[SPARK-8481] [MLLIB] GaussianMixtureModel predict accepting single vector

Resubmit of [apache#6906] for adding single-vec predict to GMMs

CC: dkobylarz  mengxr

To be merged with master and branch-1.5
Primary author: dkobylarz

Author: Dariusz Kobylarz <[email protected]>

Closes apache#8039 from jkbradley/gmm-predict-vec and squashes the following commits:

bfbedc4 [Dariusz Kobylarz] [SPARK-8481] [MLlib] GaussianMixtureModel predict accepting single vector

Author: dkobylarz

mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixtureModel.scala

@@ -66,6 +66,12 @@ class GaussianMixtureModel(
     responsibilityMatrix.map(r => r.indexOf(r.max))
   }
 
+  /** Maps given point to its cluster index. */
+  def predict(point: Vector): Int = {
+    val r = computeSoftAssignments(point.toBreeze.toDenseVector, gaussians, weights, k)
+    r.indexOf(r.max)
+  }
+
   /** Java-friendly version of [[predict()]] */
   def predict(points: JavaRDD[Vector]): JavaRDD[java.lang.Integer] =
     predict(points.rdd).toJavaRDD().asInstanceOf[JavaRDD[java.lang.Integer]]
@@ -83,6 +89,13 @@ class GaussianMixtureModel(
     }
   }
 
+  /**
+   * Given the input vector, return the membership values to all mixture components.
+   */
+  def predictSoft(point: Vector): Array[Double] = {
+    computeSoftAssignments(point.toBreeze.toDenseVector, gaussians, weights, k)
+  }
+
   /**
    * Compute the partial assignments for each vector
    */

mllib/src/test/scala/org/apache/spark/mllib/clustering/GaussianMixtureSuite.scala

@@ -148,6 +148,16 @@ class GaussianMixtureSuite extends SparkFunSuite with MLlibTestSparkContext {
     }
   }
 
+  test("model prediction, parallel and local") {
+    val data = sc.parallelize(GaussianTestData.data)
+    val gmm = new GaussianMixture().setK(2).setSeed(0).run(data)
+
+    val batchPredictions = gmm.predict(data)
+    batchPredictions.zip(data).collect().foreach { case (batchPred, datum) =>
+      assert(batchPred === gmm.predict(datum))
+    }
+  }
+
   object GaussianTestData {
 
     val data = Array(