[SPARK-5987] [MLlib] Save/load for GaussianMixtureModels

Should be self explanatory.

Author: MechCoder <manojkumarsivaraj334@gmail.com>

Closes #4986 from MechCoder/spark-5987 and squashes the following commits:

7d2cd56 [MechCoder] Iterate over dataframe in a better way
e7a14cb [MechCoder] Minor
33c84f9 [MechCoder] Store as Array[Data] instead of Data[Array]
505bd57 [MechCoder] Rebased over master and used MatrixUDT
7422bb4 [MechCoder] Store sigmas as Array[Double] instead of Array[Array[Double]]
b9794e4 [MechCoder] Minor
cb77095 [MechCoder] [SPARK-5987] Save/load for GaussianMixtureModels

1 files changed, 8 insertions, 0 deletions

diff --git a/docs/mllib-clustering.md b/docs/mllib-clustering.md
index 0b6db4fcb7..f5aa15b7d9 100644
--- a/docs/mllib-clustering.md
+++ b/docs/mllib-clustering.md
@@ -173,6 +173,7 @@ to the algorithm. We then output the parameters of the mixture model.
 
 {% highlight scala %}
 import org.apache.spark.mllib.clustering.GaussianMixture
+import org.apache.spark.mllib.clustering.GaussianMixtureModel
 import org.apache.spark.mllib.linalg.Vectors
 
 // Load and parse the data
@@ -182,6 +183,10 @@ val parsedData = data.map(s => Vectors.dense(s.trim.split(' ').map(_.toDouble)))
 // Cluster the data into two classes using GaussianMixture
 val gmm = new GaussianMixture().setK(2).run(parsedData)
 
+// Save and load model
+gmm.save(sc, "myGMMModel")
+val sameModel = GaussianMixtureModel.load(sc, "myGMMModel")
+
 // output parameters of max-likelihood model
 for (i <- 0 until gmm.k) {
   println("weight=%f\nmu=%s\nsigma=\n%s\n" format
@@ -231,6 +236,9 @@ public class GaussianMixtureExample {
     // Cluster the data into two classes using GaussianMixture
     GaussianMixtureModel gmm = new GaussianMixture().setK(2).run(parsedData.rdd());
 
+    // Save and load GaussianMixtureModel
+    gmm.save(sc, "myGMMModel")
+    GaussianMixtureModel sameModel = GaussianMixtureModel.load(sc, "myGMMModel")
     // Output the parameters of the mixture model
     for(int j=0; j<gmm.k(); j++) {
         System.out.println("weight=%f\nmu=%s\nsigma=\n%s\n",