Author: jeastman
Date: Sun Feb 12 19:03:59 2012
New Revision: 1243298

URL: http://svn.apache.org/viewvc?rev=1243298&view=rev
Log:
Reformatted using Eclipse-Lucene-Codestyle but with 120 char text width

Modified:
    mahout/trunk/core/src/main/java/org/apache/mahout/clustering/CIMapper.java
    mahout/trunk/core/src/main/java/org/apache/mahout/clustering/CIReducer.java
    
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/ClusterIterator.java
    
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/ClusterWritable.java
    
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/TestClusterClassifier.java

Modified: 
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/CIMapper.java
URL: 
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/CIMapper.java?rev=1243298&r1=1243297&r2=1243298&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/clustering/CIMapper.java 
(original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/clustering/CIMapper.java 
Sun Feb 12 19:03:59 2012
@@ -12,17 +12,18 @@ import org.apache.mahout.math.Vector;
 import org.apache.mahout.math.Vector.Element;
 import org.apache.mahout.math.VectorWritable;
 
-public class CIMapper extends
-    Mapper<WritableComparable<?>,VectorWritable,IntWritable,ClusterWritable> {
+public class CIMapper extends 
Mapper<WritableComparable<?>,VectorWritable,IntWritable,ClusterWritable> {
   
   private ClusterClassifier classifier;
-
+  
   private ClusteringPolicy policy;
-
+  
   /*
    * (non-Javadoc)
    * 
-   * @see 
org.apache.hadoop.mapreduce.Mapper#setup(org.apache.hadoop.mapreduce.Mapper 
.Context)
+   * @see
+   * 
org.apache.hadoop.mapreduce.Mapper#setup(org.apache.hadoop.mapreduce.Mapper
+   * .Context)
    */
   @Override
   protected void setup(Context context) throws IOException, 
InterruptedException {
@@ -31,12 +32,12 @@ public class CIMapper extends
     policy = new KMeansClusteringPolicy();
     super.setup(context);
   }
-
+  
   /*
    * (non-Javadoc)
    * 
-   * @see org.apache.hadoop.mapreduce.Mapper#map(java.lang.Object, 
java.lang.Object,
-   * org.apache.hadoop.mapreduce.Mapper.Context)
+   * @see org.apache.hadoop.mapreduce.Mapper#map(java.lang.Object,
+   * java.lang.Object, org.apache.hadoop.mapreduce.Mapper.Context)
    */
   @Override
   protected void map(WritableComparable<?> key, VectorWritable value, Context 
context) throws IOException,
@@ -48,11 +49,13 @@ public class CIMapper extends
       classifier.train(el.index(), value.get(), el.get());
     }
   }
-
+  
   /*
    * (non-Javadoc)
    * 
-   * @see 
org.apache.hadoop.mapreduce.Mapper#cleanup(org.apache.hadoop.mapreduce. 
Mapper.Context)
+   * @see
+   * org.apache.hadoop.mapreduce.Mapper#cleanup(org.apache.hadoop.mapreduce.
+   * Mapper.Context)
    */
   @Override
   protected void cleanup(Context context) throws IOException, 
InterruptedException {
@@ -64,5 +67,5 @@ public class CIMapper extends
     }
     super.cleanup(context);
   }
-
+  
 }

Modified: 
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/CIReducer.java
URL: 
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/CIReducer.java?rev=1243298&r1=1243297&r2=1243298&view=diff
==============================================================================
--- mahout/trunk/core/src/main/java/org/apache/mahout/clustering/CIReducer.java 
(original)
+++ mahout/trunk/core/src/main/java/org/apache/mahout/clustering/CIReducer.java 
Sun Feb 12 19:03:59 2012
@@ -24,15 +24,15 @@ import org.apache.hadoop.io.IntWritable;
 import org.apache.hadoop.mapreduce.Reducer;
 
 public class CIReducer extends 
Reducer<IntWritable,ClusterWritable,IntWritable,ClusterWritable> {
-
+  
   @Override
-  protected void reduce(IntWritable key, Iterable<ClusterWritable> values,
-      Context context) throws IOException, InterruptedException {
-    Iterator<ClusterWritable> iter =values.iterator();
+  protected void reduce(IntWritable key, Iterable<ClusterWritable> values, 
Context context) throws IOException,
+      InterruptedException {
+    Iterator<ClusterWritable> iter = values.iterator();
     ClusterWritable first = null;
-    while(iter.hasNext()){
+    while (iter.hasNext()) {
       ClusterWritable cw = iter.next();
-      if (first == null){
+      if (first == null) {
         first = cw;
       } else {
         first.getValue().observe(cw.getValue());

Modified: 
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/ClusterIterator.java
URL: 
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/ClusterIterator.java?rev=1243298&r1=1243297&r2=1243298&view=diff
==============================================================================
--- 
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/ClusterIterator.java
 (original)
+++ 
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/ClusterIterator.java
 Sun Feb 12 19:03:59 2012
@@ -45,26 +45,32 @@ import com.google.common.collect.Lists;
 import com.google.common.io.Closeables;
 
 /**
- * This is an experimental clustering iterator which works with a 
ClusteringPolicy and a prior ClusterClassifier which
- * has been initialized with a set of models. To date, it has been tested with 
k-means and Dirichlet clustering. See
- * examples DisplayKMeans and DisplayDirichlet which have been switched over 
to use it.
+ * This is an experimental clustering iterator which works with a
+ * ClusteringPolicy and a prior ClusterClassifier which has been initialized
+ * with a set of models. To date, it has been tested with k-means and Dirichlet
+ * clustering. See examples DisplayKMeans and DisplayDirichlet which have been
+ * switched over to use it.
  */
 public class ClusterIterator {
-
+  
   public static final String PRIOR_PATH_KEY = 
"org.apache.mahout.clustering.prior.path";
-
+  
   public ClusterIterator(ClusteringPolicy policy) {
     this.policy = policy;
   }
-
+  
   private final ClusteringPolicy policy;
-
+  
   /**
-   * Iterate over data using a prior-trained ClusterClassifier, for a number 
of iterations
+   * Iterate over data using a prior-trained ClusterClassifier, for a number of
+   * iterations
    * 
-   * @param data a {@code List<Vector>} of input vectors
-   * @param classifier a prior ClusterClassifier
-   * @param numIterations the int number of iterations to perform
+   * @param data
+   *          a {@code List<Vector>} of input vectors
+   * @param classifier
+   *          a prior ClusterClassifier
+   * @param numIterations
+   *          the int number of iterations to perform
    * @return the posterior ClusterClassifier
    */
   public ClusterClassifier iterate(Iterable<Vector> data, ClusterClassifier 
classifier, int numIterations) {
@@ -87,15 +93,19 @@ public class ClusterIterator {
     }
     return classifier;
   }
-
+  
   /**
-   * Iterate over data using a prior-trained ClusterClassifier, for a number 
of iterations using a sequential
-   * implementation
+   * Iterate over data using a prior-trained ClusterClassifier, for a number of
+   * iterations using a sequential implementation
    * 
-   * @param inPath a Path to input VectorWritables
-   * @param priorPath a Path to the prior classifier
-   * @param outPath a Path of output directory
-   * @param numIterations the int number of iterations to perform
+   * @param inPath
+   *          a Path to input VectorWritables
+   * @param priorPath
+   *          a Path to the prior classifier
+   * @param outPath
+   *          a Path of output directory
+   * @param numIterations
+   *          the int number of iterations to perform
    * @throws IOException
    */
   public void iterateSeq(Path inPath, Path priorPath, Path outPath, int 
numIterations) throws IOException {
@@ -123,15 +133,19 @@ public class ClusterIterator {
       writeClassifier(classifier, new Path(outPath, "classifier-" + 
iteration));
     }
   }
-
+  
   /**
-   * Iterate over data using a prior-trained ClusterClassifier, for a number 
of iterations using a mapreduce
-   * implementation
+   * Iterate over data using a prior-trained ClusterClassifier, for a number of
+   * iterations using a mapreduce implementation
    * 
-   * @param inPath a Path to input VectorWritables
-   * @param priorPath a Path to the prior classifier
-   * @param outPath a Path of output directory
-   * @param numIterations the int number of iterations to perform
+   * @param inPath
+   *          a Path to input VectorWritables
+   * @param priorPath
+   *          a Path to the prior classifier
+   * @param outPath
+   *          a Path of output directory
+   * @param numIterations
+   *          the int number of iterations to perform
    */
   public void iterateMR(Path inPath, Path priorPath, Path outPath, int 
numIterations) throws IOException,
       InterruptedException, ClassNotFoundException {
@@ -139,7 +153,7 @@ public class ClusterIterator {
     HadoopUtil.delete(conf, outPath);
     for (int iteration = 1; iteration <= numIterations; iteration++) {
       conf.set(PRIOR_PATH_KEY, priorPath.toString());
-
+      
       String jobName = "Cluster Iterator running iteration " + iteration + " 
over priorPath: " + priorPath;
       System.out.println(jobName);
       Job job = new Job(conf, jobName);
@@ -147,17 +161,17 @@ public class ClusterIterator {
       job.setMapOutputValueClass(ClusterWritable.class);
       job.setOutputKeyClass(IntWritable.class);
       job.setOutputValueClass(ClusterWritable.class);
-
+      
       job.setInputFormatClass(SequenceFileInputFormat.class);
       job.setOutputFormatClass(SequenceFileOutputFormat.class);
       job.setMapperClass(CIMapper.class);
       job.setReducerClass(CIReducer.class);
-
+      
       FileInputFormat.addInputPath(job, inPath);
       Path clustersOut = new Path(outPath, "clusters-" + iteration);
       priorPath = clustersOut;
       FileOutputFormat.setOutputPath(job, clustersOut);
-
+      
       job.setJarByClass(ClusterIterator.class);
       if (!job.waitForCompletion(true)) {
         throw new InterruptedException("Cluster Iteration " + iteration + " 
failed processing " + priorPath);
@@ -168,13 +182,16 @@ public class ClusterIterator {
       }
     }
   }
-
+  
   /**
-   * Return if all of the Clusters in the parts in the filePath have converged 
or not
+   * Return if all of the Clusters in the parts in the filePath have converged
+   * or not
    * 
-   * @param filePath the file path to the single file containing the clusters
+   * @param filePath
+   *          the file path to the single file containing the clusters
    * @return true if all Clusters are converged
-   * @throws IOException if there was an IO error
+   * @throws IOException
+   *           if there was an IO error
    */
   private boolean isConverged(Path filePath, Configuration conf, FileSystem 
fs) throws IOException {
     for (FileStatus part : fs.listStatus(filePath, PathFilters.partFilter())) {
@@ -190,7 +207,7 @@ public class ClusterIterator {
     }
     return true;
   }
-
+  
   public static void writeClassifier(ClusterClassifier classifier, Path 
outPath) throws IOException {
     Configuration config = new Configuration();
     FileSystem fs = FileSystem.get(outPath.toUri(), config);
@@ -209,7 +226,7 @@ public class ClusterIterator {
       }
     }
   }
-
+  
   public static ClusterClassifier readClassifier(Path inPath) throws 
IOException {
     Configuration config = new Configuration();
     List<Cluster> clusters = Lists.newArrayList();

Modified: 
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/ClusterWritable.java
URL: 
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/ClusterWritable.java?rev=1243298&r1=1243297&r2=1243298&view=diff
==============================================================================
--- 
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/ClusterWritable.java
 (original)
+++ 
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/ClusterWritable.java
 Sun Feb 12 19:03:59 2012
@@ -24,25 +24,25 @@ import org.apache.hadoop.io.Writable;
 import org.apache.mahout.classifier.sgd.PolymorphicWritable;
 
 public class ClusterWritable implements Writable {
-
+  
   private Cluster value;
-
+  
   public Cluster getValue() {
     return value;
   }
-
+  
   public void setValue(Cluster value) {
     this.value = value;
   }
-
+  
   @Override
   public void write(DataOutput out) throws IOException {
     PolymorphicWritable.write(out, value);
   }
-
+  
   @Override
   public void readFields(DataInput in) throws IOException {
     value = PolymorphicWritable.read(in, Cluster.class);
   }
-
+  
 }

Modified: 
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/TestClusterClassifier.java
URL: 
http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/TestClusterClassifier.java?rev=1243298&r1=1243297&r2=1243298&view=diff
==============================================================================
--- 
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/TestClusterClassifier.java
 (original)
+++ 
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/TestClusterClassifier.java
 Sun Feb 12 19:03:59 2012
@@ -39,7 +39,7 @@ import org.junit.Test;
 import com.google.common.collect.Lists;
 
 public final class TestClusterClassifier extends MahoutTestCase {
-
+  
   private static ClusterClassifier newDMClassifier() {
     List<Cluster> models = Lists.newArrayList();
     DistanceMeasure measure = new ManhattanDistanceMeasure();
@@ -48,7 +48,7 @@ public final class TestClusterClassifier
     models.add(new DistanceMeasureCluster(new DenseVector(2).assign(-1), 2, 
measure));
     return new ClusterClassifier(models);
   }
-
+  
   private static ClusterClassifier newClusterClassifier() {
     List<Cluster> models = Lists.newArrayList();
     DistanceMeasure measure = new ManhattanDistanceMeasure();
@@ -57,7 +57,7 @@ public final class TestClusterClassifier
     models.add(new org.apache.mahout.clustering.kmeans.Cluster(new 
DenseVector(2).assign(-1), 2, measure));
     return new ClusterClassifier(models);
   }
-
+  
   private static ClusterClassifier newSoftClusterClassifier() {
     List<Cluster> models = Lists.newArrayList();
     DistanceMeasure measure = new ManhattanDistanceMeasure();
@@ -66,7 +66,7 @@ public final class TestClusterClassifier
     models.add(new SoftCluster(new DenseVector(2).assign(-1), 2, measure));
     return new ClusterClassifier(models);
   }
-
+  
   private static ClusterClassifier newGaussianClassifier() {
     List<Cluster> models = Lists.newArrayList();
     models.add(new GaussianCluster(new DenseVector(2).assign(1), new 
DenseVector(2).assign(1), 0));
@@ -74,13 +74,13 @@ public final class TestClusterClassifier
     models.add(new GaussianCluster(new DenseVector(2).assign(-1), new 
DenseVector(2).assign(1), 2));
     return new ClusterClassifier(models);
   }
-
+  
   private ClusterClassifier writeAndRead(ClusterClassifier classifier) throws 
IOException {
     Path path = new Path(getTestTempDirPath(), "output");
     ClusterIterator.writeClassifier(classifier, path);
     return ClusterIterator.readClassifier(path);
   }
-
+  
   @Test
   public void testDMClusterClassification() {
     ClusterClassifier classifier = newDMClassifier();
@@ -89,7 +89,7 @@ public final class TestClusterClassifier
     pdf = classifier.classify(new DenseVector(2).assign(2));
     assertEquals("[2,2]", "[0.493, 0.296, 0.211]", 
AbstractCluster.formatVector(pdf, null));
   }
-
+  
   @Test
   public void testCanopyClassification() {
     List<Cluster> models = Lists.newArrayList();
@@ -103,7 +103,7 @@ public final class TestClusterClassifier
     pdf = classifier.classify(new DenseVector(2).assign(2));
     assertEquals("[2,2]", "[0.493, 0.296, 0.211]", 
AbstractCluster.formatVector(pdf, null));
   }
-
+  
   @Test
   public void testClusterClassification() {
     ClusterClassifier classifier = newClusterClassifier();
@@ -112,7 +112,7 @@ public final class TestClusterClassifier
     pdf = classifier.classify(new DenseVector(2).assign(2));
     assertEquals("[2,2]", "[0.493, 0.296, 0.211]", 
AbstractCluster.formatVector(pdf, null));
   }
-
+  
   @Test(expected = UnsupportedOperationException.class)
   public void testMSCanopyClassification() {
     List<Cluster> models = Lists.newArrayList();
@@ -123,7 +123,7 @@ public final class TestClusterClassifier
     ClusterClassifier classifier = new ClusterClassifier(models);
     classifier.classify(new DenseVector(2));
   }
-
+  
   @Test
   public void testSoftClusterClassification() {
     ClusterClassifier classifier = newSoftClusterClassifier();
@@ -132,7 +132,7 @@ public final class TestClusterClassifier
     pdf = classifier.classify(new DenseVector(2).assign(2));
     assertEquals("[2,2]", "[0.735, 0.184, 0.082]", 
AbstractCluster.formatVector(pdf, null));
   }
-
+  
   @Test
   public void testGaussianClusterClassification() {
     ClusterClassifier classifier = newGaussianClassifier();
@@ -141,7 +141,7 @@ public final class TestClusterClassifier
     pdf = classifier.classify(new DenseVector(2).assign(2));
     assertEquals("[2,2]", "[0.952, 0.047, 0.000]", 
AbstractCluster.formatVector(pdf, null));
   }
-
+  
   @Test
   public void testDMClassifierSerialization() throws Exception {
     ClusterClassifier classifier = newDMClassifier();
@@ -150,7 +150,7 @@ public final class TestClusterClassifier
     assertEquals(classifier.getModels().get(0).getClass().getName(), 
classifierOut.getModels().get(0).getClass()
         .getName());
   }
-
+  
   @Test
   public void testClusterClassifierSerialization() throws Exception {
     ClusterClassifier classifier = newClusterClassifier();
@@ -159,7 +159,7 @@ public final class TestClusterClassifier
     assertEquals(classifier.getModels().get(0).getClass().getName(), 
classifierOut.getModels().get(0).getClass()
         .getName());
   }
-
+  
   @Test
   public void testSoftClusterClassifierSerialization() throws Exception {
     ClusterClassifier classifier = newSoftClusterClassifier();
@@ -168,7 +168,7 @@ public final class TestClusterClassifier
     assertEquals(classifier.getModels().get(0).getClass().getName(), 
classifierOut.getModels().get(0).getClass()
         .getName());
   }
-
+  
   @Test
   public void testGaussianClassifierSerialization() throws Exception {
     ClusterClassifier classifier = newGaussianClassifier();
@@ -177,7 +177,7 @@ public final class TestClusterClassifier
     assertEquals(classifier.getModels().get(0).getClass().getName(), 
classifierOut.getModels().get(0).getClass()
         .getName());
   }
-
+  
   @Test
   public void testClusterIteratorKMeans() {
     List<Vector> data = 
TestKmeansClustering.getPoints(TestKmeansClustering.REFERENCE);
@@ -190,7 +190,7 @@ public final class TestClusterClassifier
       System.out.println(cluster.asFormatString(null));
     }
   }
-
+  
   @Test
   public void testClusterIteratorDirichlet() {
     List<Vector> data = 
TestKmeansClustering.getPoints(TestKmeansClustering.REFERENCE);
@@ -203,7 +203,7 @@ public final class TestClusterClassifier
       System.out.println(cluster.asFormatString(null));
     }
   }
-
+  
   @Test
   public void testSeqFileClusterIteratorKMeans() throws IOException {
     Path pointsPath = getTestTempDirPath("points");
@@ -224,7 +224,7 @@ public final class TestClusterClassifier
     ClusteringPolicy policy = new KMeansClusteringPolicy();
     ClusterIterator iterator = new ClusterIterator(policy);
     iterator.iterateSeq(pointsPath, path, outPath, 5);
-
+    
     for (int i = 1; i <= 5; i++) {
       System.out.println("Classifier-" + i);
       ClusterClassifier posterior = ClusterIterator.readClassifier(new 
Path(outPath, "classifier-" + i));
@@ -232,10 +232,10 @@ public final class TestClusterClassifier
       for (Cluster cluster : posterior.getModels()) {
         System.out.println(cluster.asFormatString(null));
       }
-
+      
     }
   }
-
+  
   @Test
   public void testMRFileClusterIteratorKMeans() throws IOException, 
InterruptedException, ClassNotFoundException {
     Path pointsPath = getTestTempDirPath("points");
@@ -256,7 +256,7 @@ public final class TestClusterClassifier
     ClusteringPolicy policy = new KMeansClusteringPolicy();
     ClusterIterator iterator = new ClusterIterator(policy);
     iterator.iterateMR(pointsPath, path, outPath, 5);
-
+    
     for (int i = 1; i <= 5; i++) {
       System.out.println("Classifier-" + i);
       ClusterClassifier posterior = ClusterIterator.readClassifier(new 
Path(outPath, "clusters-" + i));
@@ -264,7 +264,7 @@ public final class TestClusterClassifier
       for (Cluster cluster : posterior.getModels()) {
         System.out.println(cluster.asFormatString(null));
       }
-
+      
     }
   }
 }


Reply via email to