From 781df499836e4216939e0febdcd5f89d30645759 Mon Sep 17 00:00:00 2001
From: Yuhao Yang <hhbyyh@gmail.com>
Date: Wed, 13 Apr 2016 13:58:35 -0700
Subject: [SPARK-13089][ML] [Doc] spark.ml Naive Bayes user guide and examples

jira: https://issues.apache.org/jira/browse/SPARK-13089

Add section in ml-classification.md for NaiveBayes DataFrame-based API, plus example code (using include_example to clip code from examples/ folder files).

Author: Yuhao Yang <hhbyyh@gmail.com>

Closes #11015 from hhbyyh/naiveBayesDoc.
---
 .../spark/examples/ml/NaiveBayesExample.scala      | 58 ++++++++++++++++++++++
 1 file changed, 58 insertions(+)
 create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/NaiveBayesExample.scala

(limited to 'examples/src/main/scala')

diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/NaiveBayesExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/NaiveBayesExample.scala
new file mode 100644
index 0000000000..5ea1270c97
--- /dev/null
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/NaiveBayesExample.scala
@@ -0,0 +1,58 @@
+/*
+ * 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.
+ */
+
+// scalastyle:off println
+package org.apache.spark.examples.ml
+
+import org.apache.spark.{SparkConf, SparkContext}
+// $example on$
+import org.apache.spark.ml.classification.{NaiveBayes}
+import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
+// $example off$
+import org.apache.spark.sql.SQLContext
+
+object NaiveBayesExample {
+  def main(args: Array[String]): Unit = {
+    val conf = new SparkConf().setAppName("NaiveBayesExample")
+    val sc = new SparkContext(conf)
+    val sqlContext = new SQLContext(sc)
+    // $example on$
+    // Load the data stored in LIBSVM format as a DataFrame.
+    val data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
+
+    // Split the data into training and test sets (30% held out for testing)
+    val Array(trainingData, testData) = data.randomSplit(Array(0.7, 0.3))
+
+    // Train a NaiveBayes model.
+    val model = new NaiveBayes()
+      .fit(trainingData)
+
+    // Select example rows to display.
+    val predictions = model.transform(testData)
+    predictions.show()
+
+    // Select (prediction, true label) and compute test error
+    val evaluator = new MulticlassClassificationEvaluator()
+      .setLabelCol("label")
+      .setPredictionCol("prediction")
+      .setMetricName("precision")
+    val precision = evaluator.evaluate(predictions)
+    println("Precision:" + precision)
+    // $example off$
+  }
+}
+// scalastyle:on println
-- 
cgit v1.2.3