remove main from NaiveBayes and add an example NaiveBayes app

Author: mengxr

examples/src/main/scala/org/apache/spark/examples/mllib/SparseNaiveBayes.scala

@@ -0,0 +1,100 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.examples.mllib
+
+import org.apache.log4j.{Level, Logger}
+import scopt.OptionParser
+
+import org.apache.spark.{SparkConf, SparkContext}
+import org.apache.spark.mllib.classification.NaiveBayes
+import org.apache.spark.mllib.util.{MLUtils, MulticlassLabelParser}
+
+/**
+ * An example naive Bayes app. Run with
+ * {{{
+ * ./bin/spark-example org.apache.spark.examples.mllib.SparseNaiveBayes [options] <input>
+ * }}}
+ * If you use it as a template to create your own app, please use `spark-submit` to submit your app.
+ */
+object SparseNaiveBayes extends App {
+
+  case class NaiveBayesParams(
+      input: String = null,
+      minPartitions: Int = 0,
+      numFeatures: Int = -1,
+      lambda: Double = 1.0)
+
+  val defaultParams = NaiveBayesParams()
+
+  val parser = new OptionParser[NaiveBayesParams]("SparseNaiveBayes") {
+    head("SparseNaiveBayes: an example naive Bayes app for LIBSVM data.")
+    opt[Int]("numPartitions")
+      .text("min number of partitions")
+      .action((x, c) => c.copy(minPartitions = x))
+    opt[Int]("numFeatures")
+      .text("number of features")
+      .action((x, c) => c.copy(numFeatures = x))
+    opt[Double]("lambda")
+      .text(s"lambda (smoothing constant), default: ${defaultParams.lambda}")
+      .action((x, c) => c.copy(lambda = x))
+    arg[String]("<input>")
+      .text("input paths to labeled examples in LIBSVM format")
+      .required()
+      .action((x, c) => c.copy(input = x))
+  }
+
+  parser.parse(args, defaultParams).map { params =>
+    run(params)
+  }.getOrElse {
+    sys.exit(1)
+  }
+
+  def run(params: NaiveBayesParams) {
+    val conf = new SparkConf().setAppName(s"SparseNaiveBayes with $params")
+    val sc = new SparkContext(conf)
+
+    Logger.getRootLogger.setLevel(Level.WARN)
+
+    val minPartitions =
+      if (params.minPartitions > 0) params.minPartitions else sc.defaultMinPartitions
+
+    val examples = MLUtils.loadLibSVMData(sc, params.input, MulticlassLabelParser,
+      params.numFeatures, minPartitions)
+    // Cache examples because it will be used in both training and evaluation.
+    examples.cache()
+
+    val splits = examples.randomSplit(Array(0.8, 0.2))
+    val training = splits(0)
+    val test = splits(1)
+
+    val numTraining = training.count()
+    val numTest = test.count()
+
+    println(s"numTraining = $numTraining, numTest = $numTest.")
+
+    val model = new NaiveBayes().setLambda(params.lambda).run(training)
+
+    val prediction = model.predict(test.map(_.features))
+    val predictionAndLabel = prediction.zip(test.map(_.label))
+    val accuracy = predictionAndLabel.filter(x => x._1 == x._2).count().toDouble / numTest
+
+    println(s"Test accuracy = $accuracy.")
+
+    sc.stop()
+  }
+}

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

@@ -158,23 +158,4 @@ object NaiveBayes {
   def train(input: RDD[LabeledPoint], lambda: Double): NaiveBayesModel = {
     new NaiveBayes(lambda).run(input)
   }
-
-  def main(args: Array[String]) {
-    if (args.length != 2 && args.length != 3) {
-      println("Usage: NaiveBayes <master> <input_dir> [<lambda>]")
-      System.exit(1)
-    }
-    val sc = new SparkContext(args(0), "NaiveBayes")
-    val data = MLUtils.loadLabeledData(sc, args(1))
-    val model = if (args.length == 2) {
-      NaiveBayes.train(data)
-    } else {
-      NaiveBayes.train(data, args(2).toDouble)
-    }
-
-    println("Pi\n: " + model.pi)
-    println("Theta:\n" + model.theta)
-
-    sc.stop()
-  }
 }