From c0e48dfa611fa5d94132af7e6f6731f60ab833da Mon Sep 17 00:00:00 2001
From: Yu ISHIKAWA <yuu.ishikawa@gmail.com>
Date: Tue, 10 Nov 2015 16:42:28 -0800
Subject: [PATCH] [SPARK-11566] [MLLIB] [PYTHON] Refactoring
GaussianMixtureModel.gaussians in Python
cc jkbradley
Author: Yu ISHIKAWA <yuu.ishikawa@gmail.com>
Closes #9534 from yu-iskw/SPARK-11566.
---
.../python/GaussianMixtureModelWrapper.scala | 21 ++++++-------------
python/pyspark/mllib/clustering.py | 2 +-
2 files changed, 7 insertions(+), 16 deletions(-)
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/api/python/GaussianMixtureModelWrapper.scala b/mllib/src/main/scala/org/apache/spark/mllib/api/python/GaussianMixtureModelWrapper.scala
index 0ec88ef77d..6a3b20c88d 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/api/python/GaussianMixtureModelWrapper.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/api/python/GaussianMixtureModelWrapper.scala
@@ -17,14 +17,11 @@
package org.apache.spark.mllib.api.python
-import java.util.{List => JList}
-
-import scala.collection.JavaConverters._
-import scala.collection.mutable.ArrayBuffer
+import scala.collection.JavaConverters
import org.apache.spark.SparkContext
-import org.apache.spark.mllib.linalg.{Vector, Vectors, Matrix}
import org.apache.spark.mllib.clustering.GaussianMixtureModel
+import org.apache.spark.mllib.linalg.{Vector, Vectors}
/**
* Wrapper around GaussianMixtureModel to provide helper methods in Python
@@ -36,17 +33,11 @@ private[python] class GaussianMixtureModelWrapper(model: GaussianMixtureModel) {
/**
* Returns gaussians as a List of Vectors and Matrices corresponding each MultivariateGaussian
*/
- val gaussians: JList[Object] = {
- val modelGaussians = model.gaussians
- var i = 0
- var mu = ArrayBuffer.empty[Vector]
- var sigma = ArrayBuffer.empty[Matrix]
- while (i < k) {
- mu += modelGaussians(i).mu
- sigma += modelGaussians(i).sigma
- i += 1
+ val gaussians: Array[Byte] = {
+ val modelGaussians = model.gaussians.map { gaussian =>
+ Array[Any](gaussian.mu, gaussian.sigma)
}
- List(mu.toArray, sigma.toArray).map(_.asInstanceOf[Object]).asJava
+ SerDe.dumps(JavaConverters.seqAsJavaListConverter(modelGaussians).asJava)
}
def save(sc: SparkContext, path: String): Unit = model.save(sc, path)
diff --git a/python/pyspark/mllib/clustering.py b/python/pyspark/mllib/clustering.py
index 1fa061dc2d..c9e6f1dec6 100644
--- a/python/pyspark/mllib/clustering.py
+++ b/python/pyspark/mllib/clustering.py
@@ -266,7 +266,7 @@ class GaussianMixtureModel(JavaModelWrapper, JavaSaveable, JavaLoader):
"""
return [
MultivariateGaussian(gaussian[0], gaussian[1])
- for gaussian in zip(*self.call("gaussians"))]
+ for gaussian in self.call("gaussians")]
@property
@since('1.4.0')
--
GitLab