You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by sr...@apache.org on 2016/01/12 12:50:40 UTC
spark git commit: [SPARK-7615][MLLIB] MLLIB Word2Vec wordVectors
divided by Euclidean Norm equals to zero
Repository: spark
Updated Branches:
refs/heads/master 8cfa218f4 -> c48f2a3a5
[SPARK-7615][MLLIB] MLLIB Word2Vec wordVectors divided by Euclidean Norm equals to zero
Cosine similarity with 0 vector should be 0
Related to https://github.com/apache/spark/pull/10152
Author: Sean Owen <so...@cloudera.com>
Closes #10696 from srowen/SPARK-7615.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/c48f2a3a
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/c48f2a3a
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/c48f2a3a
Branch: refs/heads/master
Commit: c48f2a3a5fd714ad2ff19b29337e55583988431e
Parents: 8cfa218
Author: Sean Owen <so...@cloudera.com>
Authored: Tue Jan 12 11:50:33 2016 +0000
Committer: Sean Owen <so...@cloudera.com>
Committed: Tue Jan 12 11:50:33 2016 +0000
----------------------------------------------------------------------
.../main/scala/org/apache/spark/mllib/feature/Word2Vec.scala | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/c48f2a3a/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala
index dc5d070..dee8988 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala
@@ -543,7 +543,12 @@ class Word2VecModel private[spark] (
val cosVec = cosineVec.map(_.toDouble)
var ind = 0
while (ind < numWords) {
- cosVec(ind) /= wordVecNorms(ind)
+ val norm = wordVecNorms(ind)
+ if (norm == 0.0) {
+ cosVec(ind) = 0.0
+ } else {
+ cosVec(ind) /= norm
+ }
ind += 1
}
wordList.zip(cosVec)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org