From e4f3eec5b750389ce3f7c6d023bb7db3b0f8cf29 Mon Sep 17 00:00:00 2001
From: Dongjoon Hyun <dongjoon@apache.org>
Date: Tue, 26 Apr 2016 13:58:29 -0700
Subject: [PATCH] [SPARK-14907][MLLIB] Use repartition in
GLMRegressionModel.save
## What changes were proposed in this pull request?
This PR changes `GLMRegressionModel.save` function like the following code that is similar to other algorithms' parquet write.
```
- val dataRDD: DataFrame = sc.parallelize(Seq(data), 1).toDF()
- // TODO: repartition with 1 partition after SPARK-5532 gets fixed
- dataRDD.write.parquet(Loader.dataPath(path))
+ sqlContext.createDataFrame(Seq(data)).repartition(1).write.parquet(Loader.dataPath(path))
```
## How was this patch tested?
Manual.
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes #12676 from dongjoon-hyun/SPARK-14907.
---
.../spark/mllib/regression/impl/GLMRegressionModel.scala | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/impl/GLMRegressionModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/impl/GLMRegressionModel.scala
index a6e1767fe2..7696fdf2dc 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/regression/impl/GLMRegressionModel.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/impl/GLMRegressionModel.scala
@@ -48,7 +48,6 @@ private[regression] object GLMRegressionModel {
weights: Vector,
intercept: Double): Unit = {
val sqlContext = SQLContext.getOrCreate(sc)
- import sqlContext.implicits._
// Create JSON metadata.
val metadata = compact(render(
@@ -58,9 +57,7 @@ private[regression] object GLMRegressionModel {
// Create Parquet data.
val data = Data(weights, intercept)
- val dataRDD: DataFrame = sc.parallelize(Seq(data), 1).toDF()
- // TODO: repartition with 1 partition after SPARK-5532 gets fixed
- dataRDD.write.parquet(Loader.dataPath(path))
+ sqlContext.createDataFrame(Seq(data)).repartition(1).write.parquet(Loader.dataPath(path))
}
/**
--
GitLab