From f94a3d7190911804309a7941ade5d5e96a3c2028 Mon Sep 17 00:00:00 2001
From: Yuhao Yang <hhbyyh@gmail.com>
Date: Wed, 11 Mar 2015 12:26:19 +0800
Subject: [PATCH 1/2] add get for KMeans

---
 .../spark/mllib/clustering/KMeans.scala       | 35 +++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala
index 11633e824231..88bfbbb953e8 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala
@@ -52,18 +52,33 @@ class KMeans private (
    */
   def this() = this(2, 20, 1, KMeans.K_MEANS_PARALLEL, 5, 1e-4, Utils.random.nextLong())
 
+  /**
+   * Number of clusters to create (k).
+   */
+  def getK: Int = k
+
   /** Set the number of clusters to create (k). Default: 2. */
   def setK(k: Int): this.type = {
     this.k = k
     this
   }
 
+  /**
+   * Maximum number of iterations to run.
+   */
+  def getMaxIterations: Int = maxIterations
+
   /** Set maximum number of iterations to run. Default: 20. */
   def setMaxIterations(maxIterations: Int): this.type = {
     this.maxIterations = maxIterations
     this
   }
 
+  /**
+   * The initialization algorithm. This can be either "random" or "k-means||".
+   */
+  def getInitializationMode: String = initializationMode
+
   /**
    * Set the initialization algorithm. This can be either "random" to choose random points as
    * initial cluster centers, or "k-means||" to use a parallel variant of k-means++
@@ -77,6 +92,11 @@ class KMeans private (
     this
   }
 
+  /**
+   * Number of runs of the algorithm to execute in parallel.
+   */
+  def getRuns: Int = runs
+
   /**
    * :: Experimental ::
    * Set the number of runs of the algorithm to execute in parallel. We initialize the algorithm
@@ -92,6 +112,11 @@ class KMeans private (
     this
   }
 
+  /**
+   * Number of steps for the k-means|| initialization mode
+   */
+  def getInitializationSteps: Int = initializationSteps
+
   /**
    * Set the number of steps for the k-means|| initialization mode. This is an advanced
    * setting -- the default of 5 is almost always enough. Default: 5.
@@ -104,6 +129,11 @@ class KMeans private (
     this
   }
 
+  /**
+   * The distance threshold within which we've consider centers to have converged.
+   */
+  def getEpsilon: Double = epsilon
+
   /**
    * Set the distance threshold within which we've consider centers to have converged.
    * If all centers move less than this Euclidean distance, we stop iterating one run.
@@ -113,6 +143,11 @@ class KMeans private (
     this
   }
 
+  /**
+   * The random seed for cluster initialization.
+   */
+  def getSeed: Long = seed
+
   /** Set the random seed for cluster initialization. */
   def setSeed(seed: Long): this.type = {
     this.seed = seed

From f44d4dc38947b30762de359958f6f55f07eb6d6b Mon Sep 17 00:00:00 2001
From: Yuhao Yang <hhbyyh@gmail.com>
Date: Wed, 11 Mar 2015 16:07:46 +0800
Subject: [PATCH 2/2] add experimental to getRuns

---
 .../main/scala/org/apache/spark/mllib/clustering/KMeans.scala   | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala
index 88bfbbb953e8..e41f941fd2c2 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala
@@ -93,8 +93,10 @@ class KMeans private (
   }
 
   /**
+   * :: Experimental ::
    * Number of runs of the algorithm to execute in parallel.
    */
+  @Experimental
   def getRuns: Int = runs
 
   /**