add Experimental annotation

pdeyhim · Apr 9, 2014 · 6b9f8e2 · 6b9f8e2
1 parent 8773d0d
commit 6b9f8e2
Show file tree

Hide file tree

Showing 15 changed files with 34 additions and 4 deletions.
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala b/mllib/src/main/scala/org/apache/spark/mllib/classification/NaiveBayes.scala
@@ -19,6 +19,7 @@ package org.apache.spark.mllib.classification
 
 import breeze.linalg.{DenseMatrix => BDM, DenseVector => BDV, argmax => brzArgmax, sum => brzSum}
 
+import org.apache.spark.annotation.Experimental
 import org.apache.spark.{Logging, SparkContext}
 import org.apache.spark.SparkContext._
 import org.apache.spark.mllib.linalg.Vector
@@ -36,6 +37,7 @@ import org.apache.spark.rdd.RDD
  * @param theta log of class conditional probabilities, whose dimension is C-by-D,
  *              where D is number of features
  */
+@Experimental
 class NaiveBayesModel(
     val labels: Array[Double],
     val pi: Array[Double],

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala
@@ -21,6 +21,7 @@ import scala.collection.mutable.ArrayBuffer
 
 import breeze.linalg.{DenseVector => BDV, Vector => BV, norm => breezeNorm}
 
+import org.apache.spark.annotation.Experimental
 import org.apache.spark.{Logging, SparkContext}
 import org.apache.spark.SparkContext._
 import org.apache.spark.mllib.linalg.{Vector, Vectors}
@@ -400,6 +401,7 @@ object KMeans {
   /**
    * :: Experimental ::
    */
+  @Experimental
   def main(args: Array[String]) {
     if (args.length < 4) {
       println("Usage: KMeans <master> <input_file> <k> <max_iterations> [<runs>]")

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala b/mllib/src/main/scala/org/apache/spark/mllib/recommendation/ALS.scala
@@ -25,6 +25,7 @@ import scala.util.Sorting
 import com.esotericsoftware.kryo.Kryo
 import org.jblas.{DoubleMatrix, SimpleBlas, Solve}
 
+import org.apache.spark.annotation.Experimental
 import org.apache.spark.broadcast.Broadcast
 import org.apache.spark.{Logging, HashPartitioner, Partitioner, SparkContext, SparkConf}
 import org.apache.spark.storage.StorageLevel
@@ -142,6 +143,7 @@ class ALS private (
    *
    * Sets the constant used in computing confidence in implicit ALS. Default: 1.0.
    */
+  @Experimental
   def setAlpha(alpha: Double): ALS = {
     this.alpha = alpha
     this

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala
@@ -19,6 +19,7 @@ package org.apache.spark.mllib.regression
 
 import breeze.linalg.{DenseVector => BDV, SparseVector => BSV}
 
+import org.apache.spark.annotation.Experimental
 import org.apache.spark.{Logging, SparkException}
 import org.apache.spark.rdd.RDD
 import org.apache.spark.mllib.optimization._
@@ -105,6 +106,7 @@ abstract class GeneralizedLinearAlgorithm[M <: GeneralizedLinearModel]
    *
    * Set if the algorithm should validate data before training. Default true.
    */
+  @Experimental
   def setValidateData(validateData: Boolean): this.type = {
     this.validateData = validateData
     this

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala
@@ -19,6 +19,7 @@ package org.apache.spark.mllib.tree
 
 import scala.util.control.Breaks._
 
+import org.apache.spark.annotation.Experimental
 import org.apache.spark.{Logging, SparkContext}
 import org.apache.spark.SparkContext._
 import org.apache.spark.mllib.regression.LabeledPoint
@@ -41,6 +42,7 @@ import org.apache.spark.mllib.linalg.{Vector, Vectors}
  *                 of algorithm (classification, regression, etc.), feature type (continuous,
  *                 categorical), depth of the tree, quantile calculation strategy, etc.
  */
+@Experimental
 class DecisionTree (private val strategy: Strategy) extends Serializable with Logging {
 
   /**

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala
@@ -17,11 +17,14 @@
 
 package org.apache.spark.mllib.tree.configuration
 
+import org.apache.spark.annotation.Experimental
+
 /**
  * :: Experimental ::
  *
  * Enum to select the algorithm for the decision tree
  */
+@Experimental
 object Algo extends Enumeration {
   type Algo = Value
   val Classification, Regression = Value

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala
@@ -17,11 +17,14 @@
 
 package org.apache.spark.mllib.tree.configuration
 
+import org.apache.spark.annotation.Experimental
+
 /**
  * :: Experimental ::
  *
  * Enum to describe whether a feature is "continuous" or "categorical"
  */
+@Experimental
 object FeatureType extends Enumeration {
   type FeatureType = Value
   val Continuous, Categorical = Value

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala
@@ -17,11 +17,14 @@
 
 package org.apache.spark.mllib.tree.configuration
 
+import org.apache.spark.annotation.Experimental
+
 /**
  * :: Experimental ::
  *
  * Enum for selecting the quantile calculation strategy
  */
+@Experimental
 object QuantileStrategy extends Enumeration {
   type QuantileStrategy = Value
   val Sort, MinMax, ApproxHist = Value

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala
@@ -17,6 +17,7 @@
 
 package org.apache.spark.mllib.tree.configuration
 
+import org.apache.spark.annotation.Experimental
 import org.apache.spark.mllib.tree.impurity.Impurity
 import org.apache.spark.mllib.tree.configuration.Algo._
 import org.apache.spark.mllib.tree.configuration.QuantileStrategy._
@@ -36,6 +37,7 @@ import org.apache.spark.mllib.tree.configuration.QuantileStrategy._
  *                                1, 2, ... , k-1. It's important to note that features are
  *                                zero-indexed.
  */
+@Experimental
 class Strategy (
     val algo: Algo,
     val impurity: Impurity,

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Entropy.scala
@@ -17,14 +17,15 @@
 
 package org.apache.spark.mllib.tree.impurity
 
-import org.apache.spark.annotation.DeveloperApi
+import org.apache.spark.annotation.{DeveloperApi, Experimental}
 
 /**
  * :: Experimental ::
  *
  * Class for calculating [[http://en.wikipedia.org/wiki/Binary_entropy_function entropy]] during
  * binary classification.
  */
+@Experimental
 object Entropy extends Impurity {
 
   private[tree] def log2(x: Double) = scala.math.log(x) / scala.math.log(2)

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala
@@ -17,7 +17,7 @@
 
 package org.apache.spark.mllib.tree.impurity
 
-import org.apache.spark.annotation.DeveloperApi
+import org.apache.spark.annotation.{DeveloperApi, Experimental}
 
 /**
  * :: Experimental ::
@@ -26,6 +26,7 @@ import org.apache.spark.annotation.DeveloperApi
  * [[http://en.wikipedia.org/wiki/Decision_tree_learning#Gini_impurity Gini impurity]]
  * during binary classification.
  */
+@Experimental
 object Gini extends Impurity {
 
   /**

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala
@@ -17,13 +17,14 @@
 
 package org.apache.spark.mllib.tree.impurity
 
-import org.apache.spark.annotation.DeveloperApi
+import org.apache.spark.annotation.{DeveloperApi, Experimental}
 
 /**
  * :: Experimental ::
  *
  * Trait for calculating information gain.
  */
+@Experimental
 trait Impurity extends Serializable {
 
   /**

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Variance.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Variance.scala
@@ -17,13 +17,14 @@
 
 package org.apache.spark.mllib.tree.impurity
 
-import org.apache.spark.annotation.DeveloperApi
+import org.apache.spark.annotation.{DeveloperApi, Experimental}
 
 /**
  * :: Experimental ::
  *
  * Class for calculating variance during regression
  */
+@Experimental
 object Variance extends Impurity {
    override def calculate(c0: Double, c1: Double): Double =
      throw new UnsupportedOperationException("Variance.calculate")

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala
@@ -17,6 +17,7 @@
 
 package org.apache.spark.mllib.tree.model
 
+import org.apache.spark.annotation.Experimental
 import org.apache.spark.mllib.tree.configuration.Algo._
 import org.apache.spark.rdd.RDD
 import org.apache.spark.mllib.linalg.Vector
@@ -28,6 +29,7 @@ import org.apache.spark.mllib.linalg.Vector
  * @param topNode root node
  * @param algo algorithm type -- classification or regression
  */
+@Experimental
 class DecisionTreeModel(val topNode: Node, val algo: Algo) extends Serializable {
 
   /**

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala
@@ -20,6 +20,7 @@ package org.apache.spark.mllib.util
 import breeze.linalg.{Vector => BV, DenseVector => BDV, SparseVector => BSV,
   squaredDistance => breezeSquaredDistance}
 
+import org.apache.spark.annotation.Experimental
 import org.apache.spark.SparkContext
 import org.apache.spark.rdd.RDD
 import org.apache.spark.mllib.regression.LabeledPoint
@@ -133,6 +134,7 @@ object MLUtils {
    * @return An RDD of LabeledPoint. Each labeled point has two elements: the first element is
    *         the label, and the second element represents the feature values (an array of Double).
    */
+  @Experimental
   def loadLabeledData(sc: SparkContext, dir: String): RDD[LabeledPoint] = {
     sc.textFile(dir).map { line =>
       val parts = line.split(',')
@@ -152,6 +154,7 @@ object MLUtils {
    * @param data An RDD of LabeledPoints containing data to be saved.
    * @param dir Directory to save the data.
    */
+  @Experimental
   def saveLabeledData(data: RDD[LabeledPoint], dir: String) {
     val dataStr = data.map(x => x.label + "," + x.features.toArray.mkString(" "))
     dataStr.saveAsTextFile(dir)