[SPARK-13201][SPARK-13200] Deprecation warning cleanups: KMeans & MFD…

…ataGenerator

KMeans:
Make a private non-deprecated version of setRuns API so that we can call it from the PythonAPI without deprecation warnings in our own build. Also use it internally when being called from train. Add a logWarning for non-1 values

MFDataGenerator:
Apparently we are calling round on an integer which now in Scala 2.11 results in a warning (it didn't make any sense before either). Figure out if this is a mistake we can just remove or if we got the types wrong somewhere.

I put these two together since they are both deprecation fixes in MLlib and pretty small, but I can split them up if we would prefer it that way.

Author: Holden Karau <holden@us.ibm.com>

Closes #11112 from holdenk/SPARK-13201-non-deprecated-setRuns-SPARK-mathround-integer.

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

@@ -357,7 +357,7 @@ private[python] class PythonMLLibAPI extends Serializable {
     val kMeansAlg = new KMeans()
       .setK(k)
       .setMaxIterations(maxIterations)
-      .setRuns(runs)
+      .internalSetRuns(runs)
       .setInitializationMode(initializationMode)
       .setInitializationSteps(initializationSteps)
       .setEpsilon(epsilon)

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

@@ -119,9 +119,18 @@ class KMeans private (
   @Since("0.8.0")
   @deprecated("Support for runs is deprecated. This param will have no effect in 2.0.0.", "1.6.0")
   def setRuns(runs: Int): this.type = {
+    internalSetRuns(runs)
+  }
+
+  // Internal version of setRuns for Python API, this should be removed at the same time as setRuns
+  // this is done to avoid deprecation warnings in our build.
+  private[mllib] def internalSetRuns(runs: Int): this.type = {
     if (runs <= 0) {
       throw new IllegalArgumentException("Number of runs must be positive")
     }
+    if (runs != 1) {
+      logWarning("Setting number of runs is deprecated and will have no effect in 2.0.0")
+    }
     this.runs = runs
     this
   }
@@ -502,7 +511,7 @@ object KMeans {
       seed: Long): KMeansModel = {
     new KMeans().setK(k)
       .setMaxIterations(maxIterations)
-      .setRuns(runs)
+      .internalSetRuns(runs)
       .setInitializationMode(initializationMode)
       .setSeed(seed)
       .run(data)
@@ -528,7 +537,7 @@ object KMeans {
       initializationMode: String): KMeansModel = {
     new KMeans().setK(k)
       .setMaxIterations(maxIterations)
-      .setRuns(runs)
+      .internalSetRuns(runs)
       .setInitializationMode(initializationMode)
       .run(data)
   }

mllib/src/main/scala/org/apache/spark/mllib/util/MFDataGenerator.scala

@@ -105,8 +105,7 @@ object MFDataGenerator {
 
     // optionally generate testing data
     if (test) {
-      val testSampSize = math.min(
-        math.round(sampSize * testSampFact), math.round(mn - sampSize)).toInt
+      val testSampSize = math.min(math.round(sampSize * testSampFact).toInt, mn - sampSize)
       val testOmega = shuffled.slice(sampSize, sampSize + testSampSize)
       val testOrdered = testOmega.sortWith(_ < _).toArray
       val testData: RDD[(Int, Int, Double)] = sc.parallelize(testOrdered)