diff options
Diffstat (limited to 'mllib')
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala | 8 |
1 files changed, 7 insertions, 1 deletions
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 5995d6df97..6c386cacfb 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 @@ -476,13 +476,15 @@ private[python] class PythonMLLibAPI extends Serializable { learningRate: Double, numPartitions: Int, numIterations: Int, - seed: Long): Word2VecModelWrapper = { + seed: Long, + minCount: Int): Word2VecModelWrapper = { val word2vec = new Word2Vec() .setVectorSize(vectorSize) .setLearningRate(learningRate) .setNumPartitions(numPartitions) .setNumIterations(numIterations) .setSeed(seed) + .setMinCount(minCount) try { val model = word2vec.fit(dataJRDD.rdd.persist(StorageLevel.MEMORY_AND_DISK_SER)) new Word2VecModelWrapper(model) @@ -516,6 +518,10 @@ private[python] class PythonMLLibAPI extends Serializable { val words = result.map(_._1) List(words, similarity).map(_.asInstanceOf[Object]).asJava } + + def getVectors: JMap[String, JList[Float]] = { + model.getVectors.map({case (k, v) => (k, v.toList.asJava)}).asJava + } } /** |