From 7e70708a99949549adde00cb6246a9582bbc4929 Mon Sep 17 00:00:00 2001
From: Xiangrui Meng <meng@databricks.com>
Date: Sat, 16 Aug 2014 15:13:34 -0700
Subject: [SPARK-3048][MLLIB] add LabeledPoint.parse and remove
 loadStreamingLabeledPoints

Move `parse()` from `LabeledPointParser` to `LabeledPoint` and make it public. This breaks binary compatibility only when a user uses synthesized methods like `tupled` and `curried`, which is rare.

`LabeledPoint.parse` is more consistent with `Vectors.parse`, which is why `LabeledPointParser` is not preferred.

freeman-lab tdas

Author: Xiangrui Meng <meng@databricks.com>

Closes #1952 from mengxr/labelparser and squashes the following commits:

c818fb2 [Xiangrui Meng] merge master
ce20e6f [Xiangrui Meng] update mima excludes
b386b8d [Xiangrui Meng] fix tests
2436b3d [Xiangrui Meng] add parse() to LabeledPoint
---
 .../apache/spark/mllib/regression/LabeledPoint.scala    |  2 +-
 .../regression/StreamingLinearRegressionWithSGD.scala   |  2 +-
 .../scala/org/apache/spark/mllib/util/MLUtils.scala     | 17 ++---------------
 3 files changed, 4 insertions(+), 17 deletions(-)

(limited to 'mllib/src/main')

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/LabeledPoint.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/LabeledPoint.scala
index 62a03af4a9..17c753c566 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/regression/LabeledPoint.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/LabeledPoint.scala
@@ -36,7 +36,7 @@ case class LabeledPoint(label: Double, features: Vector) {
 /**
  * Parser for [[org.apache.spark.mllib.regression.LabeledPoint]].
  */
-private[mllib] object LabeledPointParser {
+object LabeledPoint {
   /**
    * Parses a string resulted from `LabeledPoint#toString` into
    * an [[org.apache.spark.mllib.regression.LabeledPoint]].
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearRegressionWithSGD.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearRegressionWithSGD.scala
index 8851097050..1d11fde247 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearRegressionWithSGD.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearRegressionWithSGD.scala
@@ -18,7 +18,7 @@
 package org.apache.spark.mllib.regression
 
 import org.apache.spark.annotation.Experimental
-import org.apache.spark.mllib.linalg.{Vector, Vectors}
+import org.apache.spark.mllib.linalg.Vector
 
 /**
  * Train or predict a linear regression model on streaming data. Training uses
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala
index f4cce86a65..ca35100aa9 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala
@@ -27,7 +27,7 @@ import org.apache.spark.SparkContext
 import org.apache.spark.rdd.RDD
 import org.apache.spark.rdd.PartitionwiseSampledRDD
 import org.apache.spark.util.random.BernoulliSampler
-import org.apache.spark.mllib.regression.{LabeledPointParser, LabeledPoint}
+import org.apache.spark.mllib.regression.LabeledPoint
 import org.apache.spark.mllib.linalg.{Vector, Vectors}
 import org.apache.spark.storage.StorageLevel
 import org.apache.spark.streaming.StreamingContext
@@ -185,7 +185,7 @@ object MLUtils {
    * @return labeled points stored as an RDD[LabeledPoint]
    */
   def loadLabeledPoints(sc: SparkContext, path: String, minPartitions: Int): RDD[LabeledPoint] =
-    sc.textFile(path, minPartitions).map(LabeledPointParser.parse)
+    sc.textFile(path, minPartitions).map(LabeledPoint.parse)
 
   /**
    * Loads labeled points saved using `RDD[LabeledPoint].saveAsTextFile` with the default number of
@@ -194,19 +194,6 @@ object MLUtils {
   def loadLabeledPoints(sc: SparkContext, dir: String): RDD[LabeledPoint] =
     loadLabeledPoints(sc, dir, sc.defaultMinPartitions)
 
-  /**
-   * Loads streaming labeled points from a stream of text files
-   * where points are in the same format as used in `RDD[LabeledPoint].saveAsTextFile`.
-   * See `StreamingContext.textFileStream` for more details on how to
-   * generate a stream from files
-   *
-   * @param ssc Streaming context
-   * @param dir Directory path in any Hadoop-supported file system URI
-   * @return Labeled points stored as a DStream[LabeledPoint]
-   */
-  def loadStreamingLabeledPoints(ssc: StreamingContext, dir: String): DStream[LabeledPoint] =
-    ssc.textFileStream(dir).map(LabeledPointParser.parse)
-
   /**
    * Load labeled data from a file. The data format used here is
    * <L>, <f1> <f2> ...
-- 
cgit v1.2.3