Author: srowen
Date: Fri Aug 13 19:32:53 2010
New Revision: 985331
URL: http://svn.apache.org/viewvc?rev=985331&view=rev
Log:
MAHOUT-477
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/RowSimilarityJob.java
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/SimilarityMatrixEntryKey.java
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/RowSimilarityJob.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/RowSimilarityJob.java?rev=985331&r1=985330&r2=985331&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/RowSimilarityJob.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/RowSimilarityJob.java
Fri Aug 13 19:32:53 2010
@@ -32,6 +32,7 @@ import org.apache.hadoop.mapreduce.Mappe
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
+import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;
import org.apache.hadoop.util.ToolRunner;
import org.apache.mahout.common.AbstractJob;
import org.apache.mahout.math.RandomAccessSparseVector;
@@ -167,7 +168,7 @@ public class RowSimilarityJob extends Ab
IntWritable.class,
VectorWritable.class,
SequenceFileOutputFormat.class);
-
asMatrix.setPartitionerClass(SimilarityMatrixEntryKey.SimilarityMatrixEntryKeyPartitioner.class);
+ asMatrix.setPartitionerClass(HashPartitioner.class);
asMatrix.setGroupingComparatorClass(SimilarityMatrixEntryKey.SimilarityMatrixEntryKeyGroupingComparator.class);
asMatrix.getConfiguration().setInt(MAX_SIMILARITIES_PER_ROW,
maxSimilaritiesPerRow);
asMatrix.waitForCompletion(true);
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/SimilarityMatrixEntryKey.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/SimilarityMatrixEntryKey.java?rev=985331&r1=985330&r2=985331&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/SimilarityMatrixEntryKey.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/SimilarityMatrixEntryKey.java
Fri Aug 13 19:32:53 2010
@@ -23,9 +23,7 @@ import java.io.IOException;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
-import org.apache.hadoop.mapreduce.Partitioner;
import org.apache.mahout.math.Varint;
-import org.apache.mahout.math.hadoop.DistributedRowMatrix.MatrixEntryWritable;
import
org.apache.mahout.math.hadoop.similarity.RowSimilarityJob.EntriesToVectorsReducer;
/**
@@ -114,14 +112,6 @@ public class SimilarityMatrixEntryKey im
}
}
- public static class SimilarityMatrixEntryKeyPartitioner
- extends Partitioner<SimilarityMatrixEntryKey,MatrixEntryWritable> {
- @Override
- public int getPartition(SimilarityMatrixEntryKey key, MatrixEntryWritable
value, int numPartitions) {
- return (key.hashCode() * 127) % numPartitions;
- }
- }
-
public static class SimilarityMatrixEntryKeyGroupingComparator extends
WritableComparator {
protected SimilarityMatrixEntryKeyGroupingComparator() {