spark-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From dbt...@apache.org
Subject spark git commit: [SPARK-10235] [MLLIB] update since versions in mllib.regression
Date Wed, 26 Aug 2015 05:49:51 GMT
Repository: spark
Updated Branches:
  refs/heads/branch-1.5 6d8ebc801 -> 08d390f45


[SPARK-10235] [MLLIB] update since versions in mllib.regression

Same as #8421 but for `mllib.regression`.

cc freeman-lab dbtsai

Author: Xiangrui Meng <meng@databricks.com>

Closes #8426 from mengxr/SPARK-10235 and squashes the following commits:

6cd28e4 [Xiangrui Meng] update since versions in mllib.regression

(cherry picked from commit 4657fa1f37d41dd4c7240a960342b68c7c591f48)
Signed-off-by: DB Tsai <dbt@netflix.com>


Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/08d390f4
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/08d390f4
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/08d390f4

Branch: refs/heads/branch-1.5
Commit: 08d390f457f80ffdc2dfce61ea579d9026047f12
Parents: 6d8ebc8
Author: Xiangrui Meng <meng@databricks.com>
Authored: Tue Aug 25 22:49:33 2015 -0700
Committer: DB Tsai <dbt@netflix.com>
Committed: Tue Aug 25 22:49:46 2015 -0700

----------------------------------------------------------------------
 .../regression/GeneralizedLinearAlgorithm.scala     |  6 ++++--
 .../spark/mllib/regression/IsotonicRegression.scala | 16 +++++++++-------
 .../spark/mllib/regression/LabeledPoint.scala       |  5 +++--
 .../org/apache/spark/mllib/regression/Lasso.scala   |  9 ++++++---
 .../spark/mllib/regression/LinearRegression.scala   |  9 ++++++---
 .../spark/mllib/regression/RidgeRegression.scala    | 12 +++++++-----
 .../mllib/regression/StreamingLinearAlgorithm.scala |  8 +++-----
 .../StreamingLinearRegressionWithSGD.scala          | 11 +++++++++--
 8 files changed, 47 insertions(+), 29 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/spark/blob/08d390f4/mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala
b/mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala
index 509f6a2..7e3b4d5 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala
@@ -38,7 +38,9 @@ import org.apache.spark.storage.StorageLevel
  */
 @Since("0.8.0")
 @DeveloperApi
-abstract class GeneralizedLinearModel(val weights: Vector, val intercept: Double)
+abstract class GeneralizedLinearModel @Since("1.0.0") (
+    @Since("1.0.0") val weights: Vector,
+    @Since("0.8.0") val intercept: Double)
   extends Serializable {
 
   /**
@@ -107,7 +109,7 @@ abstract class GeneralizedLinearAlgorithm[M <: GeneralizedLinearModel]
    * The optimizer to solve the problem.
    *
    */
-  @Since("1.0.0")
+  @Since("0.8.0")
   def optimizer: Optimizer
 
   /** Whether to add intercept (default: false). */

http://git-wip-us.apache.org/repos/asf/spark/blob/08d390f4/mllib/src/main/scala/org/apache/spark/mllib/regression/IsotonicRegression.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/IsotonicRegression.scala
b/mllib/src/main/scala/org/apache/spark/mllib/regression/IsotonicRegression.scala
index 31ca7c2..877d31b 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/regression/IsotonicRegression.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/IsotonicRegression.scala
@@ -50,10 +50,10 @@ import org.apache.spark.sql.SQLContext
  */
 @Since("1.3.0")
 @Experimental
-class IsotonicRegressionModel (
-    val boundaries: Array[Double],
-    val predictions: Array[Double],
-    val isotonic: Boolean) extends Serializable with Saveable {
+class IsotonicRegressionModel @Since("1.3.0") (
+    @Since("1.3.0") val boundaries: Array[Double],
+    @Since("1.3.0") val predictions: Array[Double],
+    @Since("1.3.0") val isotonic: Boolean) extends Serializable with Saveable {
 
   private val predictionOrd = if (isotonic) Ordering[Double] else Ordering[Double].reverse
 
@@ -63,7 +63,6 @@ class IsotonicRegressionModel (
 
   /**
    * A Java-friendly constructor that takes two Iterable parameters and one Boolean parameter.
-   *
    */
   @Since("1.4.0")
   def this(boundaries: java.lang.Iterable[Double],
@@ -214,8 +213,6 @@ object IsotonicRegressionModel extends Loader[IsotonicRegressionModel]
{
     }
   }
 
-  /**
-   */
   @Since("1.4.0")
   override def load(sc: SparkContext, path: String): IsotonicRegressionModel = {
     implicit val formats = DefaultFormats
@@ -256,6 +253,7 @@ object IsotonicRegressionModel extends Loader[IsotonicRegressionModel]
{
  * @see [[http://en.wikipedia.org/wiki/Isotonic_regression Isotonic regression (Wikipedia)]]
  */
 @Experimental
+@Since("1.3.0")
 class IsotonicRegression private (private var isotonic: Boolean) extends Serializable {
 
   /**
@@ -263,6 +261,7 @@ class IsotonicRegression private (private var isotonic: Boolean) extends
Seriali
    *
    * @return New instance of IsotonicRegression.
    */
+  @Since("1.3.0")
   def this() = this(true)
 
   /**
@@ -271,6 +270,7 @@ class IsotonicRegression private (private var isotonic: Boolean) extends
Seriali
    * @param isotonic Isotonic (increasing) or antitonic (decreasing) sequence.
    * @return This instance of IsotonicRegression.
    */
+  @Since("1.3.0")
   def setIsotonic(isotonic: Boolean): this.type = {
     this.isotonic = isotonic
     this
@@ -286,6 +286,7 @@ class IsotonicRegression private (private var isotonic: Boolean) extends
Seriali
    *              the algorithm is executed.
    * @return Isotonic regression model.
    */
+  @Since("1.3.0")
   def run(input: RDD[(Double, Double, Double)]): IsotonicRegressionModel = {
     val preprocessedInput = if (isotonic) {
       input
@@ -311,6 +312,7 @@ class IsotonicRegression private (private var isotonic: Boolean) extends
Seriali
    *              the algorithm is executed.
    * @return Isotonic regression model.
    */
+  @Since("1.3.0")
   def run(input: JavaRDD[(JDouble, JDouble, JDouble)]): IsotonicRegressionModel = {
     run(input.rdd.retag.asInstanceOf[RDD[(Double, Double, Double)]])
   }

http://git-wip-us.apache.org/repos/asf/spark/blob/08d390f4/mllib/src/main/scala/org/apache/spark/mllib/regression/LabeledPoint.scala
----------------------------------------------------------------------
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 f7fe1b7..c284ad2 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
@@ -29,11 +29,12 @@ import org.apache.spark.SparkException
  *
  * @param label Label for this data point.
  * @param features List of features for this data point.
- *
  */
 @Since("0.8.0")
 @BeanInfo
-case class LabeledPoint(label: Double, features: Vector) {
+case class LabeledPoint @Since("1.0.0") (
+    @Since("0.8.0") label: Double,
+    @Since("1.0.0") features: Vector) {
   override def toString: String = {
     s"($label,$features)"
   }

http://git-wip-us.apache.org/repos/asf/spark/blob/08d390f4/mllib/src/main/scala/org/apache/spark/mllib/regression/Lasso.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/Lasso.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/Lasso.scala
index 556411a..a9aba17 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/regression/Lasso.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/Lasso.scala
@@ -34,9 +34,9 @@ import org.apache.spark.rdd.RDD
  *
  */
 @Since("0.8.0")
-class LassoModel (
-    override val weights: Vector,
-    override val intercept: Double)
+class LassoModel @Since("1.1.0") (
+    @Since("1.0.0") override val weights: Vector,
+    @Since("0.8.0") override val intercept: Double)
   extends GeneralizedLinearModel(weights, intercept)
   with RegressionModel with Serializable with Saveable with PMMLExportable {
 
@@ -84,6 +84,7 @@ object LassoModel extends Loader[LassoModel] {
  * its corresponding right hand side label y.
  * See also the documentation for the precise formulation.
  */
+@Since("0.8.0")
 class LassoWithSGD private (
     private var stepSize: Double,
     private var numIterations: Int,
@@ -93,6 +94,7 @@ class LassoWithSGD private (
 
   private val gradient = new LeastSquaresGradient()
   private val updater = new L1Updater()
+  @Since("0.8.0")
   override val optimizer = new GradientDescent(gradient, updater)
     .setStepSize(stepSize)
     .setNumIterations(numIterations)
@@ -103,6 +105,7 @@ class LassoWithSGD private (
    * Construct a Lasso object with default parameters: {stepSize: 1.0, numIterations: 100,
    * regParam: 0.01, miniBatchFraction: 1.0}.
    */
+  @Since("0.8.0")
   def this() = this(1.0, 100, 0.01, 1.0)
 
   override protected def createModel(weights: Vector, intercept: Double) = {

http://git-wip-us.apache.org/repos/asf/spark/blob/08d390f4/mllib/src/main/scala/org/apache/spark/mllib/regression/LinearRegression.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/LinearRegression.scala
b/mllib/src/main/scala/org/apache/spark/mllib/regression/LinearRegression.scala
index 00ab06e..4996ace 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/regression/LinearRegression.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/LinearRegression.scala
@@ -34,9 +34,9 @@ import org.apache.spark.rdd.RDD
  *
  */
 @Since("0.8.0")
-class LinearRegressionModel (
-    override val weights: Vector,
-    override val intercept: Double)
+class LinearRegressionModel @Since("1.1.0") (
+    @Since("1.0.0") override val weights: Vector,
+    @Since("0.8.0") override val intercept: Double)
   extends GeneralizedLinearModel(weights, intercept) with RegressionModel with Serializable
   with Saveable with PMMLExportable {
 
@@ -85,6 +85,7 @@ object LinearRegressionModel extends Loader[LinearRegressionModel] {
  * its corresponding right hand side label y.
  * See also the documentation for the precise formulation.
  */
+@Since("0.8.0")
 class LinearRegressionWithSGD private[mllib] (
     private var stepSize: Double,
     private var numIterations: Int,
@@ -93,6 +94,7 @@ class LinearRegressionWithSGD private[mllib] (
 
   private val gradient = new LeastSquaresGradient()
   private val updater = new SimpleUpdater()
+  @Since("0.8.0")
   override val optimizer = new GradientDescent(gradient, updater)
     .setStepSize(stepSize)
     .setNumIterations(numIterations)
@@ -102,6 +104,7 @@ class LinearRegressionWithSGD private[mllib] (
    * Construct a LinearRegression object with default parameters: {stepSize: 1.0,
    * numIterations: 100, miniBatchFraction: 1.0}.
    */
+  @Since("0.8.0")
   def this() = this(1.0, 100, 1.0)
 
   override protected[mllib] def createModel(weights: Vector, intercept: Double) = {

http://git-wip-us.apache.org/repos/asf/spark/blob/08d390f4/mllib/src/main/scala/org/apache/spark/mllib/regression/RidgeRegression.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/RidgeRegression.scala
b/mllib/src/main/scala/org/apache/spark/mllib/regression/RidgeRegression.scala
index 21a791d..0a44ff5 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/regression/RidgeRegression.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/RidgeRegression.scala
@@ -35,9 +35,9 @@ import org.apache.spark.rdd.RDD
  *
  */
 @Since("0.8.0")
-class RidgeRegressionModel (
-    override val weights: Vector,
-    override val intercept: Double)
+class RidgeRegressionModel @Since("1.1.0") (
+    @Since("1.0.0") override val weights: Vector,
+    @Since("0.8.0") override val intercept: Double)
   extends GeneralizedLinearModel(weights, intercept)
   with RegressionModel with Serializable with Saveable with PMMLExportable {
 
@@ -85,6 +85,7 @@ object RidgeRegressionModel extends Loader[RidgeRegressionModel] {
  * its corresponding right hand side label y.
  * See also the documentation for the precise formulation.
  */
+@Since("0.8.0")
 class RidgeRegressionWithSGD private (
     private var stepSize: Double,
     private var numIterations: Int,
@@ -94,7 +95,7 @@ class RidgeRegressionWithSGD private (
 
   private val gradient = new LeastSquaresGradient()
   private val updater = new SquaredL2Updater()
-
+  @Since("0.8.0")
   override val optimizer = new GradientDescent(gradient, updater)
     .setStepSize(stepSize)
     .setNumIterations(numIterations)
@@ -105,6 +106,7 @@ class RidgeRegressionWithSGD private (
    * Construct a RidgeRegression object with default parameters: {stepSize: 1.0, numIterations:
100,
    * regParam: 0.01, miniBatchFraction: 1.0}.
    */
+  @Since("0.8.0")
   def this() = this(1.0, 100, 0.01, 1.0)
 
   override protected def createModel(weights: Vector, intercept: Double) = {
@@ -134,7 +136,7 @@ object RidgeRegressionWithSGD {
    *        the number of features in the data.
    *
    */
-  @Since("0.8.0")
+  @Since("1.0.0")
   def train(
       input: RDD[LabeledPoint],
       numIterations: Int,

http://git-wip-us.apache.org/repos/asf/spark/blob/08d390f4/mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearAlgorithm.scala
----------------------------------------------------------------------
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearAlgorithm.scala
b/mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearAlgorithm.scala
index cd3ed8a..73948b2 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearAlgorithm.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearAlgorithm.scala
@@ -22,7 +22,7 @@ import scala.reflect.ClassTag
 import org.apache.spark.Logging
 import org.apache.spark.annotation.{DeveloperApi, Since}
 import org.apache.spark.api.java.JavaSparkContext.fakeClassTag
-import org.apache.spark.mllib.linalg.{Vector, Vectors}
+import org.apache.spark.mllib.linalg.Vector
 import org.apache.spark.streaming.api.java.{JavaDStream, JavaPairDStream}
 import org.apache.spark.streaming.dstream.DStream
 
@@ -83,9 +83,8 @@ abstract class StreamingLinearAlgorithm[
    * batch of data from the stream.
    *
    * @param data DStream containing labeled data
-   *
    */
-  @Since("1.3.0")
+  @Since("1.1.0")
   def trainOn(data: DStream[LabeledPoint]): Unit = {
     if (model.isEmpty) {
       throw new IllegalArgumentException("Model must be initialized before starting training.")
@@ -105,7 +104,6 @@ abstract class StreamingLinearAlgorithm[
 
   /**
    * Java-friendly version of `trainOn`.
-   *
    */
   @Since("1.3.0")
   def trainOn(data: JavaDStream[LabeledPoint]): Unit = trainOn(data.dstream)
@@ -129,7 +127,7 @@ abstract class StreamingLinearAlgorithm[
    * Java-friendly version of `predictOn`.
    *
    */
-  @Since("1.1.0")
+  @Since("1.3.0")
   def predictOn(data: JavaDStream[Vector]): JavaDStream[java.lang.Double] = {
     JavaDStream.fromDStream(predictOn(data.dstream).asInstanceOf[DStream[java.lang.Double]])
   }

http://git-wip-us.apache.org/repos/asf/spark/blob/08d390f4/mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearRegressionWithSGD.scala
----------------------------------------------------------------------
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 26654e4..fe1d487 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
@@ -17,7 +17,7 @@
 
 package org.apache.spark.mllib.regression
 
-import org.apache.spark.annotation.Experimental
+import org.apache.spark.annotation.{Experimental, Since}
 import org.apache.spark.mllib.linalg.Vector
 
 /**
@@ -41,6 +41,7 @@ import org.apache.spark.mllib.linalg.Vector
  *    .trainOn(DStream)
  */
 @Experimental
+@Since("1.1.0")
 class StreamingLinearRegressionWithSGD private[mllib] (
     private var stepSize: Double,
     private var numIterations: Int,
@@ -54,8 +55,10 @@ class StreamingLinearRegressionWithSGD private[mllib] (
    * Initial weights must be set before using trainOn or predictOn
    * (see `StreamingLinearAlgorithm`)
    */
+  @Since("1.1.0")
   def this() = this(0.1, 50, 1.0)
 
+  @Since("1.1.0")
   val algorithm = new LinearRegressionWithSGD(stepSize, numIterations, miniBatchFraction)
 
   protected var model: Option[LinearRegressionModel] = None
@@ -63,6 +66,7 @@ class StreamingLinearRegressionWithSGD private[mllib] (
   /**
    * Set the step size for gradient descent. Default: 0.1.
    */
+  @Since("1.1.0")
   def setStepSize(stepSize: Double): this.type = {
     this.algorithm.optimizer.setStepSize(stepSize)
     this
@@ -71,6 +75,7 @@ class StreamingLinearRegressionWithSGD private[mllib] (
   /**
    * Set the number of iterations of gradient descent to run per update. Default: 50.
    */
+  @Since("1.1.0")
   def setNumIterations(numIterations: Int): this.type = {
     this.algorithm.optimizer.setNumIterations(numIterations)
     this
@@ -79,6 +84,7 @@ class StreamingLinearRegressionWithSGD private[mllib] (
   /**
    * Set the fraction of each batch to use for updates. Default: 1.0.
    */
+  @Since("1.1.0")
   def setMiniBatchFraction(miniBatchFraction: Double): this.type = {
     this.algorithm.optimizer.setMiniBatchFraction(miniBatchFraction)
     this
@@ -87,6 +93,7 @@ class StreamingLinearRegressionWithSGD private[mllib] (
   /**
    * Set the initial weights.
    */
+  @Since("1.1.0")
   def setInitialWeights(initialWeights: Vector): this.type = {
     this.model = Some(algorithm.createModel(initialWeights, 0.0))
     this
@@ -95,9 +102,9 @@ class StreamingLinearRegressionWithSGD private[mllib] (
   /**
    * Set the convergence tolerance. Default: 0.001.
    */
+  @Since("1.5.0")
   def setConvergenceTol(tolerance: Double): this.type = {
     this.algorithm.optimizer.setConvergenceTol(tolerance)
     this
   }
-
 }


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org


Mime
View raw message