From c8cf4533a168849ed62248c57da2d2195b482ea6 Mon Sep 17 00:00:00 2001
From: Nick Pentreath <nickp@za.ibm.com>
Date: Fri, 3 Jun 2016 15:54:12 -0700
Subject: [PATCH 1/6] Add missing @Since annotations to ml.feature package

---
 .../apache/spark/ml/feature/Binarizer.scala   |  8 +++++-
 .../apache/spark/ml/feature/Bucketizer.scala  |  9 ++++++-
 .../spark/ml/feature/ChiSqSelector.scala      | 15 +++++++++--
 .../spark/ml/feature/CountVectorizer.scala    | 20 ++++++++++++--
 .../org/apache/spark/ml/feature/DCT.scala     |  6 ++++-
 .../spark/ml/feature/ElementwiseProduct.scala |  6 ++++-
 .../apache/spark/ml/feature/HashingTF.scala   | 10 ++++++-
 .../org/apache/spark/ml/feature/IDF.scala     | 14 +++++++---
 .../apache/spark/ml/feature/Interaction.scala |  4 +--
 .../spark/ml/feature/MaxAbsScaler.scala       | 16 ++++++++----
 .../spark/ml/feature/MinMaxScaler.scala       | 19 +++++++++++---
 .../org/apache/spark/ml/feature/NGram.scala   |  6 ++++-
 .../apache/spark/ml/feature/Normalizer.scala  |  6 ++++-
 .../spark/ml/feature/OneHotEncoder.scala      |  7 ++++-
 .../org/apache/spark/ml/feature/PCA.scala     | 19 ++++++++++----
 .../ml/feature/PolynomialExpansion.scala      |  6 ++++-
 .../ml/feature/QuantileDiscretizer.scala      |  8 +++++-
 .../apache/spark/ml/feature/RFormula.scala    | 11 ++++++--
 .../spark/ml/feature/SQLTransformer.scala     |  2 +-
 .../spark/ml/feature/StandardScaler.scala     | 20 ++++++++++----
 .../spark/ml/feature/StopWordsRemover.scala   | 10 ++++++-
 .../spark/ml/feature/StringIndexer.scala      | 26 +++++++++++++++----
 .../apache/spark/ml/feature/Tokenizer.scala   | 16 ++++++++++--
 .../spark/ml/feature/VectorAssembler.scala    |  6 ++++-
 .../spark/ml/feature/VectorIndexer.scala      | 20 ++++++++++----
 .../spark/ml/feature/VectorSlicer.scala       | 10 ++++++-
 .../apache/spark/ml/feature/Word2Vec.scala    | 25 +++++++++++++++---
 python/pyspark/ml/feature.py                  |  2 +-
 28 files changed, 267 insertions(+), 60 deletions(-)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala
index 318c8b8b2f7d6..a9156a44a99ce 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala
@@ -35,9 +35,11 @@ import org.apache.spark.sql.types._
  * Binarize a column of continuous features given a threshold.
  */
 @Experimental
-final class Binarizer(override val uid: String)
+@Since("1.4.0")
+final class Binarizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
   extends Transformer with HasInputCol with HasOutputCol with DefaultParamsWritable {
 
+  @Since("1.4.0")
   def this() = this(Identifiable.randomUID("binarizer"))
 
   /**
@@ -51,17 +53,21 @@ final class Binarizer(override val uid: String)
     new DoubleParam(this, "threshold", "threshold used to binarize continuous features")
 
   /** @group getParam */
+  @Since("1.4.0")
   def getThreshold: Double = $(threshold)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setThreshold(value: Double): this.type = set(threshold, value)
 
   setDefault(threshold -> 0.0)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   @Since("2.0.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala
index ff988cc815160..2310659c89276 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala
@@ -35,9 +35,11 @@ import org.apache.spark.sql.types.{DoubleType, StructField, StructType}
  * `Bucketizer` maps a column of continuous features to a column of feature buckets.
  */
 @Experimental
-final class Bucketizer(override val uid: String)
+@Since("1.4.0")
+final class Bucketizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
   extends Model[Bucketizer] with HasInputCol with HasOutputCol with DefaultParamsWritable {
 
+  @Since("1.4.0")
   def this() = this(Identifiable.randomUID("bucketizer"))
 
   /**
@@ -57,15 +59,19 @@ final class Bucketizer(override val uid: String)
     Bucketizer.checkSplits)
 
   /** @group getParam */
+  @Since("1.4.0")
   def getSplits: Array[Double] = $(splits)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setSplits(value: Array[Double]): this.type = set(splits, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   @Since("2.0.0")
@@ -96,6 +102,7 @@ final class Bucketizer(override val uid: String)
   }
 }
 
+@Since("1.6.0")
 object Bucketizer extends DefaultParamsReadable[Bucketizer] {
 
   /** We require splits to be of length >= 3 and to be in strictly increasing order. */
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala
index e73a8f5d66087..c7c6926e95e24 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala
@@ -62,21 +62,27 @@ private[feature] trait ChiSqSelectorParams extends Params
  * categorical label.
  */
 @Experimental
-final class ChiSqSelector(override val uid: String)
+@Since("1.6.0")
+final class ChiSqSelector @Since("1.6.0") (@Since("1.6.0") override val uid: String)
   extends Estimator[ChiSqSelectorModel] with ChiSqSelectorParams with DefaultParamsWritable {
 
+  @Since("1.6.0")
   def this() = this(Identifiable.randomUID("chiSqSelector"))
 
   /** @group setParam */
+  @Since("1.6.0")
   def setNumTopFeatures(value: Int): this.type = set(numTopFeatures, value)
 
   /** @group setParam */
+  @Since("1.6.0")
   def setFeaturesCol(value: String): this.type = set(featuresCol, value)
 
   /** @group setParam */
+  @Since("1.6.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   /** @group setParam */
+  @Since("1.6.0")
   def setLabelCol(value: String): this.type = set(labelCol, value)
 
   @Since("2.0.0")
@@ -112,23 +118,28 @@ object ChiSqSelector extends DefaultParamsReadable[ChiSqSelector] {
  * Model fitted by [[ChiSqSelector]].
  */
 @Experimental
+@Since("1.6.0")
 final class ChiSqSelectorModel private[ml] (
-    override val uid: String,
+    @Since("1.6.0") override val uid: String,
     private val chiSqSelector: feature.ChiSqSelectorModel)
   extends Model[ChiSqSelectorModel] with ChiSqSelectorParams with MLWritable {
 
   import ChiSqSelectorModel._
 
   /** list of indices to select (filter). Must be ordered asc */
+  @Since("1.6.0")
   val selectedFeatures: Array[Int] = chiSqSelector.selectedFeatures
 
   /** @group setParam */
+  @Since("1.6.0")
   def setFeaturesCol(value: String): this.type = set(featuresCol, value)
 
   /** @group setParam */
+  @Since("1.6.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   /** @group setParam */
+  @Since("1.6.0")
   def setLabelCol(value: String): this.type = set(labelCol, value)
 
   @Since("2.0.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala
index 272567d09cda7..1c217512be99a 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala
@@ -120,27 +120,35 @@ private[feature] trait CountVectorizerParams extends Params with HasInputCol wit
  * Extracts a vocabulary from document collections and generates a [[CountVectorizerModel]].
  */
 @Experimental
-class CountVectorizer(override val uid: String)
+@Since("1.5.0")
+class CountVectorizer @Since("1.5.0") (@Since("1.5.0") override val uid: String)
   extends Estimator[CountVectorizerModel] with CountVectorizerParams with DefaultParamsWritable {
 
+  @Since("1.5.0")
   def this() = this(Identifiable.randomUID("cntVec"))
 
   /** @group setParam */
+  @Since("1.5.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setVocabSize(value: Int): this.type = set(vocabSize, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setMinDF(value: Double): this.type = set(minDF, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setMinTF(value: Double): this.type = set(minTF, value)
 
   /** @group setParam */
+  @Since("2.0.0")
   def setBinary(value: Boolean): this.type = set(binary, value)
 
   @Since("2.0.0")
@@ -196,26 +204,34 @@ object CountVectorizer extends DefaultParamsReadable[CountVectorizer] {
  * @param vocabulary An Array over terms. Only the terms in the vocabulary will be counted.
  */
 @Experimental
-class CountVectorizerModel(override val uid: String, val vocabulary: Array[String])
+@Since("1.5.0")
+class CountVectorizerModel(
+    @Since("1.5.0") override val uid: String,
+    @Since("1.5.0") val vocabulary: Array[String])
   extends Model[CountVectorizerModel] with CountVectorizerParams with MLWritable {
 
   import CountVectorizerModel._
 
+  @Since("1.5.0")
   def this(vocabulary: Array[String]) = {
     this(Identifiable.randomUID("cntVecModel"), vocabulary)
     set(vocabSize, vocabulary.length)
   }
 
   /** @group setParam */
+  @Since("1.5.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setMinTF(value: Double): this.type = set(minTF, value)
 
   /** @group setParam */
+  @Since("2.0.0")
   def setBinary(value: Boolean): this.type = set(binary, value)
 
   /** Dictionary created from [[vocabulary]] and its indices, broadcast once for [[transform()]] */
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala
index 301358ef1226c..46a3de0926eea 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala
@@ -36,9 +36,11 @@ import org.apache.spark.sql.types.DataType
  * More information on [[https://en.wikipedia.org/wiki/Discrete_cosine_transform#DCT-II Wikipedia]].
  */
 @Experimental
-class DCT(override val uid: String)
+@Since("1.5.0")
+class DCT @Since("1.5.0") (@Since("1.5.0") override val uid: String)
   extends UnaryTransformer[Vector, Vector, DCT] with DefaultParamsWritable {
 
+  @Since("1.5.0")
   def this() = this(Identifiable.randomUID("dct"))
 
   /**
@@ -50,9 +52,11 @@ class DCT(override val uid: String)
     this, "inverse", "Set transformer to perform inverse DCT")
 
   /** @group setParam */
+  @Since("1.5.0")
   def setInverse(value: Boolean): this.type = set(inverse, value)
 
   /** @group getParam */
+  @Since("1.5.0")
   def getInverse: Boolean = $(inverse)
 
   setDefault(inverse -> false)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
index 9d2e60fa3f1e4..abef6c0990ea9 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
@@ -33,9 +33,11 @@ import org.apache.spark.sql.types.DataType
  * multiplier.
  */
 @Experimental
-class ElementwiseProduct(override val uid: String)
+@Since("1.4.0")
+class ElementwiseProduct @Since("1.4.0") (@Since("1.4.0") override val uid: String)
   extends UnaryTransformer[Vector, Vector, ElementwiseProduct] with DefaultParamsWritable {
 
+  @Since("1.4.0")
   def this() = this(Identifiable.randomUID("elemProd"))
 
   /**
@@ -45,9 +47,11 @@ class ElementwiseProduct(override val uid: String)
   val scalingVec: Param[Vector] = new Param(this, "scalingVec", "vector for hadamard product")
 
   /** @group setParam */
+  @Since("1.4.0")
   def setScalingVec(value: Vector): this.type = set(scalingVec, value)
 
   /** @group getParam */
+  @Since("1.4.0")
   def getScalingVec: Vector = getOrDefault(scalingVec)
 
   override protected def createTransformFunc: Vector => Vector = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala
index 94e1825ba61e4..269510b5c6cb4 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala
@@ -38,15 +38,19 @@ import org.apache.spark.sql.types.{ArrayType, StructType}
  * otherwise the features will not be mapped evenly to the columns.
  */
 @Experimental
-class HashingTF(override val uid: String)
+@Since("1.2.0")
+class HashingTF @Since("1.4.0") (@Since("1.4.0") override val uid: String)
   extends Transformer with HasInputCol with HasOutputCol with DefaultParamsWritable {
 
+  @Since("1.2.0")
   def this() = this(Identifiable.randomUID("hashingTF"))
 
   /** @group setParam */
+  @Since("1.4.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   /**
@@ -71,15 +75,19 @@ class HashingTF(override val uid: String)
   setDefault(numFeatures -> (1 << 18), binary -> false)
 
   /** @group getParam */
+  @Since("1.2.0")
   def getNumFeatures: Int = $(numFeatures)
 
   /** @group setParam */
+  @Since("1.2.0")
   def setNumFeatures(value: Int): this.type = set(numFeatures, value)
 
   /** @group getParam */
+  @Since("2.0.0")
   def getBinary: Boolean = $(binary)
 
   /** @group setParam */
+  @Since("2.0.0")
   def setBinary(value: Boolean): this.type = set(binary, value)
 
   @Since("2.0.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
index 08beda6d7515d..38d0da1c1d7fa 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
@@ -64,18 +64,23 @@ private[feature] trait IDFBase extends Params with HasInputCol with HasOutputCol
  * Compute the Inverse Document Frequency (IDF) given a collection of documents.
  */
 @Experimental
-final class IDF(override val uid: String) extends Estimator[IDFModel] with IDFBase
-  with DefaultParamsWritable {
+@Since("1.4.0")
+final class IDF @Since("1.4.0") (@Since("1.4.0") override val uid: String)
+  extends Estimator[IDFModel] with IDFBase with DefaultParamsWritable {
 
+  @Since("1.4.0")
   def this() = this(Identifiable.randomUID("idf"))
 
   /** @group setParam */
+  @Since("1.4.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setMinDocFreq(value: Int): this.type = set(minDocFreq, value)
 
   @Since("2.0.0")
@@ -107,17 +112,20 @@ object IDF extends DefaultParamsReadable[IDF] {
  * Model fitted by [[IDF]].
  */
 @Experimental
+@Since("1.4.0")
 class IDFModel private[ml] (
-    override val uid: String,
+    @Since("1.4.0") override val uid: String,
     idfModel: feature.IDFModel)
   extends Model[IDFModel] with IDFBase with MLWritable {
 
   import IDFModel._
 
   /** @group setParam */
+  @Since("1.4.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   @Since("2.0.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Interaction.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Interaction.scala
index fa65ff987917e..dca28b5c5d34f 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Interaction.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Interaction.scala
@@ -42,9 +42,9 @@ import org.apache.spark.sql.types._
  * `Vector(6, 8)` if all input features were numeric. If the first feature was instead nominal
  * with four categories, the output would then be `Vector(0, 0, 0, 0, 3, 4, 0, 0)`.
  */
-@Since("1.6.0")
 @Experimental
-class Interaction @Since("1.6.0") (override val uid: String) extends Transformer
+@Since("1.6.0")
+class Interaction @Since("1.6.0") (@Since("1.6.0") override val uid: String) extends Transformer
   with HasInputCols with HasOutputCol with DefaultParamsWritable {
 
   @Since("1.6.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala
index 7298a18ff83b5..006d6413cbeb6 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala
@@ -54,16 +54,19 @@ private[feature] trait MaxAbsScalerParams extends Params with HasInputCol with H
  * any sparsity.
  */
 @Experimental
-class MaxAbsScaler @Since("2.0.0") (override val uid: String)
+@Since("2.0.0")
+class MaxAbsScaler @Since("2.0.0") (@Since("2.0.0") override val uid: String)
   extends Estimator[MaxAbsScalerModel] with MaxAbsScalerParams with DefaultParamsWritable {
 
   @Since("2.0.0")
   def this() = this(Identifiable.randomUID("maxAbsScal"))
 
   /** @group setParam */
+  @Since("2.0.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("2.0.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   @Since("2.0.0")
@@ -88,7 +91,7 @@ class MaxAbsScaler @Since("2.0.0") (override val uid: String)
   override def copy(extra: ParamMap): MaxAbsScaler = defaultCopy(extra)
 }
 
-@Since("1.6.0")
+@Since("2.0.0")
 object MaxAbsScaler extends DefaultParamsReadable[MaxAbsScaler] {
 
   @Since("1.6.0")
@@ -101,17 +104,20 @@ object MaxAbsScaler extends DefaultParamsReadable[MaxAbsScaler] {
  *
  */
 @Experimental
+@Since("2.0.0")
 class MaxAbsScalerModel private[ml] (
-    override val uid: String,
-    val maxAbs: Vector)
+    @Since("2.0.0") override val uid: String,
+    @Since("2.0.0") val maxAbs: Vector)
   extends Model[MaxAbsScalerModel] with MaxAbsScalerParams with MLWritable {
 
   import MaxAbsScalerModel._
 
   /** @group setParam */
+  @Since("2.0.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("2.0.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   @Since("2.0.0")
@@ -139,7 +145,7 @@ class MaxAbsScalerModel private[ml] (
   override def write: MLWriter = new MaxAbsScalerModelWriter(this)
 }
 
-@Since("1.6.0")
+@Since("2.0.0")
 object MaxAbsScalerModel extends MLReadable[MaxAbsScalerModel] {
 
   private[MaxAbsScalerModel]
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
index a27bed5333c56..0260c9d6f13aa 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
@@ -85,23 +85,29 @@ private[feature] trait MinMaxScalerParams extends Params with HasInputCol with H
  * transformer will be DenseVector even for sparse input.
  */
 @Experimental
-class MinMaxScaler(override val uid: String)
+@Since("1.5.0")
+class MinMaxScaler @Since("1.5.0") (@Since("1.5.0") override val uid: String)
   extends Estimator[MinMaxScalerModel] with MinMaxScalerParams with DefaultParamsWritable {
 
+  @Since("1.5.0")
   def this() = this(Identifiable.randomUID("minMaxScal"))
 
   setDefault(min -> 0.0, max -> 1.0)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setMin(value: Double): this.type = set(min, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setMax(value: Double): this.type = set(max, value)
 
   @Since("2.0.0")
@@ -138,24 +144,29 @@ object MinMaxScaler extends DefaultParamsReadable[MinMaxScaler] {
  * TODO: The transformer does not yet set the metadata in the output column (SPARK-8529).
  */
 @Experimental
+@Since("1.5.0")
 class MinMaxScalerModel private[ml] (
-    override val uid: String,
-    val originalMin: Vector,
-    val originalMax: Vector)
+    @Since("1.5.0") override val uid: String,
+    @Since("1.5.0") val originalMin: Vector,
+    @Since("1.5.0") val originalMax: Vector)
   extends Model[MinMaxScalerModel] with MinMaxScalerParams with MLWritable {
 
   import MinMaxScalerModel._
 
   /** @group setParam */
+  @Since("1.5.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setMin(value: Double): this.type = set(min, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setMax(value: Double): this.type = set(max, value)
 
   @Since("2.0.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/NGram.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/NGram.scala
index f8bc7e3f0c031..0b8d8c6146528 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/NGram.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/NGram.scala
@@ -35,9 +35,11 @@ import org.apache.spark.sql.types.{ArrayType, DataType, StringType}
  * returned.
  */
 @Experimental
-class NGram(override val uid: String)
+@Since("1.5.0")
+class NGram @Since("1.5.0") (@Since("1.5.0") override val uid: String)
   extends UnaryTransformer[Seq[String], Seq[String], NGram] with DefaultParamsWritable {
 
+  @Since("1.5.0")
   def this() = this(Identifiable.randomUID("ngram"))
 
   /**
@@ -49,9 +51,11 @@ class NGram(override val uid: String)
     ParamValidators.gtEq(1))
 
   /** @group setParam */
+  @Since("1.5.0")
   def setN(value: Int): this.type = set(n, value)
 
   /** @group getParam */
+  @Since("1.5.0")
   def getN: Int = $(n)
 
   setDefault(n -> 2)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala
index 942ac7ebdb3bd..2f650e5c70a7c 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala
@@ -31,9 +31,11 @@ import org.apache.spark.sql.types.DataType
  * Normalize a vector to have unit norm using the given p-norm.
  */
 @Experimental
-class Normalizer(override val uid: String)
+@Since("1.4.0")
+class Normalizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
   extends UnaryTransformer[Vector, Vector, Normalizer] with DefaultParamsWritable {
 
+  @Since("1.4.0")
   def this() = this(Identifiable.randomUID("normalizer"))
 
   /**
@@ -46,9 +48,11 @@ class Normalizer(override val uid: String)
   setDefault(p -> 2.0)
 
   /** @group getParam */
+  @Since("1.4.0")
   def getP: Double = $(p)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setP(value: Double): this.type = set(p, value)
 
   override protected def createTransformFunc: Vector => Vector = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala
index 3d1e6dd818829..4f2e826505be4 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala
@@ -43,9 +43,11 @@ import org.apache.spark.sql.types.{DoubleType, NumericType, StructType}
  * @see [[StringIndexer]] for converting categorical values into category indices
  */
 @Experimental
-class OneHotEncoder(override val uid: String) extends Transformer
+@Since("1.4.0")
+class OneHotEncoder @Since("1.4.0") (@Since("1.4.0") override val uid: String) extends Transformer
   with HasInputCol with HasOutputCol with DefaultParamsWritable {
 
+  @Since("1.4.0")
   def this() = this(Identifiable.randomUID("oneHot"))
 
   /**
@@ -57,12 +59,15 @@ class OneHotEncoder(override val uid: String) extends Transformer
   setDefault(dropLast -> true)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setDropLast(value: Boolean): this.type = set(dropLast, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   override def transformSchema(schema: StructType): StructType = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
index 2f667af9d10bd..479f49b0abaf4 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
@@ -65,18 +65,24 @@ private[feature] trait PCAParams extends Params with HasInputCol with HasOutputC
  * principal components.
  */
 @Experimental
-class PCA (override val uid: String) extends Estimator[PCAModel] with PCAParams
-  with DefaultParamsWritable {
+@Since("1.5.0")
+class PCA @Since("1.5.0") (
+    @Since("1.5.0") override val uid: String)
+  extends Estimator[PCAModel] with PCAParams with DefaultParamsWritable {
 
+  @Since("1.5.0")
   def this() = this(Identifiable.randomUID("pca"))
 
   /** @group setParam */
+  @Since("1.5.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setK(value: Int): this.type = set(k, value)
 
   /**
@@ -116,18 +122,21 @@ object PCA extends DefaultParamsReadable[PCA] {
  *                          each principal component.
  */
 @Experimental
+@Since("1.5.0")
 class PCAModel private[ml] (
-    override val uid: String,
-    val pc: DenseMatrix,
-    val explainedVariance: DenseVector)
+    @Since("1.5.0") override val uid: String,
+    @Since("1.6.0") val pc: DenseMatrix,
+    @Since("2.0.0") val explainedVariance: DenseVector)
   extends Model[PCAModel] with PCAParams with MLWritable {
 
   import PCAModel._
 
   /** @group setParam */
+  @Since("1.5.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   /**
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala
index a01867701bd8b..284dfb36e050a 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala
@@ -35,9 +35,11 @@ import org.apache.spark.sql.types.DataType
  * `(x, y)`, if we want to expand it with degree 2, then we get `(x, x * x, y, x * y, y * y)`.
  */
 @Experimental
-class PolynomialExpansion(override val uid: String)
+@Since("1.4.0")
+class PolynomialExpansion @Since("1.4.0") (@Since("1.4.0") override val uid: String)
   extends UnaryTransformer[Vector, Vector, PolynomialExpansion] with DefaultParamsWritable {
 
+  @Since("1.4.0")
   def this() = this(Identifiable.randomUID("poly"))
 
   /**
@@ -51,9 +53,11 @@ class PolynomialExpansion(override val uid: String)
   setDefault(degree -> 2)
 
   /** @group getParam */
+  @Since("1.4.0")
   def getDegree: Int = $(degree)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setDegree(value: Int): this.type = set(degree, value)
 
   override protected def createTransformFunc: Vector => Vector = { v =>
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
index 1fefaa1fdd8df..50ac9a7e76128 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
@@ -74,21 +74,27 @@ private[feature] trait QuantileDiscretizerBase extends Params
  * covering all real values.
  */
 @Experimental
-final class QuantileDiscretizer(override val uid: String)
+@Since("1.6.0")
+final class QuantileDiscretizer @Since("1.6.0") (@Since("1.6.0") override val uid: String)
   extends Estimator[Bucketizer] with QuantileDiscretizerBase with DefaultParamsWritable {
 
+  @Since("1.6.0")
   def this() = this(Identifiable.randomUID("quantileDiscretizer"))
 
   /** @group setParam */
+  @Since("2.0.0")
   def setRelativeError(value: Double): this.type = set(relativeError, value)
 
   /** @group setParam */
+  @Since("1.6.0")
   def setNumBuckets(value: Int): this.type = set(numBuckets, value)
 
   /** @group setParam */
+  @Since("1.6.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.6.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   override def transformSchema(schema: StructType): StructType = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
index a7ca0fe252b0d..085a83f103869 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
@@ -70,9 +70,11 @@ private[feature] trait RFormulaBase extends HasFeaturesCol with HasLabelCol {
  * will be created from the specified response variable in the formula.
  */
 @Experimental
-class RFormula(override val uid: String)
+@Since("1.5.0")
+class RFormula @Since("1.5.0") (@Since("1.5.0") override val uid: String)
   extends Estimator[RFormulaModel] with RFormulaBase with DefaultParamsWritable {
 
+  @Since("1.5.0")
   def this() = this(Identifiable.randomUID("rFormula"))
 
   /**
@@ -86,15 +88,19 @@ class RFormula(override val uid: String)
    * @group setParam
    * @param value an R formula in string form (e.g. "y ~ x + z")
    */
+  @Since("1.5.0")
   def setFormula(value: String): this.type = set(formula, value)
 
   /** @group getParam */
+  @Since("1.5.0")
   def getFormula: String = $(formula)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setFeaturesCol(value: String): this.type = set(featuresCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setLabelCol(value: String): this.type = set(labelCol, value)
 
   /** Whether the formula specifies fitting an intercept. */
@@ -201,8 +207,9 @@ object RFormula extends DefaultParamsReadable[RFormula] {
  * @param pipelineModel the fitted feature model, including factor to index mappings.
  */
 @Experimental
+@Since("1.5.0")
 class RFormulaModel private[feature](
-    override val uid: String,
+    @Since("1.5.0") override val uid: String,
     private[ml] val resolvedFormula: ResolvedRFormula,
     private[ml] val pipelineModel: PipelineModel)
   extends Model[RFormulaModel] with RFormulaBase with MLWritable {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/SQLTransformer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/SQLTransformer.scala
index bd8f9494fb193..b8715746fee5b 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/SQLTransformer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/SQLTransformer.scala
@@ -39,7 +39,7 @@ import org.apache.spark.sql.types.StructType
  */
 @Experimental
 @Since("1.6.0")
-class SQLTransformer @Since("1.6.0") (override val uid: String) extends Transformer
+class SQLTransformer @Since("1.6.0") (@Since("1.6.0") override val uid: String) extends Transformer
   with DefaultParamsWritable {
 
   @Since("1.6.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
index 7cec369c23a8f..aab24ae692831 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
@@ -85,21 +85,28 @@ private[feature] trait StandardScalerParams extends Params with HasInputCol with
  * which is computed as the square root of the unbiased sample variance.
  */
 @Experimental
-class StandardScaler(override val uid: String) extends Estimator[StandardScalerModel]
-  with StandardScalerParams with DefaultParamsWritable {
+@Since("1.2.0")
+class StandardScaler @Since("1.2.0") (
+    @Since("1.4.0") override val uid: String)
+  extends Estimator[StandardScalerModel] with StandardScalerParams with DefaultParamsWritable {
 
+  @Since("1.2.0")
   def this() = this(Identifiable.randomUID("stdScal"))
 
   /** @group setParam */
+  @Since("1.2.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.2.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setWithMean(value: Boolean): this.type = set(withMean, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setWithStd(value: Boolean): this.type = set(withStd, value)
 
   @Since("2.0.0")
@@ -135,18 +142,21 @@ object StandardScaler extends DefaultParamsReadable[StandardScaler] {
  * @param mean Mean of the StandardScalerModel
  */
 @Experimental
+@Since("1.2.0")
 class StandardScalerModel private[ml] (
-    override val uid: String,
-    val std: Vector,
-    val mean: Vector)
+    @Since("1.4.0") override val uid: String,
+    @Since("1.5.0") val std: Vector,
+    @Since("1.5.0") val mean: Vector)
   extends Model[StandardScalerModel] with StandardScalerParams with MLWritable {
 
   import StandardScalerModel._
 
   /** @group setParam */
+  @Since("1.2.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.2.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   @Since("2.0.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
index 11864cb8f439a..1f111ccab8fc5 100755
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
@@ -33,15 +33,19 @@ import org.apache.spark.sql.types.{ArrayType, StringType, StructType}
  * @see [[http://en.wikipedia.org/wiki/Stop_words]]
  */
 @Experimental
-class StopWordsRemover(override val uid: String)
+@Since("1.5.0")
+class StopWordsRemover @Since("1.5.0") (@Since("1.5.0") override val uid: String)
   extends Transformer with HasInputCol with HasOutputCol with DefaultParamsWritable {
 
+  @Since("1.5.0")
   def this() = this(Identifiable.randomUID("stopWords"))
 
   /** @group setParam */
+  @Since("1.5.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   /**
@@ -54,9 +58,11 @@ class StopWordsRemover(override val uid: String)
     new StringArrayParam(this, "stopWords", "the words to be filtered out")
 
   /** @group setParam */
+  @Since("1.5.0")
   def setStopWords(value: Array[String]): this.type = set(stopWords, value)
 
   /** @group getParam */
+  @Since("1.5.0")
   def getStopWords: Array[String] = $(stopWords)
 
   /**
@@ -68,9 +74,11 @@ class StopWordsRemover(override val uid: String)
     "whether to do a case-sensitive comparison over the stop words")
 
   /** @group setParam */
+  @Since("1.5.0")
   def setCaseSensitive(value: Boolean): this.type = set(caseSensitive, value)
 
   /** @group getParam */
+  @Since("1.5.0")
   def getCaseSensitive: Boolean = $(caseSensitive)
 
   setDefault(stopWords -> StopWordsRemover.loadDefaultStopWords("english"), caseSensitive -> false)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
index cc0571fd7e39b..c7931c50f2cdf 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
@@ -64,22 +64,27 @@ private[feature] trait StringIndexerBase extends Params with HasInputCol with Ha
  * @see [[IndexToString]] for the inverse transformation
  */
 @Experimental
-class StringIndexer(override val uid: String) extends Estimator[StringIndexerModel]
+@Since("1.4.0")
+class StringIndexer @Since("1.4.0") (
+    @Since("1.4.0") override val uid: String) extends Estimator[StringIndexerModel]
   with StringIndexerBase with DefaultParamsWritable {
 
+  @Since("1.4.0")
   def this() = this(Identifiable.randomUID("strIdx"))
 
   /** @group setParam */
+  @Since("1.6.0")
   def setHandleInvalid(value: String): this.type = set(handleInvalid, value)
   setDefault(handleInvalid, "error")
 
   /** @group setParam */
+  @Since("1.4.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
-
   @Since("2.0.0")
   override def fit(dataset: Dataset[_]): StringIndexerModel = {
     val counts = dataset.select(col($(inputCol)).cast(StringType))
@@ -115,13 +120,15 @@ object StringIndexer extends DefaultParamsReadable[StringIndexer] {
  * @param labels  Ordered list of labels, corresponding to indices to be assigned.
  */
 @Experimental
+@Since("1.4.0")
 class StringIndexerModel (
-    override val uid: String,
-    val labels: Array[String])
+    @Since("1.4.0") override val uid: String,
+    @Since("1.5.0") val labels: Array[String])
   extends Model[StringIndexerModel] with StringIndexerBase with MLWritable {
 
   import StringIndexerModel._
 
+  @Since("1.5.0")
   def this(labels: Array[String]) = this(Identifiable.randomUID("strIdx"), labels)
 
   private val labelToIndex: OpenHashMap[String, Double] = {
@@ -136,13 +143,16 @@ class StringIndexerModel (
   }
 
   /** @group setParam */
+  @Since("1.6.0")
   def setHandleInvalid(value: String): this.type = set(handleInvalid, value)
   setDefault(handleInvalid, "error")
 
   /** @group setParam */
+  @Since("1.4.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   @Since("2.0.0")
@@ -245,19 +255,24 @@ object StringIndexerModel extends MLReadable[StringIndexerModel] {
  * @see [[StringIndexer]] for converting strings into indices
  */
 @Experimental
-class IndexToString private[ml] (override val uid: String)
+@Since("1.5.0")
+class IndexToString private[ml] (@Since("1.5.0") override val uid: String)
   extends Transformer with HasInputCol with HasOutputCol with DefaultParamsWritable {
 
+  @Since("1.5.0")
   def this() =
     this(Identifiable.randomUID("idxToStr"))
 
   /** @group setParam */
+  @Since("1.5.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setLabels(value: Array[String]): this.type = set(labels, value)
 
   /**
@@ -271,6 +286,7 @@ class IndexToString private[ml] (override val uid: String)
       " If not provided or if empty, then metadata from inputCol is used instead.")
 
   /** @group getParam */
+  @Since("1.5.0")
   final def getLabels: Array[String] = $(labels)
 
   override def transformSchema(schema: StructType): StructType = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala
index 8456a0e915804..64ac592397cea 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala
@@ -30,9 +30,11 @@ import org.apache.spark.sql.types.{ArrayType, DataType, StringType}
  * @see [[RegexTokenizer]]
  */
 @Experimental
-class Tokenizer(override val uid: String)
+@Since("1.2.0")
+class Tokenizer @Since("1.2.0") (@Since("1.4.0") override val uid: String)
   extends UnaryTransformer[String, Seq[String], Tokenizer] with DefaultParamsWritable {
 
+  @Since("1.4.0")
   def this() = this(Identifiable.randomUID("tok"))
 
   override protected def createTransformFunc: String => Seq[String] = {
@@ -63,9 +65,11 @@ object Tokenizer extends DefaultParamsReadable[Tokenizer] {
  * It returns an array of strings that can be empty.
  */
 @Experimental
-class RegexTokenizer(override val uid: String)
+@Since("1.4.0")
+class RegexTokenizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
   extends UnaryTransformer[String, Seq[String], RegexTokenizer] with DefaultParamsWritable {
 
+  @Since("1.4.0")
   def this() = this(Identifiable.randomUID("regexTok"))
 
   /**
@@ -77,9 +81,11 @@ class RegexTokenizer(override val uid: String)
     ParamValidators.gtEq(0))
 
   /** @group setParam */
+  @Since("1.4.0")
   def setMinTokenLength(value: Int): this.type = set(minTokenLength, value)
 
   /** @group getParam */
+  @Since("1.4.0")
   def getMinTokenLength: Int = $(minTokenLength)
 
   /**
@@ -90,9 +96,11 @@ class RegexTokenizer(override val uid: String)
   val gaps: BooleanParam = new BooleanParam(this, "gaps", "Set regex to match gaps or tokens")
 
   /** @group setParam */
+  @Since("1.4.0")
   def setGaps(value: Boolean): this.type = set(gaps, value)
 
   /** @group getParam */
+  @Since("1.4.0")
   def getGaps: Boolean = $(gaps)
 
   /**
@@ -103,9 +111,11 @@ class RegexTokenizer(override val uid: String)
   val pattern: Param[String] = new Param(this, "pattern", "regex pattern used for tokenizing")
 
   /** @group setParam */
+  @Since("1.4.0")
   def setPattern(value: String): this.type = set(pattern, value)
 
   /** @group getParam */
+  @Since("1.4.0")
   def getPattern: String = $(pattern)
 
   /**
@@ -117,9 +127,11 @@ class RegexTokenizer(override val uid: String)
     "whether to convert all characters to lowercase before tokenizing.")
 
   /** @group setParam */
+  @Since("1.6.0")
   def setToLowercase(value: Boolean): this.type = set(toLowercase, value)
 
   /** @group getParam */
+  @Since("1.6.0")
   def getToLowercase: Boolean = $(toLowercase)
 
   setDefault(minTokenLength -> 1, gaps -> true, pattern -> "\\s+", toLowercase -> true)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala
index 1bc24202b7615..f5dd26f712a03 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala
@@ -36,15 +36,19 @@ import org.apache.spark.sql.types._
  * A feature transformer that merges multiple columns into a vector column.
  */
 @Experimental
-class VectorAssembler(override val uid: String)
+@Since("1.4.0")
+class VectorAssembler @Since("1.4.0") (@Since("1.4.0") override val uid: String)
   extends Transformer with HasInputCols with HasOutputCol with DefaultParamsWritable {
 
+  @Since("1.4.0")
   def this() = this(Identifiable.randomUID("vecAssembler"))
 
   /** @group setParam */
+  @Since("1.4.0")
   def setInputCols(value: Array[String]): this.type = set(inputCols, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   @Since("2.0.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala
index d814528ec48d1..aae71d759eca6 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala
@@ -94,18 +94,24 @@ private[ml] trait VectorIndexerParams extends Params with HasInputCol with HasOu
  *  - Add option for allowing unknown categories.
  */
 @Experimental
-class VectorIndexer(override val uid: String) extends Estimator[VectorIndexerModel]
-  with VectorIndexerParams with DefaultParamsWritable {
+@Since("1.4.0")
+class VectorIndexer @Since("1.4.0") (
+    @Since("1.4.0") override val uid: String)
+  extends Estimator[VectorIndexerModel] with VectorIndexerParams with DefaultParamsWritable {
 
+  @Since("1.4.0")
   def this() = this(Identifiable.randomUID("vecIdx"))
 
   /** @group setParam */
+  @Since("1.4.0")
   def setMaxCategories(value: Int): this.type = set(maxCategories, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   @Since("2.0.0")
@@ -256,15 +262,17 @@ object VectorIndexer extends DefaultParamsReadable[VectorIndexer] {
  *                      If a feature is not in this map, it is treated as continuous.
  */
 @Experimental
+@Since("1.4.0")
 class VectorIndexerModel private[ml] (
-    override val uid: String,
-    val numFeatures: Int,
-    val categoryMaps: Map[Int, Map[Double, Int]])
+    @Since("1.4.0") override val uid: String,
+    @Since("1.4.0") val numFeatures: Int,
+    @Since("1.4.0") val categoryMaps: Map[Int, Map[Double, Int]])
   extends Model[VectorIndexerModel] with VectorIndexerParams with MLWritable {
 
   import VectorIndexerModel._
 
   /** Java-friendly version of [[categoryMaps]] */
+  @Since("1.4.0")
   def javaCategoryMaps: JMap[JInt, JMap[JDouble, JInt]] = {
     categoryMaps.mapValues(_.asJava).asJava.asInstanceOf[JMap[JInt, JMap[JDouble, JInt]]]
   }
@@ -342,9 +350,11 @@ class VectorIndexerModel private[ml] (
   }
 
   /** @group setParam */
+  @Since("1.4.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   @Since("2.0.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala
index 103738cd91c09..78902e72893fc 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala
@@ -41,9 +41,11 @@ import org.apache.spark.sql.types.StructType
  * followed by the selected names (in the order given).
  */
 @Experimental
-final class VectorSlicer(override val uid: String)
+@Since("1.5.0")
+final class VectorSlicer @Since("1.5.0") (@Since("1.5.0") override val uid: String)
   extends Transformer with HasInputCol with HasOutputCol with DefaultParamsWritable {
 
+  @Since("1.5.0")
   def this() = this(Identifiable.randomUID("vectorSlicer"))
 
   /**
@@ -59,9 +61,11 @@ final class VectorSlicer(override val uid: String)
   setDefault(indices -> Array.empty[Int])
 
   /** @group getParam */
+  @Since("1.5.0")
   def getIndices: Array[Int] = $(indices)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setIndices(value: Array[Int]): this.type = set(indices, value)
 
   /**
@@ -78,15 +82,19 @@ final class VectorSlicer(override val uid: String)
   setDefault(names -> Array.empty[String])
 
   /** @group getParam */
+  @Since("1.5.0")
   def getNames: Array[String] = $(names)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setNames(value: Array[String]): this.type = set(names, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.5.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   @Since("2.0.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
index 33515b22400be..803ff4202b0a5 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
@@ -120,39 +120,52 @@ private[feature] trait Word2VecBase extends Params
  * natural language processing or machine learning process.
  */
 @Experimental
-final class Word2Vec(override val uid: String) extends Estimator[Word2VecModel] with Word2VecBase
-  with DefaultParamsWritable {
+@Since("1.4.0")
+final class Word2Vec @Since("1.4.0") (
+    @Since("1.4.0") override val uid: String)
+  extends Estimator[Word2VecModel] with Word2VecBase with DefaultParamsWritable {
 
+  @Since("1.4.0")
   def this() = this(Identifiable.randomUID("w2v"))
 
   /** @group setParam */
+  @Since("1.4.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setVectorSize(value: Int): this.type = set(vectorSize, value)
 
   /** @group expertSetParam */
+  @Since("1.6.0")
   def setWindowSize(value: Int): this.type = set(windowSize, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setStepSize(value: Double): this.type = set(stepSize, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setNumPartitions(value: Int): this.type = set(numPartitions, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setMaxIter(value: Int): this.type = set(maxIter, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setSeed(value: Long): this.type = set(seed, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setMinCount(value: Int): this.type = set(minCount, value)
 
   /** @group setParam */
+  @Since("2.0.0")
   def setMaxSentenceLength(value: Int): this.type = set(maxSentenceLength, value)
 
   @Since("2.0.0")
@@ -191,8 +204,9 @@ object Word2Vec extends DefaultParamsReadable[Word2Vec] {
  * Model fitted by [[Word2Vec]].
  */
 @Experimental
+@Since("1.4.0")
 class Word2VecModel private[ml] (
-    override val uid: String,
+    @Since("1.4.0") override val uid: String,
     @transient private val wordVectors: feature.Word2VecModel)
   extends Model[Word2VecModel] with Word2VecBase with MLWritable {
 
@@ -202,6 +216,7 @@ class Word2VecModel private[ml] (
    * Returns a dataframe with two fields, "word" and "vector", with "word" being a String and
    * and the vector the DenseVector that it is mapped to.
    */
+  @Since("1.5.0")
   @transient lazy val getVectors: DataFrame = {
     val spark = SparkSession.builder().getOrCreate()
     val wordVec = wordVectors.getVectors.mapValues(vec => Vectors.dense(vec.map(_.toDouble)))
@@ -213,6 +228,7 @@ class Word2VecModel private[ml] (
    * Returns a dataframe with the words and the cosine similarities between the
    * synonyms and the given word.
    */
+  @Since("1.5.0")
   def findSynonyms(word: String, num: Int): DataFrame = {
     findSynonyms(wordVectors.transform(word), num)
   }
@@ -222,15 +238,18 @@ class Word2VecModel private[ml] (
    * of the word. Returns a dataframe with the words and the cosine similarities between the
    * synonyms and the given word vector.
    */
+  @Since("1.5.0")
   def findSynonyms(word: Vector, num: Int): DataFrame = {
     val spark = SparkSession.builder().getOrCreate()
     spark.createDataFrame(wordVectors.findSynonyms(word, num)).toDF("word", "similarity")
   }
 
   /** @group setParam */
+  @Since("1.4.0")
   def setInputCol(value: String): this.type = set(inputCol, value)
 
   /** @group setParam */
+  @Since("1.4.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
   /**
diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py
index a28764a7528dc..1b9b2b9465a0f 100755
--- a/python/pyspark/ml/feature.py
+++ b/python/pyspark/ml/feature.py
@@ -149,7 +149,7 @@ class Bucketizer(JavaTransformer, HasInputCol, HasOutputCol, JavaMLReadable, Jav
     >>> loadedBucketizer.getSplits() == bucketizer.getSplits()
     True
 
-    .. versionadded:: 1.3.0
+    .. versionadded:: 1.4.0
     """
 
     splits = \

From 86766a9ed79f6d7df59dad53c1f22f568a77d00a Mon Sep 17 00:00:00 2001
From: Nick Pentreath <nickp@za.ibm.com>
Date: Mon, 13 Jun 2016 13:53:00 +0200
Subject: [PATCH 2/6] Fix 'uid' contstructor annotations

---
 .../scala/org/apache/spark/ml/feature/StandardScaler.scala    | 2 +-
 .../main/scala/org/apache/spark/ml/feature/Tokenizer.scala    | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
index aab24ae692831..6e175ae4528fb 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
@@ -86,7 +86,7 @@ private[feature] trait StandardScalerParams extends Params with HasInputCol with
  */
 @Experimental
 @Since("1.2.0")
-class StandardScaler @Since("1.2.0") (
+class StandardScaler @Since("1.4.0") (
     @Since("1.4.0") override val uid: String)
   extends Estimator[StandardScalerModel] with StandardScalerParams with DefaultParamsWritable {
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala
index 64ac592397cea..ff98341a6f683 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala
@@ -31,10 +31,10 @@ import org.apache.spark.sql.types.{ArrayType, DataType, StringType}
  */
 @Experimental
 @Since("1.2.0")
-class Tokenizer @Since("1.2.0") (@Since("1.4.0") override val uid: String)
+class Tokenizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
   extends UnaryTransformer[String, Seq[String], Tokenizer] with DefaultParamsWritable {
 
-  @Since("1.4.0")
+  @Since("1.2.0")
   def this() = this(Identifiable.randomUID("tok"))
 
   override protected def createTransformFunc: String => Seq[String] = {

From 86ab82b97d386bf8e1356640e2fb3e1a80d68014 Mon Sep 17 00:00:00 2001
From: Nick Pentreath <nickp@za.ibm.com>
Date: Fri, 17 Jun 2016 10:14:11 +0200
Subject: [PATCH 3/6] Add annotations for param vals

---
 .../main/scala/org/apache/spark/ml/feature/Binarizer.scala    | 1 +
 .../main/scala/org/apache/spark/ml/feature/Bucketizer.scala   | 1 +
 mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala    | 1 +
 .../org/apache/spark/ml/feature/ElementwiseProduct.scala      | 1 +
 .../main/scala/org/apache/spark/ml/feature/HashingTF.scala    | 2 ++
 mllib/src/main/scala/org/apache/spark/ml/feature/NGram.scala  | 1 +
 .../main/scala/org/apache/spark/ml/feature/Normalizer.scala   | 1 +
 .../scala/org/apache/spark/ml/feature/OneHotEncoder.scala     | 1 +
 .../org/apache/spark/ml/feature/PolynomialExpansion.scala     | 1 +
 .../src/main/scala/org/apache/spark/ml/feature/RFormula.scala | 1 +
 .../scala/org/apache/spark/ml/feature/StopWordsRemover.scala  | 2 ++
 .../scala/org/apache/spark/ml/feature/StringIndexer.scala     | 1 +
 .../main/scala/org/apache/spark/ml/feature/Tokenizer.scala    | 4 ++++
 .../main/scala/org/apache/spark/ml/feature/VectorSlicer.scala | 2 ++
 14 files changed, 20 insertions(+)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala
index a9156a44a99ce..9867c6f355a0a 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala
@@ -49,6 +49,7 @@ final class Binarizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
    * Default: 0.0
    * @group param
    */
+  @Since("1.4.0")
   val threshold: DoubleParam =
     new DoubleParam(this, "threshold", "threshold used to binarize continuous features")
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala
index 2310659c89276..599bc69c64bcf 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala
@@ -50,6 +50,7 @@ final class Bucketizer @Since("1.4.0") (@Since("1.4.0") override val uid: String
    * otherwise, values outside the splits specified will be treated as errors.
    * @group param
    */
+  @Since("1.4.0")
   val splits: DoubleArrayParam = new DoubleArrayParam(this, "splits",
     "Split points for mapping continuous features into buckets. With n+1 splits, there are n " +
       "buckets. A bucket defined by splits x,y holds values in the range [x,y) except the last " +
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala
index 46a3de0926eea..9605145e12c27 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala
@@ -48,6 +48,7 @@ class DCT @Since("1.5.0") (@Since("1.5.0") override val uid: String)
    * Default: false
    * @group param
    */
+  @Since("1.5.0")
   def inverse: BooleanParam = new BooleanParam(
     this, "inverse", "Set transformer to perform inverse DCT")
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
index abef6c0990ea9..c018679a112c9 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
@@ -44,6 +44,7 @@ class ElementwiseProduct @Since("1.4.0") (@Since("1.4.0") override val uid: Stri
    * the vector to multiply with input vectors
    * @group param
    */
+  @Since("1.4.0")
   val scalingVec: Param[Vector] = new Param(this, "scalingVec", "vector for hadamard product")
 
   /** @group setParam */
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala
index 269510b5c6cb4..cb9ec3cc87d8e 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala
@@ -58,6 +58,7 @@ class HashingTF @Since("1.4.0") (@Since("1.4.0") override val uid: String)
    * (default = 2^18^)
    * @group param
    */
+  @Since("1.2.0")
   val numFeatures = new IntParam(this, "numFeatures", "number of features (> 0)",
     ParamValidators.gt(0))
 
@@ -68,6 +69,7 @@ class HashingTF @Since("1.4.0") (@Since("1.4.0") override val uid: String)
    * (default = false)
    * @group param
    */
+  @Since("2.0.0")
   val binary = new BooleanParam(this, "binary", "If true, all non zero counts are set to 1. " +
     "This is useful for discrete probabilistic models that model binary events rather " +
     "than integer counts")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/NGram.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/NGram.scala
index 0b8d8c6146528..9c1f1ad443bba 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/NGram.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/NGram.scala
@@ -47,6 +47,7 @@ class NGram @Since("1.5.0") (@Since("1.5.0") override val uid: String)
    * Default: 2, bigram features
    * @group param
    */
+  @Since("1.5.0")
   val n: IntParam = new IntParam(this, "n", "number elements per n-gram (>=1)",
     ParamValidators.gtEq(1))
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala
index 2f650e5c70a7c..f9cbad90c9f3f 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala
@@ -43,6 +43,7 @@ class Normalizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
    * (default: p = 2)
    * @group param
    */
+  @Since("1.4.0")
   val p = new DoubleParam(this, "p", "the p norm value", ParamValidators.gtEq(1))
 
   setDefault(p -> 2.0)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala
index 4f2e826505be4..63ed92e04bec7 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala
@@ -54,6 +54,7 @@ class OneHotEncoder @Since("1.4.0") (@Since("1.4.0") override val uid: String) e
    * Whether to drop the last category in the encoded vector (default: true)
    * @group param
    */
+  @Since("1.4.0")
   final val dropLast: BooleanParam =
     new BooleanParam(this, "dropLast", "whether to drop the last category")
   setDefault(dropLast -> true)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala
index 284dfb36e050a..0185cdda40f88 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala
@@ -47,6 +47,7 @@ class PolynomialExpansion @Since("1.4.0") (@Since("1.4.0") override val uid: Str
    * Default: 2
    * @group param
    */
+  @Since("1.4.0")
   val degree = new IntParam(this, "degree", "the polynomial degree to expand (>= 1)",
     ParamValidators.gtEq(1))
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
index 085a83f103869..8df5567bf77b4 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
@@ -81,6 +81,7 @@ class RFormula @Since("1.5.0") (@Since("1.5.0") override val uid: String)
    * R formula parameter. The formula is provided in string form.
    * @group param
    */
+  @Since("1.5.0")
   val formula: Param[String] = new Param(this, "formula", "R model formula")
 
   /**
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
index 1f111ccab8fc5..b69383ef57643 100755
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
@@ -54,6 +54,7 @@ class StopWordsRemover @Since("1.5.0") (@Since("1.5.0") override val uid: String
    * @see [[StopWordsRemover.loadDefaultStopWords()]]
    * @group param
    */
+  @Since("1.5.0")
   val stopWords: StringArrayParam =
     new StringArrayParam(this, "stopWords", "the words to be filtered out")
 
@@ -70,6 +71,7 @@ class StopWordsRemover @Since("1.5.0") (@Since("1.5.0") override val uid: String
    * Default: false
    * @group param
    */
+  @Since("1.5.0")
   val caseSensitive: BooleanParam = new BooleanParam(this, "caseSensitive",
     "whether to do a case-sensitive comparison over the stop words")
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
index c7931c50f2cdf..79de67a4a2e3c 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
@@ -281,6 +281,7 @@ class IndexToString private[ml] (@Since("1.5.0") override val uid: String)
    * Default: Not specified, in which case [[inputCol]] metadata is used for labels.
    * @group param
    */
+  @Since("1.5.0")
   final val labels: StringArrayParam = new StringArrayParam(this, "labels",
     "Optional array of labels specifying index-string mapping." +
       " If not provided or if empty, then metadata from inputCol is used instead.")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala
index ff98341a6f683..7b4305a222ce1 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala
@@ -77,6 +77,7 @@ class RegexTokenizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
    * Default: 1, to avoid returning empty strings
    * @group param
    */
+  @Since("1.4.0")
   val minTokenLength: IntParam = new IntParam(this, "minTokenLength", "minimum token length (>= 0)",
     ParamValidators.gtEq(0))
 
@@ -93,6 +94,7 @@ class RegexTokenizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
    * Default: true
    * @group param
    */
+  @Since("1.4.0")
   val gaps: BooleanParam = new BooleanParam(this, "gaps", "Set regex to match gaps or tokens")
 
   /** @group setParam */
@@ -108,6 +110,7 @@ class RegexTokenizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
    * Default: `"\\s+"`
    * @group param
    */
+  @Since("1.4.0")
   val pattern: Param[String] = new Param(this, "pattern", "regex pattern used for tokenizing")
 
   /** @group setParam */
@@ -123,6 +126,7 @@ class RegexTokenizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
    * Default: true
    * @group param
    */
+  @Since("1.6.0")
   final val toLowercase: BooleanParam = new BooleanParam(this, "toLowercase",
     "whether to convert all characters to lowercase before tokenizing.")
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala
index 78902e72893fc..862c7f0d8f2f9 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala
@@ -54,6 +54,7 @@ final class VectorSlicer @Since("1.5.0") (@Since("1.5.0") override val uid: Stri
    * Default: Empty array
    * @group param
    */
+  @Since("1.5.0")
   val indices = new IntArrayParam(this, "indices",
     "An array of indices to select features from a vector column." +
       " There can be no overlap with names.", VectorSlicer.validIndices)
@@ -75,6 +76,7 @@ final class VectorSlicer @Since("1.5.0") (@Since("1.5.0") override val uid: Stri
    * Default: Empty Array
    * @group param
    */
+  @Since("1.5.0")
   val names = new StringArrayParam(this, "names",
     "An array of feature names to select features from a vector column." +
       " There can be no overlap with indices.", VectorSlicer.validNames)

From 2fc676aafd8d5ceaa37cfae01cbd42ee41836fd2 Mon Sep 17 00:00:00 2001
From: Nick Pentreath <nickp@za.ibm.com>
Date: Fri, 17 Jun 2016 11:13:20 +0200
Subject: [PATCH 4/6] Fix annotations for save/load for max abs scaler

---
 .../scala/org/apache/spark/ml/feature/MaxAbsScaler.scala    | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala
index 006d6413cbeb6..261d45d7a82a8 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala
@@ -94,7 +94,7 @@ class MaxAbsScaler @Since("2.0.0") (@Since("2.0.0") override val uid: String)
 @Since("2.0.0")
 object MaxAbsScaler extends DefaultParamsReadable[MaxAbsScaler] {
 
-  @Since("1.6.0")
+  @Since("2.0.0")
   override def load(path: String): MaxAbsScaler = super.load(path)
 }
 
@@ -177,9 +177,9 @@ object MaxAbsScalerModel extends MLReadable[MaxAbsScalerModel] {
     }
   }
 
-  @Since("1.6.0")
+  @Since("2.0.0")
   override def read: MLReader[MaxAbsScalerModel] = new MaxAbsScalerModelReader
 
-  @Since("1.6.0")
+  @Since("2.0.0")
   override def load(path: String): MaxAbsScalerModel = super.load(path)
 }

From 8c24513b4e3179fa9773573e7513c6112faea4f9 Mon Sep 17 00:00:00 2001
From: Nick Pentreath <nickp@za.ibm.com>
Date: Fri, 17 Jun 2016 11:45:20 +0200
Subject: [PATCH 5/6] Add annotations for 'transformSchema' and 'copy'

---
 .../main/scala/org/apache/spark/ml/feature/Binarizer.scala  | 2 ++
 .../main/scala/org/apache/spark/ml/feature/Bucketizer.scala | 2 ++
 .../scala/org/apache/spark/ml/feature/ChiSqSelector.scala   | 4 ++++
 .../scala/org/apache/spark/ml/feature/CountVectorizer.scala | 4 ++++
 .../main/scala/org/apache/spark/ml/feature/HashingTF.scala  | 2 ++
 mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala  | 4 ++++
 .../scala/org/apache/spark/ml/feature/MaxAbsScaler.scala    | 4 ++++
 .../scala/org/apache/spark/ml/feature/MinMaxScaler.scala    | 4 ++++
 .../scala/org/apache/spark/ml/feature/OneHotEncoder.scala   | 2 ++
 mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala  | 4 ++++
 .../org/apache/spark/ml/feature/PolynomialExpansion.scala   | 1 +
 .../org/apache/spark/ml/feature/QuantileDiscretizer.scala   | 2 ++
 .../main/scala/org/apache/spark/ml/feature/RFormula.scala   | 6 ++++++
 .../scala/org/apache/spark/ml/feature/StandardScaler.scala  | 4 ++++
 .../org/apache/spark/ml/feature/StopWordsRemover.scala      | 2 ++
 .../scala/org/apache/spark/ml/feature/StringIndexer.scala   | 6 ++++++
 .../main/scala/org/apache/spark/ml/feature/Tokenizer.scala  | 2 ++
 .../scala/org/apache/spark/ml/feature/VectorAssembler.scala | 2 ++
 .../scala/org/apache/spark/ml/feature/VectorIndexer.scala   | 4 ++++
 .../scala/org/apache/spark/ml/feature/VectorSlicer.scala    | 2 ++
 .../main/scala/org/apache/spark/ml/feature/Word2Vec.scala   | 4 ++++
 21 files changed, 67 insertions(+)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala
index 9867c6f355a0a..fa9634fdfa7e9 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Binarizer.scala
@@ -103,6 +103,7 @@ final class Binarizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
     }
   }
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     val inputType = schema($(inputCol)).dataType
     val outputColName = $(outputCol)
@@ -122,6 +123,7 @@ final class Binarizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
     StructType(schema.fields :+ outCol)
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): Binarizer = defaultCopy(extra)
 }
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala
index 599bc69c64bcf..caffc39e2be14 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala
@@ -93,11 +93,13 @@ final class Bucketizer @Since("1.4.0") (@Since("1.4.0") override val uid: String
     attr.toStructField()
   }
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     SchemaUtils.checkColumnType(schema, $(inputCol), DoubleType)
     SchemaUtils.appendColumn(schema, prepOutputField(schema))
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): Bucketizer = {
     defaultCopy[Bucketizer](extra).setParent(parent)
   }
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala
index c7c6926e95e24..1c329267d70d8 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala
@@ -97,12 +97,14 @@ final class ChiSqSelector @Since("1.6.0") (@Since("1.6.0") override val uid: Str
     copyValues(new ChiSqSelectorModel(uid, chiSqSelector).setParent(this))
   }
 
+  @Since("1.6.0")
   override def transformSchema(schema: StructType): StructType = {
     SchemaUtils.checkColumnType(schema, $(featuresCol), new VectorUDT)
     SchemaUtils.checkNumericType(schema, $(labelCol))
     SchemaUtils.appendColumn(schema, $(outputCol), new VectorUDT)
   }
 
+  @Since("1.6.0")
   override def copy(extra: ParamMap): ChiSqSelector = defaultCopy(extra)
 }
 
@@ -154,6 +156,7 @@ final class ChiSqSelectorModel private[ml] (
     dataset.withColumn($(outputCol), selector(col($(featuresCol))), newField.metadata)
   }
 
+  @Since("1.6.0")
   override def transformSchema(schema: StructType): StructType = {
     SchemaUtils.checkColumnType(schema, $(featuresCol), new VectorUDT)
     val newField = prepOutputField(schema)
@@ -176,6 +179,7 @@ final class ChiSqSelectorModel private[ml] (
     newAttributeGroup.toStructField()
   }
 
+  @Since("1.6.0")
   override def copy(extra: ParamMap): ChiSqSelectorModel = {
     val copied = new ChiSqSelectorModel(uid, chiSqSelector)
     copyValues(copied, extra).setParent(parent)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala
index 1c217512be99a..3250fe55980d0 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala
@@ -184,10 +184,12 @@ class CountVectorizer @Since("1.5.0") (@Since("1.5.0") override val uid: String)
     copyValues(new CountVectorizerModel(uid, vocab).setParent(this))
   }
 
+  @Since("1.5.0")
   override def transformSchema(schema: StructType): StructType = {
     validateAndTransformSchema(schema)
   }
 
+  @Since("1.5.0")
   override def copy(extra: ParamMap): CountVectorizer = defaultCopy(extra)
 }
 
@@ -268,10 +270,12 @@ class CountVectorizerModel(
     dataset.withColumn($(outputCol), vectorizer(col($(inputCol))))
   }
 
+  @Since("1.5.0")
   override def transformSchema(schema: StructType): StructType = {
     validateAndTransformSchema(schema)
   }
 
+  @Since("1.5.0")
   override def copy(extra: ParamMap): CountVectorizerModel = {
     val copied = new CountVectorizerModel(uid, vocabulary).setParent(parent)
     copyValues(copied, extra)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala
index cb9ec3cc87d8e..6ca7336cd048e 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/HashingTF.scala
@@ -102,6 +102,7 @@ class HashingTF @Since("1.4.0") (@Since("1.4.0") override val uid: String)
     dataset.select(col("*"), t(col($(inputCol))).as($(outputCol), metadata))
   }
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     val inputType = schema($(inputCol)).dataType
     require(inputType.isInstanceOf[ArrayType],
@@ -110,6 +111,7 @@ class HashingTF @Since("1.4.0") (@Since("1.4.0") override val uid: String)
     SchemaUtils.appendColumn(schema, attrGroup.toStructField())
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): HashingTF = defaultCopy(extra)
 }
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
index 38d0da1c1d7fa..680f55be26a8d 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
@@ -93,10 +93,12 @@ final class IDF @Since("1.4.0") (@Since("1.4.0") override val uid: String)
     copyValues(new IDFModel(uid, idf).setParent(this))
   }
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     validateAndTransformSchema(schema)
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): IDF = defaultCopy(extra)
 }
 
@@ -136,10 +138,12 @@ class IDFModel private[ml] (
     dataset.withColumn($(outputCol), idf(col($(inputCol))))
   }
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     validateAndTransformSchema(schema)
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): IDFModel = {
     val copied = new IDFModel(uid, idfModel)
     copyValues(copied, extra).setParent(parent)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala
index 261d45d7a82a8..31a58152671cd 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/MaxAbsScaler.scala
@@ -84,10 +84,12 @@ class MaxAbsScaler @Since("2.0.0") (@Since("2.0.0") override val uid: String)
     copyValues(new MaxAbsScalerModel(uid, Vectors.dense(maxAbs)).setParent(this))
   }
 
+  @Since("2.0.0")
   override def transformSchema(schema: StructType): StructType = {
     validateAndTransformSchema(schema)
   }
 
+  @Since("2.0.0")
   override def copy(extra: ParamMap): MaxAbsScaler = defaultCopy(extra)
 }
 
@@ -132,10 +134,12 @@ class MaxAbsScalerModel private[ml] (
     dataset.withColumn($(outputCol), reScale(col($(inputCol))))
   }
 
+  @Since("2.0.0")
   override def transformSchema(schema: StructType): StructType = {
     validateAndTransformSchema(schema)
   }
 
+  @Since("2.0.0")
   override def copy(extra: ParamMap): MaxAbsScalerModel = {
     val copied = new MaxAbsScalerModel(uid, maxAbs)
     copyValues(copied, extra).setParent(parent)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
index 0260c9d6f13aa..9d6361726652b 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
@@ -120,10 +120,12 @@ class MinMaxScaler @Since("1.5.0") (@Since("1.5.0") override val uid: String)
     copyValues(new MinMaxScalerModel(uid, summary.min, summary.max).setParent(this))
   }
 
+  @Since("1.5.0")
   override def transformSchema(schema: StructType): StructType = {
     validateAndTransformSchema(schema)
   }
 
+  @Since("1.5.0")
   override def copy(extra: ParamMap): MinMaxScaler = defaultCopy(extra)
 }
 
@@ -192,10 +194,12 @@ class MinMaxScalerModel private[ml] (
     dataset.withColumn($(outputCol), reScale(col($(inputCol))))
   }
 
+  @Since("1.5.0")
   override def transformSchema(schema: StructType): StructType = {
     validateAndTransformSchema(schema)
   }
 
+  @Since("1.5.0")
   override def copy(extra: ParamMap): MinMaxScalerModel = {
     val copied = new MinMaxScalerModel(uid, originalMin, originalMax)
     copyValues(copied, extra).setParent(parent)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala
index 63ed92e04bec7..4fafc1e349c22 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoder.scala
@@ -71,6 +71,7 @@ class OneHotEncoder @Since("1.4.0") (@Since("1.4.0") override val uid: String) e
   @Since("1.4.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     val inputColName = $(inputCol)
     val outputColName = $(outputCol)
@@ -174,6 +175,7 @@ class OneHotEncoder @Since("1.4.0") (@Since("1.4.0") override val uid: String) e
     dataset.select(col("*"), encode(col(inputColName).cast(DoubleType)).as(outputColName, metadata))
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): OneHotEncoder = defaultCopy(extra)
 }
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
index 479f49b0abaf4..130e3586e263d 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
@@ -99,10 +99,12 @@ class PCA @Since("1.5.0") (
     copyValues(new PCAModel(uid, pcaModel.pc, pcaModel.explainedVariance).setParent(this))
   }
 
+  @Since("1.5.0")
   override def transformSchema(schema: StructType): StructType = {
     validateAndTransformSchema(schema)
   }
 
+  @Since("1.5.0")
   override def copy(extra: ParamMap): PCA = defaultCopy(extra)
 }
 
@@ -158,10 +160,12 @@ class PCAModel private[ml] (
     dataset.withColumn($(outputCol), pcaOp(col($(inputCol))))
   }
 
+  @Since("1.5.0")
   override def transformSchema(schema: StructType): StructType = {
     validateAndTransformSchema(schema)
   }
 
+  @Since("1.5.0")
   override def copy(extra: ParamMap): PCAModel = {
     val copied = new PCAModel(uid, pc, explainedVariance)
     copyValues(copied, extra).setParent(parent)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala
index 0185cdda40f88..7b35fdeaf40c6 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala
@@ -67,6 +67,7 @@ class PolynomialExpansion @Since("1.4.0") (@Since("1.4.0") override val uid: Str
 
   override protected def outputDataType: DataType = new VectorUDT()
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): PolynomialExpansion = defaultCopy(extra)
 }
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
index 50ac9a7e76128..96b8e7d9f7faf 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/QuantileDiscretizer.scala
@@ -97,6 +97,7 @@ final class QuantileDiscretizer @Since("1.6.0") (@Since("1.6.0") override val ui
   @Since("1.6.0")
   def setOutputCol(value: String): this.type = set(outputCol, value)
 
+  @Since("1.6.0")
   override def transformSchema(schema: StructType): StructType = {
     SchemaUtils.checkColumnType(schema, $(inputCol), DoubleType)
     val inputFields = schema.fields
@@ -118,6 +119,7 @@ final class QuantileDiscretizer @Since("1.6.0") (@Since("1.6.0") override val ui
     copyValues(bucketizer.setParent(this))
   }
 
+  @Since("1.6.0")
   override def copy(extra: ParamMap): QuantileDiscretizer = defaultCopy(extra)
 }
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
index 8df5567bf77b4..546dc7e8c08ff 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
@@ -177,6 +177,7 @@ class RFormula @Since("1.5.0") (@Since("1.5.0") override val uid: String)
     copyValues(new RFormulaModel(uid, resolvedFormula, pipelineModel).setParent(this))
   }
 
+  @Since("1.5.0")
   // optimistic schema; does not contain any ML attributes
   override def transformSchema(schema: StructType): StructType = {
     if (hasLabelCol(schema)) {
@@ -187,8 +188,10 @@ class RFormula @Since("1.5.0") (@Since("1.5.0") override val uid: String)
     }
   }
 
+  @Since("1.5.0")
   override def copy(extra: ParamMap): RFormula = defaultCopy(extra)
 
+  @Since("2.0.0")
   override def toString: String = s"RFormula(${get(formula).getOrElse("")}) (uid=$uid)"
 }
 
@@ -221,6 +224,7 @@ class RFormulaModel private[feature](
     transformLabel(pipelineModel.transform(dataset))
   }
 
+  @Since("1.5.0")
   override def transformSchema(schema: StructType): StructType = {
     checkCanTransform(schema)
     val withFeatures = pipelineModel.transformSchema(schema)
@@ -239,9 +243,11 @@ class RFormulaModel private[feature](
     }
   }
 
+  @Since("1.5.0")
   override def copy(extra: ParamMap): RFormulaModel = copyValues(
     new RFormulaModel(uid, resolvedFormula, pipelineModel))
 
+  @Since("2.0.0")
   override def toString: String = s"RFormulaModel($resolvedFormula) (uid=$uid)"
 
   private def transformLabel(dataset: Dataset[_]): DataFrame = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
index 6e175ae4528fb..dcb871131b7b8 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
@@ -120,10 +120,12 @@ class StandardScaler @Since("1.4.0") (
     copyValues(new StandardScalerModel(uid, scalerModel.std, scalerModel.mean).setParent(this))
   }
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     validateAndTransformSchema(schema)
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): StandardScaler = defaultCopy(extra)
 }
 
@@ -171,10 +173,12 @@ class StandardScalerModel private[ml] (
     dataset.withColumn($(outputCol), scale(col($(inputCol))))
   }
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     validateAndTransformSchema(schema)
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): StandardScalerModel = {
     val copied = new StandardScalerModel(uid, std, mean)
     copyValues(copied, extra).setParent(parent)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
index b69383ef57643..1a6f42f773cd7 100755
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StopWordsRemover.scala
@@ -105,6 +105,7 @@ class StopWordsRemover @Since("1.5.0") (@Since("1.5.0") override val uid: String
     dataset.select(col("*"), t(col($(inputCol))).as($(outputCol), metadata))
   }
 
+  @Since("1.5.0")
   override def transformSchema(schema: StructType): StructType = {
     val inputType = schema($(inputCol)).dataType
     require(inputType.sameType(ArrayType(StringType)),
@@ -112,6 +113,7 @@ class StopWordsRemover @Since("1.5.0") (@Since("1.5.0") override val uid: String
     SchemaUtils.appendColumn(schema, $(outputCol), inputType, schema($(inputCol)).nullable)
   }
 
+  @Since("1.5.0")
   override def copy(extra: ParamMap): StopWordsRemover = defaultCopy(extra)
 }
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
index 79de67a4a2e3c..0f7337ce6b554 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StringIndexer.scala
@@ -95,10 +95,12 @@ class StringIndexer @Since("1.4.0") (
     copyValues(new StringIndexerModel(uid, labels).setParent(this))
   }
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     validateAndTransformSchema(schema)
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): StringIndexer = defaultCopy(extra)
 }
 
@@ -187,6 +189,7 @@ class StringIndexerModel (
       indexer(dataset($(inputCol)).cast(StringType)).as($(outputCol), metadata))
   }
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     if (schema.fieldNames.contains($(inputCol))) {
       validateAndTransformSchema(schema)
@@ -196,6 +199,7 @@ class StringIndexerModel (
     }
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): StringIndexerModel = {
     val copied = new StringIndexerModel(uid, labels)
     copyValues(copied, extra).setParent(parent)
@@ -290,6 +294,7 @@ class IndexToString private[ml] (@Since("1.5.0") override val uid: String)
   @Since("1.5.0")
   final def getLabels: Array[String] = $(labels)
 
+  @Since("1.5.0")
   override def transformSchema(schema: StructType): StructType = {
     val inputColName = $(inputCol)
     val inputDataType = schema(inputColName).dataType
@@ -327,6 +332,7 @@ class IndexToString private[ml] (@Since("1.5.0") override val uid: String)
       indexer(dataset($(inputCol)).cast(DoubleType)).as(outputColName))
   }
 
+  @Since("1.5.0")
   override def copy(extra: ParamMap): IndexToString = {
     defaultCopy(extra)
   }
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala
index 7b4305a222ce1..010c948749f3b 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala
@@ -47,6 +47,7 @@ class Tokenizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
 
   override protected def outputDataType: DataType = new ArrayType(StringType, true)
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): Tokenizer = defaultCopy(extra)
 }
 
@@ -154,6 +155,7 @@ class RegexTokenizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
 
   override protected def outputDataType: DataType = new ArrayType(StringType, true)
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): RegexTokenizer = defaultCopy(extra)
 }
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala
index f5dd26f712a03..4939dabd987ec 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorAssembler.scala
@@ -110,6 +110,7 @@ class VectorAssembler @Since("1.4.0") (@Since("1.4.0") override val uid: String)
     dataset.select(col("*"), assembleFunc(struct(args: _*)).as($(outputCol), metadata))
   }
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     val inputColNames = $(inputCols)
     val outputColName = $(outputCol)
@@ -126,6 +127,7 @@ class VectorAssembler @Since("1.4.0") (@Since("1.4.0") override val uid: String)
     StructType(schema.fields :+ new StructField(outputColName, new VectorUDT, true))
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): VectorAssembler = defaultCopy(extra)
 }
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala
index aae71d759eca6..52db996c841b3 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorIndexer.scala
@@ -132,6 +132,7 @@ class VectorIndexer @Since("1.4.0") (
     copyValues(model)
   }
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     // We do not transfer feature metadata since we do not know what types of features we will
     // produce in transform().
@@ -142,6 +143,7 @@ class VectorIndexer @Since("1.4.0") (
     SchemaUtils.appendColumn(schema, $(outputCol), dataType)
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): VectorIndexer = defaultCopy(extra)
 }
 
@@ -366,6 +368,7 @@ class VectorIndexerModel private[ml] (
     dataset.withColumn($(outputCol), newCol, newField.metadata)
   }
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     val dataType = new VectorUDT
     require(isDefined(inputCol),
@@ -425,6 +428,7 @@ class VectorIndexerModel private[ml] (
     newAttributeGroup.toStructField()
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): VectorIndexerModel = {
     val copied = new VectorIndexerModel(uid, numFeatures, categoryMaps)
     copyValues(copied, extra).setParent(parent)
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala
index 862c7f0d8f2f9..6769e490c51c7 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/VectorSlicer.scala
@@ -144,6 +144,7 @@ final class VectorSlicer @Since("1.5.0") (@Since("1.5.0") override val uid: Stri
     indFeatures ++ nameFeatures
   }
 
+  @Since("1.5.0")
   override def transformSchema(schema: StructType): StructType = {
     require($(indices).length > 0 || $(names).length > 0,
       s"VectorSlicer requires that at least one feature be selected.")
@@ -158,6 +159,7 @@ final class VectorSlicer @Since("1.5.0") (@Since("1.5.0") override val uid: Stri
     StructType(outputFields)
   }
 
+  @Since("1.5.0")
   override def copy(extra: ParamMap): VectorSlicer = defaultCopy(extra)
 }
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
index 803ff4202b0a5..05c4f2f1a7891 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Word2Vec.scala
@@ -185,10 +185,12 @@ final class Word2Vec @Since("1.4.0") (
     copyValues(new Word2VecModel(uid, wordVectors).setParent(this))
   }
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     validateAndTransformSchema(schema)
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): Word2Vec = defaultCopy(extra)
 }
 
@@ -281,10 +283,12 @@ class Word2VecModel private[ml] (
     dataset.withColumn($(outputCol), word2Vec(col($(inputCol))))
   }
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     validateAndTransformSchema(schema)
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): Word2VecModel = {
     val copied = new Word2VecModel(uid, wordVectors)
     copyValues(copied, extra).setParent(parent)

From 34b5f37d4a111a80c622fb7244ef54220e9167fd Mon Sep 17 00:00:00 2001
From: Nick Pentreath <nickp@za.ibm.com>
Date: Mon, 20 Jun 2016 10:16:17 +0200
Subject: [PATCH 6/6] Anything with new ml.linalg is since 2.0.0

---
 .../apache/spark/ml/feature/ElementwiseProduct.scala | 12 ++++++------
 .../main/scala/org/apache/spark/ml/feature/IDF.scala |  2 +-
 .../org/apache/spark/ml/feature/MinMaxScaler.scala   |  4 ++--
 .../org/apache/spark/ml/feature/Normalizer.scala     | 12 ++++++------
 .../main/scala/org/apache/spark/ml/feature/PCA.scala |  2 +-
 .../spark/ml/feature/PolynomialExpansion.scala       | 12 ++++++------
 .../org/apache/spark/ml/feature/StandardScaler.scala |  4 ++--
 python/pyspark/ml/feature.py                         |  8 ++++----
 8 files changed, 28 insertions(+), 28 deletions(-)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
index c018679a112c9..92fefb1e6c0f3 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala
@@ -33,26 +33,26 @@ import org.apache.spark.sql.types.DataType
  * multiplier.
  */
 @Experimental
-@Since("1.4.0")
-class ElementwiseProduct @Since("1.4.0") (@Since("1.4.0") override val uid: String)
+@Since("2.0.0")
+class ElementwiseProduct @Since("2.0.0") (@Since("2.0.0") override val uid: String)
   extends UnaryTransformer[Vector, Vector, ElementwiseProduct] with DefaultParamsWritable {
 
-  @Since("1.4.0")
+  @Since("2.0.0")
   def this() = this(Identifiable.randomUID("elemProd"))
 
   /**
    * the vector to multiply with input vectors
    * @group param
    */
-  @Since("1.4.0")
+  @Since("2.0.0")
   val scalingVec: Param[Vector] = new Param(this, "scalingVec", "vector for hadamard product")
 
   /** @group setParam */
-  @Since("1.4.0")
+  @Since("2.0.0")
   def setScalingVec(value: Vector): this.type = set(scalingVec, value)
 
   /** @group getParam */
-  @Since("1.4.0")
+  @Since("2.0.0")
   def getScalingVec: Vector = getOrDefault(scalingVec)
 
   override protected def createTransformFunc: Vector => Vector = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
index 680f55be26a8d..cf03a2845ced5 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/IDF.scala
@@ -150,7 +150,7 @@ class IDFModel private[ml] (
   }
 
   /** Returns the IDF vector. */
-  @Since("1.6.0")
+  @Since("2.0.0")
   def idf: Vector = idfModel.idf.asML
 
   @Since("1.6.0")
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
index 9d6361726652b..dd5a1f9b41fc8 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
@@ -149,8 +149,8 @@ object MinMaxScaler extends DefaultParamsReadable[MinMaxScaler] {
 @Since("1.5.0")
 class MinMaxScalerModel private[ml] (
     @Since("1.5.0") override val uid: String,
-    @Since("1.5.0") val originalMin: Vector,
-    @Since("1.5.0") val originalMax: Vector)
+    @Since("2.0.0") val originalMin: Vector,
+    @Since("2.0.0") val originalMax: Vector)
   extends Model[MinMaxScalerModel] with MinMaxScalerParams with MLWritable {
 
   import MinMaxScalerModel._
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala
index f9cbad90c9f3f..9a4e682890f12 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/Normalizer.scala
@@ -31,11 +31,11 @@ import org.apache.spark.sql.types.DataType
  * Normalize a vector to have unit norm using the given p-norm.
  */
 @Experimental
-@Since("1.4.0")
-class Normalizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
+@Since("2.0.0")
+class Normalizer @Since("2.0.0") (@Since("2.0.0") override val uid: String)
   extends UnaryTransformer[Vector, Vector, Normalizer] with DefaultParamsWritable {
 
-  @Since("1.4.0")
+  @Since("2.0.0")
   def this() = this(Identifiable.randomUID("normalizer"))
 
   /**
@@ -43,17 +43,17 @@ class Normalizer @Since("1.4.0") (@Since("1.4.0") override val uid: String)
    * (default: p = 2)
    * @group param
    */
-  @Since("1.4.0")
+  @Since("2.0.0")
   val p = new DoubleParam(this, "p", "the p norm value", ParamValidators.gtEq(1))
 
   setDefault(p -> 2.0)
 
   /** @group getParam */
-  @Since("1.4.0")
+  @Since("2.0.0")
   def getP: Double = $(p)
 
   /** @group setParam */
-  @Since("1.4.0")
+  @Since("2.0.0")
   def setP(value: Double): this.type = set(p, value)
 
   override protected def createTransformFunc: Vector => Vector = {
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
index 130e3586e263d..b89c85991f39a 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/PCA.scala
@@ -127,7 +127,7 @@ object PCA extends DefaultParamsReadable[PCA] {
 @Since("1.5.0")
 class PCAModel private[ml] (
     @Since("1.5.0") override val uid: String,
-    @Since("1.6.0") val pc: DenseMatrix,
+    @Since("2.0.0") val pc: DenseMatrix,
     @Since("2.0.0") val explainedVariance: DenseVector)
   extends Model[PCAModel] with PCAParams with MLWritable {
 
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala
index 7b35fdeaf40c6..026014c7d64e3 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/PolynomialExpansion.scala
@@ -35,11 +35,11 @@ import org.apache.spark.sql.types.DataType
  * `(x, y)`, if we want to expand it with degree 2, then we get `(x, x * x, y, x * y, y * y)`.
  */
 @Experimental
-@Since("1.4.0")
-class PolynomialExpansion @Since("1.4.0") (@Since("1.4.0") override val uid: String)
+@Since("2.0.0")
+class PolynomialExpansion @Since("2.0.0") (@Since("2.0.0") override val uid: String)
   extends UnaryTransformer[Vector, Vector, PolynomialExpansion] with DefaultParamsWritable {
 
-  @Since("1.4.0")
+  @Since("2.0.0")
   def this() = this(Identifiable.randomUID("poly"))
 
   /**
@@ -47,18 +47,18 @@ class PolynomialExpansion @Since("1.4.0") (@Since("1.4.0") override val uid: Str
    * Default: 2
    * @group param
    */
-  @Since("1.4.0")
+  @Since("2.0.0")
   val degree = new IntParam(this, "degree", "the polynomial degree to expand (>= 1)",
     ParamValidators.gtEq(1))
 
   setDefault(degree -> 2)
 
   /** @group getParam */
-  @Since("1.4.0")
+  @Since("2.0.0")
   def getDegree: Int = $(degree)
 
   /** @group setParam */
-  @Since("1.4.0")
+  @Since("2.0.0")
   def setDegree(value: Int): this.type = set(degree, value)
 
   override protected def createTransformFunc: Vector => Vector = { v =>
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
index dcb871131b7b8..5e1bacf876caf 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/StandardScaler.scala
@@ -147,8 +147,8 @@ object StandardScaler extends DefaultParamsReadable[StandardScaler] {
 @Since("1.2.0")
 class StandardScalerModel private[ml] (
     @Since("1.4.0") override val uid: String,
-    @Since("1.5.0") val std: Vector,
-    @Since("1.5.0") val mean: Vector)
+    @Since("2.0.0") val std: Vector,
+    @Since("2.0.0") val mean: Vector)
   extends Model[StandardScalerModel] with StandardScalerParams with MLWritable {
 
   import StandardScalerModel._
diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py
index 1b9b2b9465a0f..1e9ec0fbb411c 100755
--- a/python/pyspark/ml/feature.py
+++ b/python/pyspark/ml/feature.py
@@ -486,14 +486,14 @@ def setParams(self, scalingVec=None, inputCol=None, outputCol=None):
         kwargs = self.setParams._input_kwargs
         return self._set(**kwargs)
 
-    @since("1.5.0")
+    @since("2.0.0")
     def setScalingVec(self, value):
         """
         Sets the value of :py:attr:`scalingVec`.
         """
         return self._set(scalingVec=value)
 
-    @since("1.5.0")
+    @since("2.0.0")
     def getScalingVec(self):
         """
         Gets the value of scalingVec or its default value.
@@ -1584,7 +1584,7 @@ class StandardScalerModel(JavaModel, JavaMLReadable, JavaMLWritable):
     """
 
     @property
-    @since("1.5.0")
+    @since("2.0.0")
     def std(self):
         """
         Standard deviation of the StandardScalerModel.
@@ -1592,7 +1592,7 @@ def std(self):
         return self._call_java("std")
 
     @property
-    @since("1.5.0")
+    @since("2.0.0")
     def mean(self):
         """
         Mean of the StandardScalerModel.