diff options
Diffstat (limited to 'mllib')
| -rw-r--r-- | mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala | 9 |
1 files changed, 9 insertions, 0 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 a66a404d5c..458fab48fe 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 @@ -75,6 +75,15 @@ private[python] class PythonMLLibAPI extends Serializable { minPartitions: Int): JavaRDD[LabeledPoint] = MLUtils.loadLabeledPoints(jsc.sc, path, minPartitions) + /** + * Loads and serializes vectors saved with `RDD#saveAsTextFile`. + * @param jsc Java SparkContext + * @param path file or directory path in any Hadoop-supported file system URI + * @return serialized vectors in a RDD + */ + def loadVectors(jsc: JavaSparkContext, path: String): RDD[Vector] = + MLUtils.loadVectors(jsc.sc, path) + private def trainRegressionModel( learner: GeneralizedLinearAlgorithm[_ <: GeneralizedLinearModel], data: JavaRDD[LabeledPoint], |