From e232720a65dfb9ae6135cbb7674e35eddd88d625 Mon Sep 17 00:00:00 2001 From: Yuhao Yang Date: Mon, 30 Nov 2015 14:56:51 -0800 Subject: [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. Original PR is reverted due to document build error. https://github.com/apache/spark/pull/9722 mengxr feynmanliang yinxusen Sorry for the troubling. Author: Yuhao Yang Closes #9974 from hhbyyh/ldaMLExample. --- .../apache/spark/examples/ml/JavaLDAExample.java | 97 ++++++++++++++++++++++ .../org/apache/spark/examples/ml/LDAExample.scala | 77 +++++++++++++++++ 2 files changed, 174 insertions(+) create mode 100644 examples/src/main/java/org/apache/spark/examples/ml/JavaLDAExample.java create mode 100644 examples/src/main/scala/org/apache/spark/examples/ml/LDAExample.scala (limited to 'examples') diff --git a/examples/src/main/java/org/apache/spark/examples/ml/JavaLDAExample.java b/examples/src/main/java/org/apache/spark/examples/ml/JavaLDAExample.java new file mode 100644 index 0000000000..3a5d3237c8 --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/ml/JavaLDAExample.java @@ -0,0 +1,97 @@ +/* + * 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; +// $example on$ +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; +// $example off$ + +/** + * An example demonstrating LDA + * Run with + * 
+ * bin/run-example ml.JavaLDAExample
+ *
+ */ +public class JavaLDAExample { + + // $example on$ + private static class ParseVector implements Function { + 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 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(); + } + // $example off$ +} 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 -- cgit v1.2.3