[SPARK-11689][ML] Add user guide and example code for LDA under spark.ml

jira: https://issues.apache.org/jira/browse/SPARK-11689

Add simple user guide for LDA under spark.ml and example code under examples/. Use include_example to include example code in the user guide markdown. Check SPARK-11606 for instructions.

Author: Yuhao Yang <hhbyyh@gmail.com>

Closes #9722 from hhbyyh/ldaMLExample.

1 files changed, 77 insertions, 0 deletions

diff --git a/examples/src/main/scala/org/apache/spark/examples/ml/LDAExample.scala b/examples/src/main/scala/org/apache/spark/examples/ml/LDAExample.scala
new file mode 100644
index 0000000000..419ce3d87a
--- /dev/null
+++ b/examples/src/main/scala/org/apache/spark/examples/ml/LDAExample.scala
@@ -0,0 +1,77 @@
+/*
+ * 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
+
+// scalastyle:off println
+import org.apache.spark.{SparkContext, SparkConf}
+import org.apache.spark.mllib.linalg.{VectorUDT, Vectors}
+// $example on$
+import org.apache.spark.ml.clustering.LDA
+import org.apache.spark.sql.{Row, SQLContext}
+import org.apache.spark.sql.types.{StructField, StructType}
+// $example off$
+
+/**
+ * An example demonstrating a LDA of ML pipeline.
+ * Run with
+ * {{{
+ * bin/run-example ml.LDAExample
+ * }}}
+ */
+object LDAExample {
+
+  final val FEATURES_COL = "features"
+
+  def main(args: Array[String]): Unit = {
+
+    val input = "data/mllib/sample_lda_data.txt"
+    // Creates a Spark context and a SQL context
+    val conf = new SparkConf().setAppName(s"${this.getClass.getSimpleName}")
+    val sc = new SparkContext(conf)
+    val sqlContext = new SQLContext(sc)
+
+    // $example on$
+    // Loads data
+    val rowRDD = sc.textFile(input).filter(_.nonEmpty)
+      .map(_.split(" ").map(_.toDouble)).map(Vectors.dense).map(Row(_))
+    val schema = StructType(Array(StructField(FEATURES_COL, new VectorUDT, false)))
+    val dataset = sqlContext.createDataFrame(rowRDD, schema)
+
+    // Trains a LDA model
+    val lda = new LDA()
+      .setK(10)
+      .setMaxIter(10)
+      .setFeaturesCol(FEATURES_COL)
+    val model = lda.fit(dataset)
+    val transformed = model.transform(dataset)
+
+    val ll = model.logLikelihood(dataset)
+    val lp = model.logPerplexity(dataset)
+
+    // describeTopics
+    val topics = model.describeTopics(3)
+
+    // Shows the result
+    topics.show(false)
+    transformed.show(false)
+
+    // $example off$
+    sc.stop()
+  }
+}
+// scalastyle:on println