[SPARK-10654][MLLIB] Add columnSimilarities to IndexedRowMatrix

Add columnSimilarities to IndexedRowMatrix by delegating to functionality already in RowMatrix.

With a test.

Author: Reza Zadeh <reza@databricks.com>

Closes #8792 from rezazadeh/colsims.

1 files changed, 13 insertions, 0 deletions

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala
index e6af0c0ec7..976299124c 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala
@@ -68,6 +68,19 @@ class IndexedRowMatrix @Since("1.0.0") (
     nRows
   }
 
+
+  /**
+   * Compute all cosine similarities between columns of this matrix using the brute-force
+   * approach of computing normalized dot products.
+   *
+   * @return An n x n sparse upper-triangular matrix of cosine similarities between
+   *         columns of this matrix.
+   */
+  @Since("1.6.0")
+  def columnSimilarities(): CoordinateMatrix = {
+    toRowMatrix().columnSimilarities()
+  }
+
   /**
    * Drops row indices and converts this matrix to a
    * [[org.apache.spark.mllib.linalg.distributed.RowMatrix]].