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/JavaNaiveBayesExample.java   | 64 ++++++++++++++++++++++
 1 file changed, 64 insertions(+)
 create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java

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

diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java
new file mode 100644
index 0000000000..41d7ad75b9
--- /dev/null
+++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaNaiveBayesExample.java
@@ -0,0 +1,64 @@
+/*
+ * 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.ml;
+
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaSparkContext;
+// $example on$
+import org.apache.spark.ml.classification.NaiveBayes;
+import org.apache.spark.ml.classification.NaiveBayesModel;
+import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SQLContext;
+// $example off$
+
+/**
+ * An example for Naive Bayes Classification.
+ */
+public class JavaNaiveBayesExample {
+
+  public static void main(String[] args) {
+    SparkConf conf = new SparkConf().setAppName("JavaNaiveBayesExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+    SQLContext jsql = new SQLContext(jsc);
+
+    // $example on$
+    // Load training data
+    Dataset<Row> dataFrame = jsql.read().format("libsvm").load("data/mllib/sample_libsvm_data.txt");
+    // Split the data into train and test
+    Dataset<Row>[] splits = dataFrame.randomSplit(new double[]{0.6, 0.4}, 1234L);
+    Dataset<Row> train = splits[0];
+    Dataset<Row> test = splits[1];
+
+    // create the trainer and set its parameters
+    NaiveBayes nb = new NaiveBayes();
+    // train the model
+    NaiveBayesModel model = nb.fit(train);
+    // compute precision on the test set
+    Dataset<Row> result = model.transform(test);
+    Dataset<Row> predictionAndLabels = result.select("prediction", "label");
+    MulticlassClassificationEvaluator evaluator = new MulticlassClassificationEvaluator()
+      .setMetricName("precision");
+    System.out.println("Precision = " + evaluator.evaluate(predictionAndLabels));
+    // $example off$
+
+    jsc.stop();
+  }
+}
-- 
cgit v1.2.3