From 0ddba6d88ff093a96b4931f71bd0a599afbbca78 Mon Sep 17 00:00:00 2001
From: Holden Karau <holden@us.ibm.com>
Date: Tue, 19 Jan 2016 10:15:54 -0800
Subject: [SPARK-11944][PYSPARK][MLLIB] python mllib.clustering.bisecting k
 means

From the coverage issues for 1.6 : Add Python API for mllib.clustering.BisectingKMeans.

Author: Holden Karau <holden@us.ibm.com>

Closes #10150 from holdenk/SPARK-11937-python-api-coverage-SPARK-11944-python-mllib.clustering.BisectingKMeans.
---
 .../apache/spark/mllib/api/python/PythonMLLibAPI.scala  | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'mllib')

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 061db56c74..05f9a76d32 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
@@ -119,6 +119,23 @@ private[python] class PythonMLLibAPI extends Serializable {
     }
   }
 
+  /**
+   * Java stub for Python mllib BisectingKMeans.run()
+   */
+  def trainBisectingKMeans(
+      data: JavaRDD[Vector],
+      k: Int,
+      maxIterations: Int,
+      minDivisibleClusterSize: Double,
+      seed: Long): BisectingKMeansModel = {
+    new BisectingKMeans()
+      .setK(k)
+      .setMaxIterations(maxIterations)
+      .setMinDivisibleClusterSize(minDivisibleClusterSize)
+      .setSeed(seed)
+      .run(data)
+  }
+
   /**
    * Java stub for Python mllib LinearRegressionWithSGD.train()
    */
-- 
cgit v1.2.3