Author: ssc
Date: Fri Sep 9 07:55:32 2011
New Revision: 1167030
URL: http://svn.apache.org/viewvc?rev=1167030&view=rev
Log:
MAHOUT-767 Improve RowSimilarityJob performance, fixed typos
Modified:
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
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CityBlockSimilarity.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CityBlockSimilarity.java?rev=1167030&r1=1167029&r2=1167030&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CityBlockSimilarity.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CityBlockSimilarity.java
Fri Sep 9 07:55:32 2011
@@ -25,7 +25,7 @@ public class CityBlockSimilarity extends
}
@Override
- public boolean consider(int numNonZeroEntriesA, int numNonZeroEntriesB,
double maxValueA, double treshold) {
+ public boolean consider(int numNonZeroEntriesA, int numNonZeroEntriesB,
double maxValueA, double threshold) {
return true;
}
}
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CooccurrenceCountSimilarity.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CooccurrenceCountSimilarity.java?rev=1167030&r1=1167029&r2=1167030&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CooccurrenceCountSimilarity.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CooccurrenceCountSimilarity.java
Fri Sep 9 07:55:32 2011
@@ -25,7 +25,7 @@ public class CooccurrenceCountSimilarity
}
@Override
- public boolean consider(int numNonZeroEntriesA, int numNonZeroEntriesB,
double maxValueA, double treshold) {
- return numNonZeroEntriesA >= treshold && numNonZeroEntriesB >= treshold;
+ public boolean consider(int numNonZeroEntriesA, int numNonZeroEntriesB,
double maxValueA, double threshold) {
+ return numNonZeroEntriesA >= threshold && numNonZeroEntriesB >= threshold;
}
}
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CosineSimilarity.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CosineSimilarity.java?rev=1167030&r1=1167029&r2=1167030&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CosineSimilarity.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/CosineSimilarity.java
Fri Sep 9 07:55:32 2011
@@ -42,7 +42,7 @@ public class CosineSimilarity implements
}
@Override
- public boolean consider(int numNonZeroEntriesA, int numNonZeroEntriesB,
double maxValueA, double treshold) {
- return numNonZeroEntriesB >= treshold / maxValueA;
+ public boolean consider(int numNonZeroEntriesA, int numNonZeroEntriesB,
double maxValueA, double threshold) {
+ return numNonZeroEntriesB >= threshold / maxValueA;
}
}
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/EuclideanDistanceSimilarity.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/EuclideanDistanceSimilarity.java?rev=1167030&r1=1167029&r2=1167030&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/EuclideanDistanceSimilarity.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/EuclideanDistanceSimilarity.java
Fri Sep 9 07:55:32 2011
@@ -51,7 +51,7 @@ public class EuclideanDistanceSimilarity
}
@Override
- public boolean consider(int numNonZeroEntriesA, int numNonZeroEntriesB,
double maxValueA, double treshold) {
+ public boolean consider(int numNonZeroEntriesA, int numNonZeroEntriesB,
double maxValueA, double threshold) {
return true;
}
}
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/LoglikelihoodSimilarity.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/LoglikelihoodSimilarity.java?rev=1167030&r1=1167029&r2=1167030&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/LoglikelihoodSimilarity.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/LoglikelihoodSimilarity.java
Fri Sep 9 07:55:32 2011
@@ -30,7 +30,7 @@ public class LoglikelihoodSimilarity ext
}
@Override
- public boolean consider(int numNonZeroEntriesA, int numNonZeroEntriesB,
double maxValueA, double treshold) {
+ public boolean consider(int numNonZeroEntriesA, int numNonZeroEntriesB,
double maxValueA, double threshold) {
return true;
}
}
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/TanimotoCoefficientSimilarity.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/TanimotoCoefficientSimilarity.java?rev=1167030&r1=1167029&r2=1167030&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/TanimotoCoefficientSimilarity.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/TanimotoCoefficientSimilarity.java
Fri Sep 9 07:55:32 2011
@@ -25,7 +25,7 @@ public class TanimotoCoefficientSimilari
}
@Override
- public boolean consider(int numNonZeroEntriesA, int numNonZeroEntriesB,
double maxValueA, double treshold) {
- return numNonZeroEntriesA >= numNonZeroEntriesB * treshold;
+ public boolean consider(int numNonZeroEntriesA, int numNonZeroEntriesB,
double maxValueA, double threshold) {
+ return numNonZeroEntriesA >= numNonZeroEntriesB * threshold;
}
}
Modified:
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/VectorSimilarityMeasure.java
URL:
http://svn.apache.org/viewvc/mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/VectorSimilarityMeasure.java?rev=1167030&r1=1167029&r2=1167030&view=diff
==============================================================================
---
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/VectorSimilarityMeasure.java
(original)
+++
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/VectorSimilarityMeasure.java
Fri Sep 9 07:55:32 2011
@@ -27,5 +27,5 @@ public interface VectorSimilarityMeasure
double norm(Vector vector);
double aggregate(double nonZeroValueA, double nonZeroValueB);
double similarity(double summedAggregations, double normA, double normB, int
numberOfColumns);
- boolean consider(int numNonZeroEntriesA, int numNonZeroEntriesB, double
maxValueA, double treshold);
+ boolean consider(int numNonZeroEntriesA, int numNonZeroEntriesB, double
maxValueA, double threshold);
}