Repository: spark Updated Branches: refs/heads/branch-1.5 eaeebb92f -> f5ed9ede9
SPARK-8916 [Documentation, MLlib] Add @since tags to mllib.regression Added since tags to mllib.regression Author: Prayag Chandran <[email protected]> Closes #7518 from prayagchandran/sinceTags and squashes the following commits: fa4dda2 [Prayag Chandran] Re-formatting 6c6d584 [Prayag Chandran] Corrected a few tags. Removed few unnecessary tags 1a0365f [Prayag Chandran] Reformating and adding a few more tags 89fdb66 [Prayag Chandran] SPARK-8916 [Documentation, MLlib] Add @since tags to mllib.regression (cherry picked from commit 18523c130548f0438dff8d1f25531fd2ed36e517) Signed-off-by: DB Tsai <[email protected]> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/f5ed9ede Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/f5ed9ede Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/f5ed9ede Branch: refs/heads/branch-1.5 Commit: f5ed9ede9f962b8d36c897ac9ca798947ae5b96f Parents: eaeebb9 Author: Prayag Chandran <[email protected]> Authored: Mon Aug 17 17:26:08 2015 -0700 Committer: DB Tsai <[email protected]> Committed: Mon Aug 17 17:26:27 2015 -0700 ---------------------------------------------------------------------- .../regression/GeneralizedLinearAlgorithm.scala | 26 +++++++++++++++- .../mllib/regression/IsotonicRegression.scala | 23 +++++++++++++- .../spark/mllib/regression/LabeledPoint.scala | 6 ++++ .../apache/spark/mllib/regression/Lasso.scala | 21 +++++++++++++ .../mllib/regression/LinearRegression.scala | 21 +++++++++++++ .../mllib/regression/RegressionModel.scala | 9 ++++++ .../mllib/regression/RidgeRegression.scala | 21 +++++++++++++ .../regression/StreamingLinearAlgorithm.scala | 32 +++++++++++++++++--- .../StreamingLinearRegressionWithSGD.scala | 21 +++++++++---- 9 files changed, 168 insertions(+), 12 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/f5ed9ede/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 6709bd7..2980b94 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 @@ -34,6 +34,8 @@ import org.apache.spark.storage.StorageLevel * * @param weights Weights computed for every feature. * @param intercept Intercept computed for this model. + * + * @since 0.8.0 */ @DeveloperApi abstract class GeneralizedLinearModel(val weights: Vector, val intercept: Double) @@ -53,6 +55,8 @@ abstract class GeneralizedLinearModel(val weights: Vector, val intercept: Double * * @param testData RDD representing data points to be predicted * @return RDD[Double] where each entry contains the corresponding prediction + * + * @since 1.0.0 */ def predict(testData: RDD[Vector]): RDD[Double] = { // A small optimization to avoid serializing the entire model. Only the weightsMatrix @@ -71,6 +75,8 @@ abstract class GeneralizedLinearModel(val weights: Vector, val intercept: Double * * @param testData array representing a single data point * @return Double prediction from the trained model + * + * @since 1.0.0 */ def predict(testData: Vector): Double = { predictPoint(testData, weights, intercept) @@ -88,6 +94,8 @@ abstract class GeneralizedLinearModel(val weights: Vector, val intercept: Double * :: DeveloperApi :: * GeneralizedLinearAlgorithm implements methods to train a Generalized Linear Model (GLM). * This class should be extended with an Optimizer to create a new GLM. + * + * @since 0.8.0 */ @DeveloperApi abstract class GeneralizedLinearAlgorithm[M <: GeneralizedLinearModel] @@ -95,7 +103,11 @@ abstract class GeneralizedLinearAlgorithm[M <: GeneralizedLinearModel] protected val validators: Seq[RDD[LabeledPoint] => Boolean] = List() - /** The optimizer to solve the problem. */ + /** + * The optimizer to solve the problem. + * + * @since 1.0.0 + */ def optimizer: Optimizer /** Whether to add intercept (default: false). */ @@ -130,6 +142,8 @@ abstract class GeneralizedLinearAlgorithm[M <: GeneralizedLinearModel] /** * The dimension of training features. + * + * @since 1.4.0 */ def getNumFeatures: Int = this.numFeatures @@ -153,12 +167,16 @@ abstract class GeneralizedLinearAlgorithm[M <: GeneralizedLinearModel] /** * Get if the algorithm uses addIntercept + * + * @since 1.4.0 */ def isAddIntercept: Boolean = this.addIntercept /** * Set if the algorithm should add an intercept. Default false. * We set the default to false because adding the intercept will cause memory allocation. + * + * @since 0.8.0 */ def setIntercept(addIntercept: Boolean): this.type = { this.addIntercept = addIntercept @@ -167,6 +185,8 @@ abstract class GeneralizedLinearAlgorithm[M <: GeneralizedLinearModel] /** * Set if the algorithm should validate data before training. Default true. + * + * @since 0.8.0 */ def setValidateData(validateData: Boolean): this.type = { this.validateData = validateData @@ -176,6 +196,8 @@ abstract class GeneralizedLinearAlgorithm[M <: GeneralizedLinearModel] /** * Run the algorithm with the configured parameters on an input * RDD of LabeledPoint entries. + * + * @since 0.8.0 */ def run(input: RDD[LabeledPoint]): M = { if (numFeatures < 0) { @@ -208,6 +230,8 @@ abstract class GeneralizedLinearAlgorithm[M <: GeneralizedLinearModel] /** * Run the algorithm with the configured parameters on an input RDD * of LabeledPoint entries starting from the initial weights provided. + * + * @since 1.0.0 */ def run(input: RDD[LabeledPoint], initialWeights: Vector): M = { http://git-wip-us.apache.org/repos/asf/spark/blob/f5ed9ede/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 f3b46c7..8995591 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 @@ -46,6 +46,8 @@ import org.apache.spark.sql.SQLContext * @param predictions Array of predictions associated to the boundaries at the same index. * Results of isotonic regression and therefore monotone. * @param isotonic indicates whether this is isotonic or antitonic. + * + * @since 1.3.0 */ @Experimental class IsotonicRegressionModel ( @@ -59,7 +61,11 @@ class IsotonicRegressionModel ( assertOrdered(boundaries) assertOrdered(predictions)(predictionOrd) - /** A Java-friendly constructor that takes two Iterable parameters and one Boolean parameter. */ + /** + * A Java-friendly constructor that takes two Iterable parameters and one Boolean parameter. + * + * @since 1.4.0 + */ def this(boundaries: java.lang.Iterable[Double], predictions: java.lang.Iterable[Double], isotonic: java.lang.Boolean) = { @@ -83,6 +89,8 @@ class IsotonicRegressionModel ( * * @param testData Features to be labeled. * @return Predicted labels. + * + * @since 1.3.0 */ def predict(testData: RDD[Double]): RDD[Double] = { testData.map(predict) @@ -94,6 +102,8 @@ class IsotonicRegressionModel ( * * @param testData Features to be labeled. * @return Predicted labels. + * + * @since 1.3.0 */ def predict(testData: JavaDoubleRDD): JavaDoubleRDD = { JavaDoubleRDD.fromRDD(predict(testData.rdd.retag.asInstanceOf[RDD[Double]])) @@ -114,6 +124,8 @@ class IsotonicRegressionModel ( * 3) If testData falls between two values in boundary array then prediction is treated * as piecewise linear function and interpolated value is returned. In case there are * multiple values with the same boundary then the same rules as in 2) are used. + * + * @since 1.3.0 */ def predict(testData: Double): Double = { @@ -148,6 +160,9 @@ class IsotonicRegressionModel ( /** A convenient method for boundaries called by the Python API. */ private[mllib] def predictionVector: Vector = Vectors.dense(predictions) + /** + * @since 1.4.0 + */ override def save(sc: SparkContext, path: String): Unit = { IsotonicRegressionModel.SaveLoadV1_0.save(sc, path, boundaries, predictions, isotonic) } @@ -155,6 +170,9 @@ class IsotonicRegressionModel ( override protected def formatVersion: String = "1.0" } +/** + * @since 1.4.0 + */ object IsotonicRegressionModel extends Loader[IsotonicRegressionModel] { import org.apache.spark.mllib.util.Loader._ @@ -200,6 +218,9 @@ object IsotonicRegressionModel extends Loader[IsotonicRegressionModel] { } } + /** + * @since 1.4.0 + */ override def load(sc: SparkContext, path: String): IsotonicRegressionModel = { implicit val formats = DefaultFormats val (loadedClassName, version, metadata) = loadMetadata(sc, path) http://git-wip-us.apache.org/repos/asf/spark/blob/f5ed9ede/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 d5fea82..8b51011 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 @@ -28,6 +28,8 @@ 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) { @@ -38,11 +40,15 @@ case class LabeledPoint(label: Double, features: Vector) { /** * Parser for [[org.apache.spark.mllib.regression.LabeledPoint]]. + * + * @since 1.1.0 */ object LabeledPoint { /** * Parses a string resulted from `LabeledPoint#toString` into * an [[org.apache.spark.mllib.regression.LabeledPoint]]. + * + * @since 1.1.0 */ def parse(s: String): LabeledPoint = { if (s.startsWith("(")) { http://git-wip-us.apache.org/repos/asf/spark/blob/f5ed9ede/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 4f48238..03eb589 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 @@ -30,6 +30,8 @@ import org.apache.spark.rdd.RDD * * @param weights Weights computed for every feature. * @param intercept Intercept computed for this model. + * + * @since 0.8.0 */ class LassoModel ( override val weights: Vector, @@ -44,6 +46,9 @@ class LassoModel ( weightMatrix.toBreeze.dot(dataMatrix.toBreeze) + intercept } + /** + * @since 1.3.0 + */ override def save(sc: SparkContext, path: String): Unit = { GLMRegressionModel.SaveLoadV1_0.save(sc, path, this.getClass.getName, weights, intercept) } @@ -51,8 +56,14 @@ class LassoModel ( override protected def formatVersion: String = "1.0" } +/** + * @since 1.3.0 + */ object LassoModel extends Loader[LassoModel] { + /** + * @since 1.3.0 + */ override def load(sc: SparkContext, path: String): LassoModel = { val (loadedClassName, version, metadata) = Loader.loadMetadata(sc, path) // Hard-code class name string in case it changes in the future @@ -106,6 +117,8 @@ class LassoWithSGD private ( /** * Top-level methods for calling Lasso. + * + * @since 0.8.0 */ object LassoWithSGD { @@ -123,6 +136,8 @@ object LassoWithSGD { * @param miniBatchFraction Fraction of data to be used per iteration. * @param initialWeights Initial set of weights to be used. Array should be equal in size to * the number of features in the data. + * + * @since 1.0.0 */ def train( input: RDD[LabeledPoint], @@ -146,6 +161,8 @@ object LassoWithSGD { * @param stepSize Step size to be used for each iteration of gradient descent. * @param regParam Regularization parameter. * @param miniBatchFraction Fraction of data to be used per iteration. + * + * @since 0.8.0 */ def train( input: RDD[LabeledPoint], @@ -167,6 +184,8 @@ object LassoWithSGD { * @param regParam Regularization parameter. * @param numIterations Number of iterations of gradient descent to run. * @return a LassoModel which has the weights and offset from training. + * + * @since 0.8.0 */ def train( input: RDD[LabeledPoint], @@ -185,6 +204,8 @@ object LassoWithSGD { * matrix A as well as the corresponding right hand side label y * @param numIterations Number of iterations of gradient descent to run. * @return a LassoModel which has the weights and offset from training. + * + * @since 0.8.0 */ def train( input: RDD[LabeledPoint], http://git-wip-us.apache.org/repos/asf/spark/blob/f5ed9ede/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 9453c4f..fb5c220 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 @@ -30,6 +30,8 @@ import org.apache.spark.rdd.RDD * * @param weights Weights computed for every feature. * @param intercept Intercept computed for this model. + * + * @since 0.8.0 */ class LinearRegressionModel ( override val weights: Vector, @@ -44,6 +46,9 @@ class LinearRegressionModel ( weightMatrix.toBreeze.dot(dataMatrix.toBreeze) + intercept } + /** + * @since 1.3.0 + */ override def save(sc: SparkContext, path: String): Unit = { GLMRegressionModel.SaveLoadV1_0.save(sc, path, this.getClass.getName, weights, intercept) } @@ -51,8 +56,14 @@ class LinearRegressionModel ( override protected def formatVersion: String = "1.0" } +/** + * @since 1.3.0 + */ object LinearRegressionModel extends Loader[LinearRegressionModel] { + /** + * @since 1.3.0 + */ override def load(sc: SparkContext, path: String): LinearRegressionModel = { val (loadedClassName, version, metadata) = Loader.loadMetadata(sc, path) // Hard-code class name string in case it changes in the future @@ -105,6 +116,8 @@ class LinearRegressionWithSGD private[mllib] ( /** * Top-level methods for calling LinearRegression. + * + * @since 0.8.0 */ object LinearRegressionWithSGD { @@ -121,6 +134,8 @@ object LinearRegressionWithSGD { * @param miniBatchFraction Fraction of data to be used per iteration. * @param initialWeights Initial set of weights to be used. Array should be equal in size to * the number of features in the data. + * + * @since 1.0.0 */ def train( input: RDD[LabeledPoint], @@ -142,6 +157,8 @@ object LinearRegressionWithSGD { * @param numIterations Number of iterations of gradient descent to run. * @param stepSize Step size to be used for each iteration of gradient descent. * @param miniBatchFraction Fraction of data to be used per iteration. + * + * @since 0.8.0 */ def train( input: RDD[LabeledPoint], @@ -161,6 +178,8 @@ object LinearRegressionWithSGD { * @param stepSize Step size to be used for each iteration of Gradient Descent. * @param numIterations Number of iterations of gradient descent to run. * @return a LinearRegressionModel which has the weights and offset from training. + * + * @since 0.8.0 */ def train( input: RDD[LabeledPoint], @@ -178,6 +197,8 @@ object LinearRegressionWithSGD { * matrix A as well as the corresponding right hand side label y * @param numIterations Number of iterations of gradient descent to run. * @return a LinearRegressionModel which has the weights and offset from training. + * + * @since 0.8.0 */ def train( input: RDD[LabeledPoint], http://git-wip-us.apache.org/repos/asf/spark/blob/f5ed9ede/mllib/src/main/scala/org/apache/spark/mllib/regression/RegressionModel.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/RegressionModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/RegressionModel.scala index 214ac4d..b097fd3 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/regression/RegressionModel.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/RegressionModel.scala @@ -24,6 +24,9 @@ import org.apache.spark.api.java.JavaRDD import org.apache.spark.mllib.linalg.Vector import org.apache.spark.rdd.RDD +/** + * @since 0.8.0 + */ @Experimental trait RegressionModel extends Serializable { /** @@ -31,6 +34,8 @@ trait RegressionModel extends Serializable { * * @param testData RDD representing data points to be predicted * @return RDD[Double] where each entry contains the corresponding prediction + * + * @since 1.0.0 */ def predict(testData: RDD[Vector]): RDD[Double] @@ -39,6 +44,8 @@ trait RegressionModel extends Serializable { * * @param testData array representing a single data point * @return Double prediction from the trained model + * + * @since 1.0.0 */ def predict(testData: Vector): Double @@ -46,6 +53,8 @@ trait RegressionModel extends Serializable { * Predict values for examples stored in a JavaRDD. * @param testData JavaRDD representing data points to be predicted * @return a JavaRDD[java.lang.Double] where each entry contains the corresponding prediction + * + * @since 1.0.0 */ def predict(testData: JavaRDD[Vector]): JavaRDD[java.lang.Double] = predict(testData.rdd).toJavaRDD().asInstanceOf[JavaRDD[java.lang.Double]] http://git-wip-us.apache.org/repos/asf/spark/blob/f5ed9ede/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 7d28ffa..5bced6b 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 @@ -31,6 +31,8 @@ import org.apache.spark.rdd.RDD * * @param weights Weights computed for every feature. * @param intercept Intercept computed for this model. + * + * @since 0.8.0 */ class RidgeRegressionModel ( override val weights: Vector, @@ -45,6 +47,9 @@ class RidgeRegressionModel ( weightMatrix.toBreeze.dot(dataMatrix.toBreeze) + intercept } + /** + * @since 1.3.0 + */ override def save(sc: SparkContext, path: String): Unit = { GLMRegressionModel.SaveLoadV1_0.save(sc, path, this.getClass.getName, weights, intercept) } @@ -52,8 +57,14 @@ class RidgeRegressionModel ( override protected def formatVersion: String = "1.0" } +/** + * @since 1.3.0 + */ object RidgeRegressionModel extends Loader[RidgeRegressionModel] { + /** + * @since 1.3.0 + */ override def load(sc: SparkContext, path: String): RidgeRegressionModel = { val (loadedClassName, version, metadata) = Loader.loadMetadata(sc, path) // Hard-code class name string in case it changes in the future @@ -108,6 +119,8 @@ class RidgeRegressionWithSGD private ( /** * Top-level methods for calling RidgeRegression. + * + * @since 0.8.0 */ object RidgeRegressionWithSGD { @@ -124,6 +137,8 @@ object RidgeRegressionWithSGD { * @param miniBatchFraction Fraction of data to be used per iteration. * @param initialWeights Initial set of weights to be used. Array should be equal in size to * the number of features in the data. + * + * @since 0.8.0 */ def train( input: RDD[LabeledPoint], @@ -146,6 +161,8 @@ object RidgeRegressionWithSGD { * @param stepSize Step size to be used for each iteration of gradient descent. * @param regParam Regularization parameter. * @param miniBatchFraction Fraction of data to be used per iteration. + * + * @since 0.8.0 */ def train( input: RDD[LabeledPoint], @@ -166,6 +183,8 @@ object RidgeRegressionWithSGD { * @param regParam Regularization parameter. * @param numIterations Number of iterations of gradient descent to run. * @return a RidgeRegressionModel which has the weights and offset from training. + * + * @since 0.8.0 */ def train( input: RDD[LabeledPoint], @@ -183,6 +202,8 @@ object RidgeRegressionWithSGD { * @param input RDD of (label, array of features) pairs. * @param numIterations Number of iterations of gradient descent to run. * @return a RidgeRegressionModel which has the weights and offset from training. + * + * @since 0.8.0 */ def train( input: RDD[LabeledPoint], http://git-wip-us.apache.org/repos/asf/spark/blob/f5ed9ede/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 141052b..a2ab95c 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 @@ -53,6 +53,8 @@ import org.apache.spark.streaming.dstream.DStream * It is also ok to call trainOn on different streams; this will update * the model using each of the different sources, in sequence. * + * + * @since 1.1.0 */ @DeveloperApi abstract class StreamingLinearAlgorithm[ @@ -65,7 +67,11 @@ abstract class StreamingLinearAlgorithm[ /** The algorithm to use for updating. */ protected val algorithm: A - /** Return the latest model. */ + /** + * Return the latest model. + * + * @since 1.1.0 + */ def latestModel(): M = { model.get } @@ -77,6 +83,8 @@ abstract class StreamingLinearAlgorithm[ * batch of data from the stream. * * @param data DStream containing labeled data + * + * @since 1.3.0 */ def trainOn(data: DStream[LabeledPoint]): Unit = { if (model.isEmpty) { @@ -95,7 +103,11 @@ abstract class StreamingLinearAlgorithm[ } } - /** Java-friendly version of `trainOn`. */ + /** + * Java-friendly version of `trainOn`. + * + * @since 1.3.0 + */ def trainOn(data: JavaDStream[LabeledPoint]): Unit = trainOn(data.dstream) /** @@ -103,6 +115,8 @@ abstract class StreamingLinearAlgorithm[ * * @param data DStream containing feature vectors * @return DStream containing predictions + * + * @since 1.1.0 */ def predictOn(data: DStream[Vector]): DStream[Double] = { if (model.isEmpty) { @@ -111,7 +125,11 @@ abstract class StreamingLinearAlgorithm[ data.map{x => model.get.predict(x)} } - /** Java-friendly version of `predictOn`. */ + /** + * Java-friendly version of `predictOn`. + * + * @since 1.1.0 + */ def predictOn(data: JavaDStream[Vector]): JavaDStream[java.lang.Double] = { JavaDStream.fromDStream(predictOn(data.dstream).asInstanceOf[DStream[java.lang.Double]]) } @@ -121,6 +139,8 @@ abstract class StreamingLinearAlgorithm[ * @param data DStream containing feature vectors * @tparam K key type * @return DStream containing the input keys and the predictions as values + * + * @since 1.1.0 */ def predictOnValues[K: ClassTag](data: DStream[(K, Vector)]): DStream[(K, Double)] = { if (model.isEmpty) { @@ -130,7 +150,11 @@ abstract class StreamingLinearAlgorithm[ } - /** Java-friendly version of `predictOnValues`. */ + /** + * Java-friendly version of `predictOnValues`. + * + * @since 1.3.0 + */ def predictOnValues[K](data: JavaPairDStream[K, Vector]): JavaPairDStream[K, java.lang.Double] = { implicit val tag = fakeClassTag[K] JavaPairDStream.fromPairDStream( http://git-wip-us.apache.org/repos/asf/spark/blob/f5ed9ede/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 c6d0446..537a052 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 @@ -39,7 +39,6 @@ import org.apache.spark.mllib.linalg.Vector * .setNumIterations(10) * .setInitialWeights(Vectors.dense(...)) * .trainOn(DStream) - * */ @Experimental class StreamingLinearRegressionWithSGD private[mllib] ( @@ -61,31 +60,41 @@ class StreamingLinearRegressionWithSGD private[mllib] ( protected var model: Option[LinearRegressionModel] = None - /** Set the step size for gradient descent. Default: 0.1. */ + /** + * Set the step size for gradient descent. Default: 0.1. + */ def setStepSize(stepSize: Double): this.type = { this.algorithm.optimizer.setStepSize(stepSize) this } - /** Set the number of iterations of gradient descent to run per update. Default: 50. */ + /** + * Set the number of iterations of gradient descent to run per update. Default: 50. + */ def setNumIterations(numIterations: Int): this.type = { this.algorithm.optimizer.setNumIterations(numIterations) this } - /** Set the fraction of each batch to use for updates. Default: 1.0. */ + /** + * Set the fraction of each batch to use for updates. Default: 1.0. + */ def setMiniBatchFraction(miniBatchFraction: Double): this.type = { this.algorithm.optimizer.setMiniBatchFraction(miniBatchFraction) this } - /** Set the initial weights. */ + /** + * Set the initial weights. + */ def setInitialWeights(initialWeights: Vector): this.type = { this.model = Some(algorithm.createModel(initialWeights, 0.0)) this } - /** Set the convergence tolerance. */ + /** + * Set the convergence tolerance. + */ def setConvergenceTol(tolerance: Double): this.type = { this.algorithm.optimizer.setConvergenceTol(tolerance) this --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
