[SPARK-9704] [ML] Made ProbabilisticClassifier, Identifiable, VectorU…

…DT public APIs Made ProbabilisticClassifier, Identifiable, VectorUDT public. All are annotated as DeveloperApi. CC: mengxr EronWright Author: Joseph K. Bradley <[email protected]> Closes #8004 from jkbradley/ml-api-public-items and squashes the following commits: 7ebefda [Joseph K. Bradley] update per code review 7ff0768 [Joseph K. Bradley] attepting to add mima fix 756d84c [Joseph K. Bradley] VectorUDT annotated as AlphaComponent ae7767d [Joseph K. Bradley] added another warning 94fd553 [Joseph K. Bradley] Made ProbabilisticClassifier, Identifiable, VectorUDT public APIs
kiszk · Aug 13, 2015 · d2d5e7f · d2d5e7f
1 parent 4413d08
commit d2d5e7f
Show file tree

Hide file tree

Showing 4 changed files with 24 additions and 10 deletions.
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/ProbabilisticClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/ProbabilisticClassifier.scala
@@ -50,7 +50,7 @@ private[classification] trait ProbabilisticClassifierParams
  * @tparam M  Concrete Model type
  */
 @DeveloperApi
-private[spark] abstract class ProbabilisticClassifier[
+abstract class ProbabilisticClassifier[
     FeaturesType,
     E <: ProbabilisticClassifier[FeaturesType, E, M],
     M <: ProbabilisticClassificationModel[FeaturesType, M]]
@@ -74,7 +74,7 @@ private[spark] abstract class ProbabilisticClassifier[
  * @tparam M  Concrete Model type
  */
 @DeveloperApi
-private[spark] abstract class ProbabilisticClassificationModel[
+abstract class ProbabilisticClassificationModel[
     FeaturesType,
     M <: ProbabilisticClassificationModel[FeaturesType, M]]
   extends ClassificationModel[FeaturesType, M] with ProbabilisticClassifierParams {

diff --git a/mllib/src/main/scala/org/apache/spark/ml/util/Identifiable.scala b/mllib/src/main/scala/org/apache/spark/ml/util/Identifiable.scala
@@ -19,11 +19,19 @@ package org.apache.spark.ml.util
 
 import java.util.UUID
 
+import org.apache.spark.annotation.DeveloperApi
+
 
 /**
+ * :: DeveloperApi ::
+ *
  * Trait for an object with an immutable unique ID that identifies itself and its derivatives.
+ *
+ * WARNING: There have not yet been final discussions on this API, so it may be broken in future
+ *          releases.
  */
-private[spark] trait Identifiable {
+@DeveloperApi
+trait Identifiable {
 
   /**
    * An immutable unique ID for the object and its derivatives.
@@ -33,7 +41,11 @@ private[spark] trait Identifiable {
   override def toString: String = uid
 }
 
-private[spark] object Identifiable {
+/**
+ * :: DeveloperApi ::
+ */
+@DeveloperApi
+object Identifiable {
 
   /**
    * Returns a random UID that concatenates the given prefix, "_", and 12 random hex chars.

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala
@@ -26,7 +26,7 @@ import scala.collection.JavaConverters._
 import breeze.linalg.{DenseVector => BDV, SparseVector => BSV, Vector => BV}
 
 import org.apache.spark.SparkException
-import org.apache.spark.annotation.DeveloperApi
+import org.apache.spark.annotation.AlphaComponent
 import org.apache.spark.mllib.util.NumericParser
 import org.apache.spark.sql.catalyst.InternalRow
 import org.apache.spark.sql.catalyst.expressions.GenericMutableRow
@@ -159,15 +159,13 @@ sealed trait Vector extends Serializable {
 }
 
 /**
- * :: DeveloperApi ::
+ * :: AlphaComponent ::
  *
  * User-defined type for [[Vector]] which allows easy interaction with SQL
  * via [[org.apache.spark.sql.DataFrame]].
- *
- * NOTE: This is currently private[spark] but will be made public later once it is stabilized.
  */
-@DeveloperApi
-private[spark] class VectorUDT extends UserDefinedType[Vector] {
+@AlphaComponent
+class VectorUDT extends UserDefinedType[Vector] {
 
   override def sqlType: StructType = {
     // type: 0 = sparse, 1 = dense

diff --git a/project/MimaExcludes.scala b/project/MimaExcludes.scala
@@ -178,6 +178,10 @@ object MimaExcludes {
             // SPARK-4751 Dynamic allocation for standalone mode
             ProblemFilters.exclude[MissingMethodProblem](
               "org.apache.spark.SparkContext.supportDynamicAllocation")
+          ) ++ Seq(
+            // SPARK-9704 Made ProbabilisticClassifier, Identifiable, VectorUDT public APIs
+            ProblemFilters.exclude[IncompatibleResultTypeProblem](
+              "org.apache.spark.mllib.linalg.VectorUDT.serialize")
           )
 
         case v if v.startsWith("1.4") =>