[SPARK-5726] [MLLIB] Rename HadamardProduct to ElementwiseProduct

Author: ogeagla

docs/mllib-feature-extraction.md

@@ -477,9 +477,9 @@ sc.stop();
 </div>
 </div>
 
-## HadamardProduct
+## ElementwiseProduct
 
-HadamardProduct scales individual vector samples by a provided weighting vector component-wise.  This represents the [Hadamard product](https://en.wikipedia.org/wiki/Hadamard_product_%28matrices%29) between the input vector, `v` and weighting vector, `w`, to yield a result vector.
+ElementwiseProduct multiplies individual vector samples by a provided weighting vector component-wise.  This represents the [Hadamard product](https://en.wikipedia.org/wiki/Hadamard_product_%28matrices%29) between the input vector, `v` and transforming vector, `w`, to yield a result vector.
 
 `\[ \begin{pmatrix}
 v_1 \\
@@ -497,53 +497,53 @@ v_N
   \end{pmatrix}
 \]`
 
-[`HadamardProduct`](api/scala/index.html#org.apache.spark.mllib.feature.HadamardProduct) has the following parameter in the constructor:
+[`ElementwiseProduct`](api/scala/index.html#org.apache.spark.mllib.feature.ElementwiseProduct) has the following parameter in the constructor:
 
-* `w` Vector, the scaling vector.
+* `w` Vector, the transforming vector.
 
-`HadamardProduct` implements [`VectorTransformer`](api/scala/index.html#org.apache.spark.mllib.feature.VectorTransformer) which can apply the weighting on a `Vector` to produce a transformed `Vector` or on an `RDD[Vector]` to produce a transformed `RDD[Vector]`.
+`ElementwiseProduct` implements [`VectorTransformer`](api/scala/index.html#org.apache.spark.mllib.feature.VectorTransformer) which can apply the weighting on a `Vector` to produce a transformed `Vector` or on an `RDD[Vector]` to produce a transformed `RDD[Vector]`.
 
 ### Example
 
-This example below demonstrates how to load a simple vectors file, extract a set of vectors, then weight those vectors using a weighting vector value.
+This example below demonstrates how to load a simple vectors file, extract a set of vectors, then transform those vectors using a transforming vector value.
 
 
 <div class="codetabs">
 <div data-lang="scala">
 {% highlight scala %}
 import org.apache.spark.SparkContext._
-import org.apache.spark.mllib.feature.HadamardProduct
+import org.apache.spark.mllib.feature.ElementwiseProduct
 import org.apache.spark.mllib.linalg.Vectors
 
 //load and parse the data
 val data = sc.textFile("data/mllib/kmeans_data.txt")
 val parsedData = data.map(s => Vectors.dense(s.split(' ').map(_.toDouble)))
 
-val weightingVector = Vectors.dense(0.0, 1.0, 2.0)
-val scaler = new HadamardProduct(weightingVector)
+val transformingVector = Vectors.dense(0.0, 1.0, 2.0)
+val transformer = new ElementwiseProduct(transformingVector)
 
 //same results:
-val weightedData = scaler.transform(parsedData)
-val weightedData2 = parsedData.map(x => scaler.transform(x))
+val transformedData = transformer.transform(parsedData)
+val transformedData2 = parsedData.map(x => transformer.transform(x))
 
 {% endhighlight %}
 </div>
 
 <div data-lang="python">
 {% highlight python %}
 from pyspark.mllib.linalg import Vectors
-from pyspark.mllib.feature import HadamardProduct
+from pyspark.mllib.feature import ElementwiseProduct
 
 # Load and parse the data
 data = sc.textFile("data/mllib/kmeans_data.txt")
 parsedData = data.map(lambda line: array([float(x) for x in line.split(' ')]))
 
-weightingVector = Vectors.dense(0.0, 1.0, 2.0)
-scaler = HadamardProduct(weightingVector)
+transformingVector = Vectors.dense(0.0, 1.0, 2.0)
+transformer = ElementwiseProduct(transformingVector)
 
 # Same results:
-weightedData = scaler.transform(parsedData)
-weightedData2 = parsedData.map(lambda x: scaler.transform(x))
+transformedData = transformer.transform(parsedData)
+transformedData2 = parsedData.map(lambda x: transformer.transform(x))
 
 {% endhighlight %}
 </div>

mllib/src/main/scala/org/apache/spark/ml/feature/HadamardProductTF.scala renamed to mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProductTF.scala

@@ -20,7 +20,7 @@ package org.apache.spark.ml.feature
 import org.apache.spark.annotation.AlphaComponent
 import org.apache.spark.ml.UnaryTransformer
 import org.apache.spark.ml.param.{Param, ParamMap}
-import org.apache.spark.mllib.feature.HadamardProduct
+import org.apache.spark.mllib.feature.ElementwiseProduct
 import org.apache.spark.mllib.linalg.{Vector, VectorUDT}
 import org.apache.spark.sql.types.DataType
 
@@ -29,16 +29,16 @@ import org.apache.spark.sql.types.DataType
  * Maps a vector to the hadamard product of it and a reference vector.
  */
 @AlphaComponent
-class HadamardProductTF extends UnaryTransformer[Vector, Vector, HadamardProductTF] {
+class ElementwiseProductTF extends UnaryTransformer[Vector, Vector, ElementwiseProductTF] {
 
   /** the vector to multiply with input vectors */
   val scalingVec : Param[Vector] = new Param(this, "scalingVector", "vector for hadamard product")
   def setScalingVec(value: Vector) = set(scalingVec, value)
   def getScalingVec: Vector = get(scalingVec)
 
   override protected def createTransformFunc(paramMap: ParamMap): Vector => Vector = {
-    val hadScaler = new HadamardProduct(paramMap(scalingVec))
-    hadScaler.transform
+    val elemScaler = new ElementwiseProduct(paramMap(scalingVec))
+    elemScaler.transform
   }
 
   override protected def outputDataType: DataType = new VectorUDT()

mllib/src/main/scala/org/apache/spark/mllib/feature/HadamardProduct.scala renamed to mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala

@@ -22,12 +22,12 @@ import org.apache.spark.mllib.linalg._
 
 /**
  * :: Experimental ::
- * Component-wise scaling of dense vectors by a provided vector's components.
+ * Element-wise product of dense vectors by a provided vector's components.
  *
  * @param scalingVector The values used to scale the reference vector's individual components.
  */
 @Experimental
-class HadamardProduct(val scalingVector: Vector) extends VectorTransformer {
+class ElementwiseProduct(val scalingVector: Vector) extends VectorTransformer {
 
   /**
    * Does the hadamard product transformation.

mllib/src/test/scala/org/apache/spark/mllib/feature/HadamardProductSuite.scala renamed to mllib/src/test/scala/org/apache/spark/mllib/feature/ElementwiseProductSuite.scala

@@ -22,7 +22,7 @@ import org.apache.spark.mllib.util.MLlibTestSparkContext
 import org.scalatest.FunSuite
 import org.apache.spark.mllib.util.TestingUtils._
 
-class HadamardProductSuite extends FunSuite with MLlibTestSparkContext{
+class ElementwiseProductSuite extends FunSuite with MLlibTestSparkContext{
 
   val denseData =  Array(
     Vectors.dense(1.0, 1.0, 0.0, 0.0),
@@ -43,31 +43,31 @@ class HadamardProductSuite extends FunSuite with MLlibTestSparkContext{
 
   val scalingVector = Vectors.dense(2.0, 0.5, 0.0, 0.25)
 
-  test("hadamard product should properly apply vector to dense data set") {
+  test("elementwise (hadamard) product should properly apply vector to dense data set") {
 
-    val scaler = new HadamardProduct(scalingVector)
-    val scaledData = scaler.transform(sc.makeRDD(denseData))
+    val transformer = new ElementwiseProduct(scalingVector)
+    val transformedData = transformer.transform(sc.makeRDD(denseData))
 
-    val scaledVecs = scaledData.collect()
+    val transformedVecs = transformedData.collect()
 
-    val fourthVec = scaledVecs.apply(3).toArray
+    val fourthVec = transformedVecs.apply(3).toArray
 
     assert(fourthVec.apply(0) === 2.0, "product by 2.0 should have been applied")
     assert(fourthVec.apply(1) === 2.0, "product by 0.5 should have been applied")
     assert(fourthVec.apply(2) === 0.0, "product by 0.0 should have been applied")
     assert(fourthVec.apply(3) === -2.25, "product by 0.25 should have been applied")
   }
 
-  test("hadamard product should properly apply vector to sparse data set") {
+  test("elementwise (hadamard) product should properly apply vector to sparse data set") {
 
     val dataRDD = sc.parallelize(sparseData, 3)
 
     val scalingVec = Vectors.dense(1.0, 0.0, 0.5)
 
-    val hadScaler = new HadamardProduct(scalingVec)
+    val transformer = new ElementwiseProduct(scalingVec)
 
-    val data2 = sparseData.map(hadScaler.transform)
-    val data2RDD = hadScaler.transform(dataRDD)
+    val data2 = sparseData.map(transformer.transform)
+    val data2RDD = transformer.transform(dataRDD)
 
     assert((sparseData, data2, data2RDD.collect()).zipped.forall {
       case (v1: DenseVector, v2: DenseVector, v3: DenseVector) => true