small cleanups

Author: jkbradley

mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala

@@ -27,7 +27,8 @@ import org.apache.spark.sql.types.DataType
 /**
  * :: AlphaComponent ::
  * Outputs the Hadamard product (i.e., the element-wise product) of each input vector with a
- * provided "weight" vector.  In other words, it scales each column of the dataset by a scalar multiplier.
+ * provided "weight" vector.  In other words, it scales each column of the dataset by a scalar
+ * multiplier.
  */
 @AlphaComponent
 class ElementwiseProduct extends UnaryTransformer[Vector, Vector, ElementwiseProduct] {

mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala

@@ -17,16 +17,17 @@
 
 package org.apache.spark.mllib.feature
 
-import org.apache.spark.annotation.AlphaComponent
+import org.apache.spark.annotation.Experimental
 import org.apache.spark.mllib.linalg._
 
 /**
- * :: AlphaComponent ::
- * Outputs the Hadamard product (i.e., the element-wise product) of each input vector with a provided
- * "weight" vector. In other words, it scales each column of the dataset by a scalar multiplier.
+ * :: Experimental ::
+ * Outputs the Hadamard product (i.e., the element-wise product) of each input vector with a
+ * provided "weight" vector. In other words, it scales each column of the dataset by a scalar
+ * multiplier.
  * @param scalingVector The values used to scale the reference vector's individual components.
  */
-@AlphaComponent
+@Experimental
 class ElementwiseProduct(val scalingVector: Vector) extends VectorTransformer {
 
   /**
@@ -37,7 +38,7 @@ class ElementwiseProduct(val scalingVector: Vector) extends VectorTransformer {
    */
   override def transform(vector: Vector): Vector = {
     require(vector.size == scalingVector.size,
-      s"vector sizes do not match: ${scalingVector.size} ${vector.size}")
+      s"vector sizes do not match: Expected ${scalingVector.size} but found ${vector.size}")
     vector match {
       case dv: DenseVector =>
         val values: Array[Double] = dv.values.clone()
@@ -50,7 +51,7 @@ class ElementwiseProduct(val scalingVector: Vector) extends VectorTransformer {
         Vectors.dense(values)
       case SparseVector(size, indices, vs) =>
         val values = vs.clone()
-        val dim = values.size
+        val dim = values.length
         var i = 0
         while (i < dim) {
           values(i) *= scalingVector(indices(i))

mllib/src/test/scala/org/apache/spark/mllib/feature/ElementwiseProductSuite.scala

@@ -25,29 +25,24 @@ import org.apache.spark.mllib.util.TestingUtils._
 
 class ElementwiseProductSuite extends FunSuite with MLlibTestSparkContext {
 
-  val denseData = Array(
-    Vectors.dense(1.0, 4.0, 1.9, -9.0)
-  )
-
-  val sparseData = Array(
-    Vectors.sparse(3, Seq((1, -1.0), (2, -3.0)))
-  )
-
-  val scalingVector = Vectors.dense(2.0, 0.5, 0.0, 0.25)
-
   test("elementwise (hadamard) product should properly apply vector to dense data set") {
-    val transformer = new ElementwiseProduct(scalingVector)
+    val denseData = Array(
+      Vectors.dense(1.0, 4.0, 1.9, -9.0)
+    )
+    val scalingVec = Vectors.dense(2.0, 0.5, 0.0, 0.25)
+    val transformer = new ElementwiseProduct(scalingVec)
     val transformedData = transformer.transform(sc.makeRDD(denseData))
     val transformedVecs = transformedData.collect()
-    val transformedVec = transformedVecs(0).toArray
-
-    assert(transformedVec(0) === 2.0, "product by 2.0 should have been applied")
-    assert(transformedVec(1) === 2.0, "product by 0.5 should have been applied")
-    assert(transformedVec(2) === 0.0, "product by 0.0 should have been applied")
-    assert(transformedVec(3) === -2.25, "product by 0.25 should have been applied")
+    val transformedVec = transformedVecs(0)
+    val expectedVec = Vectors.dense(2.0, 2.0, 0.0, -2.25)
+    assert(transformedVec ~== expectedVec absTol 1E-5,
+      s"Expected transformed vector $expectedVec but found $transformedVec")
   }
 
   test("elementwise (hadamard) product should properly apply vector to sparse data set") {
+    val sparseData = Array(
+      Vectors.sparse(3, Seq((1, -1.0), (2, -3.0)))
+    )
     val dataRDD = sc.parallelize(sparseData, 3)
     val scalingVec = Vectors.dense(1.0, 0.0, 0.5)
     val transformer = new ElementwiseProduct(scalingVec)