diff options
author | Yu ISHIKAWA <yuu.ishikawa@gmail.com> | 2015-11-06 22:56:29 -0800 |
---|---|---|
committer | Davies Liu <davies.liu@gmail.com> | 2015-11-06 22:56:29 -0800 |
commit | 2ff0e79a8647cca5c9c57f613a07e739ac4f677e (patch) | |
tree | 8f79d410c855c4099f572b4b1eba1fd858e83aff /mllib/src | |
parent | 7f741905b06ed6d3dfbff6db41a3355dab71aa3c (diff) | |
download | spark-2ff0e79a8647cca5c9c57f613a07e739ac4f677e.tar.gz spark-2ff0e79a8647cca5c9c57f613a07e739ac4f677e.tar.bz2 spark-2ff0e79a8647cca5c9c57f613a07e739ac4f677e.zip |
[SPARK-8467] [MLLIB] [PYSPARK] Add LDAModel.describeTopics() in Python
Could jkbradley and davies review it?
- Create a wrapper class: `LDAModelWrapper` for `LDAModel`. Because we can't deal with the return value of`describeTopics` in Scala from pyspark directly. `Array[(Array[Int], Array[Double])]` is too complicated to convert it.
- Add `loadLDAModel` in `PythonMLlibAPI`. Since `LDAModel` in Scala is an abstract class and we need to call `load` of `DistributedLDAModel`.
[[SPARK-8467] Add LDAModel.describeTopics() in Python - ASF JIRA](https://issues.apache.org/jira/browse/SPARK-8467)
Author: Yu ISHIKAWA <yuu.ishikawa@gmail.com>
Closes #8643 from yu-iskw/SPARK-8467-2.
Diffstat (limited to 'mllib/src')
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/mllib/api/python/LDAModelWrapper.scala | 46 | ||||
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala | 13 |
2 files changed, 57 insertions, 2 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/api/python/LDAModelWrapper.scala b/mllib/src/main/scala/org/apache/spark/mllib/api/python/LDAModelWrapper.scala new file mode 100644 index 0000000000..63282eee6e --- /dev/null +++ b/mllib/src/main/scala/org/apache/spark/mllib/api/python/LDAModelWrapper.scala @@ -0,0 +1,46 @@ +/* + * 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.mllib.api.python + +import scala.collection.JavaConverters + +import org.apache.spark.SparkContext +import org.apache.spark.mllib.clustering.LDAModel +import org.apache.spark.mllib.linalg.Matrix + +/** + * Wrapper around LDAModel to provide helper methods in Python + */ +private[python] class LDAModelWrapper(model: LDAModel) { + + def topicsMatrix(): Matrix = model.topicsMatrix + + def vocabSize(): Int = model.vocabSize + + def describeTopics(): Array[Byte] = describeTopics(this.model.vocabSize) + + def describeTopics(maxTermsPerTopic: Int): Array[Byte] = { + val topics = model.describeTopics(maxTermsPerTopic).map { case (terms, termWeights) => + val jTerms = JavaConverters.seqAsJavaListConverter(terms).asJava + val jTermWeights = JavaConverters.seqAsJavaListConverter(termWeights).asJava + Array[Any](jTerms, jTermWeights) + } + SerDe.dumps(JavaConverters.seqAsJavaListConverter(topics).asJava) + } + + def save(sc: SparkContext, path: String): Unit = model.save(sc, path) +} diff --git a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala index 40c41806cd..54b03a9f90 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala @@ -517,7 +517,7 @@ private[python] class PythonMLLibAPI extends Serializable { topicConcentration: Double, seed: java.lang.Long, checkpointInterval: Int, - optimizer: String): LDAModel = { + optimizer: String): LDAModelWrapper = { val algo = new LDA() .setK(k) .setMaxIterations(maxIterations) @@ -535,7 +535,16 @@ private[python] class PythonMLLibAPI extends Serializable { case _ => throw new IllegalArgumentException("input values contains invalid type value.") } } - algo.run(documents) + val model = algo.run(documents) + new LDAModelWrapper(model) + } + + /** + * Load a LDA model + */ + def loadLDAModel(jsc: JavaSparkContext, path: String): LDAModelWrapper = { + val model = DistributedLDAModel.load(jsc.sc, path) + new LDAModelWrapper(model) } |