mahout-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From jeast...@apache.org
Subject svn commit: r966816 [2/2] - in /mahout/trunk: core/src/main/java/org/apache/mahout/clustering/fuzzykmeans/ core/src/main/java/org/apache/mahout/clustering/kmeans/ core/src/main/java/org/apache/mahout/clustering/meanshift/ core/src/test/java/org/apache/...
Date Thu, 22 Jul 2010 19:25:21 GMT
Modified: mahout/trunk/core/src/test/java/org/apache/mahout/clustering/kmeans/TestKmeansClustering.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/kmeans/TestKmeansClustering.java?rev=966816&r1=966815&r2=966816&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/clustering/kmeans/TestKmeansClustering.java
(original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/clustering/kmeans/TestKmeansClustering.java
Thu Jul 22 19:25:20 2010
@@ -351,6 +351,61 @@ public class TestKmeansClustering extend
   }
 
   /** Story: User wishes to run kmeans job on reference data */
+  public void testKMeansSeqJob() throws Exception {
+    List<VectorWritable> points = getPointsWritable(reference);
+  
+    Path pointsPath = getTestTempDirPath("points");
+    Path clustersPath = getTestTempDirPath("clusters");
+    Configuration conf = new Configuration();
+    ClusteringTestUtils.writePointsToFile(points, new Path(pointsPath, "file1"), fs, conf);
+    ClusteringTestUtils.writePointsToFile(points, new Path(pointsPath, "file2"), fs, conf);
+    for (int k = 1; k < points.size(); k++) {
+      System.out.println("testKMeansMRJob k= " + k);
+      // pick k initial cluster centers at random
+      Path path = new Path(clustersPath, "part-00000");
+      FileSystem fs = FileSystem.get(path.toUri(), conf);
+      SequenceFile.Writer writer = new SequenceFile.Writer(fs, conf, path, Text.class, Cluster.class);
+  
+      for (int i = 0; i < k + 1; i++) {
+        Vector vec = points.get(i).get();
+  
+        Cluster cluster = new Cluster(vec, i);
+        // add the center so the centroid will be correct upon output
+        cluster.addPoint(cluster.getCenter());
+        writer.append(new Text(cluster.getIdentifier()), cluster);
+      }
+      writer.close();
+      // now run the Job
+      Path outputPath = getTestTempDirPath("output");
+      //KMeansDriver.runJob(pointsPath, clustersPath, outputPath, EuclideanDistanceMeasure.class.getName(),
0.001, 10, k + 1, true);
+      String[] args = { optKey(DefaultOptionCreator.INPUT_OPTION), pointsPath.toString(),
+          optKey(DefaultOptionCreator.CLUSTERS_IN_OPTION), clustersPath.toString(), optKey(DefaultOptionCreator.OUTPUT_OPTION),
+          outputPath.toString(), optKey(DefaultOptionCreator.DISTANCE_MEASURE_OPTION), EuclideanDistanceMeasure.class.getName(),
+          optKey(DefaultOptionCreator.CONVERGENCE_DELTA_OPTION), "0.001", optKey(DefaultOptionCreator.MAX_ITERATIONS_OPTION),
"2",
+          optKey(DefaultOptionCreator.CLUSTERING_OPTION), optKey(DefaultOptionCreator.OVERWRITE_OPTION),
+          optKey(DefaultOptionCreator.METHOD_OPTION), DefaultOptionCreator.SEQUENTIAL_METHOD
};
+      new KMeansDriver().run(args);
+  
+      // now compare the expected clusters with actual
+      Path clusteredPointsPath = new Path(outputPath, "clusteredPoints");
+      SequenceFile.Reader reader = new SequenceFile.Reader(fs, new Path(clusteredPointsPath,
"part-m-0"), conf);
+      int[] expect = expectedNumPoints[k];
+      DummyOutputCollector<IntWritable, WeightedVectorWritable> collector = new DummyOutputCollector<IntWritable,
WeightedVectorWritable>();
+      // The key is the clusterId
+      IntWritable clusterId = new IntWritable(0);
+      // The value is the weighted vector
+      WeightedVectorWritable value = new WeightedVectorWritable();
+      while (reader.next(clusterId, value)) {
+        collector.collect(clusterId, value);
+        clusterId = new IntWritable(0);
+        value = new WeightedVectorWritable();
+      }
+      reader.close();
+      assertEquals("clusters[" + k + ']', expect.length, collector.getKeys().size());
+    }
+  }
+
+  /** Story: User wishes to run kmeans job on reference data */
   public void testKMeansMRJob() throws Exception {
     List<VectorWritable> points = getPointsWritable(reference);
 
@@ -378,15 +433,11 @@ public class TestKmeansClustering extend
       // now run the Job
       Path outputPath = getTestTempDirPath("output");
       //KMeansDriver.runJob(pointsPath, clustersPath, outputPath, EuclideanDistanceMeasure.class.getName(),
0.001, 10, k + 1, true);
-      String[] args = { 
-          optKey(DefaultOptionCreator.INPUT_OPTION), pointsPath.toString(), 
-          optKey(DefaultOptionCreator.CLUSTERS_IN_OPTION), clustersPath.toString(), 
-          optKey(DefaultOptionCreator.OUTPUT_OPTION), outputPath.toString(),
-          optKey(DefaultOptionCreator.DISTANCE_MEASURE_OPTION), EuclideanDistanceMeasure.class.getName(),
-          optKey(DefaultOptionCreator.CONVERGENCE_DELTA_OPTION), "0.001", 
-          optKey(DefaultOptionCreator.MAX_ITERATIONS_OPTION), "2",
-          optKey(DefaultOptionCreator.CLUSTERING_OPTION), 
-          optKey(DefaultOptionCreator.OVERWRITE_OPTION) };
+      String[] args = { optKey(DefaultOptionCreator.INPUT_OPTION), pointsPath.toString(),
+          optKey(DefaultOptionCreator.CLUSTERS_IN_OPTION), clustersPath.toString(), optKey(DefaultOptionCreator.OUTPUT_OPTION),
+          outputPath.toString(), optKey(DefaultOptionCreator.DISTANCE_MEASURE_OPTION), EuclideanDistanceMeasure.class.getName(),
+          optKey(DefaultOptionCreator.CONVERGENCE_DELTA_OPTION), "0.001", optKey(DefaultOptionCreator.MAX_ITERATIONS_OPTION),
"2",
+          optKey(DefaultOptionCreator.CLUSTERING_OPTION), optKey(DefaultOptionCreator.OVERWRITE_OPTION)
};
       new KMeansDriver().run(args);
 
       // now compare the expected clusters with actual
@@ -435,7 +486,8 @@ public class TestKmeansClustering extend
                         0.001,
                         10,
                         1,
-                        true);
+                        true,
+                        false);
 
     // now compare the expected clusters with actual
     Path clusteredPointsPath = new Path(outputPath, "clusteredPoints");

Modified: mahout/trunk/core/src/test/java/org/apache/mahout/clustering/meanshift/TestMeanShift.java
URL: http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/meanshift/TestMeanShift.java?rev=966816&r1=966815&r2=966816&view=diff
==============================================================================
--- mahout/trunk/core/src/test/java/org/apache/mahout/clustering/meanshift/TestMeanShift.java
(original)
+++ mahout/trunk/core/src/test/java/org/apache/mahout/clustering/meanshift/TestMeanShift.java
Thu Jul 22 19:25:20 2010
@@ -312,16 +312,12 @@ public class TestMeanShift extends Mahou
     // now run the Job using the run() command. Other tests can continue to use runJob().
     Path output = getTestTempDirPath("output");
     //MeanShiftCanopyDriver.runJob(input, output, EuclideanDistanceMeasure.class.getName(),
4, 1, 0.5, 10, false, false);
-    String[] args = { 
-        optKey(DefaultOptionCreator.INPUT_OPTION), getTestTempDirPath("testdata").toString(),
-        optKey(DefaultOptionCreator.OUTPUT_OPTION), output.toString(), 
-        optKey(DefaultOptionCreator.DISTANCE_MEASURE_OPTION), EuclideanDistanceMeasure.class.getName(),

-        optKey(DefaultOptionCreator.T1_OPTION), "4", 
-        optKey(DefaultOptionCreator.T2_OPTION), "1",
-        optKey(DefaultOptionCreator.CLUSTERING_OPTION), 
-        optKey(DefaultOptionCreator.MAX_ITERATIONS_OPTION), "4",
-        optKey(DefaultOptionCreator.CONVERGENCE_DELTA_OPTION), "0.5", 
-        optKey(DefaultOptionCreator.OVERWRITE_OPTION)  };
+    String[] args = { optKey(DefaultOptionCreator.INPUT_OPTION), getTestTempDirPath("testdata").toString(),
+        optKey(DefaultOptionCreator.OUTPUT_OPTION), output.toString(), optKey(DefaultOptionCreator.DISTANCE_MEASURE_OPTION),
+        EuclideanDistanceMeasure.class.getName(), optKey(DefaultOptionCreator.T1_OPTION),
"4",
+        optKey(DefaultOptionCreator.T2_OPTION), "1", optKey(DefaultOptionCreator.CLUSTERING_OPTION),
+        optKey(DefaultOptionCreator.MAX_ITERATIONS_OPTION), "4", optKey(DefaultOptionCreator.CONVERGENCE_DELTA_OPTION),
"0.5",
+        optKey(DefaultOptionCreator.OVERWRITE_OPTION) };
     new MeanShiftCanopyDriver().run(args);
     Path outPart = new Path(output, "clusters-3/part-r-00000");
     SequenceFile.Reader reader = new SequenceFile.Reader(fs, outPart, conf);
@@ -334,4 +330,42 @@ public class TestMeanShift extends Mahou
     reader.close();
     assertEquals("count", 3, count);
   }
+
+  /**
+   * Story: User can produce final point clustering using a Hadoop map/reduce job and a
+   * EuclideanDistanceMeasure.
+   */
+  public void testCanopyEuclideanSeqJob() throws Exception {
+    Path input = getTestTempDirPath("testdata");
+    Configuration conf = new Configuration();
+    FileSystem fs = FileSystem.get(input.toUri(), conf);
+    List<VectorWritable> points = new ArrayList<VectorWritable>();
+    for (Vector v : raw) {
+      points.add(new VectorWritable(v));
+    }
+    ClusteringTestUtils.writePointsToFile(points, getTestTempFilePath("testdata/file1"),
fs, conf);
+    ClusteringTestUtils.writePointsToFile(points, getTestTempFilePath("testdata/file2"),
fs, conf);
+    // now run the Job using the run() command. Other tests can continue to use runJob().
+    Path output = getTestTempDirPath("output");
+    System.out.println("Output Path: " + output.toString());
+    //MeanShiftCanopyDriver.runJob(input, output, EuclideanDistanceMeasure.class.getName(),
4, 1, 0.5, 10, false, false);
+    String[] args = { optKey(DefaultOptionCreator.INPUT_OPTION), getTestTempDirPath("testdata").toString(),
+        optKey(DefaultOptionCreator.OUTPUT_OPTION), output.toString(), optKey(DefaultOptionCreator.DISTANCE_MEASURE_OPTION),
+        EuclideanDistanceMeasure.class.getName(), optKey(DefaultOptionCreator.T1_OPTION),
"4",
+        optKey(DefaultOptionCreator.T2_OPTION), "1", optKey(DefaultOptionCreator.CLUSTERING_OPTION),
+        optKey(DefaultOptionCreator.MAX_ITERATIONS_OPTION), "4", optKey(DefaultOptionCreator.CONVERGENCE_DELTA_OPTION),
"0.5",
+        optKey(DefaultOptionCreator.OVERWRITE_OPTION), optKey(DefaultOptionCreator.METHOD_OPTION),
+        DefaultOptionCreator.SEQUENTIAL_METHOD };
+    new MeanShiftCanopyDriver().run(args);
+    Path outPart = new Path(output, "clusters-4/part-r-00000");
+    SequenceFile.Reader reader = new SequenceFile.Reader(fs, outPart, conf);
+    Text key = new Text();
+    MeanShiftCanopy value = new MeanShiftCanopy();
+    int count = 0;
+    while (reader.next(key, value)) {
+      count++;
+    }
+    reader.close();
+    assertEquals("count", 5, count);
+  }
 }

Modified: mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/fuzzykmeans/Job.java
URL: http://svn.apache.org/viewvc/mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/fuzzykmeans/Job.java?rev=966816&r1=966815&r2=966816&view=diff
==============================================================================
--- mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/fuzzykmeans/Job.java
(original)
+++ mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/fuzzykmeans/Job.java
Thu Jul 22 19:25:20 2010
@@ -182,7 +182,8 @@ public final class Job extends FuzzyKMea
                              fuzziness,
                              true,
                              true,
-                             0.0);
+                             0.0,
+                             false);
     // run ClusterDumper
     ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-3"), new Path(output,
"clusteredPoints"));
     clusterDumper.printClusters(null);

Modified: mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/kmeans/Job.java
URL: http://svn.apache.org/viewvc/mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/kmeans/Job.java?rev=966816&r1=966815&r2=966816&view=diff
==============================================================================
--- mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/kmeans/Job.java
(original)
+++ mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/kmeans/Job.java
Thu Jul 22 19:25:20 2010
@@ -96,7 +96,7 @@ public final class Job extends KMeansDri
           .get(DefaultOptionCreator.NUM_CLUSTERS_OPTION)));
     }
     boolean runClustering = hasOption(DefaultOptionCreator.CLUSTERING_OPTION);
-    runJob(input, clusters, output, measureClass, convergenceDelta, maxIterations, numReduceTasks,
runClustering);
+    runJob(input, clusters, output, measureClass, convergenceDelta, maxIterations, numReduceTasks,
runClustering, false);
     return 0;
   }
 
@@ -144,7 +144,7 @@ public final class Job extends KMeansDri
                         convergenceDelta,
                         maxIterations,
                         1,
-                        true);
+                        true, false);
     // run ClusterDumper
     ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-" + maxIterations),
new Path(output,
                                                                                         
                   "clusteredPoints"));

Modified: mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/meanshift/Job.java
URL: http://svn.apache.org/viewvc/mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/meanshift/Job.java?rev=966816&r1=966815&r2=966816&view=diff
==============================================================================
--- mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/meanshift/Job.java
(original)
+++ mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/meanshift/Job.java
Thu Jul 22 19:25:20 2010
@@ -87,7 +87,7 @@ public final class Job extends MeanShift
     int maxIterations = Integer.parseInt(getOption(DefaultOptionCreator.MAX_ITERATIONS_OPTION));
     boolean inputIsCanopies = hasOption(INPUT_IS_CANOPIES_OPTION);
 
-    runJob(input, output, measureClass, t1, t2, convergenceDelta, maxIterations, inputIsCanopies,
runClustering);
+    runJob(input, output, measureClass, t1, t2, convergenceDelta, maxIterations, inputIsCanopies,
runClustering, false);
     return 0;
   }
 
@@ -137,7 +137,7 @@ public final class Job extends MeanShift
                                  convergenceDelta,
                                  maxIterations,
                                  true,
-                                 true);
+                                 true, false);
     // run ClusterDumper
     ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-" + maxIterations),
new Path(output,
                                                                                         
                   "clusteredPoints"));

Modified: mahout/trunk/utils/src/test/java/org/apache/mahout/clustering/TestClusterDumper.java
URL: http://svn.apache.org/viewvc/mahout/trunk/utils/src/test/java/org/apache/mahout/clustering/TestClusterDumper.java?rev=966816&r1=966815&r2=966816&view=diff
==============================================================================
--- mahout/trunk/utils/src/test/java/org/apache/mahout/clustering/TestClusterDumper.java (original)
+++ mahout/trunk/utils/src/test/java/org/apache/mahout/clustering/TestClusterDumper.java Thu
Jul 22 19:25:20 2010
@@ -84,8 +84,10 @@ public class TestClusterDumper extends M
   private void getSampleData(String[] docs2) throws IOException {
     sampleData = new ArrayList<VectorWritable>();
     RAMDirectory directory = new RAMDirectory();
-    IndexWriter writer = new IndexWriter(directory, new StandardAnalyzer(Version.LUCENE_CURRENT),
true,
-        IndexWriter.MaxFieldLength.UNLIMITED);
+    IndexWriter writer = new IndexWriter(directory,
+                                         new StandardAnalyzer(Version.LUCENE_CURRENT),
+                                         true,
+                                         IndexWriter.MaxFieldLength.UNLIMITED);
     for (int i = 0; i < docs2.length; i++) {
       Document doc = new Document();
       Field id = new Field("id", "doc_" + i, Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS);
@@ -120,9 +122,9 @@ public class TestClusterDumper extends M
     for (Vector vector : iterable) {
       Assert.assertNotNull(vector);
       NamedVector namedVector;
-      if (vector instanceof NamedVector){
+      if (vector instanceof NamedVector) {
         //rename it for testing purposes
-        namedVector = new NamedVector(((NamedVector)vector).getDelegate(), "P(" + i + ')');
+        namedVector = new NamedVector(((NamedVector) vector).getDelegate(), "P(" + i + ')');
 
       } else {
         namedVector = new NamedVector(vector, "P(" + i + ')');
@@ -135,62 +137,59 @@ public class TestClusterDumper extends M
 
   public void testCanopy() throws Exception { // now run the Job
     Path output = getTestTempDirPath("output");
-    CanopyDriver.runJob(getTestTempDirPath("testdata"), output,
-                        EuclideanDistanceMeasure.class.getName(), 8, 4, true, false);
+    CanopyDriver.runJob(getTestTempDirPath("testdata"), output, EuclideanDistanceMeasure.class.getName(),
8, 4, true, false);
     // run ClusterDumper
-    ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-0"),
-                                                    new Path(output, "clusteredPoints"));
+    ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-0"), new Path(output,
"clusteredPoints"));
     clusterDumper.printClusters(termDictionary);
   }
 
   public void testKmeans() throws Exception {
     // now run the Canopy job to prime kMeans canopies
     Path output = getTestTempDirPath("output");
-    CanopyDriver.runJob(getTestTempDirPath("testdata"), output,
-                        EuclideanDistanceMeasure.class.getName(), 8, 4, false, false);
+    CanopyDriver.runJob(getTestTempDirPath("testdata"), output, EuclideanDistanceMeasure.class.getName(),
8, 4, false, false);
     // now run the KMeans job
-    KMeansDriver.runJob(getTestTempDirPath("testdata"), new Path(output, "clusters-0"), output,
-                        EuclideanDistanceMeasure.class.getName(), 0.001, 10, 1, true);
+    KMeansDriver.runJob(getTestTempDirPath("testdata"), new Path(output, "clusters-0"), output,
EuclideanDistanceMeasure.class
+        .getName(), 0.001, 10, 1, true, false);
     // run ClusterDumper
-    ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-2"),
-                                                    new Path(output, "clusteredPoints"));
+    ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-2"), new Path(output,
"clusteredPoints"));
     clusterDumper.printClusters(termDictionary);
   }
 
   public void testFuzzyKmeans() throws Exception {
     // now run the Canopy job to prime kMeans canopies
     Path output = getTestTempDirPath("output");
-    CanopyDriver.runJob(getTestTempDirPath("testdata"), output,
-                        EuclideanDistanceMeasure.class.getName(), 8, 4, false, false);
+    CanopyDriver.runJob(getTestTempDirPath("testdata"), output, EuclideanDistanceMeasure.class.getName(),
8, 4, false, false);
     // now run the Fuzzy KMeans job
-    FuzzyKMeansDriver.runJob(getTestTempDirPath("testdata"), new Path(output, "clusters-0"),
output,
-                             EuclideanDistanceMeasure.class.getName(), 0.001, 10,
-        1, (float) 1.1, true, true, 0);
+    FuzzyKMeansDriver.runJob(getTestTempDirPath("testdata"), new Path(output, "clusters-0"),
output, EuclideanDistanceMeasure.class
+        .getName(), 0.001, 10, 1, (float) 1.1, true, true, 0, false);
     // run ClusterDumper
-    ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-3"),
-                                                    new Path(output, "clusteredPoints"));
+    ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-3"), new Path(output,
"clusteredPoints"));
     clusterDumper.printClusters(termDictionary);
   }
 
   public void testMeanShift() throws Exception {
     Path output = getTestTempDirPath("output");
-    MeanShiftCanopyDriver.runJob(getTestTempDirPath("testdata"), output,
-                                 CosineDistanceMeasure.class.getName(), 0.5, 0.01, 0.05,
10, false, true);
+    MeanShiftCanopyDriver.runJob(getTestTempDirPath("testdata"),
+                                 output,
+                                 CosineDistanceMeasure.class.getName(),
+                                 0.5,
+                                 0.01,
+                                 0.05,
+                                 10,
+                                 false,
+                                 true, false);
     // run ClusterDumper
-    ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-1"),
-                                                    new Path(output, "clusteredPoints"));
+    ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-1"), new Path(output,
"clusteredPoints"));
     clusterDumper.printClusters(termDictionary);
   }
 
   public void testDirichlet() throws Exception {
     Path output = getTestTempDirPath("output");
     NamedVector prototype = (NamedVector) sampleData.get(0).get();
-    DirichletDriver.runJob(getTestTempDirPath("testdata"), output,
-                           L1ModelDistribution.class.getName(), prototype.getDelegate().getClass().getName(),
-                           15, 10, 1.0, 1, true, true, 0, false);
+    DirichletDriver.runJob(getTestTempDirPath("testdata"), output, L1ModelDistribution.class.getName(),
prototype.getDelegate()
+        .getClass().getName(), 15, 10, 1.0, 1, true, true, 0, false);
     // run ClusterDumper
-    ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-10"),
-                                                    new Path(output, "clusteredPoints"));
+    ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-10"), new
Path(output, "clusteredPoints"));
     clusterDumper.printClusters(termDictionary);
   }
 }

Modified: mahout/trunk/utils/src/test/java/org/apache/mahout/clustering/cdbw/TestCDbwEvaluator.java
URL: http://svn.apache.org/viewvc/mahout/trunk/utils/src/test/java/org/apache/mahout/clustering/cdbw/TestCDbwEvaluator.java?rev=966816&r1=966815&r2=966816&view=diff
==============================================================================
--- mahout/trunk/utils/src/test/java/org/apache/mahout/clustering/cdbw/TestCDbwEvaluator.java
(original)
+++ mahout/trunk/utils/src/test/java/org/apache/mahout/clustering/cdbw/TestCDbwEvaluator.java
Thu Jul 22 19:25:20 2010
@@ -154,7 +154,7 @@ public class TestCDbwEvaluator extends M
     // now run the KMeans job
     Path output = getTestTempDirPath("output");
     KMeansDriver.runJob(getTestTempDirPath("testdata"), new Path(output, "clusters-0"), output,
-                        EuclideanDistanceMeasure.class.getName(), 0.001, 10, 1, true);
+                        EuclideanDistanceMeasure.class.getName(), 0.001, 10, 1, true, false);
     int numIterations = 2;
     CDbwDriver.runJob(new Path(output, "clusters-2"), new Path(output, "clusteredPoints"),
output,
                       EuclideanDistanceMeasure.class.getName(), numIterations, 1);
@@ -168,7 +168,7 @@ public class TestCDbwEvaluator extends M
     // now run the KMeans job
     Path output = getTestTempDirPath("output");
     FuzzyKMeansDriver.runJob(getTestTempDirPath("testdata"), new Path(output, "clusters-0"),
output,
-                             EuclideanDistanceMeasure.class.getName(), 0.001, 10, 1, 2, true,
true, 0);
+                             EuclideanDistanceMeasure.class.getName(), 0.001, 10, 1, 2, true,
true, 0, false);
     int numIterations = 2;
     CDbwDriver.runJob(new Path(output, "clusters-4"), new Path(output, "clusteredPoints"),
output,
                       EuclideanDistanceMeasure.class.getName(), numIterations, 1);
@@ -177,7 +177,7 @@ public class TestCDbwEvaluator extends M
 
   public void testMeanShift() throws Exception {
     MeanShiftCanopyDriver.runJob(getTestTempDirPath("testdata"), getTestTempDirPath("output"),
-                                 EuclideanDistanceMeasure.class.getName(), 2.1, 1.0, 0.001,
10, false, true);
+                                 EuclideanDistanceMeasure.class.getName(), 2.1, 1.0, 0.001,
10, false, true, false);
     int numIterations = 2;
     Path output = getTestTempDirPath("output");
     CDbwDriver.runJob(new Path(output, "clusters-2"), new Path(output, "clusteredPoints"),
output,



Mime
View raw message