[SPARK-10258][DOC][ML] Add @Since annotations to ml.feature

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"))
 
   /**
@@ -47,21 +49,26 @@ final class Binarizer(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")
 
   /** @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")
@@ -96,6 +103,7 @@ final class Binarizer(override val uid: String)
     }
   }
 
+  @Since("1.4.0")
   override def transformSchema(schema: StructType): StructType = {
     val inputType = schema($(inputCol)).dataType
     val outputColName = $(outputCol)
@@ -115,6 +123,7 @@ final class Binarizer(override val uid: String)
     StructType(schema.fields :+ outCol)
   }
 
+  @Since("1.4.1")
   override def copy(extra: ParamMap): Binarizer = defaultCopy(extra)
 }
 

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"))
 
   /**
@@ -48,6 +50,7 @@ final class Bucketizer(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 " +
@@ -57,15 +60,19 @@ 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")
@@ -86,16 +93,19 @@ final class Bucketizer(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)
   }
 }
 
+@Since("1.6.0")
 object Bucketizer extends DefaultParamsReadable[Bucketizer] {
 
   /** We require splits to be of length >= 3 and to be in strictly increasing order. */

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")
@@ -91,12 +97,14 @@ final class ChiSqSelector(override val uid: String)
     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)
 }
 
@@ -112,23 +120,28 @@ 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")
@@ -143,6 +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)
@@ -165,6 +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)

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")
@@ -176,10 +184,12 @@ class CountVectorizer(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)
 }
 
@@ -196,26 +206,34 @@ 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()]] */
@@ -252,10 +270,12 @@ class CountVectorizerModel(override val uid: String, val vocabulary: Array[Strin
     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)

mllib/src/main/scala/org/apache/spark/ml/feature/DCT.scala

@@ -36,23 +36,28 @@ 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"))
 
   /**
    * Indicates whether to perform the inverse DCT (true) or forward DCT (false).
    * Default: false
    * @group param
    */
+  @Since("1.5.0")
   def inverse: BooleanParam = new BooleanParam(
     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)

mllib/src/main/scala/org/apache/spark/ml/feature/ElementwiseProduct.scala

@@ -33,21 +33,26 @@ import org.apache.spark.sql.types.DataType
  * multiplier.
  */
 @Experimental
-class ElementwiseProduct(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("2.0.0")
   def this() = this(Identifiable.randomUID("elemProd"))
 
   /**
    * the vector to multiply with input vectors
    * @group param
    */
+  @Since("2.0.0")
   val scalingVec: Param[Vector] = new Param(this, "scalingVec", "vector for hadamard product")
 
   /** @group setParam */
+  @Since("2.0.0")
   def setScalingVec(value: Vector): this.type = set(scalingVec, value)
 
   /** @group getParam */
+  @Since("2.0.0")
   def getScalingVec: Vector = getOrDefault(scalingVec)
 
   override protected def createTransformFunc: Vector => Vector = {