Repository: spark Updated Branches: refs/heads/master 45ce3273c -> 5168c6ca9
[SPARK-4422][MLLIB]In some cases, Vectors.fromBreeze get wrong results. cc mengxr Author: GuoQiang Li <wi...@qq.com> Closes #3281 from witgo/SPARK-4422 and squashes the following commits: 5f1fa5e [GuoQiang Li] import order 50783bd [GuoQiang Li] review commits 7a10123 [GuoQiang Li] In some cases, Vectors.fromBreeze get wrong results. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/5168c6ca Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/5168c6ca Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/5168c6ca Branch: refs/heads/master Commit: 5168c6ca9f0008027d688661bae57c28cf386b54 Parents: 45ce327 Author: GuoQiang Li <wi...@qq.com> Authored: Sun Nov 16 21:31:51 2014 -0800 Committer: Xiangrui Meng <m...@databricks.com> Committed: Sun Nov 16 21:31:51 2014 -0800 ---------------------------------------------------------------------- .../main/scala/org/apache/spark/mllib/linalg/Vectors.scala | 2 +- .../scala/org/apache/spark/mllib/linalg/VectorsSuite.scala | 7 +++++++ 2 files changed, 8 insertions(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/5168c6ca/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala index 9fccd63..60ab2aa 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala @@ -237,7 +237,7 @@ object Vectors { private[mllib] def fromBreeze(breezeVector: BV[Double]): Vector = { breezeVector match { case v: BDV[Double] => - if (v.offset == 0 && v.stride == 1) { + if (v.offset == 0 && v.stride == 1 && v.length == v.data.length) { new DenseVector(v.data) } else { new DenseVector(v.toArray) // Can't use underlying array directly, so make a new one http://git-wip-us.apache.org/repos/asf/spark/blob/5168c6ca/mllib/src/test/scala/org/apache/spark/mllib/linalg/VectorsSuite.scala ---------------------------------------------------------------------- diff --git a/mllib/src/test/scala/org/apache/spark/mllib/linalg/VectorsSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/linalg/VectorsSuite.scala index 93a84fe..59cd85e 100644 --- a/mllib/src/test/scala/org/apache/spark/mllib/linalg/VectorsSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/mllib/linalg/VectorsSuite.scala @@ -17,6 +17,7 @@ package org.apache.spark.mllib.linalg +import breeze.linalg.{DenseMatrix => BDM} import org.scalatest.FunSuite import org.apache.spark.SparkException @@ -166,4 +167,10 @@ class VectorsSuite extends FunSuite { assert(v === udt.deserialize(udt.serialize(v))) } } + + test("fromBreeze") { + val x = BDM.zeros[Double](10, 10) + val v = Vectors.fromBreeze(x(::, 0)) + assert(v.size === x.rows) + } } --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org