Updated changes re-comments. Got rid of verbose populateMatrix method. Public api now has string instead of enumeration. Docs are updated."

Author: leahmcguire

docs/mllib-naive-bayes.md

@@ -13,12 +13,15 @@ compute the conditional probability distribution of label given an observation
 and use it for prediction.
 
 MLlib supports [multinomial naive
-Bayes](http://en.wikipedia.org/wiki/Naive_Bayes_classifier#Multinomial_naive_Bayes),
-which is typically used for [document
-classification](http://nlp.stanford.edu/IR-book/html/htmledition/naive-bayes-text-classification-1.html).
+Bayes](http://en.wikipedia.org/wiki/Naive_Bayes_classifier#Multinomial_naive_Bayes)
+and [Bernoulli naive Bayes] (http://nlp.stanford.edu/IR-book/html/htmledition/the-bernoulli-model-1.html).
+Which are typically used for [document classification]
+(http://nlp.stanford.edu/IR-book/html/htmledition/naive-bayes-text-classification-1.html).
 Within that context, each observation is a document and each
-feature represents a term whose value is the frequency of the term.
-Feature values must be nonnegative to represent term frequencies.
+feature represents a term whose value is the frequency of the term (in multinomial naive Bayes) or
+a zero or one indicating whether the term was found in the document (in Bernoulli naive Bayes).
+Feature values must be nonnegative.The model type is selected with on optional parameter
+"Multinomial" or "Bernoulli" with "Multinomial" as the default.
 [Additive smoothing](http://en.wikipedia.org/wiki/Lidstone_smoothing) can be used by
 setting the parameter $\lambda$ (default to $1.0$). For document classification, the input feature
 vectors are usually sparse, and sparse vectors should be supplied as input to take advantage of
@@ -32,7 +35,7 @@ sparsity. Since the training data is only used once, it is not necessary to cach
 [NaiveBayes](api/scala/index.html#org.apache.spark.mllib.classification.NaiveBayes$) implements
 multinomial naive Bayes. It takes an RDD of
 [LabeledPoint](api/scala/index.html#org.apache.spark.mllib.regression.LabeledPoint) and an optional
-smoothing parameter `lambda` as input, and output a
+smoothing parameter `lambda` as input, an optional model type parameter (default is Multinomial), and outputs a
 [NaiveBayesModel](api/scala/index.html#org.apache.spark.mllib.classification.NaiveBayesModel), which
 can be used for evaluation and prediction.
 
@@ -51,7 +54,7 @@ val splits = parsedData.randomSplit(Array(0.6, 0.4), seed = 11L)
 val training = splits(0)
 val test = splits(1)
 
-val model = NaiveBayes.train(training, lambda = 1.0)
+val model = NaiveBayes.train(training, lambda = 1.0, model = "Multinomial")
 
 val predictionAndLabel = test.map(p => (model.predict(p.features), p.label))
 val accuracy = 1.0 * predictionAndLabel.filter(x => x._1 == x._2).count() / test.count()

mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala

@@ -18,12 +18,13 @@
 package org.apache.spark.mllib.classification
 
 import breeze.linalg.{DenseMatrix => BDM, DenseVector => BDV, argmax => brzArgmax, sum => brzSum, Axis}
-import org.apache.spark.mllib.classification.NaiveBayesModels.NaiveBayesModels
+import breeze.numerics.{exp => brzExp, log => brzLog}
 
 import org.apache.spark.{SparkException, Logging}
 import org.apache.spark.SparkContext._
 import org.apache.spark.mllib.linalg.{DenseVector, SparseVector, Vector}
 import org.apache.spark.mllib.regression.LabeledPoint
+import org.apache.spark.mllib.classification.NaiveBayesModels.NaiveBayesModels
 import org.apache.spark.rdd.RDD
 
 
@@ -52,29 +53,14 @@ class NaiveBayesModel private[mllib] (
     val theta: Array[Array[Double]],
     val model: NaiveBayesModels) extends ClassificationModel with Serializable {
 
-  def populateMatrix(arrayIn: Array[Array[Double]],
-                     matrixIn: BDM[Double],
-                     transformation: (Double) => Double = (x) => x) = {
-    var i = 0
-    while (i < arrayIn.length) {
-      var j = 0
-      while (j < arrayIn(i).length) {
-        matrixIn(i, j) = transformation(theta(i)(j))
-        j += 1
-      }
-      i += 1
-    }
-  }
-
   private val brzPi = new BDV[Double](pi)
-  private val brzTheta = new BDM[Double](theta.length, theta(0).length)
-  populateMatrix(theta, brzTheta)
+  private val brzTheta = new BDM(theta(0).length, theta.length, theta.flatten).t
 
   private val brzNegTheta: Option[BDM[Double]] = model match {
     case NaiveBayesModels.Multinomial => None
     case NaiveBayesModels.Bernoulli =>
-      val negTheta = new BDM[Double](theta.length, theta(0).length)
-      populateMatrix(theta, negTheta, (x) => math.log(1.0 - math.exp(x)))
+      val negTheta = brzLog((brzExp(brzTheta.copy) :*= (-1.0)) :+= 1.0)
+      //((x) => math.log(1.0 - math.exp(x))
       Option(negTheta)
   }
 
@@ -244,7 +230,7 @@ object NaiveBayes {
    * @param model The type of NB model to fit from the enumeration NaiveBayesModels, can be
    *              Multinomial or Bernoulli
    */
-  def train(input: RDD[LabeledPoint], lambda: Double, model: NaiveBayesModels): NaiveBayesModel = {
-    new NaiveBayes(lambda, model).run(input)
+  def train(input: RDD[LabeledPoint], lambda: Double, model: String): NaiveBayesModel = {
+    new NaiveBayes(lambda,  NaiveBayesModels.withName(model)).run(input)
   }
 }

mllib/src/test/scala/org/apache/spark/mllib/classification/NaiveBayesSuite.scala

@@ -117,7 +117,7 @@ class NaiveBayesSuite extends FunSuite with MLlibTestSparkContext {
     val testRDD = sc.parallelize(testData, 2)
     testRDD.cache()
 
-    val model = NaiveBayes.train(testRDD, 1.0, NaiveBayesModels.Multinomial)
+    val model = NaiveBayes.train(testRDD, 1.0, "Multinomial")
     validateModelFit(pi, theta, model)
 
     val validationData = NaiveBayesSuite.generateNaiveBayesInput(pi, theta, nPoints, 17, NaiveBayesModels.Multinomial)
@@ -140,11 +140,12 @@ class NaiveBayesSuite extends FunSuite with MLlibTestSparkContext {
       Array(0.02, 0.02, 0.60, 0.02,  0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.30)  // label 2
     ).map(_.map(math.log))
 
+
     val testData = NaiveBayesSuite.generateNaiveBayesInput(pi, theta, nPoints, 45, NaiveBayesModels.Bernoulli)
     val testRDD = sc.parallelize(testData, 2)
     testRDD.cache()
 
-    val model = NaiveBayes.train(testRDD, 1.0, NaiveBayesModels.Bernoulli) ///!!! this gives same result on both models check the math
+    val model = NaiveBayes.train(testRDD, 1.0, "Bernoulli") ///!!! this gives same result on both models check the math
     validateModelFit(pi, theta, model)
 
     val validationData = NaiveBayesSuite.generateNaiveBayesInput(pi, theta, nPoints, 20, NaiveBayesModels.Bernoulli)