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

docs/ml-clustering.md

@@ -0,0 +1,30 @@
+---
+layout: global
+title: Clustering - ML
+displayTitle: <a href="ml-guide.html">ML</a> - Clustering
+---
+
+In this section, we introduce the pipeline API for [clustering in mllib](mllib-clustering.html).
+
+## Latent Dirichlet allocation (LDA)
+
+`LDA` is implemented as an `Estimator` that supports both `EMLDAOptimizer` and `OnlineLDAOptimizer`,
+and generates a `LDAModel` as the base models. Expert users may cast a `LDAModel` generated by
+`EMLDAOptimizer` to a `DistributedLDAModel` if needed.
+
+<div class="codetabs">
+
+Refer to the [Scala API docs](api/scala/index.html#org.apache.spark.ml.clustering.LDA) for more details.
+
+<div data-lang="scala" markdown="1">
+{% include_example scala/org/apache/spark/examples/ml/LDAExample.scala %}
+</div>
+
+<div data-lang="java" markdown="1">
+
+Refer to the [Java API docs](api/java/org/apache/spark/ml/clustering/LDA.html) for more details.
+
+{% include_example java/org/apache/spark/examples/ml/JavaLDAExample.java %}
+</div>
+
+</div>

docs/ml-guide.md

@@ -40,6 +40,7 @@ Also, some algorithms have additional capabilities in the `spark.ml` API; e.g.,
 provide class probabilities, and linear models provide model summaries.
 
 * [Feature extraction, transformation, and selection](ml-features.html)
+* [Clustering](ml-clustering.html)
 * [Decision Trees for classification and regression](ml-decision-tree.html)
 * [Ensembles](ml-ensembles.html)
 * [Linear methods with elastic net regularization](ml-linear-methods.html)
@@ -950,4 +951,4 @@ model.transform(test)
 {% endhighlight %}
 </div>
 
-</div>
+</div>

docs/mllib-guide.md

@@ -69,6 +69,7 @@ We list major functionality from both below, with links to detailed guides.
 concepts. It also contains sections on using algorithms within the Pipelines API, for example:
 
 * [Feature extraction, transformation, and selection](ml-features.html)
+* [Clustering](ml-clustering.html)
 * [Decision trees for classification and regression](ml-decision-tree.html)
 * [Ensembles](ml-ensembles.html)
 * [Linear methods with elastic net regularization](ml-linear-methods.html)

examples/src/main/java/org/apache/spark/examples/ml/JavaLDAExample.java

@@ -0,0 +1,94 @@
+/*
+ * 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 java.util.regex.Pattern;
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.api.java.function.Function;
+import org.apache.spark.ml.clustering.LDA;
+import org.apache.spark.ml.clustering.LDAModel;
+import org.apache.spark.mllib.linalg.Vector;
+import org.apache.spark.mllib.linalg.VectorUDT;
+import org.apache.spark.mllib.linalg.Vectors;
+import org.apache.spark.sql.DataFrame;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SQLContext;
+import org.apache.spark.sql.catalyst.expressions.GenericRow;
+import org.apache.spark.sql.types.Metadata;
+import org.apache.spark.sql.types.StructField;
+import org.apache.spark.sql.types.StructType;
+
+/**
+ * An example demonstrating LDA
+ * Run with
+ * <pre>
+ * bin/run-example ml.JavaLDAExample
+ * </pre>
+ */
+public class JavaLDAExample {
+
+  private static class ParseVector implements Function<String, Row> {
+    private static final Pattern separator = Pattern.compile(" ");
+
+    @Override
+    public Row call(String line) {
+      String[] tok = separator.split(line);
+      double[] point = new double[tok.length];
+      for (int i = 0; i < tok.length; ++i) {
+        point[i] = Double.parseDouble(tok[i]);
+      }
+      Vector[] points = {Vectors.dense(point)};
+      return new GenericRow(points);
+    }
+  }
+
+  public static void main(String[] args) {
+
+    String inputFile = "data/mllib/sample_lda_data.txt";
+
+    // Parses the arguments
+    SparkConf conf = new SparkConf().setAppName("JavaLDAExample");
+    JavaSparkContext jsc = new JavaSparkContext(conf);
+    SQLContext sqlContext = new SQLContext(jsc);
+
+    // Loads data
+    JavaRDD<Row> points = jsc.textFile(inputFile).map(new ParseVector());
+    StructField[] fields = {new StructField("features", new VectorUDT(), false, Metadata.empty())};
+    StructType schema = new StructType(fields);
+    DataFrame dataset = sqlContext.createDataFrame(points, schema);
+
+    // Trains a LDA model
+    LDA lda = new LDA()
+      .setK(10)
+      .setMaxIter(10);
+    LDAModel model = lda.fit(dataset);
+
+    System.out.println(model.logLikelihood(dataset));
+    System.out.println(model.logPerplexity(dataset));
+
+    // Shows the result
+    DataFrame topics = model.describeTopics(3);
+    topics.show(false);
+    model.transform(dataset).show(false);
+
+    jsc.stop();
+  }
+}

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