Renamed ML package to MLlib and added it to classpath

bin/compute-classpath.cmd

@@ -15,6 +15,7 @@ set CORE_DIR=%FWDIR%core
 set REPL_DIR=%FWDIR%repl
 set EXAMPLES_DIR=%FWDIR%examples
 set BAGEL_DIR=%FWDIR%bagel
+set MLLIB_DIR=%FWDIR%mllib
 set STREAMING_DIR=%FWDIR%streaming
 set PYSPARK_DIR=%FWDIR%python
 
@@ -29,6 +30,7 @@ set CLASSPATH=%CLASSPATH%;%FWDIR%lib_managed\bundles\*
 set CLASSPATH=%CLASSPATH%;%FWDIR%repl\lib\*
 set CLASSPATH=%CLASSPATH%;%FWDIR%python\lib\*
 set CLASSPATH=%CLASSPATH%;%BAGEL_DIR%\target\scala-%SCALA_VERSION%\classes
+set CLASSPATH=%CLASSPATH%;%MLLIB_DIR%\target\scala-%SCALA_VERSION%\classes
 
 rem Add hadoop conf dir - else FileSystem.*, etc fail
 rem Note, this assumes that there is either a HADOOP_CONF_DIR or YARN_CONF_DIR which hosts

bin/compute-classpath.sh

@@ -18,6 +18,7 @@ REPL_DIR="$FWDIR/repl"
 REPL_BIN_DIR="$FWDIR/repl-bin"
 EXAMPLES_DIR="$FWDIR/examples"
 BAGEL_DIR="$FWDIR/bagel"
+MLLIB_DIR="$FWDIR/mllib"
 STREAMING_DIR="$FWDIR/streaming"
 PYSPARK_DIR="$FWDIR/python"
 
@@ -49,6 +50,7 @@ if [ -e $REPL_BIN_DIR/target ]; then
   CLASSPATH+=":$EXAMPLES_JAR"
 fi
 CLASSPATH="$CLASSPATH:$BAGEL_DIR/target/scala-$SCALA_VERSION/classes"
+CLASSPATH="$CLASSPATH:$MLLIB_DIR/target/scala-$SCALA_VERSION/classes"
 for jar in `find $PYSPARK_DIR/lib -name '*jar'`; do
   CLASSPATH="$CLASSPATH:$jar"
 done

mllib/src/main/scala/spark/ml/clustering/KMeans.scala

@@ -1,4 +1,4 @@
-package spark.ml.clustering
+package spark.mllib.clustering
 
 import scala.collection.mutable.ArrayBuffer
 import scala.util.Random
@@ -6,7 +6,7 @@ import scala.util.Random
 import spark.{SparkContext, RDD}
 import spark.SparkContext._
 import spark.Logging
-import spark.ml.util.MLUtils
+import spark.mllib.util.MLUtils
 
 import org.jblas.DoubleMatrix
 
@@ -270,7 +270,8 @@ object KMeans {
   /**
    * Return the index of the closest point in `centers` to `point`, as well as its distance.
    */
-  private[ml] def findClosest(centers: Array[Array[Double]], point: Array[Double]): (Int, Double) =
+  private[mllib] def findClosest(centers: Array[Array[Double]], point: Array[Double])
+    : (Int, Double) =
   {
     var bestDistance = Double.PositiveInfinity
     var bestIndex = 0
@@ -287,7 +288,7 @@ object KMeans {
   /**
    * Return the K-means cost of a given point against the given cluster centers.
    */
-  private[ml] def pointCost(centers: Array[Array[Double]], point: Array[Double]): Double = {
+  private[mllib] def pointCost(centers: Array[Array[Double]], point: Array[Double]): Double = {
     var bestDistance = Double.PositiveInfinity
     for (i <- 0 until centers.length) {
       val distance = MLUtils.squaredDistance(point, centers(i))

mllib/src/main/scala/spark/ml/clustering/KMeansModel.scala

@@ -1,8 +1,8 @@
-package spark.ml.clustering
+package spark.mllib.clustering
 
 import spark.RDD
 import spark.SparkContext._
-import spark.ml.util.MLUtils
+import spark.mllib.util.MLUtils
 
 
 /**

mllib/src/main/scala/spark/ml/clustering/LocalKMeans.scala

@@ -1,4 +1,4 @@
-package spark.ml.clustering
+package spark.mllib.clustering
 
 import scala.util.Random
 
@@ -8,7 +8,7 @@ import org.jblas.{DoubleMatrix, SimpleBlas}
  * An utility object to run K-means locally. This is private to the ML package because it's used
  * in the initialization of KMeans but not meant to be publicly exposed.
  */
-private[ml] object LocalKMeans {
+private[mllib] object LocalKMeans {
   /**
    * Run K-means++ on the weighted point set `points`. This first does the K-means++
    * initialization procedure and then roudns of Lloyd's algorithm.

mllib/src/main/scala/spark/ml/optimization/Gradient.scala

@@ -1,4 +1,4 @@
-package spark.ml.optimization
+package spark.mllib.optimization
 
 import org.jblas.DoubleMatrix
 

mllib/src/main/scala/spark/ml/optimization/GradientDescent.scala

@@ -1,4 +1,4 @@
-package spark.ml.optimization
+package spark.mllib.optimization
 
 import spark.{Logging, RDD, SparkContext}
 import spark.SparkContext._

mllib/src/main/scala/spark/ml/optimization/Updater.scala

@@ -1,4 +1,4 @@
-package spark.ml.optimization
+package spark.mllib.optimization
 
 import org.jblas.DoubleMatrix
 

mllib/src/main/scala/spark/ml/recommendation/ALS.scala

@@ -1,4 +1,4 @@
-package spark.ml.recommendation
+package spark.mllib.recommendation
 
 import scala.collection.mutable.{ArrayBuffer, BitSet}
 import scala.util.Random

mllib/src/main/scala/spark/ml/recommendation/MatrixFactorizationModel.scala

@@ -1,4 +1,4 @@
-package spark.ml.recommendation
+package spark.mllib.recommendation
 
 import spark.RDD
 import spark.SparkContext._

mllib/src/main/scala/spark/ml/regression/LogisticRegression.scala

@@ -1,8 +1,8 @@
-package spark.ml.regression
+package spark.mllib.regression
 
 import spark.{Logging, RDD, SparkContext}
-import spark.ml.optimization._
+import spark.mllib.optimization._
-import spark.ml.util.MLUtils
+import spark.mllib.util.MLUtils
 
 import org.jblas.DoubleMatrix
 

mllib/src/main/scala/spark/ml/regression/LogisticRegressionGenerator.scala

@@ -1,11 +1,11 @@
-package spark.ml.regression
+package spark.mllib.regression
 
 import scala.util.Random
 
 import org.jblas.DoubleMatrix
 
 import spark.{RDD, SparkContext}
-import spark.ml.util.MLUtils
+import spark.mllib.util.MLUtils
 
 object LogisticRegressionGenerator {
 

mllib/src/main/scala/spark/ml/regression/Regression.scala

@@ -1,4 +1,4 @@
-package spark.ml.regression
+package spark.mllib.regression
 
 import spark.RDD
 

mllib/src/main/scala/spark/ml/regression/RidgeRegression.scala

@@ -1,8 +1,8 @@
-package spark.ml.regression
+package spark.mllib.regression
 
 import spark.{Logging, RDD, SparkContext}
 import spark.SparkContext._
-import spark.ml.util.MLUtils
+import spark.mllib.util.MLUtils
 
 import org.jblas.DoubleMatrix
 import org.jblas.Solve

mllib/src/main/scala/spark/ml/regression/RidgeRegressionGenerator.scala

@@ -1,11 +1,11 @@
-package spark.ml.regression
+package spark.mllib.regression
 
 import scala.util.Random
 
 import org.jblas.DoubleMatrix
 
 import spark.{RDD, SparkContext}
-import spark.ml.util.MLUtils
+import spark.mllib.util.MLUtils
 
 
 object RidgeRegressionGenerator {

mllib/src/main/scala/spark/ml/util/MLUtils.scala

@@ -1,4 +1,4 @@
-package spark.ml.util
+package spark.mllib.util
 
 import spark.{RDD, SparkContext}
 import spark.SparkContext._

mllib/src/test/scala/spark/ml/clustering/KMeansSuite.scala

@@ -1,4 +1,4 @@
-package spark.ml.clustering
+package spark.mllib.clustering
 
 import scala.util.Random
 

mllib/src/test/scala/spark/ml/recommendation/ALSSuite.scala

@@ -1,4 +1,4 @@
-package spark.ml.recommendation
+package spark.mllib.recommendation
 
 import scala.util.Random
 

mllib/src/test/scala/spark/ml/regression/LogisticRegressionSuite.scala

@@ -1,4 +1,4 @@
-package spark.ml.regression
+package spark.mllib.regression
 
 import scala.util.Random
 

mllib/src/test/scala/spark/ml/regression/RidgeRegressionSuite.scala

@@ -1,4 +1,4 @@
-package spark.ml.regression
+package spark.mllib.regression
 
 import scala.util.Random
 

project/SparkBuild.scala

@@ -25,7 +25,7 @@ object SparkBuild extends Build {
   //val HADOOP_MAJOR_VERSION = "2"
   //val HADOOP_YARN = true
 
-  lazy val root = Project("root", file("."), settings = rootSettings) aggregate(core, repl, examples, bagel, streaming, ml)
+  lazy val root = Project("root", file("."), settings = rootSettings) aggregate(core, repl, examples, bagel, streaming, mllib)
 
   lazy val core = Project("core", file("core"), settings = coreSettings)
 
@@ -37,7 +37,7 @@ object SparkBuild extends Build {
 
   lazy val streaming = Project("streaming", file("streaming"), settings = streamingSettings) dependsOn (core)
 
-  lazy val ml = Project("ml", file("ml"), settings = mlSettings) dependsOn (core)
+  lazy val mllib = Project("mllib", file("mllib"), settings = mllibSettings) dependsOn (core)
 
   // A configuration to set an alternative publishLocalConfiguration
   lazy val MavenCompile = config("m2r") extend(Compile)
@@ -221,8 +221,8 @@ object SparkBuild extends Build {
 
   def bagelSettings = sharedSettings ++ Seq(name := "spark-bagel")
 
-  def mlSettings = sharedSettings ++ Seq(
+  def mllibSettings = sharedSettings ++ Seq(
-    name := "spark-ml",
+    name := "spark-mllib",
     libraryDependencies ++= Seq(
       "org.jblas" % "jblas" % "1.2.3"
     )