[SPARK-6612] [MLLIB] [PYSPARK] Python KMeans parity

The following items are added to Python kmeans:

kmeans - setEpsilon, setInitializationSteps
KMeansModel - computeCost, k

Author: Hrishikesh Subramonian <hrishikesh.subramonian@flytxt.com>

Closes #5647 from FlytxtRnD/newPyKmeansAPI and squashes the following commits:

b9e451b [Hrishikesh Subramonian] set seed to fixed value in doc test
5fd3ced [Hrishikesh Subramonian] doc test corrections
20b3c68 [Hrishikesh Subramonian] python 3 fixes
4d4e695 [Hrishikesh Subramonian] added arguments in python tests
21eb84c [Hrishikesh Subramonian] Python Kmeans - setEpsilon, setInitializationSteps, k and computeCost added.

1 files changed, 14 insertions, 1 deletions

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
index 8e9a208d61..b086cec083 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
@@ -291,12 +291,16 @@ private[python] class PythonMLLibAPI extends Serializable {
       maxIterations: Int,
       runs: Int,
       initializationMode: String,
-      seed: java.lang.Long): KMeansModel = {
+      seed: java.lang.Long,
+      initializationSteps: Int,
+      epsilon: Double): KMeansModel = {
     val kMeansAlg = new KMeans()
       .setK(k)
       .setMaxIterations(maxIterations)
       .setRuns(runs)
       .setInitializationMode(initializationMode)
+      .setInitializationSteps(initializationSteps)
+      .setEpsilon(epsilon)
 
     if (seed != null) kMeansAlg.setSeed(seed)
 
@@ -308,6 +312,15 @@ private[python] class PythonMLLibAPI extends Serializable {
   }
 
   /**
+   * Java stub for Python mllib KMeansModel.computeCost()
+   */
+  def computeCostKmeansModel(
+      data: JavaRDD[Vector],
+      centers: java.util.ArrayList[Vector]): Double = {
+    new KMeansModel(centers).computeCost(data)
+  }
+
+  /**
    * Java stub for Python mllib GaussianMixture.run()
    * Returns a list containing weights, mean and covariance of each mixture component.
    */