Java ClusterWritable.getValue方法代码示例

import org.apache.mahout.clustering.iterator.ClusterWritable; //导入方法依赖的package包/类
/**
 * Create a list of SoftClusters from whatever type is passed in as the prior
 * 
 * @param conf
 *          the Configuration
 * @param clusterPath
 *          the path to the prior Clusters
 * @param clusters
 *          a List<Cluster> to put values into
 */
public static void configureWithClusterInfo(Configuration conf, Path clusterPath, List<Cluster> clusters) {
  for (Writable value : new SequenceFileDirValueIterable<Writable>(clusterPath, PathType.LIST,
      PathFilters.partFilter(), conf)) {
    Class<? extends Writable> valueClass = value.getClass();
    
    if (valueClass.equals(ClusterWritable.class)) {
      ClusterWritable clusterWritable = (ClusterWritable) value;
      value = clusterWritable.getValue();
      valueClass = value.getClass();
    }
    
    if (valueClass.equals(Kluster.class)) {
      // get the cluster info
      Kluster cluster = (Kluster) value;
      clusters.add(new SoftCluster(cluster.getCenter(), cluster.getId(), cluster.getMeasure()));
    } else if (valueClass.equals(SoftCluster.class)) {
      // get the cluster info
      clusters.add((SoftCluster) value);
    } else if (valueClass.equals(Canopy.class)) {
      // get the cluster info
      Canopy canopy = (Canopy) value;
      clusters.add(new SoftCluster(canopy.getCenter(), canopy.getId(), canopy.getMeasure()));
    } else {
      throw new IllegalStateException("Bad value class: " + valueClass);
    }
  }
  
}
 

import org.apache.mahout.clustering.iterator.ClusterWritable; //导入方法依赖的package包/类
/**
 * Create a list of Klusters from whatever Cluster type is passed in as the prior
 * 
 * @param conf
 *          the Configuration
 * @param clusterPath
 *          the path to the prior Clusters
 * @param clusters
 *          a List<Cluster> to put values into
 */
public static void configureWithClusterInfo(Configuration conf, Path clusterPath, Collection<Cluster> clusters) {
  for (Writable value : new SequenceFileDirValueIterable<Writable>(clusterPath, PathType.LIST,
      PathFilters.partFilter(), conf)) {
    Class<? extends Writable> valueClass = value.getClass();
    if (valueClass.equals(ClusterWritable.class)) {
      ClusterWritable clusterWritable = (ClusterWritable) value;
      value = clusterWritable.getValue();
      valueClass = value.getClass();
    }
    log.debug("Read 1 Cluster from {}", clusterPath);
    
    if (valueClass.equals(Kluster.class)) {
      // get the cluster info
      clusters.add((Kluster) value);
    } else if (valueClass.equals(Canopy.class)) {
      // get the cluster info
      Canopy canopy = (Canopy) value;
      clusters.add(new Kluster(canopy.getCenter(), canopy.getId(), canopy.getMeasure()));
    } else {
      throw new IllegalStateException("Bad value class: " + valueClass);
    }
  }
}
 

import org.apache.mahout.clustering.iterator.ClusterWritable; //导入方法依赖的package包/类
/**
 * Populates a list with clusters present in clusters-*-final directory.
 * 
 * @param clusterOutputPath
 *            The output path of the clustering.
 * @param conf
 *            The Hadoop Configuration
 * @return The list of clusters found by the clustering.
 * @throws IOException
 */
private static List<Cluster> populateClusterModels(Path clusterOutputPath,
		Configuration conf) throws IOException {
	List<Cluster> clusterModels = Lists.newArrayList();
	Path finalClustersPath = finalClustersPath(conf, clusterOutputPath);
	Iterator<?> it = new SequenceFileDirValueIterator<Writable>(
			finalClustersPath, PathType.LIST, PathFilters.partFilter(),
			null, false, conf);
	while (it.hasNext()) {
		ClusterWritable next = (ClusterWritable) it.next();
		Cluster cluster = next.getValue();
		cluster.configure(conf);
		clusterModels.add(cluster);
	}
	return clusterModels;
}
 

import org.apache.mahout.clustering.iterator.ClusterWritable; //导入方法依赖的package包/类
public static List<List<Cluster>> readClusters(Configuration conf, Path output)
		throws IOException {
	List<List<Cluster>> Clusters = Lists.newArrayList();
	FileSystem fs = FileSystem.get(output.toUri(), conf);

	for (FileStatus s : fs.listStatus(output, new ClustersFilter())) {
		List<Cluster> clusters = Lists.newArrayList();
		for (ClusterWritable value : new SequenceFileDirValueIterable<ClusterWritable>(
				s.getPath(), PathType.LIST, PathFilters.logsCRCFilter(),
				conf)) {
			Cluster cluster = value.getValue();
			clusters.add(cluster);
		}
		Clusters.add(clusters);
	}
	return Clusters;
}
 

import org.apache.mahout.clustering.iterator.ClusterWritable; //导入方法依赖的package包/类
/**
 * Populates a list with clusters present in clusters-*-final directory.
 * 
 * @param clusterOutputPath
 *          The output path of the clustering.
 * @param conf
 *          The Hadoop Configuration
 * @return The list of clusters found by the clustering.
 * @throws IOException
 */
private static List<Cluster> populateClusterModels(Path clusterOutputPath, Configuration conf) throws IOException {
  List<Cluster> clusterModels = new ArrayList<Cluster>();
  Path finalClustersPath = finalClustersPath(conf, clusterOutputPath);
  Iterator<?> it = new SequenceFileDirValueIterator<Writable>(finalClustersPath, PathType.LIST,
      PathFilters.partFilter(), null, false, conf);
  while (it.hasNext()) {
    ClusterWritable next = (ClusterWritable) it.next();
    Cluster cluster = next.getValue();
    cluster.configure(conf);
    clusterModels.add(cluster);
  }
  return clusterModels;
}
 

import org.apache.mahout.clustering.iterator.ClusterWritable; //导入方法依赖的package包/类
public void readFromSeqFiles(Configuration conf, Path path) throws IOException {
  Configuration config = new Configuration();
  List<Cluster> clusters = Lists.newArrayList();
  for (ClusterWritable cw : new SequenceFileDirValueIterable<ClusterWritable>(path, PathType.LIST,
      PathFilters.logsCRCFilter(), config)) {
    Cluster cluster = cw.getValue();
    cluster.configure(conf);
    clusters.add(cluster);
  }
  this.models = clusters;
  modelClass = models.get(0).getClass().getName();
  this.policy = readPolicy(path);
}
 

import org.apache.mahout.clustering.iterator.ClusterWritable; //导入方法依赖的package包/类
public static List<Cluster> populateClusterModels(Path clusterOutputPath, Configuration conf) throws IOException {
  List<Cluster> clusters = new ArrayList<Cluster>();
  FileSystem fileSystem = clusterOutputPath.getFileSystem(conf);
  FileStatus[] clusterFiles = fileSystem.listStatus(clusterOutputPath, PathFilters.finalPartFilter());
  Iterator<?> it = new SequenceFileDirValueIterator<Writable>(
      clusterFiles[0].getPath(), PathType.LIST, PathFilters.partFilter(),
      null, false, conf);
  while (it.hasNext()) {
    ClusterWritable next = (ClusterWritable) it.next();
    Cluster cluster = next.getValue();
    cluster.configure(conf);
    clusters.add(cluster);
  }
  return clusters;
}
 

import org.apache.mahout.clustering.iterator.ClusterWritable; //导入方法依赖的package包/类
public static List<MeanShiftCanopy> getCanopies(Configuration conf) {
  String statePath = conf.get(MeanShiftCanopyDriver.STATE_IN_KEY);
  List<MeanShiftCanopy> canopies = Lists.newArrayList();
  Path path = new Path(statePath);
  for (ClusterWritable clusterWritable 
       : new SequenceFileDirValueIterable<ClusterWritable>(path, PathType.LIST, PathFilters.logsCRCFilter(), conf)) {
    MeanShiftCanopy canopy = (MeanShiftCanopy)clusterWritable.getValue();
    canopies.add(canopy);
  }
  return canopies;
}
 

import org.apache.mahout.clustering.iterator.ClusterWritable; //导入方法依赖的package包/类
@Override
 protected void map(WritableComparable<?> key, ClusterWritable clusterWritable, Context context)
   throws IOException, InterruptedException {
   // canopies use canopyIds assigned when input vectors are processed as vectorIds too
MeanShiftCanopy canopy = (MeanShiftCanopy)clusterWritable.getValue();
   int vectorId = canopy.getId();
   for (MeanShiftCanopy msc : canopies) {
     for (int containedId : msc.getBoundPoints().toList()) {
       if (vectorId == containedId) {
         context.write(new IntWritable(msc.getId()),
                        new WeightedVectorWritable(1, canopy.getCenter()));
       }
     }
   }
 }
 

import org.apache.mahout.clustering.iterator.ClusterWritable; //导入方法依赖的package包/类
public static List<Cluster> populateClusterModels(Path clusterOutputPath, Configuration conf) throws IOException {
  List<Cluster> clusters = Lists.newArrayList();
  FileSystem fileSystem = clusterOutputPath.getFileSystem(conf);
  FileStatus[] clusterFiles = fileSystem.listStatus(clusterOutputPath, PathFilters.finalPartFilter());
  Iterator<?> it = new SequenceFileDirValueIterator<Writable>(
      clusterFiles[0].getPath(), PathType.LIST, PathFilters.partFilter(),
      null, false, conf);
  while (it.hasNext()) {
    ClusterWritable next = (ClusterWritable) it.next();
    Cluster cluster = next.getValue();
    cluster.configure(conf);
    clusters.add(cluster);
  }
  return clusters;
}
 

import org.apache.mahout.clustering.iterator.ClusterWritable; //导入方法依赖的package包/类
@Override
protected void map(WritableComparable<?> key, ClusterWritable clusterWritable, Context context)
  throws IOException, InterruptedException {
  MeanShiftCanopy canopy = (MeanShiftCanopy) clusterWritable.getValue();
  clusterer.mergeCanopy(canopy.shallowCopy(), canopies);
}