svn commit: r1402553 - /mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/EuclideanDistanceSimilarity.java

[srowen]

Author: srowen
Date: Fri Oct 26 15:49:47 2012
New Revision: 1402553

URL: http://svn.apache.org/viewvc?rev=1402553&view=rev
Log:
Fix possible NaN issue in Euclidean distance, per 
http://stackoverflow.com/questions/13089214/nan-distances-in-mahout-euclidean-implementation

Modified:
    
mahout/trunk/core/src/main/java/org/apache/mahout/math/hadoop/similarity/cooccurrence/measures/EuclideanDistanceSimilarity.java

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=1402553&r1=1402552&r2=1402553&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 Oct 26 15:49:47 2012
@@ -46,7 +46,9 @@ public class EuclideanDistanceSimilarity
 
   @Override
   public double similarity(double dots, double normA, double normB, int 
numberOfColumns) {
-    double euclideanDistance = Math.sqrt(normA - 2 * dots + normB);
+    // Arg can't be negative in theory, but can in practice due to rounding, 
so cap it.
+    // Also note that normA / normB are actually the squares of the norms.
+    double euclideanDistance = Math.sqrt(Math.max(0.0, normA - 2 * dots + 
normB));
     return 1.0 / (1.0 + euclideanDistance);
   }