Author: srowen
Date: Mon Apr 25 11:36:59 2011
New Revision: 1096459
URL: http://svn.apache.org/viewvc?rev=1096459&view=rev
Log:
MAHOUT-681 remove deprecated models/distributions
Removed:
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/dirichlet/models/AsymmetricSampledNormalDistribution.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/dirichlet/models/AsymmetricSampledNormalModel.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/dirichlet/models/L1Model.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/dirichlet/models/L1ModelDistribution.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/dirichlet/models/NormalModel.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/dirichlet/models/NormalModelDistribution.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/dirichlet/models/SampledNormalDistribution.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/dirichlet/models/SampledNormalModel.java
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/dirichlet/DirichletDriver.java
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/TestClusterInterface.java
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/TestVectorModelClassifier.java
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/dirichlet/TestDirichletClustering.java
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/dirichlet/TestMapReduce.java
mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/dirichlet/Job.java
mahout/trunk/utils/src/test/java/org/apache/mahout/clustering/TestClusterDumper.java
mahout/trunk/utils/src/test/java/org/apache/mahout/clustering/dirichlet/TestL1ModelClustering.java
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/dirichlet/DirichletDriver.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/dirichlet/DirichletDriver.java?rev=1096459&r1=1096458&r2=1096459&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/dirichlet/DirichletDriver.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/dirichlet/DirichletDriver.java
Mon Apr 25 11:36:59 2011
@@ -36,7 +36,7 @@ import org.apache.hadoop.util.ToolRunner
import org.apache.mahout.clustering.Cluster;
import org.apache.mahout.clustering.WeightedVectorWritable;
import org.apache.mahout.clustering.dirichlet.models.DistributionDescription;
-import org.apache.mahout.clustering.dirichlet.models.NormalModelDistribution;
+import
org.apache.mahout.clustering.dirichlet.models.GaussianClusterDistribution;
import org.apache.mahout.common.AbstractJob;
import org.apache.mahout.common.HadoopUtil;
import org.apache.mahout.common.commandline.DefaultOptionCreator;
@@ -78,8 +78,8 @@ public class DirichletDriver extends Abs
addOption(ALPHA_OPTION, "a0", "The alpha0 value for the
DirichletDistribution. Defaults to 1.0", "1.0");
addOption(MODEL_DISTRIBUTION_CLASS_OPTION,
"md",
- "The ModelDistribution class name. Defaults to
NormalModelDistribution",
- NormalModelDistribution.class.getName());
+ "The ModelDistribution class name. Defaults to
GaussianClusterDistribution",
+ GaussianClusterDistribution.class.getName());
addOption(MODEL_PROTOTYPE_CLASS_OPTION,
"mp",
"The ModelDistribution prototype Vector class name. Defaults to
RandomAccessSparseVector",
Modified:
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/TestClusterInterface.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/TestClusterInterface.java?rev=1096459&r1=1096458&r2=1096459&view=diff
==============================================================================
---
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/TestClusterInterface.java
(original)
+++
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/TestClusterInterface.java
Mon Apr 25 11:36:59 2011
@@ -19,10 +19,6 @@ package org.apache.mahout.clustering;
import org.apache.mahout.clustering.canopy.Canopy;
import org.apache.mahout.clustering.dirichlet.DirichletCluster;
-import
org.apache.mahout.clustering.dirichlet.models.AsymmetricSampledNormalModel;
-import org.apache.mahout.clustering.dirichlet.models.L1Model;
-import org.apache.mahout.clustering.dirichlet.models.NormalModel;
-import org.apache.mahout.clustering.dirichlet.models.SampledNormalModel;
import org.apache.mahout.clustering.meanshift.MeanShiftCanopy;
import org.apache.mahout.common.MahoutTestCase;
import org.apache.mahout.common.distance.DistanceMeasure;
@@ -38,72 +34,6 @@ public final class TestClusterInterface
private static final DistanceMeasure measure = new
ManhattanDistanceMeasure();
@Test
- public void testDirichletNormalModel() {
- double[] d = { 1.1, 2.2, 3.3 };
- Vector m = new DenseVector(d);
- Cluster model = new NormalModel(5, m, 0.75);
- String format = model.asFormatString(null);
- assertEquals("nm{n=0 m=[1.100, 2.200, 3.300] sd=0.75}", format);
- }
-
- @Test
- public void testDirichletSampledNormalModel() {
- double[] d = { 1.1, 2.2, 3.3 };
- Vector m = new DenseVector(d);
- Cluster model = new SampledNormalModel(5, m, 0.75);
- String format = model.asFormatString(null);
- assertEquals("snm{n=0 m=[1.100, 2.200, 3.300] sd=0.75}", format);
- }
-
- @Test
- public void testDirichletASNormalModel() {
- double[] d = { 1.1, 2.2, 3.3 };
- Vector m = new DenseVector(d);
- Cluster model = new AsymmetricSampledNormalModel(5, m, m);
- String format = model.asFormatString(null);
- assertEquals("asnm{n=0 m=[1.100, 2.200, 3.300] sd=[1.100, 2.200, 3.300]}",
format);
- }
-
- @Test
- public void testDirichletL1Model() {
- double[] d = { 1.1, 2.2, 3.3 };
- Vector m = new DenseVector(d);
- Cluster model = new L1Model(5, m);
- String format = model.asFormatString(null);
- assertEquals("l1m{n=0 c=[1.100, 2.200, 3.300]}", format);
- }
-
- @Test
- public void testDirichletNormalModelClusterAsFormatString() {
- double[] d = { 1.1, 2.2, 3.3 };
- Vector m = new DenseVector(d);
- NormalModel model = new NormalModel(5, m, 0.75);
- Cluster cluster = new DirichletCluster(model, 35.0);
- String format = cluster.asFormatString(null);
- assertEquals("C-5: nm{n=0 m=[1.100, 2.200, 3.300] sd=0.75}", format);
- }
-
- @Test
- public void testDirichletAsymmetricSampledNormalModelClusterAsFormatString()
{
- double[] d = { 1.1, 2.2, 3.3 };
- Vector m = new DenseVector(d);
- AsymmetricSampledNormalModel model = new AsymmetricSampledNormalModel(5,
m, m);
- Cluster cluster = new DirichletCluster(model, 35.0);
- String format = cluster.asFormatString(null);
- assertEquals("C-5: asnm{n=0 m=[1.100, 2.200, 3.300] sd=[1.100, 2.200,
3.300]}", format);
- }
-
- @Test
- public void testDirichletL1ModelClusterAsFormatString() {
- double[] d = { 1.1, 2.2, 3.3 };
- Vector m = new DenseVector(d);
- L1Model model = new L1Model(5, m);
- Cluster cluster = new DirichletCluster(model, 35.0);
- String format = cluster.asFormatString(null);
- assertEquals("C-5: l1m{n=0 c=[1.100, 2.200, 3.300]}", format);
- }
-
- @Test
public void testCanopyAsFormatString() {
double[] d = { 1.1, 2.2, 3.3 };
Vector m = new DenseVector(d);
Modified:
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/TestVectorModelClassifier.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/TestVectorModelClassifier.java?rev=1096459&r1=1096458&r2=1096459&view=diff
==============================================================================
---
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/TestVectorModelClassifier.java
(original)
+++
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/TestVectorModelClassifier.java
Mon Apr 25 11:36:59 2011
@@ -23,7 +23,6 @@ import java.util.List;
import org.apache.commons.lang.NotImplementedException;
import org.apache.mahout.classifier.AbstractVectorClassifier;
import org.apache.mahout.clustering.canopy.Canopy;
-import
org.apache.mahout.clustering.dirichlet.models.AsymmetricSampledNormalModel;
import org.apache.mahout.clustering.dirichlet.models.GaussianCluster;
import org.apache.mahout.clustering.fuzzykmeans.SoftCluster;
import org.apache.mahout.clustering.kmeans.Cluster;
@@ -136,22 +135,4 @@ public final class TestVectorModelClassi
AbstractCluster.formatVector(pdf, null));
}
- @Test
- public void testASNClusterClassification() {
- List<Model<VectorWritable>> models = new
ArrayList<Model<VectorWritable>>();
- models.add(new AsymmetricSampledNormalModel(0,
- new DenseVector(2).assign(1), new DenseVector(2).assign(1)));
- models.add(new AsymmetricSampledNormalModel(1, new DenseVector(2),
- new DenseVector(2).assign(1)));
- models.add(new AsymmetricSampledNormalModel(2, new DenseVector(2)
- .assign(-1), new DenseVector(2).assign(1)));
- AbstractVectorClassifier classifier = new VectorModelClassifier(models);
- Vector pdf = classifier.classify(new DenseVector(2));
- assertEquals("[0,0]", "[0.212, 0.576, 0.212]",
- AbstractCluster.formatVector(pdf, null));
- pdf = classifier.classify(new DenseVector(2).assign(2));
- assertEquals("[2,2]", "[0.952, 0.047, 0.000]",
- AbstractCluster.formatVector(pdf, null));
- }
-
}
Modified:
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/dirichlet/TestDirichletClustering.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/dirichlet/TestDirichletClustering.java?rev=1096459&r1=1096458&r2=1096459&view=diff
==============================================================================
---
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/dirichlet/TestDirichletClustering.java
(original)
+++
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/dirichlet/TestDirichletClustering.java
Mon Apr 25 11:36:59 2011
@@ -21,11 +21,8 @@ import java.util.ArrayList;
import java.util.List;
import org.apache.mahout.clustering.Cluster;
-import
org.apache.mahout.clustering.dirichlet.models.AsymmetricSampledNormalDistribution;
import
org.apache.mahout.clustering.dirichlet.models.DistanceMeasureClusterDistribution;
import
org.apache.mahout.clustering.dirichlet.models.GaussianClusterDistribution;
-import org.apache.mahout.clustering.dirichlet.models.NormalModelDistribution;
-import org.apache.mahout.clustering.dirichlet.models.SampledNormalDistribution;
import org.apache.mahout.common.MahoutTestCase;
import org.apache.mahout.math.DenseVector;
import org.apache.mahout.math.VectorWritable;
@@ -96,97 +93,7 @@ public final class TestDirichletClusteri
generateSamples(30, 0, 1, 0.1);
DirichletClusterer dc = new DirichletClusterer(sampleData,
- new
NormalModelDistribution(new VectorWritable(new DenseVector(2))),
- 1.0,
- 10,
- 1,
- 0);
- List<Cluster[]> result = dc.cluster(30);
- printResults(result, 2);
- assertNotNull(result);
- }
-
- @Test
- public void testDirichletCluster100s() {
- System.out.println("testDirichletCluster100s");
- generateSamples(40, 1, 1, 3);
- generateSamples(30, 1, 0, 0.1);
- generateSamples(30, 0, 1, 0.1);
-
- DirichletClusterer dc = new DirichletClusterer(sampleData,
- new
SampledNormalDistribution(new VectorWritable(new DenseVector(2))),
- 1.0,
- 10,
- 1,
- 0);
- List<Cluster[]> result = dc.cluster(30);
- printResults(result, 2);
- assertNotNull(result);
- }
-
- @Test
- public void testDirichletCluster100as() {
- System.out.println("testDirichletCluster100as");
- generateSamples(40, 1, 1, 3);
- generateSamples(30, 1, 0, 0.1);
- generateSamples(30, 0, 1, 0.1);
-
- DirichletClusterer dc = new DirichletClusterer(sampleData,
- new
AsymmetricSampledNormalDistribution(new VectorWritable(new DenseVector(2))),
- 1.0,
- 10,
- 1,
- 0);
- List<Cluster[]> result = dc.cluster(30);
- printResults(result, 2);
- assertNotNull(result);
- }
-
- @Test
- public void testDirichletCluster100C3() {
- System.out.println("testDirichletCluster100");
- generateSamples(40, 1, 1, 3, 3);
- generateSamples(30, 1, 0, 0.1, 3);
- generateSamples(30, 0, 1, 0.1, 3);
-
- DirichletClusterer dc = new DirichletClusterer(sampleData,
- new
NormalModelDistribution(new VectorWritable(new DenseVector(3))),
- 1.0,
- 10,
- 1,
- 0);
- List<Cluster[]> result = dc.cluster(30);
- printResults(result, 2);
- assertNotNull(result);
- }
-
- @Test
- public void testDirichletCluster100sC3() {
- System.out.println("testDirichletCluster100s");
- generateSamples(40, 1, 1, 3, 3);
- generateSamples(30, 1, 0, 0.1, 3);
- generateSamples(30, 0, 1, 0.1, 3);
-
- DirichletClusterer dc = new DirichletClusterer(sampleData,
- new
SampledNormalDistribution(new VectorWritable(new DenseVector(3))),
- 1.0,
- 10,
- 1,
- 0);
- List<Cluster[]> result = dc.cluster(30);
- printResults(result, 2);
- assertNotNull(result);
- }
-
- @Test
- public void testDirichletCluster100asC3() {
- System.out.println("testDirichletCluster100as");
- generateSamples(40, 1, 1, 3, 3);
- generateSamples(30, 1, 0, 0.1, 3);
- generateSamples(30, 0, 1, 0.1, 3);
-
- DirichletClusterer dc = new DirichletClusterer(sampleData,
- new
AsymmetricSampledNormalDistribution(new VectorWritable(new DenseVector(3))),
+ new
GaussianClusterDistribution(new VectorWritable(new DenseVector(2))),
1.0,
10,
1,
Modified:
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/dirichlet/TestMapReduce.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/test/java/org/apache/mahout/clustering/dirichlet/TestMapReduce.java?rev=1096459&r1=1096458&r2=1096459&view=diff
==============================================================================
---
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/dirichlet/TestMapReduce.java
(original)
+++
mahout/trunk/core/src/test/java/org/apache/mahout/clustering/dirichlet/TestMapReduce.java
Mon Apr 25 11:36:59 2011
@@ -38,13 +38,10 @@ import org.apache.hadoop.util.ToolRunner
import org.apache.mahout.clustering.Cluster;
import org.apache.mahout.clustering.ClusteringTestUtils;
import org.apache.mahout.clustering.Model;
-import
org.apache.mahout.clustering.dirichlet.models.AsymmetricSampledNormalModel;
import
org.apache.mahout.clustering.dirichlet.models.DistanceMeasureClusterDistribution;
import org.apache.mahout.clustering.dirichlet.models.DistributionDescription;
-import org.apache.mahout.clustering.dirichlet.models.NormalModel;
-import org.apache.mahout.clustering.dirichlet.models.NormalModelDistribution;
-import org.apache.mahout.clustering.dirichlet.models.SampledNormalDistribution;
-import org.apache.mahout.clustering.dirichlet.models.SampledNormalModel;
+import org.apache.mahout.clustering.dirichlet.models.GaussianCluster;
+import
org.apache.mahout.clustering.dirichlet.models.GaussianClusterDistribution;
import org.apache.mahout.common.DummyRecordWriter;
import org.apache.mahout.common.MahoutTestCase;
import org.apache.mahout.common.commandline.DefaultOptionCreator;
@@ -127,7 +124,7 @@ public final class TestMapReduce extends
public void testMapper() throws Exception {
generateSamples(10, 0, 0, 1);
DirichletState state =
- new DirichletState(new NormalModelDistribution(new VectorWritable(new
DenseVector(2))), 5, 1);
+ new DirichletState(new GaussianClusterDistribution(new
VectorWritable(new DenseVector(2))), 5, 1);
DirichletMapper mapper = new DirichletMapper();
mapper.setup(state);
@@ -150,7 +147,7 @@ public final class TestMapReduce extends
generateSamples(100, 0, 2, 1);
generateSamples(100, 2, 2, 1);
DirichletState state =
- new DirichletState(new SampledNormalDistribution(new
VectorWritable(new DenseVector(2))), 20, 1);
+ new DirichletState(new GaussianClusterDistribution(new
VectorWritable(new DenseVector(2))), 20, 1);
DirichletMapper mapper = new DirichletMapper();
mapper.setup(state);
@@ -182,7 +179,7 @@ public final class TestMapReduce extends
generateSamples(100, 0, 2, 1);
generateSamples(100, 2, 2, 1);
DirichletState state =
- new DirichletState(new SampledNormalDistribution(new
VectorWritable(new DenseVector(2))), 20, 1.0);
+ new DirichletState(new GaussianClusterDistribution(new
VectorWritable(new DenseVector(2))), 20, 1.0);
Collection<Model<VectorWritable>[]> models = new
ArrayList<Model<VectorWritable>[]>();
@@ -254,7 +251,7 @@ public final class TestMapReduce extends
// Now run the driver using the run() method. Others can use runJob() as
before
Integer maxIterations = 5;
DistributionDescription description =
- new DistributionDescription(SampledNormalDistribution.class.getName(),
+ new
DistributionDescription(GaussianClusterDistribution.class.getName(),
DenseVector.class.getName(),
null,
2);
@@ -294,7 +291,7 @@ public final class TestMapReduce extends
// Now run the driver using the run() method. Others can use runJob() as
before
Integer maxIterations = 5;
DistributionDescription description =
- new DistributionDescription(SampledNormalDistribution.class.getName(),
+ new
DistributionDescription(GaussianClusterDistribution.class.getName(),
DenseVector.class.getName(),
null,
2);
@@ -327,7 +324,7 @@ public final class TestMapReduce extends
// Now run the driver
int maxIterations = 3;
DistributionDescription description =
- new DistributionDescription(SampledNormalDistribution.class.getName(),
+ new
DistributionDescription(GaussianClusterDistribution.class.getName(),
DenseVector.class.getName(),
null,
2);
@@ -513,59 +510,4 @@ public final class TestMapReduce extends
ClusteringTestUtils.writePointsToFile(sampleData,
getTestTempFilePath("input/data4.txt"), fs, conf);
}
- @Test
- public void testNormalModelWritableSerialization() throws Exception {
- double[] m = { 1.1, 2.2, 3.3 };
- Writable model = new NormalModel(5, new DenseVector(m), 3.3);
- DataOutputBuffer out = new DataOutputBuffer();
- model.write(out);
- Writable model2 = new NormalModel();
- DataInputBuffer in = new DataInputBuffer();
- in.reset(out.getData(), out.getLength());
- model2.readFields(in);
- assertEquals("models", model.toString(), model2.toString());
- }
-
- @Test
- public void testSampledNormalModelWritableSerialization() throws Exception {
- double[] m = { 1.1, 2.2, 3.3 };
- Writable model = new SampledNormalModel(5, new DenseVector(m), 3.3);
- DataOutputBuffer out = new DataOutputBuffer();
- model.write(out);
- Writable model2 = new SampledNormalModel();
- DataInputBuffer in = new DataInputBuffer();
- in.reset(out.getData(), out.getLength());
- model2.readFields(in);
- assertEquals("models", model.toString(), model2.toString());
- }
-
- @Test
- public void testAsymmetricSampledNormalModelWritableSerialization() throws
Exception {
- double[] m = { 1.1, 2.2, 3.3 };
- double[] s = { 3.3, 4.4, 5.5 };
- Writable model = new AsymmetricSampledNormalModel(5, new DenseVector(m),
new DenseVector(s));
- DataOutputBuffer out = new DataOutputBuffer();
- model.write(out);
- Writable model2 = new AsymmetricSampledNormalModel();
- DataInputBuffer in = new DataInputBuffer();
- in.reset(out.getData(), out.getLength());
- model2.readFields(in);
- assertEquals("models", model.toString(), model2.toString());
- }
-
- @Test
- public void testClusterWritableSerialization() throws Exception {
- double[] m = { 1.1, 2.2, 3.3 };
- DirichletCluster cluster = new DirichletCluster(new NormalModel(5, new
DenseVector(m), 4), 10);
- DataOutputBuffer out = new DataOutputBuffer();
- cluster.write(out);
- DirichletCluster cluster2 = new DirichletCluster();
- DataInputBuffer in = new DataInputBuffer();
- in.reset(out.getData(), out.getLength());
- cluster2.readFields(in);
- assertEquals("count", cluster.getTotalCount(), cluster2.getTotalCount(),
EPSILON);
- assertNotNull("model null", cluster2.getModel());
- assertEquals("model", cluster.getModel().toString(),
cluster2.getModel().toString());
- }
-
}
Modified:
mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/dirichlet/Job.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/dirichlet/Job.java?rev=1096459&r1=1096458&r2=1096459&view=diff
==============================================================================
---
mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/dirichlet/Job.java
(original)
+++
mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/dirichlet/Job.java
Mon Apr 25 11:36:59 2011
@@ -29,7 +29,6 @@ import org.apache.mahout.clustering.conv
import org.apache.mahout.clustering.dirichlet.DirichletDriver;
import org.apache.mahout.clustering.dirichlet.models.DistributionDescription;
import
org.apache.mahout.clustering.dirichlet.models.GaussianClusterDistribution;
-import org.apache.mahout.clustering.dirichlet.models.NormalModelDistribution;
import org.apache.mahout.common.AbstractJob;
import org.apache.mahout.common.HadoopUtil;
import org.apache.mahout.common.commandline.DefaultOptionCreator;
@@ -78,8 +77,8 @@ public final class Job extends AbstractJ
addOption(new
DefaultOptionBuilder().withLongName(DirichletDriver.MODEL_DISTRIBUTION_CLASS_OPTION)
.withRequired(false).withShortName("md").withArgument(new
ArgumentBuilder()
.withName(DirichletDriver.MODEL_DISTRIBUTION_CLASS_OPTION)
-
.withDefault(NormalModelDistribution.class.getName()).withMinimum(1).withMaximum(1).create())
- .withDescription("The ModelDistribution class name. " + "Defaults to
NormalModelDistribution").create());
+
.withDefault(GaussianClusterDistribution.class.getName()).withMinimum(1).withMaximum(1).create())
+ .withDescription("The ModelDistribution class name. Defaults to
GaussianClusterDistribution").create());
addOption(new
DefaultOptionBuilder().withLongName(DirichletDriver.MODEL_PROTOTYPE_CLASS_OPTION).withRequired(false)
.withShortName("mp").withArgument(new
ArgumentBuilder().withName("prototypeClass")
.withDefault(RandomAccessSparseVector.class.getName()).withMinimum(1).withMaximum(1).create())
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=1096459&r1=1096458&r2=1096459&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
Mon Apr 25 11:36:59 2011
@@ -35,7 +35,6 @@ import org.apache.mahout.clustering.diri
import
org.apache.mahout.clustering.dirichlet.models.DistanceMeasureClusterDistribution;
import org.apache.mahout.clustering.dirichlet.models.DistributionDescription;
import
org.apache.mahout.clustering.dirichlet.models.GaussianClusterDistribution;
-import org.apache.mahout.clustering.dirichlet.models.SampledNormalDistribution;
import org.apache.mahout.clustering.fuzzykmeans.FuzzyKMeansDriver;
import org.apache.mahout.clustering.kmeans.KMeansDriver;
import org.apache.mahout.clustering.meanshift.MeanShiftCanopyDriver;
@@ -237,23 +236,6 @@ public final class TestClusterDumper ext
}
@Test
- public void testDirichlet() throws Exception {
- Path output = getTestTempDirPath("output");
- NamedVector prototype = (NamedVector) sampleData.get(0).get();
- DistributionDescription description =
- new DistributionDescription(SampledNormalDistribution.class.getName(),
- RandomAccessSparseVector.class.getName(),
- null,
- prototype.getDelegate().size());
- Configuration conf = new Configuration();
- DirichletDriver.run(conf, getTestTempDirPath("testdata"), output,
description, 15, 10, 1.0, true, true, 0, true);
- // run ClusterDumper
- ClusterDumper clusterDumper =
- new ClusterDumper(finalClusterPath(conf, output, 10), new Path(output,
"clusteredPoints"));
- clusterDumper.printClusters(termDictionary);
- }
-
- @Test
public void testDirichlet2() throws Exception {
Path output = getTestTempDirPath("output");
NamedVector prototype = (NamedVector) sampleData.get(0).get();
Modified:
mahout/trunk/utils/src/test/java/org/apache/mahout/clustering/dirichlet/TestL1ModelClustering.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/utils/src/test/java/org/apache/mahout/clustering/dirichlet/TestL1ModelClustering.java?rev=1096459&r1=1096458&r2=1096459&view=diff
==============================================================================
---
mahout/trunk/utils/src/test/java/org/apache/mahout/clustering/dirichlet/TestL1ModelClustering.java
(original)
+++
mahout/trunk/utils/src/test/java/org/apache/mahout/clustering/dirichlet/TestL1ModelClustering.java
Mon Apr 25 11:36:59 2011
@@ -35,7 +35,7 @@ import org.apache.lucene.util.Version;
import org.apache.mahout.clustering.Cluster;
import org.apache.mahout.clustering.Model;
import
org.apache.mahout.clustering.dirichlet.models.DistanceMeasureClusterDistribution;
-import org.apache.mahout.clustering.dirichlet.models.L1ModelDistribution;
+import
org.apache.mahout.clustering.dirichlet.models.GaussianClusterDistribution;
import org.apache.mahout.math.Vector;
import org.apache.mahout.math.VectorWritable;
import org.apache.mahout.utils.MahoutTestCase;
@@ -206,7 +206,8 @@ public final class TestL1ModelClustering
@Test
public void testDocs() throws Exception {
getSampleData(DOCS);
- DirichletClusterer dc = new DirichletClusterer(sampleData, new
L1ModelDistribution(sampleData.get(0)), 1.0, 15, 1, 0);
+ DirichletClusterer dc =
+ new DirichletClusterer(sampleData, new
GaussianClusterDistribution(sampleData.get(0)), 1.0, 15, 1, 0);
List<Cluster[]> result = dc.cluster(10);
assertNotNull(result);
printSamples(result, 0);
@@ -231,7 +232,8 @@ public final class TestL1ModelClustering
@Test
public void testDocs2() throws Exception {
getSampleData(DOCS2);
- DirichletClusterer dc = new DirichletClusterer(sampleData, new
L1ModelDistribution(sampleData.get(0)), 1.0, 15, 1, 0);
+ DirichletClusterer dc =
+ new DirichletClusterer(sampleData, new
GaussianClusterDistribution(sampleData.get(0)), 1.0, 15, 1, 0);
List<Cluster[]> result = dc.cluster(10);
assertNotNull(result);
printSamples(result, 0);
