[SPARK-7639] [PYSPARK] [MLLIB] Python API for KernelDensity

Python API for KernelDensity

Author: MechCoder <manojkumarsivaraj334@gmail.com>

Closes #6387 from MechCoder/spark-7639 and squashes the following commits:

17abc62 [MechCoder] add tests
2de6540 [MechCoder] style tests
bf4acc0 [MechCoder] Added doctests
84359d5 [MechCoder] [SPARK-7639] Python API for KernelDensity

1 files changed, 11 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 16f3131796..8f66bc808a 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
@@ -43,7 +43,8 @@ import org.apache.spark.mllib.regression._
 import org.apache.spark.mllib.stat.correlation.CorrelationNames
 import org.apache.spark.mllib.stat.distribution.MultivariateGaussian
 import org.apache.spark.mllib.stat.test.ChiSqTestResult
-import org.apache.spark.mllib.stat.{MultivariateStatisticalSummary, Statistics}
+import org.apache.spark.mllib.stat.{
+  KernelDensity, MultivariateStatisticalSummary, Statistics}
 import org.apache.spark.mllib.tree.configuration.{Algo, BoostingStrategy, Strategy}
 import org.apache.spark.mllib.tree.impurity._
 import org.apache.spark.mllib.tree.loss.Losses
@@ -945,6 +946,15 @@ private[python] class PythonMLLibAPI extends Serializable {
       r => (r.getSeq(0).toArray[Any], r.getSeq(1).toArray[Any])))
   }
 
+  /**
+   * Java stub for the estimate method of KernelDensity
+   */
+  def estimateKernelDensity(
+      sample: JavaRDD[Double],
+      bandwidth: Double, points: java.util.ArrayList[Double]): Array[Double] = {
+    return new KernelDensity().setSample(sample).setBandwidth(bandwidth).estimate(
+      points.asScala.toArray)
+  }
 
 }