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 ae27c57799873f534b8b4df5be9448bc7602b558..a6c049e517ee0d3ed5432ebadf68a108d6c84cf8 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
@@ -30,7 +30,6 @@ import org.apache.spark.rdd.RDD
/**
* :: DeveloperApi ::
- *
* The Java stubs necessary for the Python mllib bindings.
*/
@DeveloperApi
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 5a45f12f1aa1283dceacf46276d6fffc0414b239..18658850a2f644cba7ceabcdf0c354eb06381dd4 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
@@ -29,7 +29,6 @@ import org.apache.spark.rdd.RDD
/**
* :: Experimental ::
- *
* Model for Naive Bayes Classifiers.
*
* @param labels list of labels
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 8f565eb60a60f9e6983fdde1b1a76100181bdc01..90cf8525df52384211ebd99f9de898c0f1461e64 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
@@ -78,7 +78,6 @@ class KMeans private (
/**
* :: Experimental ::
- *
* Set the number of runs of the algorithm to execute in parallel. We initialize the algorithm
* this many times with random starting conditions (configured by the initialization mode), then
* return the best clustering found over any run. Default: 1.
@@ -398,9 +397,6 @@ object KMeans {
MLUtils.fastSquaredDistance(v1.vector, v1.norm, v2.vector, v2.norm)
}
- /**
- * :: Experimental ::
- */
@Experimental
def main(args: Array[String]) {
if (args.length < 4) {
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala
index 89d5c03d76c4235ef346601e1fdcbbb93c9962c6..56b8fdcda66ebab5f0c82e4cca1fef053605c89b 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/CoordinateMatrix.scala
@@ -34,7 +34,6 @@ case class MatrixEntry(i: Long, j: Long, value: Double)
/**
* :: Experimental ::
- *
* Represents a matrix in coordinate format.
*
* @param entries matrix entries
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala
index 24c123ab7eb51a2269214ae845b84e08d057dd5b..132b3af72d9cef42fb80b195c00783b96ffb6a18 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/IndexedRowMatrix.scala
@@ -26,7 +26,6 @@ import org.apache.spark.mllib.linalg.SingularValueDecomposition
/**
* :: Experimental ::
- *
* Represents a row of [[org.apache.spark.mllib.linalg.distributed.IndexedRowMatrix]].
*/
@Experimental
@@ -34,7 +33,6 @@ case class IndexedRow(index: Long, vector: Vector)
/**
* :: Experimental ::
- *
* Represents a row-oriented [[org.apache.spark.mllib.linalg.distributed.DistributedMatrix]] with
* indexed rows.
*
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala
index 8d32c1a6dbba10fba2476c8a97873504aa0ed4f7..f65f43dd3007b7237524d0fe4e96113b360df51a 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala
@@ -30,7 +30,6 @@ import org.apache.spark.Logging
/**
* :: Experimental ::
- *
* Represents a row-oriented distributed Matrix with no meaningful row indices.
*
* @param rows rows stored as an RDD[Vector]
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala
index 1176dc9dbc08d829ac7538e90e812c66220fc91e..679842f831c2a79f3b3b82d0ecacb6ff4b8df20f 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala
@@ -24,7 +24,6 @@ import org.apache.spark.mllib.linalg.{Vectors, Vector}
/**
* :: DeveloperApi ::
- *
* Class used to compute the gradient for a loss function, given a single data point.
*/
@DeveloperApi
@@ -56,7 +55,6 @@ abstract class Gradient extends Serializable {
/**
* :: DeveloperApi ::
- *
* Compute gradient and loss for a logistic loss function, as used in binary classification.
* See also the documentation for the precise formulation.
*/
@@ -100,7 +98,6 @@ class LogisticGradient extends Gradient {
/**
* :: DeveloperApi ::
- *
* Compute gradient and loss for a Least-squared loss function, as used in linear regression.
* This is correct for the averaged least squares loss function (mean squared error)
* L = 1/n ||A weights-y||^2
@@ -135,7 +132,6 @@ class LeastSquaresGradient extends Gradient {
/**
* :: DeveloperApi ::
- *
* Compute gradient and loss for a Hinge loss function, as used in SVM binary classification.
* See also the documentation for the precise formulation.
* NOTE: This assumes that the labels are {0,1}
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala b/mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala
index 04267d967dcadaa5e3e2e1e6147e69e276753b94..f60417f21d4b9b4b87bd528314cbaa7a4ac8d707 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala
@@ -28,7 +28,6 @@ import org.apache.spark.mllib.linalg.{Vectors, Vector}
/**
* :: DeveloperApi ::
- *
* Class used to solve an optimization problem using Gradient Descent.
* @param gradient Gradient function to be used.
* @param updater Updater to be used to update weights after every iteration.
@@ -113,7 +112,6 @@ class GradientDescent(private var gradient: Gradient, private var updater: Updat
/**
* :: DeveloperApi ::
- *
* Top-level method to run gradient descent.
*/
@DeveloperApi
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Optimizer.scala b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Optimizer.scala
index 0a313f3104b14cb8b9fa87db517b63ce6605e6fb..e41d9bbe18c37b7151d490c995e4aa2814556403 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Optimizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Optimizer.scala
@@ -24,7 +24,6 @@ import org.apache.spark.mllib.linalg.Vector
/**
* :: DeveloperApi ::
- *
* Trait for optimization problem solvers.
*/
@DeveloperApi
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Updater.scala b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Updater.scala
index e67816796c6b1be220bc25b8fad7ef9c5c6e7d86..3ed3a5b9b384395fb88de1d1456d0c655031cb78 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/optimization/Updater.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/optimization/Updater.scala
@@ -26,7 +26,6 @@ import org.apache.spark.mllib.linalg.{Vectors, Vector}
/**
* :: DeveloperApi ::
- *
* Class used to perform steps (weight update) using Gradient Descent methods.
*
* For general minimization problems, or for regularized problems of the form
@@ -64,7 +63,6 @@ abstract class Updater extends Serializable {
/**
* :: DeveloperApi ::
- *
* A simple updater for gradient descent *without* any regularization.
* Uses a step-size decreasing with the square root of the number of iterations.
*/
@@ -86,7 +84,6 @@ class SimpleUpdater extends Updater {
/**
* :: DeveloperApi ::
- *
* Updater for L1 regularized problems.
* R(w) = ||w||_1
* Uses a step-size decreasing with the square root of the number of iterations.
@@ -131,7 +128,6 @@ class L1Updater extends Updater {
/**
* :: DeveloperApi ::
- *
* Updater for L2 regularized problems.
* R(w) = 1/2 ||w||^2
* Uses a step-size decreasing with the square root of the number of iterations.
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala
index 60cbb1c1e1d86b77b2d123262faab760219ee3ad..5cc47de8ffdfcc1ef6cf5b8e507fa1ff73ad6309 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala
@@ -140,7 +140,6 @@ class ALS private (
/**
* :: Experimental ::
- *
* Sets the constant used in computing confidence in implicit ALS. Default: 1.0.
*/
@Experimental
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala
index e05224fc7caf2b49d3c0accb92ed255231fc7b35..471546cd82c7dbbedb77fb1df55b34c547c87a82 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala
@@ -70,7 +70,6 @@ class MatrixFactorizationModel(
/**
* :: DeveloperApi ::
- *
* Predict the rating of many users for many products.
* This is a Java stub for python predictAll()
*
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 c24f5afb9968689d42590c9bf7cca15893b1d692..3bd0017aa196a391de08017266637643157fb58a 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
@@ -103,7 +103,6 @@ abstract class GeneralizedLinearAlgorithm[M <: GeneralizedLinearModel]
/**
* :: Experimental ::
- *
* Set if the algorithm should validate data before training. Default true.
*/
@Experimental
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 c8a966cd5f5a8aef9a369aee199ffb2f828021e1..3019447ce4cd90d5a5b8158b2896b2fa40af46c4 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
@@ -35,7 +35,6 @@ import org.apache.spark.mllib.linalg.{Vector, Vectors}
/**
* :: Experimental ::
- *
* A class that implements a decision tree algorithm for classification and regression. It
* supports both continuous and categorical features.
* @param strategy The configuration parameters for the tree algorithm which specify the type
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala
index 017f84f3b9e8bbb8d20b180a0a4865bd1fa901bb..79a01f58319e8ffefc55e7ebab4289f399ca59f9 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.Experimental
/**
* :: Experimental ::
- *
* Enum to select the algorithm for the decision tree
*/
@Experimental
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala
index c0254c32c2dceb3258641284414d3e9173be79c5..f4c877232750fa33f505f4604dc94ca4fb924316 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.Experimental
/**
* :: Experimental ::
- *
* Enum to describe whether a feature is "continuous" or "categorical"
*/
@Experimental
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala
index b3e8b224beeaa434b377ee147780b3e47ecf2b18..7da976e55a7227f7919984c29bad1bc9d001f5b3 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.Experimental
/**
* :: Experimental ::
- *
* Enum for selecting the quantile calculation strategy
*/
@Experimental
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 482faaa9e725654b5c50e43ae5e1b212dcd1433e..8767aca47cd5a745f70210c5b054c5680bee951a 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
@@ -24,7 +24,6 @@ import org.apache.spark.mllib.tree.configuration.QuantileStrategy._
/**
* :: Experimental ::
- *
* Stores all the configuration options for tree construction
* @param algo classification or regression
* @param impurity criterion used for information gain calculation
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 55c43f2fcf9c582a3f8188fde87e446364208f9d..60f43e9278d2ae475eca153239d05e7dfe14ddcc 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
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.{DeveloperApi, Experimental}
/**
* :: Experimental ::
- *
* Class for calculating [[http://en.wikipedia.org/wiki/Binary_entropy_function entropy]] during
* binary classification.
*/
@@ -32,7 +31,6 @@ object Entropy extends Impurity {
/**
* :: DeveloperApi ::
- *
* entropy calculation
* @param c0 count of instances with label 0
* @param c1 count of instances with label 1
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 c923b8e8f4cf1e85caf25e82303a92e3d849078a..c51d76d9b4c5be6ba2ab4ffc48a240f2479c02a0 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
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.{DeveloperApi, Experimental}
/**
* :: Experimental ::
- *
* Class for calculating the
* [[http://en.wikipedia.org/wiki/Decision_tree_learning#Gini_impurity Gini impurity]]
* during binary classification.
@@ -31,7 +30,6 @@ object Gini extends Impurity {
/**
* :: DeveloperApi ::
- *
* Gini coefficient calculation
* @param c0 count of instances with label 0
* @param c1 count of instances with label 1
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala
index f407796596c6c37ca9623b7dfa4914e7a1fc9ca6..8eab247cf0932cf723587ca2bd75574942db0da2 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.{DeveloperApi, Experimental}
/**
* :: Experimental ::
- *
* Trait for calculating information gain.
*/
@Experimental
@@ -29,7 +28,6 @@ trait Impurity extends Serializable {
/**
* :: DeveloperApi ::
- *
* information calculation for binary classification
* @param c0 count of instances with label 0
* @param c1 count of instances with label 1
@@ -40,7 +38,6 @@ trait Impurity extends Serializable {
/**
* :: DeveloperApi ::
- *
* information calculation for regression
* @param count number of instances
* @param sum sum of labels
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 2c64644f4ed0f1cf534ac26a8c336593ba86ccc8..47d07122af30f9a89e402809cdd7150313db4b48 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
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.{DeveloperApi, Experimental}
/**
* :: Experimental ::
- *
* Class for calculating variance during regression
*/
@Experimental
@@ -31,7 +30,6 @@ object Variance extends Impurity {
/**
* :: DeveloperApi ::
- *
* variance calculation
* @param count number of instances
* @param sum sum of labels
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 0f76f4a049057345a38c8c96e97fc17f7c5a30e4..bf692ca8c4bd7ee9397fca74e028075662001b27 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
@@ -24,7 +24,6 @@ import org.apache.spark.mllib.linalg.Vector
/**
* :: Experimental ::
- *
* Model to store the decision tree parameters
* @param topNode root node
* @param algo algorithm type -- classification or regression
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 d36b58e92ced67cecbba154d99b2360219d28163..cc8a24cce961459a021b394a5675043366a5f131 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
@@ -21,7 +21,6 @@ import org.apache.spark.annotation.DeveloperApi
/**
* :: DeveloperApi ::
- *
* Information gain statistics for each split
* @param gain information gain value
* @param impurity current node impurity
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 339972141498cc1d83f9f28481da0165753b47fd..682f213f411a71748e7d1a7ceb2a6e9ad9ecd555 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
@@ -24,7 +24,6 @@ import org.apache.spark.mllib.linalg.Vector
/**
* :: DeveloperApi ::
- *
* Node in a decision tree
* @param id integer node id
* @param predict predicted value at the node
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 8bbb343079b499d3d992c2d23cd9f068e649879b..d7ffd386c05eeb749c703d46f2aea6de264ec200 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
@@ -22,7 +22,6 @@ import org.apache.spark.mllib.tree.configuration.FeatureType.FeatureType
/**
* :: DeveloperApi ::
- *
* Split applied to a feature
* @param feature feature index
* @param threshold threshold for continuous feature
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/DataValidators.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/DataValidators.scala
index 230c409e1be330fedcef4048221d195e35d6a42e..45f95482a1def31767f9f409d05c1a2339cdbf9d 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/util/DataValidators.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/util/DataValidators.scala
@@ -24,7 +24,6 @@ import org.apache.spark.mllib.regression.LabeledPoint
/**
* :: DeveloperApi ::
- *
* A collection of methods used to validate data before applying ML algorithms.
*/
@DeveloperApi
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/KMeansDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/KMeansDataGenerator.scala
index e693d137039876bd05c7e49700cec4e7410812f0..6eaebaf7dba9f04179e9d57ba7efc43bf2a8ec18 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/util/KMeansDataGenerator.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/util/KMeansDataGenerator.scala
@@ -25,7 +25,6 @@ import org.apache.spark.rdd.RDD
/**
* :: DeveloperApi ::
- *
* Generate test data for KMeans. This class first chooses k cluster centers
* from a d-dimensional Gaussian distribution scaled by factor r and then creates a Gaussian
* cluster with scale 1 around each center.
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 140ff92869176be24680fc3943642f0b9ddeb9e7..c8e160d00c2d66bc9677a1cd186dca77227bdd50 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
@@ -30,7 +30,6 @@ import org.apache.spark.mllib.regression.LabeledPoint
/**
* :: DeveloperApi ::
- *
* Generate sample data used for Linear Data. This class generates
* uniformly random values for every feature and adds Gaussian noise with mean `eps` to the
* response variable `Y`.
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/LogisticRegressionDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/LogisticRegressionDataGenerator.scala
index ca06b9ad585388d74899f99d7823b41e488e3fea..c82cd8fd4641cf0298637df66c802e82d2e4a32d 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/util/LogisticRegressionDataGenerator.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/util/LogisticRegressionDataGenerator.scala
@@ -27,7 +27,6 @@ import org.apache.spark.mllib.linalg.Vectors
/**
* :: DeveloperApi ::
- *
* Generate test data for LogisticRegression. This class chooses positive labels
* with probability `probOne` and scales features for positive examples by `eps`.
*/
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/MFDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/MFDataGenerator.scala
index 3bd86d68133754e88eb1235646357277a997f31a..3f413faca6bb42cc5de93263d47920b420736111 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/util/MFDataGenerator.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/util/MFDataGenerator.scala
@@ -27,29 +27,28 @@ import org.apache.spark.rdd.RDD
/**
* :: DeveloperApi ::
+ * Generate RDD(s) containing data for Matrix Factorization.
*
-* Generate RDD(s) containing data for Matrix Factorization.
-*
-* This method samples training entries according to the oversampling factor
-* 'trainSampFact', which is a multiplicative factor of the number of
-* degrees of freedom of the matrix: rank*(m+n-rank).
-*
-* It optionally samples entries for a testing matrix using
-* 'testSampFact', the percentage of the number of training entries
-* to use for testing.
-*
-* This method takes the following inputs:
-* sparkMaster (String) The master URL.
-* outputPath (String) Directory to save output.
-* m (Int) Number of rows in data matrix.
-* n (Int) Number of columns in data matrix.
-* rank (Int) Underlying rank of data matrix.
-* trainSampFact (Double) Oversampling factor.
-* noise (Boolean) Whether to add gaussian noise to training data.
-* sigma (Double) Standard deviation of added gaussian noise.
-* test (Boolean) Whether to create testing RDD.
-* testSampFact (Double) Percentage of training data to use as test data.
-*/
+ * This method samples training entries according to the oversampling factor
+ * 'trainSampFact', which is a multiplicative factor of the number of
+ * degrees of freedom of the matrix: rank*(m+n-rank).
+ *
+ * It optionally samples entries for a testing matrix using
+ * 'testSampFact', the percentage of the number of training entries
+ * to use for testing.
+ *
+ * This method takes the following inputs:
+ * sparkMaster (String) The master URL.
+ * outputPath (String) Directory to save output.
+ * m (Int) Number of rows in data matrix.
+ * n (Int) Number of columns in data matrix.
+ * rank (Int) Underlying rank of data matrix.
+ * trainSampFact (Double) Oversampling factor.
+ * noise (Boolean) Whether to add gaussian noise to training data.
+ * sigma (Double) Standard deviation of added gaussian noise.
+ * test (Boolean) Whether to create testing RDD.
+ * testSampFact (Double) Percentage of training data to use as test data.
+ */
@DeveloperApi
object MFDataGenerator {
def main(args: Array[String]) {
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala
index 7f9804deaf33f699785b533b04e4fd1b0f4fc5a1..ac2360c429e2bf8ce369557a4db0977c2249b87e 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala
@@ -124,7 +124,6 @@ object MLUtils {
/**
* :: Experimental ::
- *
* Load labeled data from a file. The data format used here is
* <L>, <f1> <f2> ...
* where <f1>, <f2> are feature values in Double and <L> is the corresponding label as Double.
@@ -146,7 +145,6 @@ object MLUtils {
/**
* :: Experimental ::
- *
* Save labeled data to a file. The data format used here is
* <L>, <f1> <f2> ...
* where <f1>, <f2> are feature values in Double and <L> is the corresponding label as Double.
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/SVMDataGenerator.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/SVMDataGenerator.scala
index 87a6f2a0c39762a66e3c125152139b377b8063db..ba8190b0e07e8774e82e87fb7fd74355c766d16a 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/util/SVMDataGenerator.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/util/SVMDataGenerator.scala
@@ -29,7 +29,6 @@ import org.apache.spark.mllib.regression.LabeledPoint
/**
* :: DeveloperApi ::
- *
* Generate sample data used for SVM. This class generates uniform random values
* for the features and adds Gaussian noise with weight 0.1 to generate labels.
*/