Add Naive Bayes to Python MLlib, and some API fixes

- Added a Python wrapper for Naive Bayes
- Updated the Scala Naive Bayes to match the style of our other
  algorithms better and in particular make it easier to call from Java
  (added builder pattern, removed default value in train method)
- Updated Python MLlib functions to not require a SparkContext; we can
  get that from the RDD the user gives
- Added a toString method in LabeledPoint
- Made the Python MLlib tests run as part of run-tests as well (before
  they could only be run individually through each file)

3 files changed, 58 insertions, 9 deletions

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
index 2d8623392e..7ca2cb2a08 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
@@ -185,6 +185,23 @@ class PythonMLLibAPI extends Serializable {
   }
 
   /**
+   * Java stub for NaiveBayes.train()
+   */
+  def trainNaiveBayes(dataBytesJRDD: JavaRDD[Array[Byte]], lambda: Double)
+      : java.util.List[java.lang.Object] =
+  {
+    val data = dataBytesJRDD.rdd.map(xBytes => {
+      val x = deserializeDoubleVector(xBytes)
+      LabeledPoint(x(0), x.slice(1, x.length))
+    })
+    val model = NaiveBayes.train(data, lambda)
+    val ret = new java.util.LinkedList[java.lang.Object]()
+    ret.add(serializeDoubleVector(model.pi))
+    ret.add(serializeDoubleMatrix(model.theta))
+    ret
+  }
+
+  /**
    * Java stub for Python mllib KMeans.train()
    */
   def trainKMeansModel(dataBytesJRDD: JavaRDD[Array[Byte]], k: Int,
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala
index 524300d6ae..f45802cd0b 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala
@@ -29,9 +29,9 @@ import org.apache.spark.rdd.RDD
  * Model for Naive Bayes Classifiers.
  *
  * @param pi Log of class priors, whose dimension is C.
- * @param theta Log of class conditional probabilities, whose dimension is CXD.
+ * @param theta Log of class conditional probabilities, whose dimension is CxD.
  */
-class NaiveBayesModel(pi: Array[Double], theta: Array[Array[Double]])
+class NaiveBayesModel(val pi: Array[Double], val theta: Array[Array[Double]])
   extends ClassificationModel with Serializable {
 
   // Create a column vector that can be used for predictions
@@ -50,10 +50,21 @@ class NaiveBayesModel(pi: Array[Double], theta: Array[Array[Double]])
 /**
  * Trains a Naive Bayes model given an RDD of `(label, features)` pairs.
  *
- * @param lambda The smooth parameter
+ * This is the Multinomial NB ([[http://tinyurl.com/lsdw6p]]) which can handle all kinds of
+ * discrete data.  For example, by converting documents into TF-IDF vectors, it can be used for
+ * document classification.  By making every vector a 0-1 vector, it can also be used as
+ * Bernoulli NB ([[http://tinyurl.com/p7c96j6]]).
  */
-class NaiveBayes private (val lambda: Double = 1.0)
-  extends Serializable with Logging {
+class NaiveBayes private (var lambda: Double)
+  extends Serializable with Logging
+{
+  def this() = this(1.0)
+
+  /** Set the smoothing parameter. Default: 1.0. */
+  def setLambda(lambda: Double): NaiveBayes = {
+    this.lambda = lambda
+    this
+  }
 
   /**
    * Run the algorithm with the configured parameters on an input RDD of LabeledPoint entries.
@@ -106,14 +117,31 @@ object NaiveBayes {
    *
    * This is the Multinomial NB ([[http://tinyurl.com/lsdw6p]]) which can handle all kinds of
    * discrete data.  For example, by converting documents into TF-IDF vectors, it can be used for
-   * document classification.  By making every vector a 0-1 vector. it can also be used as
+   * document classification.  By making every vector a 0-1 vector, it can also be used as
+   * Bernoulli NB ([[http://tinyurl.com/p7c96j6]]).
+   *
+   * This version of the method uses a default smoothing parameter of 1.0.
+   *
+   * @param input RDD of `(label, array of features)` pairs.  Every vector should be a frequency
+   *              vector or a count vector.
+   */
+  def train(input: RDD[LabeledPoint]): NaiveBayesModel = {
+    new NaiveBayes().run(input)
+  }
+
+  /**
+   * Trains a Naive Bayes model given an RDD of `(label, features)` pairs.
+   *
+   * This is the Multinomial NB ([[http://tinyurl.com/lsdw6p]]) which can handle all kinds of
+   * discrete data.  For example, by converting documents into TF-IDF vectors, it can be used for
+   * document classification.  By making every vector a 0-1 vector, it can also be used as
    * Bernoulli NB ([[http://tinyurl.com/p7c96j6]]).
    *
    * @param input RDD of `(label, array of features)` pairs.  Every vector should be a frequency
    *              vector or a count vector.
-   * @param lambda The smooth parameter
+   * @param lambda The smoothing parameter
    */
-  def train(input: RDD[LabeledPoint], lambda: Double = 1.0): NaiveBayesModel = {
+  def train(input: RDD[LabeledPoint], lambda: Double): NaiveBayesModel = {
     new NaiveBayes(lambda).run(input)
   }
 }
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/LabeledPoint.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/LabeledPoint.scala
index 63240e24dc..1a18292fe3 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/regression/LabeledPoint.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/LabeledPoint.scala
@@ -23,4 +23,8 @@ package org.apache.spark.mllib.regression
  * @param label Label for this data point.
  * @param features List of features for this data point.
  */
-case class LabeledPoint(val label: Double, val features: Array[Double])
+case class LabeledPoint(label: Double, features: Array[Double]) {
+  override def toString: String = {
+    "LabeledPoint(%s, %s)".format(label, features.mkString("[", ", ", "]"))
+  }
+}