.getcounter ( clusters.discarded). Increment (1);
   }
 }

See more highlights of this column: http://www.bianceng.cnhttp://www.bianceng.cn/Programming/sjjg/