Repository: spark Updated Branches: refs/heads/master 6f80c3e88 -> db4d317cc
[SPARK-6428][MLlib] Added explicit type for public methods and implemented hashCode when equals is defined. I want to add a checker to turn public type checking on, since future pull requests can accidentally expose a non-public type. This is the first cleanup task. Author: Reynold Xin <[email protected]> Closes #5102 from rxin/mllib-hashcode-publicmethodtypes and squashes the following commits: 617f19e [Reynold Xin] Fixed Scala compilation error. 52bc2d5 [Reynold Xin] [MLlib] Added explicit type for public methods and implemented hashCode when equals is defined. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/db4d317c Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/db4d317c Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/db4d317c Branch: refs/heads/master Commit: db4d317ccfdd9bd1dc7e8beac54ebcc35966b7d5 Parents: 6f80c3e Author: Reynold Xin <[email protected]> Authored: Fri Mar 20 14:13:02 2015 -0400 Committer: Xiangrui Meng <[email protected]> Committed: Fri Mar 20 14:13:02 2015 -0400 ---------------------------------------------------------------------- .../spark/examples/mllib/MovieLensALS.scala | 3 +- .../mllib/PowerIterationClusteringExample.scala | 4 +-- .../org/apache/spark/ml/feature/HashingTF.scala | 2 +- .../spark/mllib/api/python/PythonMLLibAPI.scala | 18 ++++++---- .../spark/mllib/classification/NaiveBayes.scala | 6 ++-- .../impl/GLMClassificationModel.scala | 2 +- .../apache/spark/mllib/clustering/KMeans.scala | 2 +- .../mllib/evaluation/MultilabelMetrics.scala | 18 +++++----- .../apache/spark/mllib/linalg/Matrices.scala | 12 +++++-- .../org/apache/spark/mllib/linalg/Vectors.scala | 4 ++- .../mllib/linalg/distributed/BlockMatrix.scala | 10 +++++- .../mllib/random/RandomDataGenerator.scala | 4 +-- .../regression/impl/GLMRegressionModel.scala | 2 +- .../mllib/tree/configuration/Strategy.scala | 9 +++-- .../spark/mllib/tree/impurity/Entropy.scala | 2 +- .../apache/spark/mllib/tree/impurity/Gini.scala | 2 +- .../spark/mllib/tree/impurity/Variance.scala | 2 +- .../mllib/tree/model/DecisionTreeModel.scala | 4 +-- .../mllib/tree/model/InformationGainStats.scala | 35 ++++++++++++-------- .../apache/spark/mllib/tree/model/Node.scala | 6 ++-- .../apache/spark/mllib/tree/model/Predict.scala | 6 +++- .../apache/spark/mllib/tree/model/Split.scala | 3 +- .../mllib/tree/model/treeEnsembleModels.scala | 6 ++-- 23 files changed, 101 insertions(+), 61 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala ---------------------------------------------------------------------- diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala index 91a0a86..1f4ca4f 100644 --- a/examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala @@ -175,7 +175,8 @@ object MovieLensALS { } /** Compute RMSE (Root Mean Squared Error). */ - def computeRmse(model: MatrixFactorizationModel, data: RDD[Rating], implicitPrefs: Boolean) = { + def computeRmse(model: MatrixFactorizationModel, data: RDD[Rating], implicitPrefs: Boolean) + : Double = { def mapPredictedRating(r: Double) = if (implicitPrefs) math.max(math.min(r, 1.0), 0.0) else r http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/examples/src/main/scala/org/apache/spark/examples/mllib/PowerIterationClusteringExample.scala ---------------------------------------------------------------------- diff --git a/examples/src/main/scala/org/apache/spark/examples/mllib/PowerIterationClusteringExample.scala b/examples/src/main/scala/org/apache/spark/examples/mllib/PowerIterationClusteringExample.scala index 91c9772..9f22d40 100644 --- a/examples/src/main/scala/org/apache/spark/examples/mllib/PowerIterationClusteringExample.scala +++ b/examples/src/main/scala/org/apache/spark/examples/mllib/PowerIterationClusteringExample.scala @@ -116,7 +116,7 @@ object PowerIterationClusteringExample { sc.stop() } - def generateCircle(radius: Double, n: Int) = { + def generateCircle(radius: Double, n: Int): Seq[(Double, Double)] = { Seq.tabulate(n) { i => val theta = 2.0 * math.Pi * i / n (radius * math.cos(theta), radius * math.sin(theta)) @@ -147,7 +147,7 @@ object PowerIterationClusteringExample { /** * Gaussian Similarity: http://en.wikipedia.org/wiki/Radial_basis_function_kernel */ - def gaussianSimilarity(p1: (Double, Double), p2: (Double, Double), sigma: Double) = { + def gaussianSimilarity(p1: (Double, Double), p2: (Double, Double), sigma: Double): Double = { val coeff = 1.0 / (math.sqrt(2.0 * math.Pi) * sigma) val expCoeff = -1.0 / 2.0 * math.pow(sigma, 2.0) val ssquares = (p1._1 - p2._1) * (p1._1 - p2._1) + (p1._2 - p2._2) * (p1._2 - p2._2) http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala index 6131ba88..fc4e127 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala @@ -41,7 +41,7 @@ class HashingTF extends UnaryTransformer[Iterable[_], Vector, HashingTF] { def getNumFeatures: Int = get(numFeatures) /** @group setParam */ - def setNumFeatures(value: Int) = set(numFeatures, value) + def setNumFeatures(value: Int): this.type = set(numFeatures, value) override protected def createTransformFunc(paramMap: ParamMap): Iterable[_] => Vector = { val hashingTF = new feature.HashingTF(paramMap(numFeatures)) http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala ---------------------------------------------------------------------- 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 cbd87ea..15ca254 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 @@ -345,9 +345,13 @@ private[python] class PythonMLLibAPI extends Serializable { def predict(userAndProducts: JavaRDD[Array[Any]]): RDD[Rating] = predict(SerDe.asTupleRDD(userAndProducts.rdd)) - def getUserFeatures = SerDe.fromTuple2RDD(userFeatures.asInstanceOf[RDD[(Any, Any)]]) + def getUserFeatures: RDD[Array[Any]] = { + SerDe.fromTuple2RDD(userFeatures.asInstanceOf[RDD[(Any, Any)]]) + } - def getProductFeatures = SerDe.fromTuple2RDD(productFeatures.asInstanceOf[RDD[(Any, Any)]]) + def getProductFeatures: RDD[Array[Any]] = { + SerDe.fromTuple2RDD(productFeatures.asInstanceOf[RDD[(Any, Any)]]) + } } @@ -909,7 +913,7 @@ private[spark] object SerDe extends Serializable { // Pickler for DenseVector private[python] class DenseVectorPickler extends BasePickler[DenseVector] { - def saveState(obj: Object, out: OutputStream, pickler: Pickler) = { + def saveState(obj: Object, out: OutputStream, pickler: Pickler): Unit = { val vector: DenseVector = obj.asInstanceOf[DenseVector] val bytes = new Array[Byte](8 * vector.size) val bb = ByteBuffer.wrap(bytes) @@ -941,7 +945,7 @@ private[spark] object SerDe extends Serializable { // Pickler for DenseMatrix private[python] class DenseMatrixPickler extends BasePickler[DenseMatrix] { - def saveState(obj: Object, out: OutputStream, pickler: Pickler) = { + def saveState(obj: Object, out: OutputStream, pickler: Pickler): Unit = { val m: DenseMatrix = obj.asInstanceOf[DenseMatrix] val bytes = new Array[Byte](8 * m.values.size) val order = ByteOrder.nativeOrder() @@ -973,7 +977,7 @@ private[spark] object SerDe extends Serializable { // Pickler for SparseVector private[python] class SparseVectorPickler extends BasePickler[SparseVector] { - def saveState(obj: Object, out: OutputStream, pickler: Pickler) = { + def saveState(obj: Object, out: OutputStream, pickler: Pickler): Unit = { val v: SparseVector = obj.asInstanceOf[SparseVector] val n = v.indices.size val indiceBytes = new Array[Byte](4 * n) @@ -1015,7 +1019,7 @@ private[spark] object SerDe extends Serializable { // Pickler for LabeledPoint private[python] class LabeledPointPickler extends BasePickler[LabeledPoint] { - def saveState(obj: Object, out: OutputStream, pickler: Pickler) = { + def saveState(obj: Object, out: OutputStream, pickler: Pickler): Unit = { val point: LabeledPoint = obj.asInstanceOf[LabeledPoint] saveObjects(out, pickler, point.label, point.features) } @@ -1031,7 +1035,7 @@ private[spark] object SerDe extends Serializable { // Pickler for Rating private[python] class RatingPickler extends BasePickler[Rating] { - def saveState(obj: Object, out: OutputStream, pickler: Pickler) = { + def saveState(obj: Object, out: OutputStream, pickler: Pickler): Unit = { val rating: Rating = obj.asInstanceOf[Rating] saveObjects(out, pickler, rating.user, rating.product, rating.rating) } http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala ---------------------------------------------------------------------- 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 2ebc7fa..068449a 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 @@ -83,10 +83,10 @@ object NaiveBayesModel extends Loader[NaiveBayesModel] { private object SaveLoadV1_0 { - def thisFormatVersion = "1.0" + def thisFormatVersion: String = "1.0" /** Hard-code class name string in case it changes in the future */ - def thisClassName = "org.apache.spark.mllib.classification.NaiveBayesModel" + def thisClassName: String = "org.apache.spark.mllib.classification.NaiveBayesModel" /** Model data for model import/export */ case class Data(labels: Array[Double], pi: Array[Double], theta: Array[Array[Double]]) @@ -174,7 +174,7 @@ class NaiveBayes private (private var lambda: Double) extends Serializable with * * @param data RDD of [[org.apache.spark.mllib.regression.LabeledPoint]]. */ - def run(data: RDD[LabeledPoint]) = { + def run(data: RDD[LabeledPoint]): NaiveBayesModel = { val requireNonnegativeValues: Vector => Unit = (v: Vector) => { val values = v match { case SparseVector(size, indices, values) => http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/classification/impl/GLMClassificationModel.scala ---------------------------------------------------------------------- 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 8956189..3b6790c 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 @@ -32,7 +32,7 @@ private[classification] object GLMClassificationModel { object SaveLoadV1_0 { - def thisFormatVersion = "1.0" + def thisFormatVersion: String = "1.0" /** Model data for import/export */ case class Data(weights: Vector, intercept: Double, threshold: Option[Double]) http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala index e41f941..0f8d6a3 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala @@ -536,5 +536,5 @@ class VectorWithNorm(val vector: Vector, val norm: Double) extends Serializable def this(array: Array[Double]) = this(Vectors.dense(array)) /** Converts the vector to a dense vector. */ - def toDense = new VectorWithNorm(Vectors.dense(vector.toArray), norm) + def toDense: VectorWithNorm = new VectorWithNorm(Vectors.dense(vector.toArray), norm) } http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/evaluation/MultilabelMetrics.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/MultilabelMetrics.scala b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/MultilabelMetrics.scala index ea10bde..a8378a7 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/evaluation/MultilabelMetrics.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/evaluation/MultilabelMetrics.scala @@ -96,30 +96,30 @@ class MultilabelMetrics(predictionAndLabels: RDD[(Array[Double], Array[Double])] * Returns precision for a given label (category) * @param label the label. */ - def precision(label: Double) = { + def precision(label: Double): Double = { val tp = tpPerClass(label) val fp = fpPerClass.getOrElse(label, 0L) - if (tp + fp == 0) 0 else tp.toDouble / (tp + fp) + if (tp + fp == 0) 0.0 else tp.toDouble / (tp + fp) } /** * Returns recall for a given label (category) * @param label the label. */ - def recall(label: Double) = { + def recall(label: Double): Double = { val tp = tpPerClass(label) val fn = fnPerClass.getOrElse(label, 0L) - if (tp + fn == 0) 0 else tp.toDouble / (tp + fn) + if (tp + fn == 0) 0.0 else tp.toDouble / (tp + fn) } /** * Returns f1-measure for a given label (category) * @param label the label. */ - def f1Measure(label: Double) = { + def f1Measure(label: Double): Double = { val p = precision(label) val r = recall(label) - if((p + r) == 0) 0 else 2 * p * r / (p + r) + if((p + r) == 0) 0.0 else 2 * p * r / (p + r) } private lazy val sumTp = tpPerClass.foldLeft(0L) { case (sum, (_, tp)) => sum + tp } @@ -130,7 +130,7 @@ class MultilabelMetrics(predictionAndLabels: RDD[(Array[Double], Array[Double])] * Returns micro-averaged label-based precision * (equals to micro-averaged document-based precision) */ - lazy val microPrecision = { + lazy val microPrecision: Double = { val sumFp = fpPerClass.foldLeft(0L){ case(cum, (_, fp)) => cum + fp} sumTp.toDouble / (sumTp + sumFp) } @@ -139,7 +139,7 @@ class MultilabelMetrics(predictionAndLabels: RDD[(Array[Double], Array[Double])] * Returns micro-averaged label-based recall * (equals to micro-averaged document-based recall) */ - lazy val microRecall = { + lazy val microRecall: Double = { val sumFn = fnPerClass.foldLeft(0.0){ case(cum, (_, fn)) => cum + fn} sumTp.toDouble / (sumTp + sumFn) } @@ -148,7 +148,7 @@ class MultilabelMetrics(predictionAndLabels: RDD[(Array[Double], Array[Double])] * Returns micro-averaged label-based f1-measure * (equals to micro-averaged document-based f1-measure) */ - lazy val microF1Measure = 2.0 * sumTp / (2 * sumTp + sumFnClass + sumFpClass) + lazy val microF1Measure: Double = 2.0 * sumTp / (2 * sumTp + sumFnClass + sumFpClass) /** * Returns the sequence of labels in ascending order http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/linalg/Matrices.scala ---------------------------------------------------------------------- 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 0e4a4d0..fdd8848 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 @@ -146,12 +146,16 @@ class DenseMatrix( def this(numRows: Int, numCols: Int, values: Array[Double]) = this(numRows, numCols, values, false) - override def equals(o: Any) = o match { + override def equals(o: Any): Boolean = o match { case m: DenseMatrix => m.numRows == numRows && m.numCols == numCols && Arrays.equals(toArray, m.toArray) case _ => false } + override def hashCode: Int = { + com.google.common.base.Objects.hashCode(numRows : Integer, numCols: Integer, toArray) + } + private[mllib] def toBreeze: BM[Double] = { if (!isTransposed) { new BDM[Double](numRows, numCols, values) @@ -173,7 +177,7 @@ class DenseMatrix( values(index(i, j)) = v } - override def copy = new DenseMatrix(numRows, numCols, values.clone()) + override def copy: DenseMatrix = new DenseMatrix(numRows, numCols, values.clone()) private[mllib] def map(f: Double => Double) = new DenseMatrix(numRows, numCols, values.map(f)) @@ -431,7 +435,9 @@ class SparseMatrix( } } - override def copy = new SparseMatrix(numRows, numCols, colPtrs, rowIndices, values.clone()) + override def copy: SparseMatrix = { + new SparseMatrix(numRows, numCols, colPtrs, rowIndices, values.clone()) + } private[mllib] def map(f: Double => Double) = new SparseMatrix(numRows, numCols, colPtrs, rowIndices, values.map(f)) http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala index e9d25dc..2cda9b2 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala @@ -183,6 +183,8 @@ private[spark] class VectorUDT extends UserDefinedType[Vector] { } } + override def hashCode: Int = 7919 + private[spark] override def asNullable: VectorUDT = this } @@ -478,7 +480,7 @@ class DenseVector(val values: Array[Double]) extends Vector { private[mllib] override def toBreeze: BV[Double] = new BDV[Double](values) - override def apply(i: Int) = values(i) + override def apply(i: Int): Double = values(i) override def copy: DenseVector = { new DenseVector(values.clone()) http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrix.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrix.scala index 1d25396..3323ae7 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrix.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/BlockMatrix.scala @@ -49,7 +49,7 @@ private[mllib] class GridPartitioner( private val rowPartitions = math.ceil(rows * 1.0 / rowsPerPart).toInt private val colPartitions = math.ceil(cols * 1.0 / colsPerPart).toInt - override val numPartitions = rowPartitions * colPartitions + override val numPartitions: Int = rowPartitions * colPartitions /** * Returns the index of the partition the input coordinate belongs to. @@ -85,6 +85,14 @@ private[mllib] class GridPartitioner( false } } + + override def hashCode: Int = { + com.google.common.base.Objects.hashCode( + rows: java.lang.Integer, + cols: java.lang.Integer, + rowsPerPart: java.lang.Integer, + colsPerPart: java.lang.Integer) + } } private[mllib] object GridPartitioner { http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/random/RandomDataGenerator.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/random/RandomDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/random/RandomDataGenerator.scala index 405bae6..9349eca 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/random/RandomDataGenerator.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/random/RandomDataGenerator.scala @@ -56,7 +56,7 @@ class UniformGenerator extends RandomDataGenerator[Double] { random.nextDouble() } - override def setSeed(seed: Long) = random.setSeed(seed) + override def setSeed(seed: Long): Unit = random.setSeed(seed) override def copy(): UniformGenerator = new UniformGenerator() } @@ -75,7 +75,7 @@ class StandardNormalGenerator extends RandomDataGenerator[Double] { random.nextGaussian() } - override def setSeed(seed: Long) = random.setSeed(seed) + override def setSeed(seed: Long): Unit = random.setSeed(seed) override def copy(): StandardNormalGenerator = new StandardNormalGenerator() } http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/regression/impl/GLMRegressionModel.scala ---------------------------------------------------------------------- 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 bd7e340..b55944f 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 @@ -32,7 +32,7 @@ private[regression] object GLMRegressionModel { object SaveLoadV1_0 { - def thisFormatVersion = "1.0" + def thisFormatVersion: String = "1.0" /** Model data for model import/export */ case class Data(weights: Vector, intercept: Double) http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala index 8d5c36d..ada227c 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala @@ -83,10 +83,13 @@ class Strategy ( @BeanProperty var useNodeIdCache: Boolean = false, @BeanProperty var checkpointInterval: Int = 10) extends Serializable { - def isMulticlassClassification = + def isMulticlassClassification: Boolean = { algo == Classification && numClasses > 2 - def isMulticlassWithCategoricalFeatures - = isMulticlassClassification && (categoricalFeaturesInfo.size > 0) + } + + def isMulticlassWithCategoricalFeatures: Boolean = { + isMulticlassClassification && (categoricalFeaturesInfo.size > 0) + } /** * Java-friendly constructor for [[org.apache.spark.mllib.tree.configuration.Strategy]] http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala index b7950e0..5ac10f3 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala @@ -71,7 +71,7 @@ object Entropy extends Impurity { * Get this impurity instance. * This is useful for passing impurity parameters to a Strategy in Java. */ - def instance = this + def instance: this.type = this } http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala index c946db9..19d3182 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala @@ -67,7 +67,7 @@ object Gini extends Impurity { * Get this impurity instance. * This is useful for passing impurity parameters to a Strategy in Java. */ - def instance = this + def instance: this.type = this } http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Variance.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Variance.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Variance.scala index df9eafa..7104a7f 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Variance.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Variance.scala @@ -58,7 +58,7 @@ object Variance extends Impurity { * Get this impurity instance. * This is useful for passing impurity parameters to a Strategy in Java. */ - def instance = this + def instance: this.type = this } http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala ---------------------------------------------------------------------- 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 8a57ebc..c9bafd6 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 @@ -120,10 +120,10 @@ object DecisionTreeModel extends Loader[DecisionTreeModel] with Logging { private[tree] object SaveLoadV1_0 { - def thisFormatVersion = "1.0" + def thisFormatVersion: String = "1.0" // Hard-code class name string in case it changes in the future - def thisClassName = "org.apache.spark.mllib.tree.DecisionTreeModel" + def thisClassName: String = "org.apache.spark.mllib.tree.DecisionTreeModel" case class PredictData(predict: Double, prob: Double) { def toPredict: Predict = new Predict(predict, prob) http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala index 80990aa..f209fda 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala @@ -38,23 +38,32 @@ class InformationGainStats( val leftPredict: Predict, val rightPredict: Predict) extends Serializable { - override def toString = { + override def toString: String = { "gain = %f, impurity = %f, left impurity = %f, right impurity = %f" .format(gain, impurity, leftImpurity, rightImpurity) } - override def equals(o: Any) = - o match { - case other: InformationGainStats => { - gain == other.gain && - impurity == other.impurity && - leftImpurity == other.leftImpurity && - rightImpurity == other.rightImpurity && - leftPredict == other.leftPredict && - rightPredict == other.rightPredict - } - case _ => false - } + override def equals(o: Any): Boolean = o match { + case other: InformationGainStats => + gain == other.gain && + impurity == other.impurity && + leftImpurity == other.leftImpurity && + rightImpurity == other.rightImpurity && + leftPredict == other.leftPredict && + rightPredict == other.rightPredict + + case _ => false + } + + override def hashCode: Int = { + com.google.common.base.Objects.hashCode( + gain: java.lang.Double, + impurity: java.lang.Double, + leftImpurity: java.lang.Double, + rightImpurity: java.lang.Double, + leftPredict, + rightPredict) + } } http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala ---------------------------------------------------------------------- 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 d961081..4f72bb8 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 @@ -50,8 +50,10 @@ class Node ( var rightNode: Option[Node], var stats: Option[InformationGainStats]) extends Serializable with Logging { - override def toString = "id = " + id + ", isLeaf = " + isLeaf + ", predict = " + predict + ", " + - "impurity = " + impurity + "split = " + split + ", stats = " + stats + override def toString: String = { + "id = " + id + ", isLeaf = " + isLeaf + ", predict = " + predict + ", " + + "impurity = " + impurity + "split = " + split + ", stats = " + stats + } /** * build the left node and right nodes if not leaf http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Predict.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Predict.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Predict.scala index ad4c0db..25990af 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Predict.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Predict.scala @@ -29,7 +29,7 @@ class Predict( val predict: Double, val prob: Double = 0.0) extends Serializable { - override def toString = { + override def toString: String = { "predict = %f, prob = %f".format(predict, prob) } @@ -39,4 +39,8 @@ class Predict( case _ => false } } + + override def hashCode: Int = { + com.google.common.base.Objects.hashCode(predict: java.lang.Double, prob: java.lang.Double) + } } http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala index b7a85f5..fb35e70 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala @@ -38,9 +38,10 @@ case class Split( featureType: FeatureType, categories: List[Double]) { - override def toString = + override def toString: String = { "Feature = " + feature + ", threshold = " + threshold + ", featureType = " + featureType + ", categories = " + categories + } } /** http://git-wip-us.apache.org/repos/asf/spark/blob/db4d317c/mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala ---------------------------------------------------------------------- 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 30a8f7c..f160852 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 @@ -79,7 +79,7 @@ object RandomForestModel extends Loader[RandomForestModel] { private object SaveLoadV1_0 { // Hard-code class name string in case it changes in the future - def thisClassName = "org.apache.spark.mllib.tree.model.RandomForestModel" + def thisClassName: String = "org.apache.spark.mllib.tree.model.RandomForestModel" } } @@ -130,7 +130,7 @@ object GradientBoostedTreesModel extends Loader[GradientBoostedTreesModel] { private object SaveLoadV1_0 { // Hard-code class name string in case it changes in the future - def thisClassName = "org.apache.spark.mllib.tree.model.GradientBoostedTreesModel" + def thisClassName: String = "org.apache.spark.mllib.tree.model.GradientBoostedTreesModel" } } @@ -257,7 +257,7 @@ private[tree] object TreeEnsembleModel extends Logging { import org.apache.spark.mllib.tree.model.DecisionTreeModel.SaveLoadV1_0.{NodeData, constructTrees} - def thisFormatVersion = "1.0" + def thisFormatVersion: String = "1.0" case class Metadata( algo: String, --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
