From 49227229cadfc8d1f39bd2bb36cc59ab68accbfd Mon Sep 17 00:00:00 2001
From: Octavian Geagla <ogeagla@gmail.com>
Date: Thu, 12 Feb 2015 19:24:45 -0700
Subject: [PATCH 1/9] [SPARK-5726] [MLLIB] Hadamard Vector Product Transformer

---
 docs/mllib-feature-extraction.md              | 73 ++++++++++++++++
 .../spark/ml/feature/HadamardProductTF.scala  | 45 ++++++++++
 .../spark/mllib/feature/HadamardProduct.scala | 62 ++++++++++++++
 .../mllib/feature/HadamardProductSuite.scala  | 83 +++++++++++++++++++
 4 files changed, 263 insertions(+)
 create mode 100644 mllib/src/main/scala/org/apache/spark/ml/feature/HadamardProductTF.scala
 create mode 100644 mllib/src/main/scala/org/apache/spark/mllib/feature/HadamardProduct.scala
 create mode 100644 mllib/src/test/scala/org/apache/spark/mllib/feature/HadamardProductSuite.scala

diff --git a/docs/mllib-feature-extraction.md b/docs/mllib-feature-extraction.md
index 80842b27effd..ced0b57dd907 100644
--- a/docs/mllib-feature-extraction.md
+++ b/docs/mllib-feature-extraction.md
@@ -477,3 +477,76 @@ sc.stop();
 </div>
 </div>
 
+## HadamardProduct
+
+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.
+
+`\[ \begin{pmatrix}
+v_1 \\
+\vdots \\
+v_N
+\end{pmatrix} \circ \begin{pmatrix}
+                    w_1 \\
+                    \vdots \\
+                    w_N
+                    \end{pmatrix}
+= \begin{pmatrix}
+  v_1 w_1 \\
+  \vdots \\
+  v_N w_N
+  \end{pmatrix}
+\]`
+
+[`HadamardProduct`](api/scala/index.html#org.apache.spark.mllib.feature.HadamardProduct) has the following parameter in the constructor:
+
+* `w` Vector, the scaling 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]`.
+
+### 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.
+
+
+<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.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)
+
+//same results:
+val weightedData = scaler.transform(parsedData)
+val weightedData2 = parsedData.map(x => scaler.transform(x))
+
+{% endhighlight %}
+</div>
+
+<div data-lang="python">
+{% highlight python %}
+from pyspark.mllib.linalg import Vectors
+from pyspark.mllib.feature import HadamardProduct
+
+# 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)
+
+# Same results:
+weightedData = scaler.transform(parsedData)
+weightedData2 = parsedData.map(lambda x: scaler.transform(x))
+
+{% endhighlight %}
+</div>
+</div>
+
+
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/HadamardProductTF.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/HadamardProductTF.scala
new file mode 100644
index 000000000000..390d037c2fe8
--- /dev/null
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/HadamardProductTF.scala
@@ -0,0 +1,45 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+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.linalg.{Vector, VectorUDT}
+import org.apache.spark.sql.types.DataType
+
+/**
+ * :: AlphaComponent
+ * Maps a vector to the hadamard product of it and a reference vector.
+ */
+@AlphaComponent
+class HadamardProductTF extends UnaryTransformer[Vector, Vector, HadamardProductTF] {
+
+  /** 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
+  }
+
+  override protected def outputDataType: DataType = new VectorUDT()
+}
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/HadamardProduct.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/HadamardProduct.scala
new file mode 100644
index 000000000000..2c6f0b7d5bca
--- /dev/null
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/HadamardProduct.scala
@@ -0,0 +1,62 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.mllib.feature
+
+import org.apache.spark.annotation.Experimental
+import org.apache.spark.mllib.linalg._
+
+/**
+ * :: Experimental ::
+ * Component-wise scaling 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 {
+
+  /**
+   * Does the hadamard product transformation.
+   *
+   * @param vector vector to be transformed.
+   * @return transformed vector.
+   */
+  override def transform(vector: Vector): Vector = {
+    require(vector.size == scalingVector.size)
+    vector match {
+      case dv: DenseVector =>
+        val values: Array[Double] = dv.values.clone()
+        val dim = scalingVector.size
+        var i = 0
+        while(i < dim) {
+          values(i) *= scalingVector(i)
+          i+=1
+        }
+        Vectors.dense(values)
+      case SparseVector(size, indices, vs) =>
+        val values = vs.clone()
+        val dim = values.size
+        var i = 0
+        while (i < dim) {
+          values(i) *= scalingVector.apply(indices(i))
+          i += 1
+        }
+        Vectors.sparse(size, indices, values)
+      case v => throw new IllegalArgumentException("Does not support vector type " + v.getClass)
+    }
+  }
+}
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/feature/HadamardProductSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/feature/HadamardProductSuite.scala
new file mode 100644
index 000000000000..c277f4309832
--- /dev/null
+++ b/mllib/src/test/scala/org/apache/spark/mllib/feature/HadamardProductSuite.scala
@@ -0,0 +1,83 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.mllib.feature
+
+import org.apache.spark.mllib.linalg.{SparseVector, DenseVector, Vector, Vectors}
+import org.apache.spark.mllib.util.MLlibTestSparkContext
+import org.scalatest.FunSuite
+import org.apache.spark.mllib.util.TestingUtils._
+
+class HadamardProductSuite extends FunSuite with MLlibTestSparkContext{
+
+  val denseData =  Array(
+    Vectors.dense(1.0, 1.0, 0.0, 0.0),
+    Vectors.dense(1.0, 2.0, -3.0, 0.0),
+    Vectors.dense(1.0, 3.0, 0.0, 0.0),
+    Vectors.dense(1.0, 4.0, 1.9, -9.0),
+    Vectors.dense(1.0, 5.0, 0.0, 0.0)
+  )
+
+  val sparseData = Array(
+    Vectors.sparse(3, Seq((0, -2.0), (1, 2.3))),
+    Vectors.sparse(3, Seq((1, -1.0), (2, -3.0))),
+    Vectors.sparse(3, Seq((1, -5.1))),
+    Vectors.sparse(3, Seq((0, 3.8), (2, 1.9))),
+    Vectors.sparse(3, Seq((0, 1.7), (1, -0.6))),
+    Vectors.sparse(3, Seq((1, 1.9)))
+  )
+
+  val scalingVector = Vectors.dense(2.0, 0.5, 0.0, 0.25)
+
+  test("hadamard product should properly apply vector to dense data set") {
+
+    val scaler = new HadamardProduct(scalingVector)
+    val scaledData = scaler.transform(sc.makeRDD(denseData))
+
+    val scaledVecs = scaledData.collect()
+
+    val fourthVec = scaledVecs.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") {
+
+    val dataRDD = sc.parallelize(sparseData, 3)
+
+    val scalingVec = Vectors.dense(1.0, 0.0, 0.5)
+
+    val hadScaler = new HadamardProduct(scalingVec)
+
+    val data2 = sparseData.map(hadScaler.transform)
+    val data2RDD = hadScaler.transform(dataRDD)
+
+    assert((sparseData, data2, data2RDD.collect()).zipped.forall {
+      case (v1: DenseVector, v2: DenseVector, v3: DenseVector) => true
+      case (v1: SparseVector, v2: SparseVector, v3: SparseVector) => true
+      case _ => false
+    }, "The vector type should be preserved after hadamard product")
+
+    assert((data2, data2RDD.collect()).zipped.forall((v1, v2) => v1 ~== v2 absTol 1E-5))
+
+    assert(data2(0) ~== Vectors.sparse(3, Seq((0, -2.0), (1, 0.0))) absTol 1E-5)
+    assert(data2(1) ~== Vectors.sparse(3, Seq((1, 0.0), (2, -1.5))) absTol 1E-5)
+  }
+}

From cb520e69fd62a77b7d1c33d4d7a093c2a7b7d57a Mon Sep 17 00:00:00 2001
From: Octavian Geagla <ogeagla@gmail.com>
Date: Fri, 13 Feb 2015 11:25:04 -0700
Subject: [PATCH 2/9] [SPARK-5726] [MLLIB] Rename HadamardProduct to
 ElementwiseProduct

---
 docs/mllib-feature-extraction.md              | 32 +++++++++----------
 ...uctTF.scala => ElementwiseProductTF.scala} |  8 ++---
 ...Product.scala => ElementwiseProduct.scala} |  4 +--
 ...te.scala => ElementwiseProductSuite.scala} | 20 ++++++------
 4 files changed, 32 insertions(+), 32 deletions(-)
 rename mllib/src/main/scala/org/apache/spark/ml/feature/{HadamardProductTF.scala => ElementwiseProductTF.scala} (87%)
 rename mllib/src/main/scala/org/apache/spark/mllib/feature/{HadamardProduct.scala => ElementwiseProduct.scala} (92%)
 rename mllib/src/test/scala/org/apache/spark/mllib/feature/{HadamardProductSuite.scala => ElementwiseProductSuite.scala} (80%)

diff --git a/docs/mllib-feature-extraction.md b/docs/mllib-feature-extraction.md
index ced0b57dd907..b71c1512ebb2 100644
--- a/docs/mllib-feature-extraction.md
+++ b/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.
 
 `\[ \begin{pmatrix}
 v_1 \\
@@ -497,34 +497,34 @@ v_N
   \end{pmatrix}
 \]`
 
-[`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>
@@ -532,18 +532,18 @@ val weightedData2 = parsedData.map(x => scaler.transform(x))
 <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>
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/HadamardProductTF.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProductTF.scala
similarity index 87%
rename from mllib/src/main/scala/org/apache/spark/ml/feature/HadamardProductTF.scala
rename to mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProductTF.scala
index 390d037c2fe8..c3b12382c814 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/HadamardProductTF.scala
+++ b/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
 
@@ -29,7 +29,7 @@ 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")
@@ -37,8 +37,8 @@ class HadamardProductTF extends UnaryTransformer[Vector, Vector, HadamardProduct
   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()
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/HadamardProduct.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
similarity index 92%
rename from mllib/src/main/scala/org/apache/spark/mllib/feature/HadamardProduct.scala
rename to mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
index 2c6f0b7d5bca..17163df0e950 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/HadamardProduct.scala
+++ b/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.
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/feature/HadamardProductSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/feature/ElementwiseProductSuite.scala
similarity index 80%
rename from mllib/src/test/scala/org/apache/spark/mllib/feature/HadamardProductSuite.scala
rename to mllib/src/test/scala/org/apache/spark/mllib/feature/ElementwiseProductSuite.scala
index c277f4309832..57840e3b255e 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/feature/HadamardProductSuite.scala
+++ b/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),
@@ -43,14 +43,14 @@ 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")
@@ -58,16 +58,16 @@ class HadamardProductSuite extends FunSuite with MLlibTestSparkContext{
     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

From e436896dd10ec03aca92aad44386223aa54eef84 Mon Sep 17 00:00:00 2001
From: Octavian Geagla <ogeagla@gmail.com>
Date: Fri, 13 Feb 2015 11:50:59 -0700
Subject: [PATCH 3/9] [SPARK-5726] [MLLIB] Remove 'TF' from
 'ElementwiseProductTF'

---
 ...{ElementwiseProductTF.scala => ElementwiseProduct.scala} | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
 rename mllib/src/main/scala/org/apache/spark/ml/feature/{ElementwiseProductTF.scala => ElementwiseProduct.scala} (88%)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProductTF.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
similarity index 88%
rename from mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProductTF.scala
rename to mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
index c3b12382c814..7a5fedf62904 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProductTF.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.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.ElementwiseProduct
+import org.apache.spark.mllib.feature
 import org.apache.spark.mllib.linalg.{Vector, VectorUDT}
 import org.apache.spark.sql.types.DataType
 
@@ -29,7 +29,7 @@ import org.apache.spark.sql.types.DataType
  * Maps a vector to the hadamard product of it and a reference vector.
  */
 @AlphaComponent
-class ElementwiseProductTF extends UnaryTransformer[Vector, Vector, ElementwiseProductTF] {
+class ElementwiseProduct extends UnaryTransformer[Vector, Vector, ElementwiseProduct] {
 
   /** the vector to multiply with input vectors */
   val scalingVec : Param[Vector] = new Param(this, "scalingVector", "vector for hadamard product")
@@ -37,7 +37,7 @@ class ElementwiseProductTF extends UnaryTransformer[Vector, Vector, ElementwiseP
   def getScalingVec: Vector = get(scalingVec)
 
   override protected def createTransformFunc(paramMap: ParamMap): Vector => Vector = {
-    val elemScaler = new ElementwiseProduct(paramMap(scalingVec))
+    val elemScaler = new feature.ElementwiseProduct(paramMap(scalingVec))
     elemScaler.transform
   }
 

From 1dffeee4910b108238efa79439372fbbab1435e4 Mon Sep 17 00:00:00 2001
From: Octavian Geagla <ogeagla@gmail.com>
Date: Fri, 24 Apr 2015 10:10:58 -0600
Subject: [PATCH 4/9] [SPARK-5726] [MLLIB] Pass style checks.

---
 .../org/apache/spark/ml/feature/ElementwiseProduct.scala      | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
index 7a5fedf62904..5d739f826c34 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
@@ -33,8 +33,8 @@ class ElementwiseProduct extends UnaryTransformer[Vector, Vector, ElementwisePro
 
   /** 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)
+  def setScalingVec(value: Vector): this.type = set(scalingVec, value)
+  def getScalingVec: Vector = getOrDefault(scalingVec)
 
   override protected def createTransformFunc(paramMap: ParamMap): Vector => Vector = {
     val elemScaler = new feature.ElementwiseProduct(paramMap(scalingVec))

From 37d4705f10ad12fd2291abbf00b30c61de6adbdf Mon Sep 17 00:00:00 2001
From: Octavian Geagla <ogeagla@gmail.com>
Date: Wed, 6 May 2015 19:53:05 -0600
Subject: [PATCH 5/9] [SPARK-5726] [MLLIB] Incorporated feedback.

---
 docs/mllib-feature-extraction.md              | 27 ++-----------
 .../spark/ml/feature/ElementwiseProduct.scala | 16 ++++++--
 .../mllib/feature/ElementwiseProduct.scala    | 17 ++++----
 .../feature/ElementwiseProductSuite.scala     | 40 ++++++-------------
 4 files changed, 37 insertions(+), 63 deletions(-)

diff --git a/docs/mllib-feature-extraction.md b/docs/mllib-feature-extraction.md
index b71c1512ebb2..03fedd01016b 100644
--- a/docs/mllib-feature-extraction.md
+++ b/docs/mllib-feature-extraction.md
@@ -479,7 +479,7 @@ sc.stop();
 
 ## ElementwiseProduct
 
-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.
+ElementwiseProduct multiplies each input vector by a provided "weight" vector, using element-wise multiplication. In other words, it scales each column of the dataset by a scalar multiplier.  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 \\
@@ -499,7 +499,7 @@ v_N
 
 [`ElementwiseProduct`](api/scala/index.html#org.apache.spark.mllib.feature.ElementwiseProduct) has the following parameter in the constructor:
 
-* `w` Vector, the transforming vector.
+* `w`: the transforming 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]`.
 
@@ -515,36 +515,17 @@ import org.apache.spark.SparkContext._
 import org.apache.spark.mllib.feature.ElementwiseProduct
 import org.apache.spark.mllib.linalg.Vectors
 
-//load and parse the data
+// 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 transformingVector = Vectors.dense(0.0, 1.0, 2.0)
 val transformer = new ElementwiseProduct(transformingVector)
 
-//same results:
+// Batch transform and per-row transform give the same results:
 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 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(' ')]))
-
-transformingVector = Vectors.dense(0.0, 1.0, 2.0)
-transformer = ElementwiseProduct(transformingVector)
-
-# Same results:
-transformedData = transformer.transform(parsedData)
-transformedData2 = parsedData.map(lambda x: transformer.transform(x))
-
 {% endhighlight %}
 </div>
 </div>
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
index 5d739f826c34..e0fe4a568a41 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
@@ -25,18 +25,26 @@ import org.apache.spark.mllib.linalg.{Vector, VectorUDT}
 import org.apache.spark.sql.types.DataType
 
 /**
- * :: AlphaComponent
- * Maps a vector to the hadamard product of it and a reference vector.
+ * :: 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.
  */
 @AlphaComponent
 class ElementwiseProduct extends UnaryTransformer[Vector, Vector, ElementwiseProduct] {
 
-  /** the vector to multiply with input vectors */
-  val scalingVec : Param[Vector] = new Param(this, "scalingVector", "vector for hadamard product")
+  /**
+    * the vector to multiply with input vectors
+    * @group param
+    */
+  val scalingVec: Param[Vector] = new Param(this, "scalingVector", "vector for hadamard product")
+
+  /** @group setParam */
   def setScalingVec(value: Vector): this.type = set(scalingVec, value)
+
+  /** @group getParam */
   def getScalingVec: Vector = getOrDefault(scalingVec)
 
   override protected def createTransformFunc(paramMap: ParamMap): Vector => Vector = {
+    require(paramMap.contains(scalingVec), s"transformation requires a weight vector: $scalingVec")
     val elemScaler = new feature.ElementwiseProduct(paramMap(scalingVec))
     elemScaler.transform
   }
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
index 17163df0e950..5700bf68b154 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
@@ -17,16 +17,16 @@
 
 package org.apache.spark.mllib.feature
 
-import org.apache.spark.annotation.Experimental
+import org.apache.spark.annotation.AlphaComponent
 import org.apache.spark.mllib.linalg._
 
 /**
- * :: Experimental ::
- * Element-wise product of dense vectors by a provided vector's components.
+ * :: 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.
  *
  * @param scalingVector The values used to scale the reference vector's individual components.
  */
-@Experimental
+@AlphaComponent
 class ElementwiseProduct(val scalingVector: Vector) extends VectorTransformer {
 
   /**
@@ -36,15 +36,16 @@ class ElementwiseProduct(val scalingVector: Vector) extends VectorTransformer {
    * @return transformed vector.
    */
   override def transform(vector: Vector): Vector = {
-    require(vector.size == scalingVector.size)
+    require(vector.size == scalingVector.size,
+      s"vector sizes do not match: ${scalingVector.size} ${vector.size}")
     vector match {
       case dv: DenseVector =>
         val values: Array[Double] = dv.values.clone()
         val dim = scalingVector.size
         var i = 0
-        while(i < dim) {
+        while (i < dim) {
           values(i) *= scalingVector(i)
-          i+=1
+          i += 1
         }
         Vectors.dense(values)
       case SparseVector(size, indices, vs) =>
@@ -52,7 +53,7 @@ class ElementwiseProduct(val scalingVector: Vector) extends VectorTransformer {
         val dim = values.size
         var i = 0
         while (i < dim) {
-          values(i) *= scalingVector.apply(indices(i))
+          values(i) *= scalingVector(indices(i))
           i += 1
         }
         Vectors.sparse(size, indices, values)
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/feature/ElementwiseProductSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/feature/ElementwiseProductSuite.scala
index 57840e3b255e..e1ec10d02d7c 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/feature/ElementwiseProductSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/feature/ElementwiseProductSuite.scala
@@ -17,55 +17,40 @@
 
 package org.apache.spark.mllib.feature
 
-import org.apache.spark.mllib.linalg.{SparseVector, DenseVector, Vector, Vectors}
-import org.apache.spark.mllib.util.MLlibTestSparkContext
 import org.scalatest.FunSuite
+
+import org.apache.spark.mllib.linalg.{DenseVector, SparseVector, Vectors}
+import org.apache.spark.mllib.util.MLlibTestSparkContext
 import org.apache.spark.mllib.util.TestingUtils._
 
-class ElementwiseProductSuite extends FunSuite with MLlibTestSparkContext{
+class ElementwiseProductSuite extends FunSuite with MLlibTestSparkContext {
 
-  val denseData =  Array(
-    Vectors.dense(1.0, 1.0, 0.0, 0.0),
-    Vectors.dense(1.0, 2.0, -3.0, 0.0),
-    Vectors.dense(1.0, 3.0, 0.0, 0.0),
-    Vectors.dense(1.0, 4.0, 1.9, -9.0),
-    Vectors.dense(1.0, 5.0, 0.0, 0.0)
+  val denseData = Array(
+    Vectors.dense(1.0, 4.0, 1.9, -9.0)
   )
 
   val sparseData = Array(
-    Vectors.sparse(3, Seq((0, -2.0), (1, 2.3))),
-    Vectors.sparse(3, Seq((1, -1.0), (2, -3.0))),
-    Vectors.sparse(3, Seq((1, -5.1))),
-    Vectors.sparse(3, Seq((0, 3.8), (2, 1.9))),
-    Vectors.sparse(3, Seq((0, 1.7), (1, -0.6))),
-    Vectors.sparse(3, Seq((1, 1.9)))
+    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 transformedData = transformer.transform(sc.makeRDD(denseData))
-
     val transformedVecs = transformedData.collect()
+    val transformedVec = transformedVecs(0).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")
+    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")
   }
 
   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 transformer = new ElementwiseProduct(scalingVec)
-
     val data2 = sparseData.map(transformer.transform)
     val data2RDD = transformer.transform(dataRDD)
 
@@ -76,7 +61,6 @@ class ElementwiseProductSuite extends FunSuite with MLlibTestSparkContext{
     }, "The vector type should be preserved after hadamard product")
 
     assert((data2, data2RDD.collect()).zipped.forall((v1, v2) => v1 ~== v2 absTol 1E-5))
-
     assert(data2(0) ~== Vectors.sparse(3, Seq((0, -2.0), (1, 0.0))) absTol 1E-5)
     assert(data2(1) ~== Vectors.sparse(3, Seq((1, 0.0), (2, -1.5))) absTol 1E-5)
   }

From ded3ac66024ce72f4112daac14d90be548dc36f9 Mon Sep 17 00:00:00 2001
From: Octavian Geagla <ogeagla@gmail.com>
Date: Wed, 6 May 2015 19:57:18 -0600
Subject: [PATCH 6/9] [SPARK-5726] [MLLIB] Pass style checks.

---
 .../org/apache/spark/ml/feature/ElementwiseProduct.scala      | 3 ++-
 .../org/apache/spark/mllib/feature/ElementwiseProduct.scala   | 4 ++--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
index e0fe4a568a41..d4c0ea040f90 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
@@ -26,7 +26,8 @@ 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.
+ * 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.
  */
 @AlphaComponent
 class ElementwiseProduct extends UnaryTransformer[Vector, Vector, ElementwiseProduct] {
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
index 5700bf68b154..bd3b5f825c18 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
@@ -22,8 +22,8 @@ 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.
- *
+ * 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

From 459516588fd9d162f10bdb0e84c09c8499db4c32 Mon Sep 17 00:00:00 2001
From: Octavian Geagla <ogeagla@gmail.com>
Date: Wed, 6 May 2015 19:58:54 -0600
Subject: [PATCH 7/9] [SPARK-5726] [MLLIB] Remove erroneous test case.

---
 .../apache/spark/mllib/feature/ElementwiseProductSuite.scala   | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/mllib/src/test/scala/org/apache/spark/mllib/feature/ElementwiseProductSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/feature/ElementwiseProductSuite.scala
index e1ec10d02d7c..b5fe36a17225 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/feature/ElementwiseProductSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/mllib/feature/ElementwiseProductSuite.scala
@@ -61,7 +61,6 @@ class ElementwiseProductSuite extends FunSuite with MLlibTestSparkContext {
     }, "The vector type should be preserved after hadamard product")
 
     assert((data2, data2RDD.collect()).zipped.forall((v1, v2) => v1 ~== v2 absTol 1E-5))
-    assert(data2(0) ~== Vectors.sparse(3, Seq((0, -2.0), (1, 0.0))) absTol 1E-5)
-    assert(data2(1) ~== Vectors.sparse(3, Seq((1, 0.0), (2, -1.5))) absTol 1E-5)
+    assert(data2(0) ~== Vectors.sparse(3, Seq((1, 0.0), (2, -1.5))) absTol 1E-5)
   }
 }

From 90f7e3962c5ddf68ae8760de30f06fb149ada688 Mon Sep 17 00:00:00 2001
From: "Joseph K. Bradley" <joseph@databricks.com>
Date: Thu, 7 May 2015 00:14:34 -0700
Subject: [PATCH 8/9] small cleanups

---
 .../spark/ml/feature/ElementwiseProduct.scala |  3 +-
 .../mllib/feature/ElementwiseProduct.scala    | 15 +++++-----
 .../feature/ElementwiseProductSuite.scala     | 29 ++++++++-----------
 3 files changed, 22 insertions(+), 25 deletions(-)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
index d4c0ea040f90..de3555a5b74d 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
+++ b/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] {
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
index bd3b5f825c18..b0985baf9b27 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
+++ b/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))
diff --git a/mllib/src/test/scala/org/apache/spark/mllib/feature/ElementwiseProductSuite.scala b/mllib/src/test/scala/org/apache/spark/mllib/feature/ElementwiseProductSuite.scala
index b5fe36a17225..f3a482abda87 100644
--- a/mllib/src/test/scala/org/apache/spark/mllib/feature/ElementwiseProductSuite.scala
+++ b/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)

From fac12ad29b6a640b6567e66e57a8176deb621dc8 Mon Sep 17 00:00:00 2001
From: Octavian Geagla <ogeagla@gmail.com>
Date: Thu, 7 May 2015 13:22:53 -0600
Subject: [PATCH 9/9] [SPARK-5726] [MLLIB] Use new createTransformFunc.

---
 .../org/apache/spark/ml/feature/ElementwiseProduct.scala  | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
index de3555a5b74d..f8b56293e3cc 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
@@ -19,7 +19,7 @@ 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.ml.param.Param
 import org.apache.spark.mllib.feature
 import org.apache.spark.mllib.linalg.{Vector, VectorUDT}
 import org.apache.spark.sql.types.DataType
@@ -45,9 +45,9 @@ class ElementwiseProduct extends UnaryTransformer[Vector, Vector, ElementwisePro
   /** @group getParam */
   def getScalingVec: Vector = getOrDefault(scalingVec)
 
-  override protected def createTransformFunc(paramMap: ParamMap): Vector => Vector = {
-    require(paramMap.contains(scalingVec), s"transformation requires a weight vector: $scalingVec")
-    val elemScaler = new feature.ElementwiseProduct(paramMap(scalingVec))
+  override protected def createTransformFunc: Vector => Vector = {
+    require(params.contains(scalingVec), s"transformation requires a weight vector")
+    val elemScaler = new feature.ElementwiseProduct($(scalingVec))
     elemScaler.transform
   }