Author: jeastman
Date: Sun Oct 17 21:26:54 2010
New Revision: 1023586
URL: http://svn.apache.org/viewvc?rev=1023586&view=rev
Log:
Adding descriptive job names to clustering jobs
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/CanopyDriver.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/dirichlet/DirichletDriver.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/fuzzykmeans/FuzzyKMeansDriver.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/KMeansDriver.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/lda/LDADriver.java
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/meanshift/MeanShiftCanopyDriver.java
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/InputDriver.java
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/InputDriver.java
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/evaluation/RepresentativePointsDriver.java
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/CanopyDriver.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/CanopyDriver.java?rev=1023586&r1=1023585&r2=1023586&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/CanopyDriver.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/canopy/CanopyDriver.java
Sun Oct 17 21:26:54 2010
@@ -233,7 +233,7 @@ public class CanopyDriver extends Abstra
conf.set(CanopyConfigKeys.T1_KEY, String.valueOf(t1));
conf.set(CanopyConfigKeys.T2_KEY, String.valueOf(t2));
- Job job = new Job(conf);
+ Job job = new Job(conf, "Canopy Driver running buildClusters over input: "
+ input);
job.setInputFormatClass(SequenceFileInputFormat.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
job.setMapperClass(CanopyMapper.class);
@@ -335,7 +335,7 @@ public class CanopyDriver extends Abstra
conf.set(CanopyConfigKeys.T2_KEY, String.valueOf(t2));
conf.set(CanopyConfigKeys.CANOPY_PATH_KEY, canopies.toString());
- Job job = new Job(conf);
+ Job job = new Job(conf, "Canopy Driver running clusterData over input: " +
points);
job.setInputFormatClass(SequenceFileInputFormat.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
job.setMapperClass(ClusterMapper.class);
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=1023586&r1=1023585&r2=1023586&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
Sun Oct 17 21:26:54 2010
@@ -357,8 +357,7 @@ public class DirichletDriver extends Abs
conf.set(NUM_CLUSTERS_KEY, Integer.toString(numClusters));
conf.set(ALPHA_0_KEY, Double.toString(alpha0));
- Job job = new Job(conf);
-
+ Job job = new Job(conf, "Dirichlet Driver running runIteration over
stateIn: " + stateIn);
job.setInputFormatClass(SequenceFileInputFormat.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
job.setOutputKeyClass(Text.class);
@@ -551,7 +550,7 @@ public class DirichletDriver extends Abs
conf.set(STATE_IN_KEY, stateIn.toString());
conf.set(EMIT_MOST_LIKELY_KEY, Boolean.toString(emitMostLikely));
conf.set(THRESHOLD_KEY, Double.toString(threshold));
- Job job = new Job(conf);
+ Job job = new Job(conf, "Dirichlet Driver running clusterData over input:
" + input);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(WeightedVectorWritable.class);
job.setMapperClass(DirichletClusterMapper.class);
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/fuzzykmeans/FuzzyKMeansDriver.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/fuzzykmeans/FuzzyKMeansDriver.java?rev=1023586&r1=1023585&r2=1023586&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/fuzzykmeans/FuzzyKMeansDriver.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/fuzzykmeans/FuzzyKMeansDriver.java
Sun Oct 17 21:26:54 2010
@@ -226,7 +226,7 @@ public class FuzzyKMeansDriver extends A
conf.set(FuzzyKMeansConfigKeys.EMIT_MOST_LIKELY_KEY,
Boolean.toString(true));
conf.set(FuzzyKMeansConfigKeys.THRESHOLD_KEY, Double.toString(0));
- Job job = new Job(conf);
+ Job job = new Job(conf, "FuzzyKMeans Driver running runIteration over
clustersIn: " + clustersIn);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(ClusterObservations.class);
job.setOutputKeyClass(Text.class);
@@ -517,7 +517,7 @@ public class FuzzyKMeansDriver extends A
// Clear output
output.getFileSystem(conf).delete(output, true);
- Job job = new Job(conf);
+ Job job = new Job(conf, "FuzzyKMeans Driver running clusterData over
input: " + input);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(WeightedVectorWritable.class);
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/KMeansDriver.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/KMeansDriver.java?rev=1023586&r1=1023585&r2=1023586&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/KMeansDriver.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/kmeans/KMeansDriver.java
Sun Oct 17 21:26:54 2010
@@ -321,8 +321,7 @@ public class KMeansDriver extends Abstra
conf.set(KMeansConfigKeys.DISTANCE_MEASURE_KEY, measureClass);
conf.set(KMeansConfigKeys.CLUSTER_CONVERGENCE_KEY, convergenceDelta);
- Job job = new Job(conf);
-
+ Job job = new Job(conf, "KMeans Driver running runIteration over
clustersIn: " + clustersIn);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(ClusterObservations.class);
job.setOutputKeyClass(Text.class);
@@ -470,7 +469,7 @@ public class KMeansDriver extends Abstra
conf.set(KMeansConfigKeys.DISTANCE_MEASURE_KEY,
measure.getClass().getName());
conf.set(KMeansConfigKeys.CLUSTER_CONVERGENCE_KEY, convergenceDelta);
- Job job = new Job(conf);
+ Job job = new Job(conf, "KMeans Driver running clusterData over input: " +
input);
job.setInputFormatClass(SequenceFileInputFormat.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
job.setOutputKeyClass(IntWritable.class);
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/lda/LDADriver.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/lda/LDADriver.java?rev=1023586&r1=1023585&r2=1023586&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/lda/LDADriver.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/lda/LDADriver.java
Sun Oct 17 21:26:54 2010
@@ -262,8 +262,7 @@ public final class LDADriver extends Abs
conf.set(NUM_WORDS_KEY, Integer.toString(numWords));
conf.set(TOPIC_SMOOTHING_KEY, Double.toString(topicSmoothing));
- Job job = new Job(conf);
-
+ Job job = new Job(conf, "LDA Driver running runIteration over stateIn: " +
stateIn);
job.setOutputKeyClass(IntPairWritable.class);
job.setOutputValueClass(DoubleWritable.class);
FileInputFormat.addInputPaths(job, input.toString());
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/meanshift/MeanShiftCanopyDriver.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/clustering/meanshift/MeanShiftCanopyDriver.java?rev=1023586&r1=1023585&r2=1023586&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/meanshift/MeanShiftCanopyDriver.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/clustering/meanshift/MeanShiftCanopyDriver.java
Sun Oct 17 21:26:54 2010
@@ -430,8 +430,7 @@ public class MeanShiftCanopyDriver exten
conf.set(MeanShiftCanopyConfigKeys.T2_KEY, String.valueOf(t2));
conf.set(MeanShiftCanopyConfigKeys.CONTROL_PATH_KEY, control.toString());
- Job job = new Job(conf);
-
+ Job job = new Job(conf, "Mean Shift Driver running runIteration over
input: " + input);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(MeanShiftCanopy.class);
@@ -539,8 +538,7 @@ public class MeanShiftCanopyDriver exten
ClassNotFoundException {
Configuration conf = new Configuration();
conf.set(STATE_IN_KEY, clustersIn.toString());
- Job job = new Job(conf);
-
+ Job job = new Job(conf, "Mean Shift Driver running clusterData over input:
" + input);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(WeightedVectorWritable.class);
job.setMapperClass(MeanShiftCanopyClusterMapper.class);
@@ -554,7 +552,7 @@ public class MeanShiftCanopyDriver exten
FileOutputFormat.setOutputPath(job, output);
if (job.waitForCompletion(true) == false) {
- throw new InterruptedException("Mean Shift Clustering failed on input "
+ clustersIn.toString());
+ throw new InterruptedException("Mean Shift Clustering failed on
clustersIn " + clustersIn.toString());
}
}
}
Modified:
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/InputDriver.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/InputDriver.java?rev=1023586&r1=1023585&r2=1023586&view=diff
==============================================================================
---
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/InputDriver.java
(original)
+++
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/InputDriver.java
Sun Oct 17 21:26:54 2010
@@ -93,8 +93,8 @@ public final class InputDriver {
throws IOException, InterruptedException, ClassNotFoundException {
Configuration conf = new Configuration();
conf.set("vector.implementation.class.name", vectorClassName);
- Job job = new Job(conf);
-
+ Job job = new Job(conf, "Input Driver running over input: " + input);
+
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(VectorWritable.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
Modified:
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/InputDriver.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/InputDriver.java?rev=1023586&r1=1023585&r2=1023586&view=diff
==============================================================================
---
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/InputDriver.java
(original)
+++
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/conversion/meanshift/InputDriver.java
Sun Oct 17 21:26:54 2010
@@ -80,7 +80,7 @@ public final class InputDriver {
public static void runJob(Path input, Path output) throws IOException,
InterruptedException, ClassNotFoundException {
Configuration conf = new Configuration();
- Job job = new Job(conf);
+ Job job = new Job(conf, "Mean Shift Input Driver running over input: " +
input);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(MeanShiftCanopy.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
Modified:
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/evaluation/RepresentativePointsDriver.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/evaluation/RepresentativePointsDriver.java?rev=1023586&r1=1023585&r2=1023586&view=diff
==============================================================================
---
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/evaluation/RepresentativePointsDriver.java
(original)
+++
mahout/trunk/utils/src/main/java/org/apache/mahout/clustering/evaluation/RepresentativePointsDriver.java
Sun Oct 17 21:26:54 2010
@@ -230,7 +230,7 @@ public final class RepresentativePointsD
throws IOException, InterruptedException, ClassNotFoundException {
conf.set(STATE_IN_KEY, stateIn.toString());
conf.set(DISTANCE_MEASURE_KEY, measure.getClass().getName());
- Job job = new Job(conf);
+ Job job = new Job(conf, "Representative Points Driver running over input:
" + input);
job.setJarByClass(RepresentativePointsDriver.class);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(VectorWritable.class);