From 61ab08549cb6fceb6de1b5c490c55a89d4bd28fa Mon Sep 17 00:00:00 2001 From: Cheng Lian Date: Tue, 17 Feb 2015 23:36:20 -0800 Subject: [Minor] [SQL] Cleans up DataFrame variable names and toDF() calls Although we've migrated to the DataFrame API, lots of code still uses `rdd` or `srdd` as local variable names. This PR tries to address these naming inconsistencies and some other minor DataFrame related style issues. [Review on Reviewable](https://reviewable.io/reviews/apache/spark/4670) Author: Cheng Lian Closes #4670 from liancheng/df-cleanup and squashes the following commits: 3e14448 [Cheng Lian] Cleans up DataFrame variable names and toDF() calls --- .../main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala | 2 +- .../spark/mllib/classification/impl/GLMClassificationModel.scala | 2 +- .../org/apache/spark/mllib/regression/impl/GLMRegressionModel.scala | 2 +- .../scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala | 2 +- .../scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala | 2 +- .../src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala | 4 ++-- 6 files changed, 7 insertions(+), 7 deletions(-) (limited to 'mllib') diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala index dd7a9469d5..b11fd4f128 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala @@ -102,7 +102,7 @@ object NaiveBayesModel extends Loader[NaiveBayesModel] { sc.parallelize(Seq(metadata), 1).saveAsTextFile(metadataPath(path)) // Create Parquet data. - val dataRDD: DataFrame = sc.parallelize(Seq(data), 1).toDF + val dataRDD: DataFrame = sc.parallelize(Seq(data), 1).toDF() dataRDD.saveAsParquetFile(dataPath(path)) } diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/impl/GLMClassificationModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/impl/GLMClassificationModel.scala index 0a358f2e4f..8956189ff1 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/classification/impl/GLMClassificationModel.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/classification/impl/GLMClassificationModel.scala @@ -62,7 +62,7 @@ private[classification] object GLMClassificationModel { // Create Parquet data. val data = Data(weights, intercept, threshold) - sc.parallelize(Seq(data), 1).toDF.saveAsParquetFile(Loader.dataPath(path)) + sc.parallelize(Seq(data), 1).toDF().saveAsParquetFile(Loader.dataPath(path)) } /** 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 7b27aaa322..bd7e340ca2 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 @@ -58,7 +58,7 @@ private[regression] object GLMRegressionModel { // Create Parquet data. val data = Data(weights, intercept) - val dataRDD: DataFrame = sc.parallelize(Seq(data), 1).toDF + val dataRDD: DataFrame = sc.parallelize(Seq(data), 1).toDF() // TODO: repartition with 1 partition after SPARK-5532 gets fixed dataRDD.saveAsParquetFile(Loader.dataPath(path)) } diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala index 5dac62b0c4..060fd5b859 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala @@ -197,7 +197,7 @@ object DecisionTreeModel extends Loader[DecisionTreeModel] { val nodes = model.topNode.subtreeIterator.toSeq val dataRDD: DataFrame = sc.parallelize(nodes) .map(NodeData.apply(0, _)) - .toDF + .toDF() dataRDD.saveAsParquetFile(Loader.dataPath(path)) } diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala index e507f247cc..4897906aea 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala @@ -289,7 +289,7 @@ private[tree] object TreeEnsembleModel { // Create Parquet data. val dataRDD = sc.parallelize(model.trees.zipWithIndex).flatMap { case (tree, treeId) => tree.topNode.subtreeIterator.toSeq.map(node => NodeData(treeId, node)) - }.toDF + }.toDF() dataRDD.saveAsParquetFile(Loader.dataPath(path)) } diff --git a/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala index b118a8dcf1..376c3626f9 100644 --- a/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala +++ b/mllib/src/test/scala/org/apache/spark/ml/recommendation/ALSSuite.scala @@ -358,8 +358,8 @@ class ALSSuite extends FunSuite with MLlibTestSparkContext with Logging { .setNumUserBlocks(numUserBlocks) .setNumItemBlocks(numItemBlocks) val alpha = als.getAlpha - val model = als.fit(training.toDF) - val predictions = model.transform(test.toDF) + val model = als.fit(training.toDF()) + val predictions = model.transform(test.toDF()) .select("rating", "prediction") .map { case Row(rating: Float, prediction: Float) => (rating.toDouble, prediction.toDouble) -- cgit v1.2.3