diff options
Diffstat (limited to 'mllib/src/main/scala')
12 files changed, 17 insertions, 17 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala index 08a51109d6..c41a611f1c 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala @@ -113,13 +113,13 @@ final class OneVsRestModel private[ml] ( val updateUDF = udf { (predictions: Map[Int, Double], prediction: Vector) => predictions + ((index, prediction(1))) } - val transformedDataset = model.transform(df).select(columns : _*) + val transformedDataset = model.transform(df).select(columns: _*) val updatedDataset = transformedDataset .withColumn(tmpColName, updateUDF(col(accColName), col(rawPredictionCol))) val newColumns = origCols ++ List(col(tmpColName)) // switch out the intermediate column with the accumulator column - updatedDataset.select(newColumns : _*).withColumnRenamed(tmpColName, accColName) + updatedDataset.select(newColumns: _*).withColumnRenamed(tmpColName, accColName) } if (handlePersistence) { diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala index f9952434d2..6cc9d02544 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala @@ -238,7 +238,7 @@ private class ColumnPruner(columnsToPrune: Set[String]) extends Transformer { override def transform(dataset: DataFrame): DataFrame = { val columnsToKeep = dataset.columns.filter(!columnsToPrune.contains(_)) - dataset.select(columnsToKeep.map(dataset.col) : _*) + dataset.select(columnsToKeep.map(dataset.col): _*) } override def transformSchema(schema: StructType): StructType = { diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala index 0b215659b3..716bc63e00 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala @@ -102,7 +102,7 @@ class VectorAssembler(override val uid: String) } } - dataset.select(col("*"), assembleFunc(struct(args : _*)).as($(outputCol), metadata)) + dataset.select(col("*"), assembleFunc(struct(args: _*)).as($(outputCol), metadata)) } override def transformSchema(schema: StructType): StructType = { diff --git a/mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala b/mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala index 6e87302c77..d3376a7dff 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala @@ -474,7 +474,7 @@ private[ml] object RandomForest extends Logging { val nodeToFeatures = getNodeToFeatures(treeToNodeToIndexInfo) val nodeToFeaturesBc = input.sparkContext.broadcast(nodeToFeatures) - val partitionAggregates : RDD[(Int, DTStatsAggregator)] = if (nodeIdCache.nonEmpty) { + val partitionAggregates: RDD[(Int, DTStatsAggregator)] = if (nodeIdCache.nonEmpty) { input.zip(nodeIdCache.get.nodeIdsForInstances).mapPartitions { points => // Construct a nodeStatsAggregators array to hold node aggregate stats, // each node will have a nodeStatsAggregator @@ -825,7 +825,7 @@ private[ml] object RandomForest extends Logging { protected[tree] def findSplits( input: RDD[LabeledPoint], metadata: DecisionTreeMetadata, - seed : Long): Array[Array[Split]] = { + seed: Long): Array[Array[Split]] = { logDebug("isMulticlass = " + metadata.isMulticlass) diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixtureModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixtureModel.scala index 5c9bc62cb0..16bc45bcb6 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixtureModel.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixtureModel.scala @@ -177,7 +177,7 @@ object GaussianMixtureModel extends Loader[GaussianMixtureModel] { } @Since("1.4.0") - override def load(sc: SparkContext, path: String) : GaussianMixtureModel = { + override def load(sc: SparkContext, path: String): GaussianMixtureModel = { val (loadedClassName, version, metadata) = Loader.loadMetadata(sc, path) implicit val formats = DefaultFormats val k = (metadata \ "k").extract[Int] diff --git a/mllib/src/main/scala/org/apache/spark/mllib/fpm/FPGrowth.scala b/mllib/src/main/scala/org/apache/spark/mllib/fpm/FPGrowth.scala index 5273ed4d76..ffae0e7ed0 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/fpm/FPGrowth.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/fpm/FPGrowth.scala @@ -134,7 +134,7 @@ object FPGrowthModel extends Loader[FPGrowthModel[_]] { loadImpl(freqItemsets, sample) } - def loadImpl[Item : ClassTag](freqItemsets: DataFrame, sample: Item): FPGrowthModel[Item] = { + def loadImpl[Item: ClassTag](freqItemsets: DataFrame, sample: Item): FPGrowthModel[Item] = { val freqItemsetsRDD = freqItemsets.select("items", "freq").map { x => val items = x.getAs[Seq[Item]](0).toArray val freq = x.getLong(1) diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala index d7a74db0b1..b08da4fb55 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala @@ -279,7 +279,7 @@ class DenseMatrix @Since("1.3.0") ( } override def hashCode: Int = { - com.google.common.base.Objects.hashCode(numRows : Integer, numCols: Integer, toArray) + com.google.common.base.Objects.hashCode(numRows: Integer, numCols: Integer, toArray) } private[mllib] def toBreeze: BM[Double] = { diff --git a/mllib/src/main/scala/org/apache/spark/mllib/pmml/export/BinaryClassificationPMMLModelExport.scala b/mllib/src/main/scala/org/apache/spark/mllib/pmml/export/BinaryClassificationPMMLModelExport.scala index 7abb1bf7ce..a8c32f72bf 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/pmml/export/BinaryClassificationPMMLModelExport.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/pmml/export/BinaryClassificationPMMLModelExport.scala @@ -27,9 +27,9 @@ import org.apache.spark.mllib.regression.GeneralizedLinearModel * PMML Model Export for GeneralizedLinearModel class with binary ClassificationModel */ private[mllib] class BinaryClassificationPMMLModelExport( - model : GeneralizedLinearModel, - description : String, - normalizationMethod : RegressionNormalizationMethodType, + model: GeneralizedLinearModel, + description: String, + normalizationMethod: RegressionNormalizationMethodType, threshold: Double) extends PMMLModelExport { diff --git a/mllib/src/main/scala/org/apache/spark/mllib/pmml/export/KMeansPMMLModelExport.scala b/mllib/src/main/scala/org/apache/spark/mllib/pmml/export/KMeansPMMLModelExport.scala index b5b824bb9c..255c6140e5 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/pmml/export/KMeansPMMLModelExport.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/pmml/export/KMeansPMMLModelExport.scala @@ -26,14 +26,14 @@ import org.apache.spark.mllib.clustering.KMeansModel /** * PMML Model Export for KMeansModel class */ -private[mllib] class KMeansPMMLModelExport(model : KMeansModel) extends PMMLModelExport{ +private[mllib] class KMeansPMMLModelExport(model: KMeansModel) extends PMMLModelExport{ populateKMeansPMML(model) /** * Export the input KMeansModel model to PMML format. */ - private def populateKMeansPMML(model : KMeansModel): Unit = { + private def populateKMeansPMML(model: KMeansModel): Unit = { pmml.getHeader.setDescription("k-means clustering") if (model.clusterCenters.length > 0) { diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala index af1f7e74c0..c73774fcd8 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala @@ -600,7 +600,7 @@ object DecisionTree extends Serializable with Logging { val nodeToFeatures = getNodeToFeatures(treeToNodeToIndexInfo) val nodeToFeaturesBc = input.sparkContext.broadcast(nodeToFeatures) - val partitionAggregates : RDD[(Int, DTStatsAggregator)] = if (nodeIdCache.nonEmpty) { + val partitionAggregates: RDD[(Int, DTStatsAggregator)] = if (nodeIdCache.nonEmpty) { input.zip(nodeIdCache.get.nodeIdsForInstances).mapPartitions { points => // Construct a nodeStatsAggregators array to hold node aggregate stats, // each node will have a nodeStatsAggregator diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala index 66f0908c12..b373c2de3e 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala @@ -83,7 +83,7 @@ class Node @Since("1.2.0") ( * @return predicted value */ @Since("1.1.0") - def predict(features: Vector) : Double = { + def predict(features: Vector): Double = { if (isLeaf) { predict.predict } else { diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala index 094528e2ec..240781bcd3 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/util/LinearDataGenerator.scala @@ -175,7 +175,7 @@ object LinearDataGenerator { nfeatures: Int, eps: Double, nparts: Int = 2, - intercept: Double = 0.0) : RDD[LabeledPoint] = { + intercept: Double = 0.0): RDD[LabeledPoint] = { val random = new Random(42) // Random values distributed uniformly in [-0.5, 0.5] val w = Array.fill(nfeatures)(random.nextDouble() - 0.5) |