Update the scala side of the pythonmllibapi and make the test a bit nicer too

Author: holdenk

mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala

@@ -399,7 +399,7 @@ private[python] class PythonMLLibAPI extends Serializable {
       val sigma = si.map(_.asInstanceOf[DenseMatrix])
       val gaussians = Array.tabulate(weight.length){
         i => new MultivariateGaussian(mean(i), sigma(i))
-      }      
+      }
       val model = new GaussianMixtureModel(weight, gaussians)
       model.predictSoft(data).map(Vectors.dense)
   }
@@ -494,7 +494,7 @@ private[python] class PythonMLLibAPI extends Serializable {
   def normalizeVector(p: Double, rdd: JavaRDD[Vector]): JavaRDD[Vector] = {
     new Normalizer(p).transform(rdd)
   }
-  
+
   /**
    * Java stub for StandardScaler.fit(). This stub returns a
    * handle to the Java object instead of the content of the Java object.
@@ -685,12 +685,14 @@ private[python] class PythonMLLibAPI extends Serializable {
       lossStr: String,
       numIterations: Int,
       learningRate: Double,
-      maxDepth: Int): GradientBoostedTreesModel = {
+      maxDepth: Int,
+      maxBins: Int): GradientBoostedTreesModel = {
     val boostingStrategy = BoostingStrategy.defaultParams(algoStr)
     boostingStrategy.setLoss(Losses.fromString(lossStr))
     boostingStrategy.setNumIterations(numIterations)
     boostingStrategy.setLearningRate(learningRate)
     boostingStrategy.treeStrategy.setMaxDepth(maxDepth)
+    boostingStrategy.treeStrategy.setMaxBins(maxBins)
     boostingStrategy.treeStrategy.categoricalFeaturesInfo = categoricalFeaturesInfo.asScala.toMap
 
     val cached = data.rdd.persist(StorageLevel.MEMORY_AND_DISK)

python/pyspark/mllib/tests.py

@@ -446,12 +446,10 @@ def test_regression(self):
         # Verify that maxBins is being passed through
         GradientBoostedTrees.trainRegressor(
             rdd, categoricalFeaturesInfo=categoricalFeaturesInfo, numIterations=4, maxBins=32)
-        try:
+        with self.assertRaises(Exception) as cm:
             GradientBoostedTrees.trainRegressor(
                 rdd, categoricalFeaturesInfo=categoricalFeaturesInfo, numIterations=4, maxBins=1)
-            self.fail("max bins was not passed through (or not verified!)")
-        except Exception:
-            self.pass()
+
 
 
 class StatTests(MLlibTestCase):