[
https://issues.apache.org/jira/browse/MAHOUT-767?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13101119#comment-13101119
]
Hudson commented on MAHOUT-767:
-------------------------------
Integrated in Mahout-Quality #1026 (See
[https://builds.apache.org/job/Mahout-Quality/1026/])
MAHOUT-767 Improve RowSimilarityJob performance, fixed typos
MAHOUT-767 Improve RowSimilarityJob performance
ssc : http://svn.apache.org/viewcvs.cgi/?root=Apache-SVN&view=rev&rev=1167030
Files :
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CityBlockSimilarity.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CooccurrenceCountSimilarity.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CosineSimilarity.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/EuclideanDistanceSimilarity.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/LoglikelihoodSimilarity.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/TanimotoCoefficientSimilarity.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/VectorSimilarityMeasure.java
ssc : http://svn.apache.org/viewcvs.cgi/?root=Apache-SVN&view=rev&rev=1167027
Files :
*
/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/MaybePruneRowsMapper.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/TasteHadoopUtils.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/ToEntityPrefsMapper.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/item/RecommenderJob.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/item/ToUserVectorReducer.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/item/ToUserVectorsReducer.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/preparation
*
/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/preparation/PreparePreferenceMatrixJob.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/preparation/ToItemVectorsMapper.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/preparation/ToItemVectorsReducer.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/similarity/item/ItemSimilarityJob.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/cf/taste/hadoop/similarity/item/ToItemVectorsReducer.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/common/AbstractJob.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/common/ClassUtils.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/graph/linkanalysis/PageRankJob.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/math/VectorWritable.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/TransposeJob.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/Cooccurrence.java
*
/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
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/SimilarityType.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/WeightedOccurrence.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/WeightedOccurrenceArray.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/WeightedRowPair.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/RowSimilarityJob.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/Vectors.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CityBlockSimilarity.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CooccurrenceCountSimilarity.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CosineSimilarity.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CountbasedMeasure.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/EuclideanDistanceSimilarity.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/LoglikelihoodSimilarity.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/PearsonCorrelationSimilarity.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/TanimotoCoefficientSimilarity.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/VectorSimilarityMeasure.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/VectorSimilarityMeasures.java
*
/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/vector
*
/mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/hadoop/MaybePruneRowsMapperTest.java
*
/mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/hadoop/als/ParallelALSFactorizationJobTest.java
*
/mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/hadoop/als/PredictionJobTest.java
*
/mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/hadoop/item/RecommenderJobTest.java
*
/mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/hadoop/item/ToUserVectorReducerTest.java
*
/mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/hadoop/item/ToUserVectorsReducerTest.java
*
/mahout/trunk/core/src/test/java/org/apache/mahout/cf/taste/hadoop/similarity/item/ItemSimilarityJobTest.java
*
/mahout/trunk/core/src/test/java/org/apache/mahout/graph/linkanalysis/PageRankJobTest.java
* /mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/MathHelper.java
*
/mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/similarity/TestRowSimilarityJob.java
*
/mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/similarity/cooccurrence
*
/mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/RowSimilarityJobTest.java
*
/mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures
*
/mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/VectorSimilarityMeasuresTest.java
*
/mahout/trunk/core/src/test/java/org/apache/mahout/math/hadoop/similarity/vector
*
/mahout/trunk/integration/src/test/java/org/apache/mahout/utils/eval/ParallelFactorizationEvaluatorTest.java
* /mahout/trunk/math/src/main/java/org/apache/mahout/math/AbstractVector.java
* /mahout/trunk/pom.xml
> Improve RowSimilarityJob performance
> ------------------------------------
>
> Key: MAHOUT-767
> URL: https://issues.apache.org/jira/browse/MAHOUT-767
> Project: Mahout
> Issue Type: Improvement
> Components: Collaborative Filtering
> Affects Versions: 0.5
> Reporter: Grant Ingersoll
> Assignee: Sebastian Schelter
> Fix For: 0.6
>
> Attachments: MAHOUT-767-2.patch, MAHOUT-767.patch
>
>
> (See
> http://www.lucidimagination.com/search/document/40c4f124795c6b5/rowsimilarity_s#42ab816c27c6a9e7
> for background)
> Currently, the RowSimilarityJob defers the calculation of the similarity
> metric until the reduce phase, while emitting many Cooccurrence objects. For
> similarity metrics that are algebraic
> (http://pig.apache.org/docs/r0.8.1/udf.html#Aggregate+Functions) we should be
> able to do much of the computation during the Mapper part of this phase and
> also take advantage of a Combiner.
> We should use a marker interface to know whether a similarity metric is
> algebraic and then make use of an appropriate Mapper implementation,
> otherwise we can fall back on our existing implementation.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
