SPARK-5400 [MLlib] Changed name of GaussianMixtureEM to GaussianMixture

Decoupling the model and the algorithm

Author: Travis Galoppo <tjg2107@columbia.edu>

Closes #4290 from tgaloppo/spark-5400 and squashes the following commits:

9c1534c [Travis Galoppo] Fixed invokation instructions in comments
d848076 [Travis Galoppo] SPARK-5400 Changed name of GaussianMixtureEM to GaussianMixture to separate model from algorithm

examples/src/main/scala/org/apache/spark/examples/mllib/DenseGmmEM.scala → examples/src/main/scala/org/apache/spark/examples/mllib/DenseGaussianMixture.scala

@@ -18,17 +18,17 @@
 package org.apache.spark.examples.mllib
 
 import org.apache.spark.{SparkConf, SparkContext}
-import org.apache.spark.mllib.clustering.GaussianMixtureEM
+import org.apache.spark.mllib.clustering.GaussianMixture
 import org.apache.spark.mllib.linalg.Vectors
 
 /**
  * An example Gaussian Mixture Model EM app. Run with
  * {{{
- * ./bin/run-example org.apache.spark.examples.mllib.DenseGmmEM <input> <k> <covergenceTol>
+ * ./bin/run-example mllib.DenseGaussianMixture <input> <k> <convergenceTol>
  * }}}
  * If you use it as a template to create your own app, please use `spark-submit` to submit your app.
  */
-object DenseGmmEM {
+object DenseGaussianMixture {
   def main(args: Array[String]): Unit = {
     if (args.length < 3) {
       println("usage: DenseGmmEM <input file> <k> <convergenceTol> [maxIterations]")
@@ -46,7 +46,7 @@ object DenseGmmEM {
       Vectors.dense(line.trim.split(' ').map(_.toDouble))
     }.cache()
       
-    val clusters = new GaussianMixtureEM()
+    val clusters = new GaussianMixture()
       .setK(k)
       .setConvergenceTol(convergenceTol)
       .setMaxIterations(maxIterations)

mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixtureEM.scala → mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixture.scala

@@ -44,7 +44,7 @@ import org.apache.spark.util.Utils
  * is considered to have occurred.
  * @param maxIterations The maximum number of iterations to perform
  */
-class GaussianMixtureEM private (
+class GaussianMixture private (
     private var k: Int, 
     private var convergenceTol: Double, 
     private var maxIterations: Int,

mllib/src/test/scala/org/apache/spark/mllib/clustering/GMMExpectationMaximizationSuite.scala → mllib/src/test/scala/org/apache/spark/mllib/clustering/GaussianMixtureSuite.scala

@@ -24,7 +24,7 @@ import org.apache.spark.mllib.stat.distribution.MultivariateGaussian
 import org.apache.spark.mllib.util.MLlibTestSparkContext
 import org.apache.spark.mllib.util.TestingUtils._
 
-class GMMExpectationMaximizationSuite extends FunSuite with MLlibTestSparkContext {
+class GaussianMixtureSuite extends FunSuite with MLlibTestSparkContext {
   test("single cluster") {
     val data = sc.parallelize(Array(
       Vectors.dense(6.0, 9.0),
@@ -39,7 +39,7 @@ class GMMExpectationMaximizationSuite extends FunSuite with MLlibTestSparkContex
 
     val seeds = Array(314589, 29032897, 50181, 494821, 4660)
     seeds.foreach { seed =>
-      val gmm = new GaussianMixtureEM().setK(1).setSeed(seed).run(data)
+      val gmm = new GaussianMixture().setK(1).setSeed(seed).run(data)
       assert(gmm.weights(0) ~== Ew absTol 1E-5)
       assert(gmm.gaussians(0).mu ~== Emu absTol 1E-5)
       assert(gmm.gaussians(0).sigma ~== Esigma absTol 1E-5)
@@ -68,7 +68,7 @@ class GMMExpectationMaximizationSuite extends FunSuite with MLlibTestSparkContex
     val Emu = Array(Vectors.dense(-4.3673), Vectors.dense(5.1604))
     val Esigma = Array(Matrices.dense(1, 1, Array(1.1098)), Matrices.dense(1, 1, Array(0.86644)))
     
-    val gmm = new GaussianMixtureEM()
+    val gmm = new GaussianMixture()
       .setK(2)
       .setInitialModel(initialGmm)
       .run(data)