You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mahout.apache.org by je...@apache.org on 2010/09/30 16:05:39 UTC
svn commit: r1003067 - in /mahout/trunk:
examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/
examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/dirichlet/
examples/src/main/java/org/apache/mahout/clustering/sy...
Author: jeastman
Date: Thu Sep 30 14:05:38 2010
New Revision: 1003067
URL: http://svn.apache.org/viewvc?rev=1003067&view=rev
Log:
Moved input conversion drivers from examples to utils as they have general utility outside of the examples
Added:
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/InputDriver.java
- copied, changed from r1002835, mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/InputDriver.java
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/InputMapper.java
- copied, changed from r1002836, mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/InputMapper.java
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/InputDriver.java
- copied, changed from r1002835, mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/meanshift/InputDriver.java
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/InputMapper.java
- copied, changed from r1002836, mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/meanshift/InputMapper.java
Removed:
mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/InputDriver.java
mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/InputMapper.java
mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/meanshift/InputDriver.java
mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/meanshift/InputMapper.java
Modified:
mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/Job.java
mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/dirichlet/Job.java
mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/fuzzykmeans/Job.java
mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/kmeans/Job.java
mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/meanshift/Job.java
Modified: mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/Job.java
URL: http://svn.apache.org/viewvc/mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/Job.java?rev=1003067&r1=1003066&r2=1003067&view=diff
==============================================================================
--- mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/Job.java (original)
+++ mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/Job.java Thu Sep 30 14:05:38 2010
@@ -24,6 +24,7 @@ import org.apache.hadoop.conf.Configurat
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.util.ToolRunner;
import org.apache.mahout.clustering.canopy.CanopyDriver;
+import org.apache.mahout.clustering.conversion.InputDriver;
import org.apache.mahout.common.AbstractJob;
import org.apache.mahout.common.HadoopUtil;
import org.apache.mahout.common.commandline.DefaultOptionCreator;
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=1003067&r1=1003066&r2=1003067&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 Thu Sep 30 14:05:38 2010
@@ -31,13 +31,13 @@ import org.apache.hadoop.fs.Path;
import org.apache.hadoop.util.ToolRunner;
import org.apache.mahout.clustering.Model;
import org.apache.mahout.clustering.ModelDistribution;
+import org.apache.mahout.clustering.conversion.InputDriver;
import org.apache.mahout.clustering.dirichlet.DirichletCluster;
import org.apache.mahout.clustering.dirichlet.DirichletDriver;
import org.apache.mahout.clustering.dirichlet.DirichletMapper;
import org.apache.mahout.clustering.dirichlet.models.AbstractVectorModelDistribution;
import org.apache.mahout.clustering.dirichlet.models.GaussianClusterDistribution;
import org.apache.mahout.clustering.dirichlet.models.NormalModelDistribution;
-import org.apache.mahout.clustering.syntheticcontrol.canopy.InputDriver;
import org.apache.mahout.common.AbstractJob;
import org.apache.mahout.common.HadoopUtil;
import org.apache.mahout.common.commandline.DefaultOptionCreator;
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=1003067&r1=1003066&r2=1003067&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 Sep 30 14:05:38 2010
@@ -28,8 +28,8 @@ import org.apache.hadoop.fs.Path;
import org.apache.hadoop.util.ToolRunner;
import org.apache.mahout.clustering.Cluster;
import org.apache.mahout.clustering.canopy.CanopyDriver;
+import org.apache.mahout.clustering.conversion.InputDriver;
import org.apache.mahout.clustering.fuzzykmeans.FuzzyKMeansDriver;
-import org.apache.mahout.clustering.syntheticcontrol.canopy.InputDriver;
import org.apache.mahout.common.AbstractJob;
import org.apache.mahout.common.HadoopUtil;
import org.apache.mahout.common.commandline.DefaultOptionCreator;
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=1003067&r1=1003066&r2=1003067&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 Sep 30 14:05:38 2010
@@ -26,8 +26,8 @@ import org.apache.hadoop.fs.Path;
import org.apache.hadoop.util.ToolRunner;
import org.apache.mahout.clustering.Cluster;
import org.apache.mahout.clustering.canopy.CanopyDriver;
+import org.apache.mahout.clustering.conversion.InputDriver;
import org.apache.mahout.clustering.kmeans.KMeansDriver;
-import org.apache.mahout.clustering.syntheticcontrol.canopy.InputDriver;
import org.apache.mahout.common.AbstractJob;
import org.apache.mahout.common.HadoopUtil;
import org.apache.mahout.common.commandline.DefaultOptionCreator;
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=1003067&r1=1003066&r2=1003067&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 Sep 30 14:05:38 2010
@@ -25,6 +25,7 @@ import org.apache.commons.cli2.builder.D
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.util.ToolRunner;
+import org.apache.mahout.clustering.conversion.meanshift.InputDriver;
import org.apache.mahout.clustering.meanshift.MeanShiftCanopyDriver;
import org.apache.mahout.common.AbstractJob;
import org.apache.mahout.common.HadoopUtil;
Copied: mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/InputDriver.java (from r1002835, mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/InputDriver.java)
URL: http://svn.apache.org/viewvc/mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/InputDriver.java?p2=mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/InputDriver.java&p1=mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/InputDriver.java&r1=1002835&r2=1003067&rev=1003067&view=diff
==============================================================================
--- mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/InputDriver.java (original)
+++ mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/InputDriver.java Thu Sep 30 14:05:38 2010
@@ -15,7 +15,7 @@
* limitations under the License.
*/
-package org.apache.mahout.clustering.syntheticcontrol.canopy;
+package org.apache.mahout.clustering.conversion;
import java.io.IOException;
@@ -40,6 +40,12 @@ import org.apache.mahout.math.VectorWrit
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
+/**
+ * This class converts text files containing space-delimited floating point numbers into
+ * Mahout sequence files of VectorWritable suitable for input to the clustering jobs in
+ * particular, and any Mahout job requiring this input in general.
+ *
+ */
public final class InputDriver {
private static final Logger log = LoggerFactory.getLogger(InputDriver.class);
Copied: mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/InputMapper.java (from r1002836, mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/InputMapper.java)
URL: http://svn.apache.org/viewvc/mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/InputMapper.java?p2=mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/InputMapper.java&p1=mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/InputMapper.java&r1=1002836&r2=1003067&rev=1003067&view=diff
==============================================================================
--- mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/canopy/InputMapper.java (original)
+++ mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/InputMapper.java Thu Sep 30 14:05:38 2010
@@ -15,7 +15,7 @@
* limitations under the License.
*/
-package org.apache.mahout.clustering.syntheticcontrol.canopy;
+package org.apache.mahout.clustering.conversion;
import java.io.IOException;
import java.lang.reflect.Constructor;
Copied: mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/InputDriver.java (from r1002835, mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/meanshift/InputDriver.java)
URL: http://svn.apache.org/viewvc/mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/InputDriver.java?p2=mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/InputDriver.java&p1=mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/meanshift/InputDriver.java&r1=1002835&r2=1003067&rev=1003067&view=diff
==============================================================================
--- mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/meanshift/InputDriver.java (original)
+++ mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/InputDriver.java Thu Sep 30 14:05:38 2010
@@ -15,7 +15,7 @@
* limitations under the License.
*/
-package org.apache.mahout.clustering.syntheticcontrol.meanshift;
+package org.apache.mahout.clustering.conversion.meanshift;
import java.io.IOException;
@@ -39,6 +39,11 @@ import org.apache.mahout.common.commandl
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
+/**
+ * This class converts text files containing space-delimited floating point numbers into
+ * Mahout sequence files of MeanShiftCanopy suitable for input to the MeanShift clustering job.
+ *
+ */
public final class InputDriver {
private static final Logger log = LoggerFactory.getLogger(InputDriver.class);
@@ -79,7 +84,7 @@ public final class InputDriver {
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(MeanShiftCanopy.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
- job.setMapperClass(org.apache.mahout.clustering.syntheticcontrol.meanshift.InputMapper.class);
+ job.setMapperClass(org.apache.mahout.clustering.conversion.meanshift.InputMapper.class);
job.setReducerClass(Reducer.class);
job.setNumReduceTasks(0);
job.setJarByClass(InputDriver.class);
Copied: mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/InputMapper.java (from r1002836, mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/meanshift/InputMapper.java)
URL: http://svn.apache.org/viewvc/mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/InputMapper.java?p2=mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/InputMapper.java&p1=mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/meanshift/InputMapper.java&r1=1002836&r2=1003067&rev=1003067&view=diff
==============================================================================
--- mahout/trunk/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/meanshift/InputMapper.java (original)
+++ mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/InputMapper.java Thu Sep 30 14:05:38 2010
@@ -15,7 +15,7 @@
* limitations under the License.
*/
-package org.apache.mahout.clustering.syntheticcontrol.meanshift;
+package org.apache.mahout.clustering.conversion.meanshift;
import java.io.IOException;
import java.util.ArrayList;