From d74ced64b6255a953646f44b6767e167ab16b5e3 Mon Sep 17 00:00:00 2001
From: MechCoder <manojkumarsivaraj334@gmail.com>
Date: Wed, 19 Aug 2015 16:58:49 +0530
Subject: [PATCH 1/4] [SPARK-10108] Add since tags to mllib.feature

---
 .../spark/mllib/feature/ChiSqSelector.scala   |  4 +++
 .../mllib/feature/ElementwiseProduct.scala    |  2 ++
 .../spark/mllib/feature/HashingTF.scala       |  9 +++++++
 .../org/apache/spark/mllib/feature/IDF.scala  |  6 +++++
 .../spark/mllib/feature/Normalizer.scala      |  5 ++++
 .../org/apache/spark/mllib/feature/PCA.scala  |  8 +++++-
 .../spark/mllib/feature/StandardScaler.scala  | 19 ++++++++++++++
 .../mllib/feature/VectorTransformer.scala     |  4 +++
 .../apache/spark/mllib/feature/Word2Vec.scala | 25 +++++++++++++++++++
 9 files changed, 81 insertions(+), 1 deletion(-)

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala
index 5f8c1dea237b4..2195a46780ad6 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala
@@ -30,6 +30,7 @@ import org.apache.spark.rdd.RDD
  * Chi Squared selector model.
  *
  * @param selectedFeatures list of indices to select (filter). Must be ordered asc
+ * @since 1.3.0
  */
 @Experimental
 class ChiSqSelectorModel (val selectedFeatures: Array[Int]) extends VectorTransformer {
@@ -51,6 +52,7 @@ class ChiSqSelectorModel (val selectedFeatures: Array[Int]) extends VectorTransf
    *
    * @param vector vector to be transformed.
    * @return transformed vector.
+   * @since 1.3.0
    */
   override def transform(vector: Vector): Vector = {
     compress(vector, selectedFeatures)
@@ -106,6 +108,7 @@ class ChiSqSelectorModel (val selectedFeatures: Array[Int]) extends VectorTransf
  * Creates a ChiSquared feature selector.
  * @param numTopFeatures number of features that selector will select
  *                       (ordered by statistic value descending)
+ * @since 1.3.0
  */
 @Experimental
 class ChiSqSelector (val numTopFeatures: Int) extends Serializable {
@@ -116,6 +119,7 @@ class ChiSqSelector (val numTopFeatures: Int) extends Serializable {
    * @param data an `RDD[LabeledPoint]` containing the labeled dataset with categorical features.
    *             Real-valued features will be treated as categorical for each distinct value.
    *             Apply feature discretizer before using this function.
+   * @since 1.3.0
    */
   def fit(data: RDD[LabeledPoint]): ChiSqSelectorModel = {
     val indices = Statistics.chiSqTest(data)
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
index d67fe6c3ee4f8..1b49092abcb74 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
@@ -26,6 +26,7 @@ import org.apache.spark.mllib.linalg._
  * provided "weight" vector. In other words, it scales each column of the dataset by a scalar
  * multiplier.
  * @param scalingVec The values used to scale the reference vector's individual components.
+ * @since 1.4.0
  */
 @Experimental
 class ElementwiseProduct(val scalingVec: Vector) extends VectorTransformer {
@@ -35,6 +36,7 @@ class ElementwiseProduct(val scalingVec: Vector) extends VectorTransformer {
    *
    * @param vector vector to be transformed.
    * @return transformed vector.
+   * @since 1.4.0
    */
   override def transform(vector: Vector): Vector = {
     require(vector.size == scalingVec.size,
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/HashingTF.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/HashingTF.scala
index c53475818395f..8bc439563bf43 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/HashingTF.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/HashingTF.scala
@@ -33,19 +33,25 @@ import org.apache.spark.util.Utils
  * Maps a sequence of terms to their term frequencies using the hashing trick.
  *
  * @param numFeatures number of features (default: 2^20^)
+ * @since 1.1.0
  */
 @Experimental
 class HashingTF(val numFeatures: Int) extends Serializable {
 
+  /**
+   * @since 1.1.0
+   */
   def this() = this(1 << 20)
 
   /**
    * Returns the index of the input term.
+   * @since 1.1.0
    */
   def indexOf(term: Any): Int = Utils.nonNegativeMod(term.##, numFeatures)
 
   /**
    * Transforms the input document into a sparse term frequency vector.
+   * @since 1.1.0
    */
   def transform(document: Iterable[_]): Vector = {
     val termFrequencies = mutable.HashMap.empty[Int, Double]
@@ -58,6 +64,7 @@ class HashingTF(val numFeatures: Int) extends Serializable {
 
   /**
    * Transforms the input document into a sparse term frequency vector (Java version).
+   * @since 1.1.0
    */
   def transform(document: JavaIterable[_]): Vector = {
     transform(document.asScala)
@@ -65,6 +72,7 @@ class HashingTF(val numFeatures: Int) extends Serializable {
 
   /**
    * Transforms the input document to term frequency vectors.
+   * @since 1.1.0
    */
   def transform[D <: Iterable[_]](dataset: RDD[D]): RDD[Vector] = {
     dataset.map(this.transform)
@@ -72,6 +80,7 @@ class HashingTF(val numFeatures: Int) extends Serializable {
 
   /**
    * Transforms the input document to term frequency vectors (Java version).
+   * @since 1.1.0
    */
   def transform[D <: JavaIterable[_]](dataset: JavaRDD[D]): JavaRDD[Vector] = {
     dataset.rdd.map(this.transform).toJavaRDD()
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/IDF.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/IDF.scala
index 3fab7ea79befc..b6d72d6e50866 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/IDF.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/IDF.scala
@@ -36,6 +36,7 @@ import org.apache.spark.rdd.RDD
  *
  * @param minDocFreq minimum of documents in which a term
  *                   should appear for filtering
+ * @since 1.1.0
  */
 @Experimental
 class IDF(val minDocFreq: Int) {
@@ -47,6 +48,7 @@ class IDF(val minDocFreq: Int) {
   /**
    * Computes the inverse document frequency.
    * @param dataset an RDD of term frequency vectors
+   * @since 1.1.0
    */
   def fit(dataset: RDD[Vector]): IDFModel = {
     val idf = dataset.treeAggregate(new IDF.DocumentFrequencyAggregator(
@@ -60,6 +62,7 @@ class IDF(val minDocFreq: Int) {
   /**
    * Computes the inverse document frequency.
    * @param dataset a JavaRDD of term frequency vectors
+   * @since 1.1.0
    */
   def fit(dataset: JavaRDD[Vector]): IDFModel = {
     fit(dataset.rdd)
@@ -170,6 +173,7 @@ class IDFModel private[spark] (val idf: Vector) extends Serializable {
    *
    * @param dataset an RDD of term frequency vectors
    * @return an RDD of TF-IDF vectors
+   * @since 1.1.0
    */
   def transform(dataset: RDD[Vector]): RDD[Vector] = {
     val bcIdf = dataset.context.broadcast(idf)
@@ -181,6 +185,7 @@ class IDFModel private[spark] (val idf: Vector) extends Serializable {
    *
    * @param v a term frequency vector
    * @return a TF-IDF vector
+   * @since 1.3.0
    */
   def transform(v: Vector): Vector = IDFModel.transform(idf, v)
 
@@ -188,6 +193,7 @@ class IDFModel private[spark] (val idf: Vector) extends Serializable {
    * Transforms term frequency (TF) vectors to TF-IDF vectors (Java version).
    * @param dataset a JavaRDD of term frequency vectors
    * @return a JavaRDD of TF-IDF vectors
+   * @since 1.1.0
    */
   def transform(dataset: JavaRDD[Vector]): JavaRDD[Vector] = {
     transform(dataset.rdd).toJavaRDD()
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala
index 32848e039eb81..1516af28a0b19 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala
@@ -30,10 +30,14 @@ import org.apache.spark.mllib.linalg.{DenseVector, SparseVector, Vector, Vectors
  * For p = Double.PositiveInfinity, max(abs(vector)) will be used as norm for normalization.
  *
  * @param p Normalization in L^p^ space, p = 2 by default.
+ * @since 1.1.0
  */
 @Experimental
 class Normalizer(p: Double) extends VectorTransformer {
 
+  /**
+   * @since 1.1.0
+   */
   def this() = this(2)
 
   require(p >= 1.0)
@@ -43,6 +47,7 @@ class Normalizer(p: Double) extends VectorTransformer {
    *
    * @param vector vector to be normalized.
    * @return normalized vector. If the norm of the input is zero, it will return the input vector.
+   * @since 1.1.0
    */
   override def transform(vector: Vector): Vector = {
     val norm = Vectors.norm(vector, p)
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala
index 2a66263d8b7d6..d33cc0b1c2e15 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala
@@ -26,6 +26,7 @@ import org.apache.spark.rdd.RDD
  * A feature transformer that projects vectors to a low-dimensional space using PCA.
  *
  * @param k number of principal components
+ * @since 1.4.0
  */
 class PCA(val k: Int) {
   require(k >= 1, s"PCA requires a number of principal components k >= 1 but was given $k")
@@ -34,6 +35,7 @@ class PCA(val k: Int) {
    * Computes a [[PCAModel]] that contains the principal components of the input vectors.
    *
    * @param sources source vectors
+   * @since 1.4.0
    */
   def fit(sources: RDD[Vector]): PCAModel = {
     require(k <= sources.first().size,
@@ -58,7 +60,10 @@ class PCA(val k: Int) {
     new PCAModel(k, pc)
   }
 
-  /** Java-friendly version of [[fit()]] */
+  /**
+   * Java-friendly version of [[fit()]]
+   * @since 1.4.0
+   */
   def fit(sources: JavaRDD[Vector]): PCAModel = fit(sources.rdd)
 }
 
@@ -75,6 +80,7 @@ class PCAModel private[spark] (val k: Int, val pc: DenseMatrix) extends VectorTr
    * @param vector vector to be transformed.
    *               Vector must be the same length as the source vectors given to [[PCA.fit()]].
    * @return transformed vector. Vector will be of length k.
+   * @since 1.4.0
    */
   override def transform(vector: Vector): Vector = {
     vector match {
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala
index c73b8f258060d..9998602b0c2ac 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala
@@ -31,10 +31,14 @@ import org.apache.spark.rdd.RDD
  * @param withMean False by default. Centers the data with mean before scaling. It will build a
  *                 dense output, so this does not work on sparse input and will raise an exception.
  * @param withStd True by default. Scales the data to unit standard deviation.
+ * @since 1.1.0
  */
 @Experimental
 class StandardScaler(withMean: Boolean, withStd: Boolean) extends Logging {
 
+  /**
+   * @since 1.1.0
+   */
   def this() = this(false, true)
 
   if (!(withMean || withStd)) {
@@ -46,6 +50,7 @@ class StandardScaler(withMean: Boolean, withStd: Boolean) extends Logging {
    *
    * @param data The data used to compute the mean and variance to build the transformation model.
    * @return a StandardScalarModel
+   * @since 1.1.0
    */
   def fit(data: RDD[Vector]): StandardScalerModel = {
     // TODO: skip computation if both withMean and withStd are false
@@ -68,6 +73,7 @@ class StandardScaler(withMean: Boolean, withStd: Boolean) extends Logging {
  * @param mean column mean values
  * @param withStd whether to scale the data to have unit standard deviation
  * @param withMean whether to center the data before scaling
+ * @since 1.1.0
  */
 @Experimental
 class StandardScalerModel (
@@ -76,6 +82,9 @@ class StandardScalerModel (
     var withStd: Boolean,
     var withMean: Boolean) extends VectorTransformer {
 
+  /**
+   * @since 1.3.0
+   */
   def this(std: Vector, mean: Vector) {
     this(std, mean, withStd = std != null, withMean = mean != null)
     require(this.withStd || this.withMean,
@@ -86,8 +95,14 @@ class StandardScalerModel (
     }
   }
 
+  /**
+   * @since 1.3.0
+   */
   def this(std: Vector) = this(std, null)
 
+  /**
+   * @since 1.3.0
+   */
   @DeveloperApi
   def setWithMean(withMean: Boolean): this.type = {
     require(!(withMean && this.mean == null), "cannot set withMean to true while mean is null")
@@ -95,6 +110,9 @@ class StandardScalerModel (
     this
   }
 
+  /**
+   * @since 1.3.0
+   */
   @DeveloperApi
   def setWithStd(withStd: Boolean): this.type = {
     require(!(withStd && this.std == null),
@@ -114,6 +132,7 @@ class StandardScalerModel (
    * @param vector Vector to be standardized.
    * @return Standardized vector. If the std of a column is zero, it will return default `0.0`
    *         for the column with zero std.
+   * @since 1.1.0
    */
   override def transform(vector: Vector): Vector = {
     require(mean.size == vector.size)
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala
index 7358c1c84f79c..9e0218d364972 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala
@@ -25,6 +25,7 @@ import org.apache.spark.rdd.RDD
 /**
  * :: DeveloperApi ::
  * Trait for transformation of a vector
+ * @since 1.1.0
  */
 @DeveloperApi
 trait VectorTransformer extends Serializable {
@@ -34,6 +35,7 @@ trait VectorTransformer extends Serializable {
    *
    * @param vector vector to be transformed.
    * @return transformed vector.
+   * @since 1.1.0
    */
   def transform(vector: Vector): Vector
 
@@ -42,6 +44,7 @@ trait VectorTransformer extends Serializable {
    *
    * @param data RDD[Vector] to be transformed.
    * @return transformed RDD[Vector].
+   * @since 1.1.0
    */
   def transform(data: RDD[Vector]): RDD[Vector] = {
     // Later in #1498 , all RDD objects are sent via broadcasting instead of akka.
@@ -54,6 +57,7 @@ trait VectorTransformer extends Serializable {
    *
    * @param data JavaRDD[Vector] to be transformed.
    * @return transformed JavaRDD[Vector].
+   * @since 1.1.0
    */
   def transform(data: JavaRDD[Vector]): JavaRDD[Vector] = {
     transform(data.rdd)
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala
index cbbd2b0c8d060..77e2eceab794a 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala
@@ -69,6 +69,7 @@ private case class VocabWord(
  * Efficient Estimation of Word Representations in Vector Space
  * and
  * Distributed Representations of Words and Phrases and their Compositionality.
+ * @since 1.1.0
  */
 @Experimental
 class Word2Vec extends Serializable with Logging {
@@ -82,6 +83,7 @@ class Word2Vec extends Serializable with Logging {
 
   /**
    * Sets vector size (default: 100).
+   * @since 1.1.0
    */
   def setVectorSize(vectorSize: Int): this.type = {
     this.vectorSize = vectorSize
@@ -90,6 +92,7 @@ class Word2Vec extends Serializable with Logging {
 
   /**
    * Sets initial learning rate (default: 0.025).
+   * @since 1.1.0
    */
   def setLearningRate(learningRate: Double): this.type = {
     this.learningRate = learningRate
@@ -98,6 +101,7 @@ class Word2Vec extends Serializable with Logging {
 
   /**
    * Sets number of partitions (default: 1). Use a small number for accuracy.
+   * @since 1.1.0
    */
   def setNumPartitions(numPartitions: Int): this.type = {
     require(numPartitions > 0, s"numPartitions must be greater than 0 but got $numPartitions")
@@ -108,6 +112,7 @@ class Word2Vec extends Serializable with Logging {
   /**
    * Sets number of iterations (default: 1), which should be smaller than or equal to number of
    * partitions.
+   * @since 1.1.0
    */
   def setNumIterations(numIterations: Int): this.type = {
     this.numIterations = numIterations
@@ -116,6 +121,7 @@ class Word2Vec extends Serializable with Logging {
 
   /**
    * Sets random seed (default: a random long integer).
+   * @since 1.1.0
    */
   def setSeed(seed: Long): this.type = {
     this.seed = seed
@@ -125,6 +131,7 @@ class Word2Vec extends Serializable with Logging {
   /**
    * Sets minCount, the minimum number of times a token must appear to be included in the word2vec
    * model's vocabulary (default: 5).
+   * @since 1.3.0
    */
   def setMinCount(minCount: Int): this.type = {
     this.minCount = minCount
@@ -262,6 +269,7 @@ class Word2Vec extends Serializable with Logging {
    * Computes the vector representation of each word in vocabulary.
    * @param dataset an RDD of words
    * @return a Word2VecModel
+   * @since 1.1.0
    */
   def fit[S <: Iterable[String]](dataset: RDD[S]): Word2VecModel = {
 
@@ -411,6 +419,7 @@ class Word2Vec extends Serializable with Logging {
    * Computes the vector representation of each word in vocabulary (Java version).
    * @param dataset a JavaRDD of words
    * @return a Word2VecModel
+   * @since 1.1.0
    */
   def fit[S <: JavaIterable[String]](dataset: JavaRDD[S]): Word2VecModel = {
     fit(dataset.rdd.map(_.asScala))
@@ -454,6 +463,9 @@ class Word2VecModel private[mllib] (
     wordVecNorms
   }
 
+  /**
+   * @since 1.5.0
+   */
   def this(model: Map[String, Array[Float]]) = {
     this(Word2VecModel.buildWordIndex(model), Word2VecModel.buildWordVectors(model))
   }
@@ -469,6 +481,9 @@ class Word2VecModel private[mllib] (
 
   override protected def formatVersion = "1.0"
 
+  /**
+   * @since 1.4.0
+   */
   def save(sc: SparkContext, path: String): Unit = {
     Word2VecModel.SaveLoadV1_0.save(sc, path, getVectors)
   }
@@ -477,6 +492,7 @@ class Word2VecModel private[mllib] (
    * Transforms a word to its vector representation
    * @param word a word
    * @return vector representation of word
+   * @since 1.1.0
    */
   def transform(word: String): Vector = {
     wordIndex.get(word) match {
@@ -493,6 +509,7 @@ class Word2VecModel private[mllib] (
    * @param word a word
    * @param num number of synonyms to find
    * @return array of (word, cosineSimilarity)
+   * @since 1.1.0
    */
   def findSynonyms(word: String, num: Int): Array[(String, Double)] = {
     val vector = transform(word)
@@ -504,6 +521,7 @@ class Word2VecModel private[mllib] (
    * @param vector vector representation of a word
    * @param num number of synonyms to find
    * @return array of (word, cosineSimilarity)
+   * @since 1.1.0
    */
   def findSynonyms(vector: Vector, num: Int): Array[(String, Double)] = {
     require(num > 0, "Number of similar words should > 0")
@@ -533,6 +551,7 @@ class Word2VecModel private[mllib] (
 
   /**
    * Returns a map of words to their vector representations.
+   * @since 1.2.0
    */
   def getVectors: Map[String, Array[Float]] = {
     wordIndex.map { case (word, ind) =>
@@ -541,6 +560,9 @@ class Word2VecModel private[mllib] (
   }
 }
 
+/**
+ * @since 1.4.0
+ */
 @Experimental
 object Word2VecModel extends Loader[Word2VecModel] {
 
@@ -600,6 +622,9 @@ object Word2VecModel extends Loader[Word2VecModel] {
     }
   }
 
+  /**
+   * @since 1.4.0
+   */
   override def load(sc: SparkContext, path: String): Word2VecModel = {
 
     val (loadedClassName, loadedVersion, metadata) = Loader.loadMetadata(sc, path)

From 3778da07e7800d0d3412d04684f5ea73c277ac82 Mon Sep 17 00:00:00 2001
From: MechCoder <manojkumarsivaraj334@gmail.com>
Date: Thu, 20 Aug 2015 01:49:28 +0530
Subject: [PATCH 2/4] replace since tag with Since annotation

---
 .../spark/mllib/feature/ChiSqSelector.scala   | 10 ++---
 .../mllib/feature/ElementwiseProduct.scala    |  6 +--
 .../spark/mllib/feature/HashingTF.scala       | 16 ++++----
 .../org/apache/spark/mllib/feature/IDF.scala  | 14 +++----
 .../spark/mllib/feature/Normalizer.scala      | 10 ++---
 .../org/apache/spark/mllib/feature/PCA.scala  |  9 +++--
 .../spark/mllib/feature/StandardScaler.scala  | 28 +++++---------
 .../mllib/feature/VectorTransformer.scala     |  8 ++--
 .../apache/spark/mllib/feature/Word2Vec.scala | 38 +++++++++----------
 9 files changed, 64 insertions(+), 75 deletions(-)

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala
index 2195a46780ad6..75dd01aa5c71f 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala
@@ -19,7 +19,7 @@ package org.apache.spark.mllib.feature
 
 import scala.collection.mutable.ArrayBuilder
 
-import org.apache.spark.annotation.Experimental
+import org.apache.spark.annotation.{Experimental, Since}
 import org.apache.spark.mllib.linalg.{DenseVector, SparseVector, Vector, Vectors}
 import org.apache.spark.mllib.regression.LabeledPoint
 import org.apache.spark.mllib.stat.Statistics
@@ -30,8 +30,8 @@ import org.apache.spark.rdd.RDD
  * Chi Squared selector model.
  *
  * @param selectedFeatures list of indices to select (filter). Must be ordered asc
- * @since 1.3.0
  */
+@Since("1.3.0")
 @Experimental
 class ChiSqSelectorModel (val selectedFeatures: Array[Int]) extends VectorTransformer {
 
@@ -52,8 +52,8 @@ class ChiSqSelectorModel (val selectedFeatures: Array[Int]) extends VectorTransf
    *
    * @param vector vector to be transformed.
    * @return transformed vector.
-   * @since 1.3.0
    */
+  @Since("1.3.0")
   override def transform(vector: Vector): Vector = {
     compress(vector, selectedFeatures)
   }
@@ -108,8 +108,8 @@ class ChiSqSelectorModel (val selectedFeatures: Array[Int]) extends VectorTransf
  * Creates a ChiSquared feature selector.
  * @param numTopFeatures number of features that selector will select
  *                       (ordered by statistic value descending)
- * @since 1.3.0
  */
+@Since("1.3.0")
 @Experimental
 class ChiSqSelector (val numTopFeatures: Int) extends Serializable {
 
@@ -119,8 +119,8 @@ class ChiSqSelector (val numTopFeatures: Int) extends Serializable {
    * @param data an `RDD[LabeledPoint]` containing the labeled dataset with categorical features.
    *             Real-valued features will be treated as categorical for each distinct value.
    *             Apply feature discretizer before using this function.
-   * @since 1.3.0
    */
+  @Since("1.3.0")
   def fit(data: RDD[LabeledPoint]): ChiSqSelectorModel = {
     val indices = Statistics.chiSqTest(data)
       .zipWithIndex.sortBy { case (res, _) => -res.statistic }
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
index 1b49092abcb74..33e2d17bb472e 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/ElementwiseProduct.scala
@@ -17,7 +17,7 @@
 
 package org.apache.spark.mllib.feature
 
-import org.apache.spark.annotation.Experimental
+import org.apache.spark.annotation.{Experimental, Since}
 import org.apache.spark.mllib.linalg._
 
 /**
@@ -26,8 +26,8 @@ import org.apache.spark.mllib.linalg._
  * provided "weight" vector. In other words, it scales each column of the dataset by a scalar
  * multiplier.
  * @param scalingVec The values used to scale the reference vector's individual components.
- * @since 1.4.0
  */
+@Since("1.4.0")
 @Experimental
 class ElementwiseProduct(val scalingVec: Vector) extends VectorTransformer {
 
@@ -36,8 +36,8 @@ class ElementwiseProduct(val scalingVec: Vector) extends VectorTransformer {
    *
    * @param vector vector to be transformed.
    * @return transformed vector.
-   * @since 1.4.0
    */
+  @Since("1.4.0")
   override def transform(vector: Vector): Vector = {
     require(vector.size == scalingVec.size,
       s"vector sizes do not match: Expected ${scalingVec.size} but found ${vector.size}")
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/HashingTF.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/HashingTF.scala
index 8bc439563bf43..e47d524b61623 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/HashingTF.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/HashingTF.scala
@@ -22,7 +22,7 @@ import java.lang.{Iterable => JavaIterable}
 import scala.collection.JavaConverters._
 import scala.collection.mutable
 
-import org.apache.spark.annotation.Experimental
+import org.apache.spark.annotation.{Experimental, Since}
 import org.apache.spark.api.java.JavaRDD
 import org.apache.spark.mllib.linalg.{Vector, Vectors}
 import org.apache.spark.rdd.RDD
@@ -33,26 +33,26 @@ import org.apache.spark.util.Utils
  * Maps a sequence of terms to their term frequencies using the hashing trick.
  *
  * @param numFeatures number of features (default: 2^20^)
- * @since 1.1.0
  */
+@Since("1.1.0")
 @Experimental
 class HashingTF(val numFeatures: Int) extends Serializable {
 
   /**
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def this() = this(1 << 20)
 
   /**
    * Returns the index of the input term.
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def indexOf(term: Any): Int = Utils.nonNegativeMod(term.##, numFeatures)
 
   /**
    * Transforms the input document into a sparse term frequency vector.
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def transform(document: Iterable[_]): Vector = {
     val termFrequencies = mutable.HashMap.empty[Int, Double]
     document.foreach { term =>
@@ -64,24 +64,24 @@ class HashingTF(val numFeatures: Int) extends Serializable {
 
   /**
    * Transforms the input document into a sparse term frequency vector (Java version).
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def transform(document: JavaIterable[_]): Vector = {
     transform(document.asScala)
   }
 
   /**
    * Transforms the input document to term frequency vectors.
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def transform[D <: Iterable[_]](dataset: RDD[D]): RDD[Vector] = {
     dataset.map(this.transform)
   }
 
   /**
    * Transforms the input document to term frequency vectors (Java version).
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def transform[D <: JavaIterable[_]](dataset: JavaRDD[D]): JavaRDD[Vector] = {
     dataset.rdd.map(this.transform).toJavaRDD()
   }
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/IDF.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/IDF.scala
index b6d72d6e50866..d5353ddd972e0 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/IDF.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/IDF.scala
@@ -19,7 +19,7 @@ package org.apache.spark.mllib.feature
 
 import breeze.linalg.{DenseVector => BDV}
 
-import org.apache.spark.annotation.Experimental
+import org.apache.spark.annotation.{Experimental, Since}
 import org.apache.spark.api.java.JavaRDD
 import org.apache.spark.mllib.linalg.{DenseVector, SparseVector, Vector, Vectors}
 import org.apache.spark.rdd.RDD
@@ -36,8 +36,8 @@ import org.apache.spark.rdd.RDD
  *
  * @param minDocFreq minimum of documents in which a term
  *                   should appear for filtering
- * @since 1.1.0
  */
+@Since("1.1.0")
 @Experimental
 class IDF(val minDocFreq: Int) {
 
@@ -48,8 +48,8 @@ class IDF(val minDocFreq: Int) {
   /**
    * Computes the inverse document frequency.
    * @param dataset an RDD of term frequency vectors
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def fit(dataset: RDD[Vector]): IDFModel = {
     val idf = dataset.treeAggregate(new IDF.DocumentFrequencyAggregator(
           minDocFreq = minDocFreq))(
@@ -62,8 +62,8 @@ class IDF(val minDocFreq: Int) {
   /**
    * Computes the inverse document frequency.
    * @param dataset a JavaRDD of term frequency vectors
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def fit(dataset: JavaRDD[Vector]): IDFModel = {
     fit(dataset.rdd)
   }
@@ -173,8 +173,8 @@ class IDFModel private[spark] (val idf: Vector) extends Serializable {
    *
    * @param dataset an RDD of term frequency vectors
    * @return an RDD of TF-IDF vectors
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def transform(dataset: RDD[Vector]): RDD[Vector] = {
     val bcIdf = dataset.context.broadcast(idf)
     dataset.mapPartitions(iter => iter.map(v => IDFModel.transform(bcIdf.value, v)))
@@ -185,16 +185,16 @@ class IDFModel private[spark] (val idf: Vector) extends Serializable {
    *
    * @param v a term frequency vector
    * @return a TF-IDF vector
-   * @since 1.3.0
    */
+  @Since("1.3.0")
   def transform(v: Vector): Vector = IDFModel.transform(idf, v)
 
   /**
    * Transforms term frequency (TF) vectors to TF-IDF vectors (Java version).
    * @param dataset a JavaRDD of term frequency vectors
    * @return a JavaRDD of TF-IDF vectors
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def transform(dataset: JavaRDD[Vector]): JavaRDD[Vector] = {
     transform(dataset.rdd).toJavaRDD()
   }
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala
index 1516af28a0b19..0e070257d9fb2 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala
@@ -17,7 +17,7 @@
 
 package org.apache.spark.mllib.feature
 
-import org.apache.spark.annotation.Experimental
+import org.apache.spark.annotation.{Experimental, Since}
 import org.apache.spark.mllib.linalg.{DenseVector, SparseVector, Vector, Vectors}
 
 /**
@@ -30,14 +30,12 @@ import org.apache.spark.mllib.linalg.{DenseVector, SparseVector, Vector, Vectors
  * For p = Double.PositiveInfinity, max(abs(vector)) will be used as norm for normalization.
  *
  * @param p Normalization in L^p^ space, p = 2 by default.
- * @since 1.1.0
  */
+@Since("1.1.0")
 @Experimental
 class Normalizer(p: Double) extends VectorTransformer {
 
-  /**
-   * @since 1.1.0
-   */
+  @Since("1.1.0")
   def this() = this(2)
 
   require(p >= 1.0)
@@ -47,8 +45,8 @@ class Normalizer(p: Double) extends VectorTransformer {
    *
    * @param vector vector to be normalized.
    * @return normalized vector. If the norm of the input is zero, it will return the input vector.
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   override def transform(vector: Vector): Vector = {
     val norm = Vectors.norm(vector, p)
 
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala
index d33cc0b1c2e15..d6c70a3aad42f 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala
@@ -17,6 +17,7 @@
 
 package org.apache.spark.mllib.feature
 
+import org.apache.spark.annotation.Experimental
 import org.apache.spark.api.java.JavaRDD
 import org.apache.spark.mllib.linalg._
 import org.apache.spark.mllib.linalg.distributed.RowMatrix
@@ -26,8 +27,8 @@ import org.apache.spark.rdd.RDD
  * A feature transformer that projects vectors to a low-dimensional space using PCA.
  *
  * @param k number of principal components
- * @since 1.4.0
  */
+@Since("1.4.0")
 class PCA(val k: Int) {
   require(k >= 1, s"PCA requires a number of principal components k >= 1 but was given $k")
 
@@ -35,8 +36,8 @@ class PCA(val k: Int) {
    * Computes a [[PCAModel]] that contains the principal components of the input vectors.
    *
    * @param sources source vectors
-   * @since 1.4.0
    */
+  @Since("1.4.0")
   def fit(sources: RDD[Vector]): PCAModel = {
     require(k <= sources.first().size,
       s"source vector size is ${sources.first().size} must be greater than k=$k")
@@ -62,8 +63,8 @@ class PCA(val k: Int) {
 
   /**
    * Java-friendly version of [[fit()]]
-   * @since 1.4.0
    */
+  @Since("1.4.0")
   def fit(sources: JavaRDD[Vector]): PCAModel = fit(sources.rdd)
 }
 
@@ -80,8 +81,8 @@ class PCAModel private[spark] (val k: Int, val pc: DenseMatrix) extends VectorTr
    * @param vector vector to be transformed.
    *               Vector must be the same length as the source vectors given to [[PCA.fit()]].
    * @return transformed vector. Vector will be of length k.
-   * @since 1.4.0
    */
+  @Since("1.4.0")
   override def transform(vector: Vector): Vector = {
     vector match {
       case dv: DenseVector =>
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala
index 9998602b0c2ac..b95d5a899001e 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala
@@ -18,7 +18,7 @@
 package org.apache.spark.mllib.feature
 
 import org.apache.spark.Logging
-import org.apache.spark.annotation.{DeveloperApi, Experimental}
+import org.apache.spark.annotation.{DeveloperApi, Experimental, Since}
 import org.apache.spark.mllib.linalg.{DenseVector, SparseVector, Vector, Vectors}
 import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
 import org.apache.spark.rdd.RDD
@@ -31,14 +31,12 @@ import org.apache.spark.rdd.RDD
  * @param withMean False by default. Centers the data with mean before scaling. It will build a
  *                 dense output, so this does not work on sparse input and will raise an exception.
  * @param withStd True by default. Scales the data to unit standard deviation.
- * @since 1.1.0
  */
+@Since("1.1.0")
 @Experimental
 class StandardScaler(withMean: Boolean, withStd: Boolean) extends Logging {
 
-  /**
-   * @since 1.1.0
-   */
+  @Since("1.1.0")
   def this() = this(false, true)
 
   if (!(withMean || withStd)) {
@@ -50,8 +48,8 @@ class StandardScaler(withMean: Boolean, withStd: Boolean) extends Logging {
    *
    * @param data The data used to compute the mean and variance to build the transformation model.
    * @return a StandardScalarModel
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def fit(data: RDD[Vector]): StandardScalerModel = {
     // TODO: skip computation if both withMean and withStd are false
     val summary = data.treeAggregate(new MultivariateOnlineSummarizer)(
@@ -73,8 +71,8 @@ class StandardScaler(withMean: Boolean, withStd: Boolean) extends Logging {
  * @param mean column mean values
  * @param withStd whether to scale the data to have unit standard deviation
  * @param withMean whether to center the data before scaling
- * @since 1.1.0
  */
+@Since("1.1.0")
 @Experimental
 class StandardScalerModel (
     val std: Vector,
@@ -83,8 +81,8 @@ class StandardScalerModel (
     var withMean: Boolean) extends VectorTransformer {
 
   /**
-   * @since 1.3.0
    */
+  @Since("1.3.0")
   def this(std: Vector, mean: Vector) {
     this(std, mean, withStd = std != null, withMean = mean != null)
     require(this.withStd || this.withMean,
@@ -95,14 +93,10 @@ class StandardScalerModel (
     }
   }
 
-  /**
-   * @since 1.3.0
-   */
+  @Since("1.3.0")
   def this(std: Vector) = this(std, null)
 
-  /**
-   * @since 1.3.0
-   */
+  @Since("1.3.0")
   @DeveloperApi
   def setWithMean(withMean: Boolean): this.type = {
     require(!(withMean && this.mean == null), "cannot set withMean to true while mean is null")
@@ -110,9 +104,7 @@ class StandardScalerModel (
     this
   }
 
-  /**
-   * @since 1.3.0
-   */
+  @Since("1.3.0")
   @DeveloperApi
   def setWithStd(withStd: Boolean): this.type = {
     require(!(withStd && this.std == null),
@@ -132,8 +124,8 @@ class StandardScalerModel (
    * @param vector Vector to be standardized.
    * @return Standardized vector. If the std of a column is zero, it will return default `0.0`
    *         for the column with zero std.
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   override def transform(vector: Vector): Vector = {
     require(mean.size == vector.size)
     if (withMean) {
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala
index 9e0218d364972..cd8a05c961618 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala
@@ -25,8 +25,8 @@ import org.apache.spark.rdd.RDD
 /**
  * :: DeveloperApi ::
  * Trait for transformation of a vector
- * @since 1.1.0
  */
+@Since("1.1.0")
 @DeveloperApi
 trait VectorTransformer extends Serializable {
 
@@ -35,8 +35,8 @@ trait VectorTransformer extends Serializable {
    *
    * @param vector vector to be transformed.
    * @return transformed vector.
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def transform(vector: Vector): Vector
 
   /**
@@ -44,8 +44,8 @@ trait VectorTransformer extends Serializable {
    *
    * @param data RDD[Vector] to be transformed.
    * @return transformed RDD[Vector].
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def transform(data: RDD[Vector]): RDD[Vector] = {
     // Later in #1498 , all RDD objects are sent via broadcasting instead of akka.
     // So it should be no longer necessary to explicitly broadcast `this` object.
@@ -57,8 +57,8 @@ trait VectorTransformer extends Serializable {
    *
    * @param data JavaRDD[Vector] to be transformed.
    * @return transformed JavaRDD[Vector].
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def transform(data: JavaRDD[Vector]): JavaRDD[Vector] = {
     transform(data.rdd)
   }
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala
index 77e2eceab794a..540603454569b 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala
@@ -32,7 +32,7 @@ import org.json4s.jackson.JsonMethods._
 import org.apache.spark.Logging
 import org.apache.spark.SparkContext
 import org.apache.spark.SparkContext._
-import org.apache.spark.annotation.Experimental
+import org.apache.spark.annotation.{Experimental, Since}
 import org.apache.spark.api.java.JavaRDD
 import org.apache.spark.mllib.linalg.{Vector, Vectors, DenseMatrix, BLAS, DenseVector}
 import org.apache.spark.mllib.util.{Loader, Saveable}
@@ -69,8 +69,8 @@ private case class VocabWord(
  * Efficient Estimation of Word Representations in Vector Space
  * and
  * Distributed Representations of Words and Phrases and their Compositionality.
- * @since 1.1.0
  */
+@Since("1.1.0")
 @Experimental
 class Word2Vec extends Serializable with Logging {
 
@@ -83,8 +83,8 @@ class Word2Vec extends Serializable with Logging {
 
   /**
    * Sets vector size (default: 100).
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def setVectorSize(vectorSize: Int): this.type = {
     this.vectorSize = vectorSize
     this
@@ -92,8 +92,8 @@ class Word2Vec extends Serializable with Logging {
 
   /**
    * Sets initial learning rate (default: 0.025).
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def setLearningRate(learningRate: Double): this.type = {
     this.learningRate = learningRate
     this
@@ -101,8 +101,8 @@ class Word2Vec extends Serializable with Logging {
 
   /**
    * Sets number of partitions (default: 1). Use a small number for accuracy.
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def setNumPartitions(numPartitions: Int): this.type = {
     require(numPartitions > 0, s"numPartitions must be greater than 0 but got $numPartitions")
     this.numPartitions = numPartitions
@@ -112,8 +112,8 @@ class Word2Vec extends Serializable with Logging {
   /**
    * Sets number of iterations (default: 1), which should be smaller than or equal to number of
    * partitions.
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def setNumIterations(numIterations: Int): this.type = {
     this.numIterations = numIterations
     this
@@ -121,8 +121,8 @@ class Word2Vec extends Serializable with Logging {
 
   /**
    * Sets random seed (default: a random long integer).
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def setSeed(seed: Long): this.type = {
     this.seed = seed
     this
@@ -131,8 +131,8 @@ class Word2Vec extends Serializable with Logging {
   /**
    * Sets minCount, the minimum number of times a token must appear to be included in the word2vec
    * model's vocabulary (default: 5).
-   * @since 1.3.0
    */
+  @Since("1.3.0")
   def setMinCount(minCount: Int): this.type = {
     this.minCount = minCount
     this
@@ -269,8 +269,8 @@ class Word2Vec extends Serializable with Logging {
    * Computes the vector representation of each word in vocabulary.
    * @param dataset an RDD of words
    * @return a Word2VecModel
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def fit[S <: Iterable[String]](dataset: RDD[S]): Word2VecModel = {
 
     val words = dataset.flatMap(x => x)
@@ -419,8 +419,8 @@ class Word2Vec extends Serializable with Logging {
    * Computes the vector representation of each word in vocabulary (Java version).
    * @param dataset a JavaRDD of words
    * @return a Word2VecModel
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def fit[S <: JavaIterable[String]](dataset: JavaRDD[S]): Word2VecModel = {
     fit(dataset.rdd.map(_.asScala))
   }
@@ -463,9 +463,7 @@ class Word2VecModel private[mllib] (
     wordVecNorms
   }
 
-  /**
-   * @since 1.5.0
-   */
+  @Since("1.5.0")
   def this(model: Map[String, Array[Float]]) = {
     this(Word2VecModel.buildWordIndex(model), Word2VecModel.buildWordVectors(model))
   }
@@ -482,8 +480,8 @@ class Word2VecModel private[mllib] (
   override protected def formatVersion = "1.0"
 
   /**
-   * @since 1.4.0
    */
+  @Since("1.4.0")
   def save(sc: SparkContext, path: String): Unit = {
     Word2VecModel.SaveLoadV1_0.save(sc, path, getVectors)
   }
@@ -492,8 +490,8 @@ class Word2VecModel private[mllib] (
    * Transforms a word to its vector representation
    * @param word a word
    * @return vector representation of word
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def transform(word: String): Vector = {
     wordIndex.get(word) match {
       case Some(ind) =>
@@ -509,8 +507,8 @@ class Word2VecModel private[mllib] (
    * @param word a word
    * @param num number of synonyms to find
    * @return array of (word, cosineSimilarity)
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def findSynonyms(word: String, num: Int): Array[(String, Double)] = {
     val vector = transform(word)
     findSynonyms(vector, num)
@@ -521,8 +519,8 @@ class Word2VecModel private[mllib] (
    * @param vector vector representation of a word
    * @param num number of synonyms to find
    * @return array of (word, cosineSimilarity)
-   * @since 1.1.0
    */
+  @Since("1.1.0")
   def findSynonyms(vector: Vector, num: Int): Array[(String, Double)] = {
     require(num > 0, "Number of similar words should > 0")
     // TODO: optimize top-k
@@ -551,8 +549,8 @@ class Word2VecModel private[mllib] (
 
   /**
    * Returns a map of words to their vector representations.
-   * @since 1.2.0
    */
+  @Since("1.2.0")
   def getVectors: Map[String, Array[Float]] = {
     wordIndex.map { case (word, ind) =>
       (word, wordVectors.slice(vectorSize * ind, vectorSize * ind + vectorSize))
@@ -561,8 +559,8 @@ class Word2VecModel private[mllib] (
 }
 
 /**
- * @since 1.4.0
  */
+@Since("1.4.0")
 @Experimental
 object Word2VecModel extends Loader[Word2VecModel] {
 
@@ -623,8 +621,8 @@ object Word2VecModel extends Loader[Word2VecModel] {
   }
 
   /**
-   * @since 1.4.0
    */
+  @Since("1.4.0")
   override def load(sc: SparkContext, path: String): Word2VecModel = {
 
     val (loadedClassName, loadedVersion, metadata) = Loader.loadMetadata(sc, path)

From 4e038243415e084cfae22445f94ac701d3de0452 Mon Sep 17 00:00:00 2001
From: MechCoder <manojkumarsivaraj334@gmail.com>
Date: Thu, 20 Aug 2015 02:12:13 +0530
Subject: [PATCH 3/4] Add missing imports

---
 .../src/main/scala/org/apache/spark/mllib/feature/PCA.scala | 2 +-
 .../org/apache/spark/mllib/feature/VectorTransformer.scala  | 2 +-
 .../scala/org/apache/spark/mllib/feature/Word2Vec.scala     | 6 ------
 3 files changed, 2 insertions(+), 8 deletions(-)

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala
index d6c70a3aad42f..a48b7bba665d7 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala
@@ -17,7 +17,7 @@
 
 package org.apache.spark.mllib.feature
 
-import org.apache.spark.annotation.Experimental
+import org.apache.spark.annotation.{Experimental, Since}
 import org.apache.spark.api.java.JavaRDD
 import org.apache.spark.mllib.linalg._
 import org.apache.spark.mllib.linalg.distributed.RowMatrix
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala
index cd8a05c961618..5778fd1d09254 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/VectorTransformer.scala
@@ -17,7 +17,7 @@
 
 package org.apache.spark.mllib.feature
 
-import org.apache.spark.annotation.DeveloperApi
+import org.apache.spark.annotation.{DeveloperApi, Since}
 import org.apache.spark.api.java.JavaRDD
 import org.apache.spark.mllib.linalg.Vector
 import org.apache.spark.rdd.RDD
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala
index 540603454569b..e6f45ae4b01d5 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala
@@ -479,8 +479,6 @@ class Word2VecModel private[mllib] (
 
   override protected def formatVersion = "1.0"
 
-  /**
-   */
   @Since("1.4.0")
   def save(sc: SparkContext, path: String): Unit = {
     Word2VecModel.SaveLoadV1_0.save(sc, path, getVectors)
@@ -558,8 +556,6 @@ class Word2VecModel private[mllib] (
   }
 }
 
-/**
- */
 @Since("1.4.0")
 @Experimental
 object Word2VecModel extends Loader[Word2VecModel] {
@@ -620,8 +616,6 @@ object Word2VecModel extends Loader[Word2VecModel] {
     }
   }
 
-  /**
-   */
   @Since("1.4.0")
   override def load(sc: SparkContext, path: String): Word2VecModel = {
 

From 4abbcb3c3eeadb83e0477637898ba914c94f51db Mon Sep 17 00:00:00 2001
From: MechCoder <manojkumarsivaraj334@gmail.com>
Date: Thu, 20 Aug 2015 23:08:31 +0530
Subject: [PATCH 4/4] update since for class variables

---
 .../org/apache/spark/mllib/feature/ChiSqSelector.scala      | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala
index 75dd01aa5c71f..fdd974d7a391e 100644
--- a/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala
+++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala
@@ -33,7 +33,8 @@ import org.apache.spark.rdd.RDD
  */
 @Since("1.3.0")
 @Experimental
-class ChiSqSelectorModel (val selectedFeatures: Array[Int]) extends VectorTransformer {
+class ChiSqSelectorModel (
+  @Since("1.3.0") val selectedFeatures: Array[Int]) extends VectorTransformer {
 
   require(isSorted(selectedFeatures), "Array has to be sorted asc")
 
@@ -111,7 +112,8 @@ class ChiSqSelectorModel (val selectedFeatures: Array[Int]) extends VectorTransf
  */
 @Since("1.3.0")
 @Experimental
-class ChiSqSelector (val numTopFeatures: Int) extends Serializable {
+class ChiSqSelector (
+  @Since("1.3.0") val numTopFeatures: Int) extends Serializable {
 
   /**
    * Returns a ChiSquared feature selector.