diff options
author | Joseph K. Bradley <joseph@databricks.com> | 2016-07-13 12:33:39 -0700 |
---|---|---|
committer | Joseph K. Bradley <joseph@databricks.com> | 2016-07-13 12:33:39 -0700 |
commit | 01f09b161217193b797c8c85969d17054c958615 (patch) | |
tree | 40d7d4f5932157f8e0f0c13228dd18063728d4d3 /mllib/src/main | |
parent | d8220c1e5e94abbdb9643672b918f0d748206db9 (diff) | |
download | spark-01f09b161217193b797c8c85969d17054c958615.tar.gz spark-01f09b161217193b797c8c85969d17054c958615.tar.bz2 spark-01f09b161217193b797c8c85969d17054c958615.zip |
[SPARK-14812][ML][MLLIB][PYTHON] Experimental, DeveloperApi annotation audit for ML
## What changes were proposed in this pull request?
General decisions to follow, except where noted:
* spark.mllib, pyspark.mllib: Remove all Experimental annotations. Leave DeveloperApi annotations alone.
* spark.ml, pyspark.ml
** Annotate Estimator-Model pairs of classes and companion objects the same way.
** For all algorithms marked Experimental with Since tag <= 1.6, remove Experimental annotation.
** For all algorithms marked Experimental with Since tag = 2.0, leave Experimental annotation.
* DeveloperApi annotations are left alone, except where noted.
* No changes to which types are sealed.
Exceptions where I am leaving items Experimental in spark.ml, pyspark.ml, mainly because the items are new:
* Model Summary classes
* MLWriter, MLReader, MLWritable, MLReadable
* Evaluator and subclasses: There is discussion of changes around evaluating multiple metrics at once for efficiency.
* RFormula: Its behavior may need to change slightly to match R in edge cases.
* AFTSurvivalRegression
* MultilayerPerceptronClassifier
DeveloperApi changes:
* ml.tree.Node, ml.tree.Split, and subclasses should no longer be DeveloperApi
## How was this patch tested?
N/A
Note to reviewers:
* spark.ml.clustering.LDA underwent significant changes (additional methods), so let me know if you want me to leave it Experimental.
* Be careful to check for cases where a class should no longer be Experimental but has an Experimental method, val, or other feature. I did not find such cases, but please verify.
Author: Joseph K. Bradley <joseph@databricks.com>
Closes #14147 from jkbradley/experimental-audit.
Diffstat (limited to 'mllib/src/main')
60 files changed, 63 insertions, 271 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala b/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala index a1d08b3a6e..d18fb69799 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala @@ -27,7 +27,7 @@ import org.json4s._ import org.json4s.jackson.JsonMethods._ import org.apache.spark.SparkContext -import org.apache.spark.annotation.{DeveloperApi, Experimental, Since} +import org.apache.spark.annotation.{DeveloperApi, Since} import org.apache.spark.internal.Logging import org.apache.spark.ml.param.{Param, ParamMap, Params} import org.apache.spark.ml.util._ @@ -78,7 +78,6 @@ abstract class PipelineStage extends Params with Logging { } /** - * :: Experimental :: * A simple pipeline, which acts as an estimator. A Pipeline consists of a sequence of stages, each * of which is either an [[Estimator]] or a [[Transformer]]. When [[Pipeline#fit]] is called, the * stages are executed in order. If a stage is an [[Estimator]], its [[Estimator#fit]] method will @@ -90,7 +89,6 @@ abstract class PipelineStage extends Params with Logging { * an identity transformer. */ @Since("1.2.0") -@Experimental class Pipeline @Since("1.4.0") ( @Since("1.4.0") override val uid: String) extends Estimator[PipelineModel] with MLWritable { @@ -282,11 +280,9 @@ object Pipeline extends MLReadable[Pipeline] { } /** - * :: Experimental :: * Represents a fitted pipeline. */ @Since("1.2.0") -@Experimental class PipelineModel private[ml] ( @Since("1.4.0") override val uid: String, @Since("1.4.0") val stages: Array[Transformer]) diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala index c65d3d5b54..082848c9de 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala @@ -21,7 +21,7 @@ import org.apache.hadoop.fs.Path import org.json4s.{DefaultFormats, JObject} import org.json4s.JsonDSL._ -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.feature.LabeledPoint import org.apache.spark.ml.linalg.{DenseVector, SparseVector, Vector, Vectors} import org.apache.spark.ml.param.ParamMap @@ -36,14 +36,12 @@ import org.apache.spark.sql.Dataset /** - * :: Experimental :: * [[http://en.wikipedia.org/wiki/Decision_tree_learning Decision tree]] learning algorithm * for classification. * It supports both binary and multiclass labels, as well as both continuous and categorical * features. */ @Since("1.4.0") -@Experimental class DecisionTreeClassifier @Since("1.4.0") ( @Since("1.4.0") override val uid: String) extends ProbabilisticClassifier[Vector, DecisionTreeClassifier, DecisionTreeClassificationModel] @@ -127,7 +125,6 @@ class DecisionTreeClassifier @Since("1.4.0") ( } @Since("1.4.0") -@Experimental object DecisionTreeClassifier extends DefaultParamsReadable[DecisionTreeClassifier] { /** Accessor for supported impurities: entropy, gini */ @Since("1.4.0") @@ -138,13 +135,11 @@ object DecisionTreeClassifier extends DefaultParamsReadable[DecisionTreeClassifi } /** - * :: Experimental :: * [[http://en.wikipedia.org/wiki/Decision_tree_learning Decision tree]] model for classification. * It supports both binary and multiclass labels, as well as both continuous and categorical * features. */ @Since("1.4.0") -@Experimental class DecisionTreeClassificationModel private[ml] ( @Since("1.4.0")override val uid: String, @Since("1.4.0")override val rootNode: Node, diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala index 4e534baddc..5946a12933 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala @@ -21,7 +21,7 @@ import com.github.fommil.netlib.BLAS.{getInstance => blas} import org.json4s.{DefaultFormats, JObject} import org.json4s.JsonDSL._ -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.internal.Logging import org.apache.spark.ml.{PredictionModel, Predictor} import org.apache.spark.ml.feature.LabeledPoint @@ -40,7 +40,6 @@ import org.apache.spark.sql.functions._ import org.apache.spark.sql.types.DoubleType /** - * :: Experimental :: * [[http://en.wikipedia.org/wiki/Gradient_boosting Gradient-Boosted Trees (GBTs)]] * learning algorithm for classification. * It supports binary labels, as well as both continuous and categorical features. @@ -57,7 +56,6 @@ import org.apache.spark.sql.types.DoubleType * [https://issues.apache.org/jira/browse/SPARK-4240] */ @Since("1.4.0") -@Experimental class GBTClassifier @Since("1.4.0") ( @Since("1.4.0") override val uid: String) extends Predictor[Vector, GBTClassifier, GBTClassificationModel] @@ -149,7 +147,6 @@ class GBTClassifier @Since("1.4.0") ( } @Since("1.4.0") -@Experimental object GBTClassifier extends DefaultParamsReadable[GBTClassifier] { /** Accessor for supported loss settings: logistic */ @@ -161,7 +158,6 @@ object GBTClassifier extends DefaultParamsReadable[GBTClassifier] { } /** - * :: Experimental :: * [[http://en.wikipedia.org/wiki/Gradient_boosting Gradient-Boosted Trees (GBTs)]] * model for classification. * It supports binary labels, as well as both continuous and categorical features. @@ -171,7 +167,6 @@ object GBTClassifier extends DefaultParamsReadable[GBTClassifier] { * @param _treeWeights Weights for the decision trees in the ensemble. */ @Since("1.6.0") -@Experimental class GBTClassificationModel private[ml]( @Since("1.6.0") override val uid: String, private val _trees: Array[DecisionTreeRegressionModel], diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala index 9c9f5ced4e..e157bdeb5b 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala @@ -151,13 +151,11 @@ private[classification] trait LogisticRegressionParams extends ProbabilisticClas } /** - * :: Experimental :: * Logistic regression. * Currently, this class only supports binary classification. It will support multiclass * in the future. */ @Since("1.2.0") -@Experimental class LogisticRegression @Since("1.2.0") ( @Since("1.4.0") override val uid: String) extends ProbabilisticClassifier[Vector, LogisticRegression, LogisticRegressionModel] @@ -475,11 +473,9 @@ object LogisticRegression extends DefaultParamsReadable[LogisticRegression] { } /** - * :: Experimental :: * Model produced by [[LogisticRegression]]. */ @Since("1.4.0") -@Experimental class LogisticRegressionModel private[spark] ( @Since("1.4.0") override val uid: String, @Since("2.0.0") val coefficients: Vector, diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala index c99ae30155..ab977c8802 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala @@ -20,7 +20,7 @@ package org.apache.spark.ml.classification import org.apache.hadoop.fs.Path import org.apache.spark.SparkException -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.PredictorParams import org.apache.spark.ml.linalg._ import org.apache.spark.ml.param.{DoubleParam, Param, ParamMap, ParamValidators} @@ -63,7 +63,6 @@ private[ml] trait NaiveBayesParams extends PredictorParams { } /** - * :: Experimental :: * Naive Bayes Classifiers. * It supports both Multinomial NB * ([[http://nlp.stanford.edu/IR-book/html/htmledition/naive-bayes-text-classification-1.html]]) @@ -74,7 +73,6 @@ private[ml] trait NaiveBayesParams extends PredictorParams { * The input feature values must be nonnegative. */ @Since("1.5.0") -@Experimental class NaiveBayes @Since("1.5.0") ( @Since("1.5.0") override val uid: String) extends ProbabilisticClassifier[Vector, NaiveBayes, NaiveBayesModel] @@ -121,14 +119,12 @@ object NaiveBayes extends DefaultParamsReadable[NaiveBayes] { } /** - * :: Experimental :: * Model produced by [[NaiveBayes]] * @param pi log of class priors, whose dimension is C (number of classes) * @param theta log of class conditional probabilities, whose dimension is C (number of classes) * by D (number of features) */ @Since("1.5.0") -@Experimental class NaiveBayesModel private[ml] ( @Since("1.5.0") override val uid: String, @Since("2.0.0") val pi: Vector, diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala index 047a378b79..f4ab0a074c 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala @@ -29,7 +29,7 @@ import org.json4s.JsonDSL._ import org.json4s.jackson.JsonMethods._ import org.apache.spark.SparkContext -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml._ import org.apache.spark.ml.attribute._ import org.apache.spark.ml.linalg.Vector @@ -117,7 +117,6 @@ private[ml] object OneVsRestParams extends ClassifierTypeTrait { } /** - * :: Experimental :: * Model produced by [[OneVsRest]]. * This stores the models resulting from training k binary classifiers: one for each class. * Each example is scored against all k models, and the model with the highest score @@ -130,7 +129,6 @@ private[ml] object OneVsRestParams extends ClassifierTypeTrait { * (taking label 0). */ @Since("1.4.0") -@Experimental final class OneVsRestModel private[ml] ( @Since("1.4.0") override val uid: String, private[ml] val labelMetadata: Metadata, @@ -260,8 +258,6 @@ object OneVsRestModel extends MLReadable[OneVsRestModel] { } /** - * :: Experimental :: - * * Reduction of Multiclass Classification to Binary Classification. * Performs reduction using one against all strategy. * For a multiclass classification with k classes, train k models (one per class). @@ -269,7 +265,6 @@ object OneVsRestModel extends MLReadable[OneVsRestModel] { * is picked to label the example. */ @Since("1.4.0") -@Experimental final class OneVsRest @Since("1.4.0") ( @Since("1.4.0") override val uid: String) extends Estimator[OneVsRestModel] with OneVsRestParams with MLWritable { diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala index 9a26a5c5b1..4ab132e5f2 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala @@ -20,7 +20,7 @@ package org.apache.spark.ml.classification import org.json4s.{DefaultFormats, JObject} import org.json4s.JsonDSL._ -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.feature.LabeledPoint import org.apache.spark.ml.linalg.{DenseVector, SparseVector, Vector, Vectors} import org.apache.spark.ml.param.ParamMap @@ -36,14 +36,12 @@ import org.apache.spark.sql.functions._ /** - * :: Experimental :: * [[http://en.wikipedia.org/wiki/Random_forest Random Forest]] learning algorithm for * classification. * It supports both binary and multiclass labels, as well as both continuous and categorical * features. */ @Since("1.4.0") -@Experimental class RandomForestClassifier @Since("1.4.0") ( @Since("1.4.0") override val uid: String) extends ProbabilisticClassifier[Vector, RandomForestClassifier, RandomForestClassificationModel] @@ -124,7 +122,6 @@ class RandomForestClassifier @Since("1.4.0") ( } @Since("1.4.0") -@Experimental object RandomForestClassifier extends DefaultParamsReadable[RandomForestClassifier] { /** Accessor for supported impurity settings: entropy, gini */ @Since("1.4.0") @@ -140,7 +137,6 @@ object RandomForestClassifier extends DefaultParamsReadable[RandomForestClassifi } /** - * :: Experimental :: * [[http://en.wikipedia.org/wiki/Random_forest Random Forest]] model for classification. * It supports both binary and multiclass labels, as well as both continuous and categorical * features. @@ -149,7 +145,6 @@ object RandomForestClassifier extends DefaultParamsReadable[RandomForestClassifi * Warning: These have null parents. */ @Since("1.4.0") -@Experimental class RandomForestClassificationModel private[ml] ( @Since("1.5.0") override val uid: String, private val _trees: Array[DecisionTreeClassificationModel], 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 fa9634fdfa..2b0862c60f 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 @@ -19,7 +19,7 @@ package org.apache.spark.ml.feature import scala.collection.mutable.ArrayBuilder -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.Transformer import org.apache.spark.ml.attribute.BinaryAttribute import org.apache.spark.ml.linalg._ @@ -31,10 +31,8 @@ import org.apache.spark.sql.functions._ import org.apache.spark.sql.types._ /** - * :: Experimental :: * Binarize a column of continuous features given a threshold. */ -@Experimental @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 { 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 caffc39e2b..100d9e7f6c 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 @@ -20,7 +20,7 @@ package org.apache.spark.ml.feature import java.{util => ju} import org.apache.spark.SparkException -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.Model import org.apache.spark.ml.attribute.NominalAttribute import org.apache.spark.ml.param._ @@ -31,10 +31,8 @@ import org.apache.spark.sql.functions._ import org.apache.spark.sql.types.{DoubleType, StructField, StructType} /** - * :: Experimental :: * `Bucketizer` maps a column of continuous features to a column of feature buckets. */ -@Experimental @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 { 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 712634dffb..bd053e886f 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 @@ -19,7 +19,7 @@ package org.apache.spark.ml.feature import org.apache.hadoop.fs.Path -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml._ import org.apache.spark.ml.attribute.{AttributeGroup, _} import org.apache.spark.ml.linalg.{Vector, VectorUDT} @@ -57,11 +57,9 @@ private[feature] trait ChiSqSelectorParams extends Params } /** - * :: Experimental :: * Chi-Squared feature selection, which selects categorical features to use for predicting a * categorical label. */ -@Experimental @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 { @@ -116,10 +114,8 @@ object ChiSqSelector extends DefaultParamsReadable[ChiSqSelector] { } /** - * :: Experimental :: * Model fitted by [[ChiSqSelector]]. */ -@Experimental @Since("1.6.0") final class ChiSqSelectorModel private[ml] ( @Since("1.6.0") override val uid: String, 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 96e6f1c512..6299f74a6b 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 @@ -18,7 +18,7 @@ package org.apache.spark.ml.feature import org.apache.hadoop.fs.Path -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.broadcast.Broadcast import org.apache.spark.ml.{Estimator, Model} import org.apache.spark.ml.linalg.{Vectors, VectorUDT} @@ -116,10 +116,8 @@ private[feature] trait CountVectorizerParams extends Params with HasInputCol wit } /** - * :: Experimental :: * Extracts a vocabulary from document collections and generates a [[CountVectorizerModel]]. */ -@Experimental @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 { @@ -201,11 +199,9 @@ object CountVectorizer extends DefaultParamsReadable[CountVectorizer] { } /** - * :: Experimental :: * Converts a text document to a sparse vector of token counts. * @param vocabulary An Array over terms. Only the terms in the vocabulary will be counted. */ -@Experimental @Since("1.5.0") class CountVectorizerModel( @Since("1.5.0") override val uid: String, 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 9605145e12..6ff36b35ca 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 @@ -19,7 +19,7 @@ package org.apache.spark.ml.feature import edu.emory.mathcs.jtransforms.dct._ -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.UnaryTransformer import org.apache.spark.ml.linalg.{Vector, Vectors, VectorUDT} import org.apache.spark.ml.param.BooleanParam @@ -27,7 +27,6 @@ import org.apache.spark.ml.util._ import org.apache.spark.sql.types.DataType /** - * :: Experimental :: * A feature transformer that takes the 1D discrete cosine transform of a real vector. No zero * padding is performed on the input vector. * It returns a real vector of the same length representing the DCT. The return vector is scaled @@ -35,7 +34,6 @@ import org.apache.spark.sql.types.DataType * * More information on [[https://en.wikipedia.org/wiki/Discrete_cosine_transform#DCT-II Wikipedia]]. */ -@Experimental @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 { 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 d07833e580..f860b3a787 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 @@ -17,7 +17,7 @@ package org.apache.spark.ml.feature -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.UnaryTransformer import org.apache.spark.ml.linalg.{Vector, VectorUDT} import org.apache.spark.ml.param.Param @@ -27,12 +27,10 @@ import org.apache.spark.mllib.linalg.VectorImplicits._ import org.apache.spark.sql.types.DataType /** - * :: Experimental :: * Outputs the Hadamard product (i.e., the element-wise product) of each input vector with a * provided "weight" vector. In other words, it scales each column of the dataset by a scalar * multiplier. */ -@Experimental @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 { 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 6ca7336cd0..a8792a35ff 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 @@ -17,7 +17,7 @@ package org.apache.spark.ml.feature -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.Transformer import org.apache.spark.ml.attribute.AttributeGroup import org.apache.spark.ml.param._ @@ -29,7 +29,6 @@ import org.apache.spark.sql.functions.{col, udf} import org.apache.spark.sql.types.{ArrayType, StructType} /** - * :: Experimental :: * Maps a sequence of terms to their term frequencies using the hashing trick. * Currently we use Austin Appleby's MurmurHash 3 algorithm (MurmurHash3_x86_32) * to calculate the hash code value for the term object. @@ -37,7 +36,6 @@ import org.apache.spark.sql.types.{ArrayType, StructType} * it is advisable to use a power of two as the numFeatures parameter; * otherwise the features will not be mapped evenly to the columns. */ -@Experimental @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 { 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 5d6287f0e3..6386dd8a10 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 @@ -19,7 +19,7 @@ package org.apache.spark.ml.feature import org.apache.hadoop.fs.Path -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml._ import org.apache.spark.ml.linalg.{Vector, VectorUDT} import org.apache.spark.ml.param._ @@ -61,10 +61,8 @@ private[feature] trait IDFBase extends Params with HasInputCol with HasOutputCol } /** - * :: Experimental :: * Compute the Inverse Document Frequency (IDF) given a collection of documents. */ -@Experimental @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 { @@ -111,10 +109,8 @@ object IDF extends DefaultParamsReadable[IDF] { } /** - * :: Experimental :: * Model fitted by [[IDF]]. */ -@Experimental @Since("1.4.0") class IDFModel private[ml] ( @Since("1.4.0") override val uid: String, 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 dca28b5c5d..7b11f86279 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 @@ -20,7 +20,7 @@ package org.apache.spark.ml.feature import scala.collection.mutable.ArrayBuilder import org.apache.spark.SparkException -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.attribute._ import org.apache.spark.ml.param._ import org.apache.spark.ml.param.shared._ @@ -32,7 +32,6 @@ import org.apache.spark.sql.functions._ import org.apache.spark.sql.types._ /** - * :: Experimental :: * Implements the feature interaction transform. This transformer takes in Double and Vector type * columns and outputs a flattened vector of their feature interactions. To handle interaction, * we first one-hot encode any nominal features. Then, a vector of the feature cross-products is @@ -42,7 +41,6 @@ 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)`. */ -@Experimental @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 { diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/LabeledPoint.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/LabeledPoint.scala index f7f1d42039..6cefa7086c 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/LabeledPoint.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/LabeledPoint.scala @@ -23,6 +23,8 @@ import org.apache.spark.annotation.{Experimental, Since} import org.apache.spark.ml.linalg.Vector /** + * :: Experimental :: + * * Class that represents the features and labels of a data point. * * @param label Label for this data point. 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 d5ad5abced..7b03f0c0f3 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 @@ -19,7 +19,7 @@ package org.apache.spark.ml.feature import org.apache.hadoop.fs.Path -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.{Estimator, Model} import org.apache.spark.ml.linalg.{Vector, Vectors, VectorUDT} import org.apache.spark.ml.param.{DoubleParam, ParamMap, Params} @@ -74,7 +74,6 @@ private[feature] trait MinMaxScalerParams extends Params with HasInputCol with H } /** - * :: Experimental :: * Rescale each feature individually to a common range [min, max] linearly using column summary * statistics, which is also known as min-max normalization or Rescaling. The rescaled value for * feature E is calculated as, @@ -85,7 +84,6 @@ private[feature] trait MinMaxScalerParams extends Params with HasInputCol with H * Note that since zero values will probably be transformed to non-zero values, output of the * transformer will be DenseVector even for sparse input. */ -@Experimental @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 { @@ -138,7 +136,6 @@ object MinMaxScaler extends DefaultParamsReadable[MinMaxScaler] { } /** - * :: Experimental :: * Model fitted by [[MinMaxScaler]]. * * @param originalMin min value for each original column during fitting @@ -146,7 +143,6 @@ 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] ( @Since("1.5.0") override val uid: String, 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 9c1f1ad443..4463aea009 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 @@ -17,14 +17,13 @@ package org.apache.spark.ml.feature -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.UnaryTransformer import org.apache.spark.ml.param._ import org.apache.spark.ml.util._ import org.apache.spark.sql.types.{ArrayType, DataType, StringType} /** - * :: Experimental :: * A feature transformer that converts the input array of strings into an array of n-grams. Null * values in the input array are ignored. * It returns an array of n-grams where each n-gram is represented by a space-separated string of @@ -34,7 +33,6 @@ import org.apache.spark.sql.types.{ArrayType, DataType, StringType} * When the input array length is less than n (number of elements per n-gram), no n-grams are * returned. */ -@Experimental @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 { 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 f9cbad90c9..eb06900580 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 @@ -17,7 +17,7 @@ package org.apache.spark.ml.feature -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.UnaryTransformer import org.apache.spark.ml.linalg.{Vector, VectorUDT} import org.apache.spark.ml.param.{DoubleParam, ParamValidators} @@ -27,10 +27,8 @@ import org.apache.spark.mllib.linalg.{Vectors => OldVectors} import org.apache.spark.sql.types.DataType /** - * :: Experimental :: * 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) extends UnaryTransformer[Vector, Vector, Normalizer] with DefaultParamsWritable { 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 01828ede6b..8b04b5de6f 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 @@ -17,7 +17,7 @@ package org.apache.spark.ml.feature -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.Transformer import org.apache.spark.ml.attribute._ import org.apache.spark.ml.linalg.Vectors @@ -29,7 +29,6 @@ import org.apache.spark.sql.functions.{col, udf} import org.apache.spark.sql.types.{DoubleType, NumericType, StructType} /** - * :: Experimental :: * A one-hot encoder that maps a column of category indices to a column of binary vectors, with * at most a single one-value per row that indicates the input category index. * For example with 5 categories, an input value of 2.0 would map to an output vector of @@ -42,7 +41,6 @@ import org.apache.spark.sql.types.{DoubleType, NumericType, StructType} * * @see [[StringIndexer]] for converting categorical values into category indices */ -@Experimental @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 { 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 ef8b08545d..6b913480fd 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 @@ -19,7 +19,7 @@ package org.apache.spark.ml.feature import org.apache.hadoop.fs.Path -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml._ import org.apache.spark.ml.linalg._ import org.apache.spark.ml.param._ @@ -59,12 +59,11 @@ private[feature] trait PCAParams extends Params with HasInputCol with HasOutputC } } + /** - * :: Experimental :: * PCA trains a model to project vectors to a lower dimensional space of the top [[PCA!.k]] * principal components. */ -@Experimental @Since("1.5.0") class PCA @Since("1.5.0") ( @Since("1.5.0") override val uid: String) @@ -116,14 +115,12 @@ object PCA extends DefaultParamsReadable[PCA] { } /** - * :: Experimental :: * Model fitted by [[PCA]]. Transforms vectors to a lower dimensional space. * * @param pc A principal components Matrix. Each column is one principal component. * @param explainedVariance A vector of proportions of variance explained by * each principal component. */ -@Experimental @Since("1.5.0") class PCAModel private[ml] ( @Since("1.5.0") override val uid: String, 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 7b35fdeaf4..72fb35bd79 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 @@ -19,7 +19,7 @@ package org.apache.spark.ml.feature import scala.collection.mutable -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.UnaryTransformer import org.apache.spark.ml.linalg._ import org.apache.spark.ml.param.{IntParam, ParamMap, ParamValidators} @@ -27,14 +27,12 @@ import org.apache.spark.ml.util._ import org.apache.spark.sql.types.DataType /** - * :: Experimental :: * Perform feature expansion in a polynomial space. As said in wikipedia of Polynomial Expansion, * which is available at [[http://en.wikipedia.org/wiki/Polynomial_expansion]], "In mathematics, an * expansion of a product of sums expresses it as a sum of products by using the fact that * multiplication distributes over addition". Take a 2-variable feature vector as an example: * `(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) extends UnaryTransformer[Vector, Vector, PolynomialExpansion] with DefaultParamsWritable { 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 96b8e7d9f7..9a636bd8a5 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 @@ -17,7 +17,7 @@ package org.apache.spark.ml.feature -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.internal.Logging import org.apache.spark.ml._ import org.apache.spark.ml.attribute.NominalAttribute @@ -64,7 +64,6 @@ private[feature] trait QuantileDiscretizerBase extends Params } /** - * :: Experimental :: * `QuantileDiscretizer` takes a column with continuous features and outputs a column with binned * categorical features. The number of bins can be set using the `numBuckets` parameter. * The bin ranges are chosen using an approximate algorithm (see the documentation for @@ -73,7 +72,6 @@ private[feature] trait QuantileDiscretizerBase extends Params * `relativeError` parameter. The lower and upper bin bounds will be `-Infinity` and `+Infinity`, * covering all real values. */ -@Experimental @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 { 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 b8715746fe..289037640f 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 @@ -17,7 +17,7 @@ package org.apache.spark.ml.feature -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.param.{Param, ParamMap} import org.apache.spark.ml.Transformer import org.apache.spark.ml.util._ @@ -25,7 +25,6 @@ import org.apache.spark.sql.{DataFrame, Dataset, Row, SparkSession} import org.apache.spark.sql.types.StructType /** - * :: Experimental :: * Implements the transformations which are defined by SQL statement. * Currently we only support SQL syntax like 'SELECT ... FROM __THIS__ ...' * where '__THIS__' represents the underlying table of the input dataset. @@ -37,7 +36,6 @@ import org.apache.spark.sql.types.StructType * - SELECT a, SQRT(b) AS b_sqrt FROM __THIS__ where a > 5 * - SELECT a, b, SUM(c) AS c_sum FROM __THIS__ GROUP BY a, b */ -@Experimental @Since("1.6.0") class SQLTransformer @Since("1.6.0") (@Since("1.6.0") override val uid: String) extends Transformer with DefaultParamsWritable { 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 b4be95494f..2494cf51a2 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 @@ -19,7 +19,7 @@ package org.apache.spark.ml.feature import org.apache.hadoop.fs.Path -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml._ import org.apache.spark.ml.linalg.{Vector, VectorUDT} import org.apache.spark.ml.param._ @@ -76,7 +76,6 @@ private[feature] trait StandardScalerParams extends Params with HasInputCol with } /** - * :: Experimental :: * Standardizes features by removing the mean and scaling to unit variance using column summary * statistics on the samples in the training set. * @@ -85,7 +84,6 @@ private[feature] trait StandardScalerParams extends Params with HasInputCol with * corrected sample standard deviation]], * which is computed as the square root of the unbiased sample variance. */ -@Experimental @Since("1.2.0") class StandardScaler @Since("1.4.0") ( @Since("1.4.0") override val uid: String) @@ -138,13 +136,11 @@ object StandardScaler extends DefaultParamsReadable[StandardScaler] { } /** - * :: Experimental :: * Model fitted by [[StandardScaler]]. * * @param std Standard deviation of the StandardScalerModel * @param mean Mean of the StandardScalerModel */ -@Experimental @Since("1.2.0") class StandardScalerModel private[ml] ( @Since("1.4.0") override val uid: String, 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 1a6f42f773..666070037c 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 @@ -17,7 +17,7 @@ package org.apache.spark.ml.feature -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.Transformer import org.apache.spark.ml.param.{BooleanParam, ParamMap, StringArrayParam} import org.apache.spark.ml.param.shared.{HasInputCol, HasOutputCol} @@ -27,12 +27,10 @@ import org.apache.spark.sql.functions.{col, udf} import org.apache.spark.sql.types.{ArrayType, StringType, StructType} /** - * :: Experimental :: * A feature transformer that filters out stop words from input. * Note: null values from input array are preserved unless adding null to stopWords explicitly. * @see [[http://en.wikipedia.org/wiki/Stop_words]] */ -@Experimental @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 { 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 028e540fe5..fe79e2ec80 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 @@ -20,7 +20,7 @@ package org.apache.spark.ml.feature import org.apache.hadoop.fs.Path import org.apache.spark.SparkException -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.{Estimator, Model, Transformer} import org.apache.spark.ml.attribute.{Attribute, NominalAttribute} import org.apache.spark.ml.param._ @@ -55,7 +55,6 @@ private[feature] trait StringIndexerBase extends Params with HasInputCol with Ha } /** - * :: Experimental :: * A label indexer that maps a string column of labels to an ML column of label indices. * If the input column is numeric, we cast it to string and index the string values. * The indices are in [0, numLabels), ordered by label frequencies. @@ -63,7 +62,6 @@ private[feature] trait StringIndexerBase extends Params with HasInputCol with Ha * * @see [[IndexToString]] for the inverse transformation */ -@Experimental @Since("1.4.0") class StringIndexer @Since("1.4.0") ( @Since("1.4.0") override val uid: String) extends Estimator[StringIndexerModel] @@ -112,7 +110,6 @@ object StringIndexer extends DefaultParamsReadable[StringIndexer] { } /** - * :: Experimental :: * Model fitted by [[StringIndexer]]. * * NOTE: During transformation, if the input column does not exist, @@ -121,7 +118,6 @@ object StringIndexer extends DefaultParamsReadable[StringIndexer] { * * @param labels Ordered list of labels, corresponding to indices to be assigned. */ -@Experimental @Since("1.4.0") class StringIndexerModel ( @Since("1.4.0") override val uid: String, @@ -250,7 +246,6 @@ object StringIndexerModel extends MLReadable[StringIndexerModel] { } /** - * :: Experimental :: * A [[Transformer]] that maps a column of indices back to a new column of corresponding * string values. * The index-string mapping is either from the ML attributes of the input column, @@ -258,7 +253,6 @@ object StringIndexerModel extends MLReadable[StringIndexerModel] { * * @see [[StringIndexer]] for converting strings into indices */ -@Experimental @Since("1.5.0") class IndexToString private[ml] (@Since("1.5.0") override val uid: String) extends Transformer with HasInputCol with HasOutputCol 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 010c948749..45d8fa94a8 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 @@ -17,19 +17,17 @@ package org.apache.spark.ml.feature -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.UnaryTransformer import org.apache.spark.ml.param._ import org.apache.spark.ml.util._ import org.apache.spark.sql.types.{ArrayType, DataType, StringType} /** - * :: Experimental :: * A tokenizer that converts the input string to lowercase and then splits it by white spaces. * * @see [[RegexTokenizer]] */ -@Experimental @Since("1.2.0") class Tokenizer @Since("1.4.0") (@Since("1.4.0") override val uid: String) extends UnaryTransformer[String, Seq[String], Tokenizer] with DefaultParamsWritable { @@ -59,13 +57,11 @@ object Tokenizer extends DefaultParamsReadable[Tokenizer] { } /** - * :: Experimental :: * A regex based tokenizer that extracts tokens either by using the provided regex pattern to split * the text (default) or repeatedly matching the regex (if `gaps` is false). * Optional parameters also allow filtering tokens using a minimal length. * It returns an array of strings that can be empty. */ -@Experimental @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 { 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 4939dabd98..142a2ae44c 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 @@ -20,7 +20,7 @@ package org.apache.spark.ml.feature import scala.collection.mutable.ArrayBuilder import org.apache.spark.SparkException -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.Transformer import org.apache.spark.ml.attribute.{Attribute, AttributeGroup, NumericAttribute, UnresolvedAttribute} import org.apache.spark.ml.linalg.{Vector, Vectors, VectorUDT} @@ -32,10 +32,8 @@ import org.apache.spark.sql.functions._ import org.apache.spark.sql.types._ /** - * :: Experimental :: * A feature transformer that merges multiple columns into a vector column. */ -@Experimental @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 { 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 5656a9f979..d1a5c2e825 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 @@ -24,7 +24,7 @@ import scala.collection.JavaConverters._ import org.apache.hadoop.fs.Path -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.{Estimator, Model} import org.apache.spark.ml.attribute._ import org.apache.spark.ml.linalg.{DenseVector, SparseVector, Vector, VectorUDT} @@ -59,7 +59,6 @@ private[ml] trait VectorIndexerParams extends Params with HasInputCol with HasOu } /** - * :: Experimental :: * Class for indexing categorical feature columns in a dataset of [[Vector]]. * * This has 2 usage modes: @@ -93,7 +92,6 @@ private[ml] trait VectorIndexerParams extends Params with HasInputCol with HasOu * - Add warning if a categorical feature has only 1 category. * - Add option for allowing unknown categories. */ -@Experimental @Since("1.4.0") class VectorIndexer @Since("1.4.0") ( @Since("1.4.0") override val uid: String) @@ -247,7 +245,6 @@ object VectorIndexer extends DefaultParamsReadable[VectorIndexer] { } /** - * :: Experimental :: * Model fitted by [[VectorIndexer]]. Transform categorical features to use 0-based indices * instead of their original values. * - Categorical features are mapped to indices. @@ -263,7 +260,6 @@ object VectorIndexer extends DefaultParamsReadable[VectorIndexer] { * Values are maps from original features values to 0-based category indices. * If a feature is not in this map, it is treated as continuous. */ -@Experimental @Since("1.4.0") class VectorIndexerModel private[ml] ( @Since("1.4.0") override val uid: String, 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 6769e490c5..966ccb85d0 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 @@ -17,7 +17,7 @@ package org.apache.spark.ml.feature -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.Transformer import org.apache.spark.ml.attribute.{Attribute, AttributeGroup} import org.apache.spark.ml.linalg._ @@ -29,7 +29,6 @@ import org.apache.spark.sql.functions._ import org.apache.spark.sql.types.StructType /** - * :: Experimental :: * This class takes a feature vector and outputs a new feature vector with a subarray of the * original features. * @@ -40,7 +39,6 @@ import org.apache.spark.sql.types.StructType * The output vector will order features with the selected indices first (in the order given), * followed by the selected names (in the order given). */ -@Experimental @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 { 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 0cac3fa2d7..c2b434c3d5 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 @@ -19,8 +19,7 @@ package org.apache.spark.ml.feature import org.apache.hadoop.fs.Path -import org.apache.spark.SparkContext -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.{Estimator, Model} import org.apache.spark.ml.linalg.{BLAS, Vector, Vectors, VectorUDT} import org.apache.spark.ml.param._ @@ -115,11 +114,9 @@ private[feature] trait Word2VecBase extends Params } /** - * :: Experimental :: * Word2Vec trains a model of `Map(String, Vector)`, i.e. transforms a word into a code for further * natural language processing or machine learning process. */ -@Experimental @Since("1.4.0") final class Word2Vec @Since("1.4.0") ( @Since("1.4.0") override val uid: String) @@ -202,10 +199,8 @@ object Word2Vec extends DefaultParamsReadable[Word2Vec] { } /** - * :: Experimental :: * Model fitted by [[Word2Vec]]. */ -@Experimental @Since("1.4.0") class Word2VecModel private[ml] ( @Since("1.4.0") override val uid: String, diff --git a/mllib/src/main/scala/org/apache/spark/ml/param/params.scala b/mllib/src/main/scala/org/apache/spark/ml/param/params.scala index ecec61a72f..e7780cf1c3 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/param/params.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/param/params.scala @@ -28,9 +28,9 @@ import scala.collection.JavaConverters._ import org.json4s._ import org.json4s.jackson.JsonMethods._ -import org.apache.spark.annotation.{DeveloperApi, Experimental, Since} -import org.apache.spark.ml.linalg.{Vector, Vectors} +import org.apache.spark.annotation.{DeveloperApi, Since} import org.apache.spark.ml.linalg.JsonVectorConverter +import org.apache.spark.ml.linalg.Vector import org.apache.spark.ml.util.Identifiable /** @@ -510,11 +510,9 @@ class IntArrayParam(parent: Params, name: String, doc: String, isValid: Array[In } /** - * :: Experimental :: * A param and its value. */ @Since("1.2.0") -@Experimental case class ParamPair[T] @Since("1.2.0") ( @Since("1.2.0") param: Param[T], @Since("1.2.0") value: T) { @@ -797,11 +795,9 @@ trait Params extends Identifiable with Serializable { abstract class JavaParams extends Params /** - * :: Experimental :: * A param to value map. */ @Since("1.2.0") -@Experimental final class ParamMap private[ml] (private val map: mutable.Map[Param[Any], Any]) extends Serializable { @@ -952,7 +948,6 @@ final class ParamMap private[ml] (private val map: mutable.Map[Param[Any], Any]) } @Since("1.2.0") -@Experimental object ParamMap { /** diff --git a/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala b/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala index 5dc2433e55..a2c4c26911 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala @@ -26,12 +26,12 @@ import scala.util.{Sorting, Try} import scala.util.hashing.byteswap64 import com.github.fommil.netlib.BLAS.{getInstance => blas} -import org.apache.hadoop.fs.{FileSystem, Path} +import org.apache.hadoop.fs.Path import org.json4s.DefaultFormats import org.json4s.JsonDSL._ import org.apache.spark.{Dependency, Partitioner, ShuffleDependency, SparkContext} -import org.apache.spark.annotation.{DeveloperApi, Experimental, Since} +import org.apache.spark.annotation.{DeveloperApi, Since} import org.apache.spark.internal.Logging import org.apache.spark.ml.{Estimator, Model} import org.apache.spark.ml.param._ @@ -222,14 +222,12 @@ private[recommendation] trait ALSParams extends ALSModelParams with HasMaxIter w } /** - * :: Experimental :: * Model fitted by ALS. * * @param rank rank of the matrix factorization model * @param userFactors a DataFrame that stores user factors in two columns: `id` and `features` * @param itemFactors a DataFrame that stores item factors in two columns: `id` and `features` */ -@Experimental @Since("1.3.0") class ALSModel private[ml] ( @Since("1.4.0") override val uid: String, @@ -333,7 +331,6 @@ object ALSModel extends MLReadable[ALSModel] { } /** - * :: Experimental :: * Alternating Least Squares (ALS) matrix factorization. * * ALS attempts to estimate the ratings matrix `R` as the product of two lower-rank matrices, @@ -362,7 +359,6 @@ object ALSModel extends MLReadable[ALSModel] { * indicated user * preferences rather than explicit ratings given to items. */ -@Experimental @Since("1.3.0") class ALS(@Since("1.4.0") override val uid: String) extends Estimator[ALSModel] with ALSParams with DefaultParamsWritable { diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala index 7ff6d0afd5..ebc6c12ddc 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala @@ -21,7 +21,7 @@ import org.apache.hadoop.fs.Path import org.json4s.{DefaultFormats, JObject} import org.json4s.JsonDSL._ -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.{PredictionModel, Predictor} import org.apache.spark.ml.feature.LabeledPoint import org.apache.spark.ml.linalg.Vector @@ -38,13 +38,11 @@ import org.apache.spark.sql.functions._ /** - * :: Experimental :: * [[http://en.wikipedia.org/wiki/Decision_tree_learning Decision tree]] learning algorithm * for regression. * It supports both continuous and categorical features. */ @Since("1.4.0") -@Experimental class DecisionTreeRegressor @Since("1.4.0") (@Since("1.4.0") override val uid: String) extends Predictor[Vector, DecisionTreeRegressor, DecisionTreeRegressionModel] with DecisionTreeRegressorParams with DefaultParamsWritable { @@ -125,7 +123,6 @@ class DecisionTreeRegressor @Since("1.4.0") (@Since("1.4.0") override val uid: S } @Since("1.4.0") -@Experimental object DecisionTreeRegressor extends DefaultParamsReadable[DecisionTreeRegressor] { /** Accessor for supported impurities: variance */ final val supportedImpurities: Array[String] = TreeRegressorParams.supportedImpurities @@ -135,13 +132,11 @@ object DecisionTreeRegressor extends DefaultParamsReadable[DecisionTreeRegressor } /** - * :: Experimental :: * [[http://en.wikipedia.org/wiki/Decision_tree_learning Decision tree]] model for regression. * It supports both continuous and categorical features. * @param rootNode Root of the decision tree */ @Since("1.4.0") -@Experimental class DecisionTreeRegressionModel private[ml] ( override val uid: String, override val rootNode: Node, diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala index 6223555504..ce355938ec 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala @@ -38,7 +38,6 @@ import org.apache.spark.sql.{DataFrame, Dataset} import org.apache.spark.sql.functions._ /** - * :: Experimental :: * [[http://en.wikipedia.org/wiki/Gradient_boosting Gradient-Boosted Trees (GBTs)]] * learning algorithm for regression. * It supports both continuous and categorical features. @@ -56,7 +55,6 @@ import org.apache.spark.sql.functions._ * [https://issues.apache.org/jira/browse/SPARK-4240] */ @Since("1.4.0") -@Experimental class GBTRegressor @Since("1.4.0") (@Since("1.4.0") override val uid: String) extends Predictor[Vector, GBTRegressor, GBTRegressionModel] with GBTRegressorParams with DefaultParamsWritable with Logging { @@ -135,7 +133,6 @@ class GBTRegressor @Since("1.4.0") (@Since("1.4.0") override val uid: String) } @Since("1.4.0") -@Experimental object GBTRegressor extends DefaultParamsReadable[GBTRegressor] { /** Accessor for supported loss settings: squared (L2), absolute (L1) */ @@ -147,8 +144,6 @@ object GBTRegressor extends DefaultParamsReadable[GBTRegressor] { } /** - * :: Experimental :: - * * [[http://en.wikipedia.org/wiki/Gradient_boosting Gradient-Boosted Trees (GBTs)]] * model for regression. * It supports both continuous and categorical features. @@ -156,7 +151,6 @@ object GBTRegressor extends DefaultParamsReadable[GBTRegressor] { * @param _treeWeights Weights for the decision trees in the ensemble. */ @Since("1.4.0") -@Experimental class GBTRegressionModel private[ml]( override val uid: String, private val _trees: Array[DecisionTreeRegressionModel], diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/IsotonicRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/IsotonicRegression.scala index 9b9429a328..35396446ed 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/regression/IsotonicRegression.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/regression/IsotonicRegression.scala @@ -19,7 +19,7 @@ package org.apache.spark.ml.regression import org.apache.hadoop.fs.Path -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.internal.Logging import org.apache.spark.ml.{Estimator, Model} import org.apache.spark.ml.linalg.{Vector, Vectors, VectorUDT} @@ -120,7 +120,6 @@ private[regression] trait IsotonicRegressionBase extends Params with HasFeatures } /** - * :: Experimental :: * Isotonic regression. * * Currently implemented using parallelized pool adjacent violators algorithm. @@ -129,7 +128,6 @@ private[regression] trait IsotonicRegressionBase extends Params with HasFeatures * Uses [[org.apache.spark.mllib.regression.IsotonicRegression]]. */ @Since("1.5.0") -@Experimental class IsotonicRegression @Since("1.5.0") (@Since("1.5.0") override val uid: String) extends Estimator[IsotonicRegressionModel] with IsotonicRegressionBase with DefaultParamsWritable { @@ -192,7 +190,6 @@ object IsotonicRegression extends DefaultParamsReadable[IsotonicRegression] { } /** - * :: Experimental :: * Model fitted by IsotonicRegression. * Predicts using a piecewise linear function. * @@ -202,7 +199,6 @@ object IsotonicRegression extends DefaultParamsReadable[IsotonicRegression] { * model trained by [[org.apache.spark.mllib.regression.IsotonicRegression]]. */ @Since("1.5.0") -@Experimental class IsotonicRegressionModel private[ml] ( override val uid: String, private val oldModel: MLlibIsotonicRegressionModel) diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala index 6b82ae14e1..c57e9eb0bf 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala @@ -54,7 +54,6 @@ private[regression] trait LinearRegressionParams extends PredictorParams with HasFitIntercept with HasStandardization with HasWeightCol with HasSolver /** - * :: Experimental :: * Linear regression. * * The learning objective is to minimize the squared error, with regularization. @@ -68,7 +67,6 @@ private[regression] trait LinearRegressionParams extends PredictorParams * - L2 + L1 (elastic net) */ @Since("1.3.0") -@Experimental class LinearRegression @Since("1.3.0") (@Since("1.3.0") override val uid: String) extends Regressor[Vector, LinearRegression, LinearRegressionModel] with LinearRegressionParams with DefaultParamsWritable with Logging { @@ -387,11 +385,9 @@ object LinearRegression extends DefaultParamsReadable[LinearRegression] { } /** - * :: Experimental :: * Model produced by [[LinearRegression]]. */ @Since("1.3.0") -@Experimental class LinearRegressionModel private[ml] ( @Since("1.4.0") override val uid: String, @Since("2.0.0") val coefficients: Vector, diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala index 4f4d3d2784..0ad00aa6f9 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala @@ -20,7 +20,7 @@ package org.apache.spark.ml.regression import org.json4s.{DefaultFormats, JObject} import org.json4s.JsonDSL._ -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.{PredictionModel, Predictor} import org.apache.spark.ml.feature.LabeledPoint import org.apache.spark.ml.linalg.Vector @@ -37,12 +37,10 @@ import org.apache.spark.sql.functions._ /** - * :: Experimental :: * [[http://en.wikipedia.org/wiki/Random_forest Random Forest]] learning algorithm for regression. * It supports both continuous and categorical features. */ @Since("1.4.0") -@Experimental class RandomForestRegressor @Since("1.4.0") (@Since("1.4.0") override val uid: String) extends Predictor[Vector, RandomForestRegressor, RandomForestRegressionModel] with RandomForestRegressorParams with DefaultParamsWritable { @@ -118,7 +116,6 @@ class RandomForestRegressor @Since("1.4.0") (@Since("1.4.0") override val uid: S } @Since("1.4.0") -@Experimental object RandomForestRegressor extends DefaultParamsReadable[RandomForestRegressor]{ /** Accessor for supported impurity settings: variance */ @Since("1.4.0") @@ -135,7 +132,6 @@ object RandomForestRegressor extends DefaultParamsReadable[RandomForestRegressor } /** - * :: Experimental :: * [[http://en.wikipedia.org/wiki/Random_forest Random Forest]] model for regression. * It supports both continuous and categorical features. * @@ -143,7 +139,6 @@ object RandomForestRegressor extends DefaultParamsReadable[RandomForestRegressor * @param numFeatures Number of features used by this model */ @Since("1.4.0") -@Experimental class RandomForestRegressionModel private[ml] ( override val uid: String, private val _trees: Array[DecisionTreeRegressionModel], diff --git a/mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala b/mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala index d5e5c45460..8144bcb7d4 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala @@ -17,17 +17,14 @@ package org.apache.spark.ml.tree -import org.apache.spark.annotation.DeveloperApi import org.apache.spark.ml.linalg.Vector import org.apache.spark.mllib.tree.impurity.ImpurityCalculator import org.apache.spark.mllib.tree.model.{ImpurityStats, InformationGainStats => OldInformationGainStats, Node => OldNode, Predict => OldPredict} /** - * :: DeveloperApi :: * Decision tree node interface. */ -@DeveloperApi sealed abstract class Node extends Serializable { // TODO: Add aggregate stats (once available). This will happen after we move the DecisionTree @@ -109,12 +106,10 @@ private[ml] object Node { } /** - * :: DeveloperApi :: * Decision tree leaf node. * @param prediction Prediction this node makes * @param impurity Impurity measure at this node (for training data) */ -@DeveloperApi class LeafNode private[ml] ( override val prediction: Double, override val impurity: Double, @@ -147,7 +142,6 @@ class LeafNode private[ml] ( } /** - * :: DeveloperApi :: * Internal Decision Tree node. * @param prediction Prediction this node would make if it were a leaf node * @param impurity Impurity measure at this node (for training data) @@ -157,7 +151,6 @@ class LeafNode private[ml] ( * @param rightChild Right-hand child node * @param split Information about the test used to split to the left or right child. */ -@DeveloperApi class InternalNode private[ml] ( override val prediction: Double, override val impurity: Double, @@ -167,6 +160,9 @@ class InternalNode private[ml] ( val split: Split, override private[ml] val impurityStats: ImpurityCalculator) extends Node { + // Note to developers: The constructor argument impurityStats should be reconsidered before we + // make the constructor public. We may be able to improve the representation. + override def toString: String = { s"InternalNode(prediction = $prediction, impurity = $impurity, split = $split)" } diff --git a/mllib/src/main/scala/org/apache/spark/ml/tree/Split.scala b/mllib/src/main/scala/org/apache/spark/ml/tree/Split.scala index 9704e15cd8..47fe3524f2 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/tree/Split.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/tree/Split.scala @@ -19,18 +19,16 @@ package org.apache.spark.ml.tree import java.util.Objects -import org.apache.spark.annotation.{DeveloperApi, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.linalg.Vector import org.apache.spark.mllib.tree.configuration.{FeatureType => OldFeatureType} import org.apache.spark.mllib.tree.model.{Split => OldSplit} /** - * :: DeveloperApi :: * Interface for a "Split," which specifies a test made at a decision tree node * to choose the left or right path. */ -@DeveloperApi sealed trait Split extends Serializable { /** Index of feature which this split tests */ @@ -67,14 +65,12 @@ private[tree] object Split { } /** - * :: DeveloperApi :: * Split which tests a categorical feature. * @param featureIndex Index of the feature to test * @param _leftCategories If the feature value is in this set of categories, then the split goes * left. Otherwise, it goes right. * @param numCategories Number of categories for this feature. */ -@DeveloperApi class CategoricalSplit private[ml] ( override val featureIndex: Int, _leftCategories: Array[Double], @@ -153,13 +149,11 @@ class CategoricalSplit private[ml] ( } /** - * :: DeveloperApi :: * Split which tests a continuous feature. * @param featureIndex Index of the feature to test * @param threshold If the feature value is <= this threshold, then the split goes left. * Otherwise, it goes right. */ -@DeveloperApi class ContinuousSplit private[ml] (override val featureIndex: Int, val threshold: Double) extends Split { diff --git a/mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala b/mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala index 7d42da4a2f..520557849b 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala @@ -25,7 +25,7 @@ import com.github.fommil.netlib.F2jBLAS import org.apache.hadoop.fs.Path import org.json4s.DefaultFormats -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.internal.Logging import org.apache.spark.ml._ import org.apache.spark.ml.evaluation.Evaluator @@ -55,11 +55,9 @@ private[ml] trait CrossValidatorParams extends ValidatorParams { } /** - * :: Experimental :: * K-fold cross validation. */ @Since("1.2.0") -@Experimental class CrossValidator @Since("1.2.0") (@Since("1.4.0") override val uid: String) extends Estimator[CrossValidatorModel] with CrossValidatorParams with MLWritable with Logging { @@ -190,7 +188,6 @@ object CrossValidator extends MLReadable[CrossValidator] { } /** - * :: Experimental :: * Model from k-fold cross validation. * * @param bestModel The best model selected from k-fold cross validation. @@ -198,7 +195,6 @@ object CrossValidator extends MLReadable[CrossValidator] { * [[CrossValidator.estimatorParamMaps]], in the corresponding order. */ @Since("1.2.0") -@Experimental class CrossValidatorModel private[ml] ( @Since("1.4.0") override val uid: String, @Since("1.2.0") val bestModel: Model[_], diff --git a/mllib/src/main/scala/org/apache/spark/ml/tuning/ParamGridBuilder.scala b/mllib/src/main/scala/org/apache/spark/ml/tuning/ParamGridBuilder.scala index 7d12f447f7..d369e7a61c 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/tuning/ParamGridBuilder.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/tuning/ParamGridBuilder.scala @@ -20,15 +20,13 @@ package org.apache.spark.ml.tuning import scala.annotation.varargs import scala.collection.mutable -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.ml.param._ /** - * :: Experimental :: * Builder for a param grid used in grid search-based model selection. */ @Since("1.2.0") -@Experimental class ParamGridBuilder @Since("1.2.0") { private val paramGrid = mutable.Map.empty[Param[_], Iterable[_]] diff --git a/mllib/src/main/scala/org/apache/spark/ml/tuning/TrainValidationSplit.scala b/mllib/src/main/scala/org/apache/spark/ml/tuning/TrainValidationSplit.scala index f6f2bad401..0fdba1cb88 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/tuning/TrainValidationSplit.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/tuning/TrainValidationSplit.scala @@ -25,7 +25,7 @@ import scala.language.existentials import org.apache.hadoop.fs.Path import org.json4s.DefaultFormats -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.internal.Logging import org.apache.spark.ml.{Estimator, Model} import org.apache.spark.ml.evaluation.Evaluator @@ -54,14 +54,12 @@ private[ml] trait TrainValidationSplitParams extends ValidatorParams { } /** - * :: Experimental :: * Validation for hyper-parameter tuning. * Randomly splits the input dataset into train and validation sets, * and uses evaluation metric on the validation set to select the best model. * Similar to [[CrossValidator]], but only splits the set once. */ @Since("1.5.0") -@Experimental class TrainValidationSplit @Since("1.5.0") (@Since("1.5.0") override val uid: String) extends Estimator[TrainValidationSplitModel] with TrainValidationSplitParams with MLWritable with Logging { @@ -188,7 +186,6 @@ object TrainValidationSplit extends MLReadable[TrainValidationSplit] { } /** - * :: Experimental :: * Model from train validation split. * * @param uid Id. @@ -196,7 +193,6 @@ object TrainValidationSplit extends MLReadable[TrainValidationSplit] { * @param validationMetrics Evaluated validation metrics. */ @Since("1.5.0") -@Experimental class TrainValidationSplitModel private[ml] ( @Since("1.5.0") override val uid: String, @Since("1.5.0") val bestModel: Model[_], diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeans.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeans.scala index 91edcf2a79..f1664ce4ab 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeans.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeans.scala @@ -22,7 +22,7 @@ import java.util.Random import scala.annotation.tailrec import scala.collection.mutable -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.api.java.JavaRDD import org.apache.spark.internal.Logging import org.apache.spark.mllib.linalg.{BLAS, Vector, Vectors} @@ -31,8 +31,6 @@ import org.apache.spark.rdd.RDD import org.apache.spark.storage.StorageLevel /** - * :: Experimental :: - * * A bisecting k-means algorithm based on the paper "A comparison of document clustering techniques" * by Steinbach, Karypis, and Kumar, with modification to fit Spark. * The algorithm starts from a single cluster that contains all points. @@ -54,7 +52,6 @@ import org.apache.spark.storage.StorageLevel * KDD Workshop on Text Mining, 2000.]] */ @Since("1.6.0") -@Experimental class BisectingKMeans private ( private var k: Int, private var maxIterations: Int, @@ -398,8 +395,6 @@ private object BisectingKMeans extends Serializable { } /** - * :: Experimental :: - * * Represents a node in a clustering tree. * * @param index node index, negative for internal nodes and non-negative for leaf nodes @@ -411,7 +406,6 @@ private object BisectingKMeans extends Serializable { * @param children children nodes */ @Since("1.6.0") -@Experimental private[clustering] class ClusteringTreeNode private[clustering] ( val index: Int, val size: Long, diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala index 11fd940b8b..8438015cce 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/BisectingKMeansModel.scala @@ -23,7 +23,7 @@ import org.json4s.jackson.JsonMethods._ import org.json4s.JsonDSL._ import org.apache.spark.SparkContext -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.api.java.JavaRDD import org.apache.spark.internal.Logging import org.apache.spark.mllib.linalg.Vector @@ -32,8 +32,6 @@ import org.apache.spark.rdd.RDD import org.apache.spark.sql.{Row, SparkSession} /** - * :: Experimental :: - * * Clustering model produced by [[BisectingKMeans]]. * The prediction is done level-by-level from the root node to a leaf node, and at each node among * its children the closest to the input point is selected. @@ -41,7 +39,6 @@ import org.apache.spark.sql.{Row, SparkSession} * @param root the root node of the clustering tree */ @Since("1.6.0") -@Experimental class BisectingKMeansModel private[clustering] ( private[clustering] val root: ClusteringTreeNode ) extends Serializable with Saveable with Logging { diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala index d295826300..9ebba1de0d 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala @@ -25,7 +25,7 @@ import org.json4s.JsonDSL._ import org.json4s.jackson.JsonMethods._ import org.apache.spark.SparkContext -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.api.java.{JavaPairRDD, JavaRDD} import org.apache.spark.graphx.{Edge, EdgeContext, Graph, VertexId} import org.apache.spark.mllib.linalg.{Matrices, Matrix, Vector, Vectors} @@ -426,13 +426,10 @@ class LocalLDAModel private[spark] ( } /** - * :: Experimental :: - * * Local (non-distributed) model fitted by [[LDA]]. * * This model stores the inferred topics only; it does not store info about the training dataset. */ -@Experimental @Since("1.5.0") object LocalLDAModel extends Loader[LocalLDAModel] { @@ -822,15 +819,12 @@ class DistributedLDAModel private[clustering] ( } /** - * :: Experimental :: - * * Distributed model fitted by [[LDA]]. * This type of model is currently only produced by Expectation-Maximization (EM). * * This model stores the inferred topics, the full training dataset, and the topic distribution * for each training document. */ -@Experimental @Since("1.5.0") object DistributedLDAModel extends Loader[DistributedLDAModel] { diff --git a/mllib/src/main/scala/org/apache/spark/mllib/fpm/AssociationRules.scala b/mllib/src/main/scala/org/apache/spark/mllib/fpm/AssociationRules.scala index 9a63cc29da..3c26d26708 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/fpm/AssociationRules.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/fpm/AssociationRules.scala @@ -19,7 +19,7 @@ package org.apache.spark.mllib.fpm import scala.collection.JavaConverters._ import scala.reflect.ClassTag -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.api.java.JavaRDD import org.apache.spark.api.java.JavaSparkContext.fakeClassTag import org.apache.spark.internal.Logging @@ -28,14 +28,11 @@ import org.apache.spark.mllib.fpm.FPGrowth.FreqItemset import org.apache.spark.rdd.RDD /** - * :: Experimental :: - * * Generates association rules from a [[RDD[FreqItemset[Item]]]. This method only generates * association rules which have a single item as the consequent. * */ @Since("1.5.0") -@Experimental class AssociationRules private[fpm] ( private var minConfidence: Double) extends Logging with Serializable { @@ -95,8 +92,6 @@ class AssociationRules private[fpm] ( object AssociationRules { /** - * :: Experimental :: - * * An association rule between sets of items. * @param antecedent hypotheses of the rule. Java users should call [[Rule#javaAntecedent]] * instead. @@ -106,7 +101,6 @@ object AssociationRules { * */ @Since("1.5.0") - @Experimental class Rule[Item] private[fpm] ( @Since("1.5.0") val antecedent: Array[Item], @Since("1.5.0") val consequent: Array[Item], diff --git a/mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala b/mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala index c13c794775..7382000791 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/fpm/PrefixSpan.scala @@ -30,7 +30,7 @@ import org.json4s.JsonDSL._ import org.json4s.jackson.JsonMethods.{compact, render} import org.apache.spark.SparkContext -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.api.java.JavaRDD import org.apache.spark.api.java.JavaSparkContext.fakeClassTag import org.apache.spark.internal.Logging @@ -42,8 +42,6 @@ import org.apache.spark.sql.types._ import org.apache.spark.storage.StorageLevel /** - * :: Experimental :: - * * A parallel PrefixSpan algorithm to mine frequent sequential patterns. * The PrefixSpan algorithm is described in J. Pei, et al., PrefixSpan: Mining Sequential Patterns * Efficiently by Prefix-Projected Pattern Growth ([[http://doi.org/10.1109/ICDE.2001.914830]]). @@ -60,7 +58,6 @@ import org.apache.spark.storage.StorageLevel * @see [[https://en.wikipedia.org/wiki/Sequential_Pattern_Mining Sequential Pattern Mining * (Wikipedia)]] */ -@Experimental @Since("1.5.0") class PrefixSpan private ( private var minSupport: Double, @@ -230,7 +227,6 @@ class PrefixSpan private ( } -@Experimental @Since("1.5.0") object PrefixSpan extends Logging { diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/SingularValueDecomposition.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/SingularValueDecomposition.scala index 4591cb88ef..8024b1c003 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/SingularValueDecomposition.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/SingularValueDecomposition.scala @@ -17,7 +17,7 @@ package org.apache.spark.mllib.linalg -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since /** * Represents singular value decomposition (SVD) factors. @@ -26,10 +26,8 @@ import org.apache.spark.annotation.{Experimental, Since} case class SingularValueDecomposition[UType, VType](U: UType, s: Vector, V: VType) /** - * :: Experimental :: * Represents QR factors. */ @Since("1.5.0") -@Experimental case class QRDecomposition[QType, RType](Q: QType, R: RType) diff --git a/mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala b/mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala index 480a64548c..f372355005 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/optimization/GradientDescent.scala @@ -21,7 +21,7 @@ import scala.collection.mutable.ArrayBuffer import breeze.linalg.{norm, DenseVector => BDV} -import org.apache.spark.annotation.{DeveloperApi, Experimental} +import org.apache.spark.annotation.DeveloperApi import org.apache.spark.internal.Logging import org.apache.spark.mllib.linalg.{Vector, Vectors} import org.apache.spark.rdd.RDD @@ -53,11 +53,9 @@ class GradientDescent private[spark] (private var gradient: Gradient, private va } /** - * :: Experimental :: * Set fraction of data to be used for each SGD iteration. * Default 1.0 (corresponding to deterministic/classical gradient descent) */ - @Experimental def setMiniBatchFraction(fraction: Double): this.type = { require(fraction > 0 && fraction <= 1.0, s"Fraction for mini-batch SGD must be in range (0, 1] but got ${fraction}") diff --git a/mllib/src/main/scala/org/apache/spark/mllib/pmml/PMMLExportable.scala b/mllib/src/main/scala/org/apache/spark/mllib/pmml/PMMLExportable.scala index 274ac7c995..5d61796f1d 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/pmml/PMMLExportable.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/pmml/PMMLExportable.scala @@ -23,7 +23,7 @@ import javax.xml.transform.stream.StreamResult import org.jpmml.model.JAXBUtil import org.apache.spark.SparkContext -import org.apache.spark.annotation.{DeveloperApi, Experimental, Since} +import org.apache.spark.annotation.{DeveloperApi, Since} import org.apache.spark.mllib.pmml.export.PMMLModelExportFactory /** @@ -45,20 +45,16 @@ trait PMMLExportable { } /** - * :: Experimental :: * Export the model to a local file in PMML format */ - @Experimental @Since("1.4.0") def toPMML(localPath: String): Unit = { toPMML(new StreamResult(new File(localPath))) } /** - * :: Experimental :: * Export the model to a directory on a distributed file system in PMML format */ - @Experimental @Since("1.4.0") def toPMML(sc: SparkContext, path: String): Unit = { val pmml = toPMML() @@ -66,20 +62,16 @@ trait PMMLExportable { } /** - * :: Experimental :: * Export the model to the OutputStream in PMML format */ - @Experimental @Since("1.4.0") def toPMML(outputStream: OutputStream): Unit = { toPMML(new StreamResult(outputStream)) } /** - * :: Experimental :: * Export the model to a String in PMML format */ - @Experimental @Since("1.4.0") def toPMML(): String = { val writer = new StringWriter diff --git a/mllib/src/main/scala/org/apache/spark/mllib/stat/test/StreamingTest.scala b/mllib/src/main/scala/org/apache/spark/mllib/stat/test/StreamingTest.scala index 4c382d7c2b..97c032de7a 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/stat/test/StreamingTest.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/stat/test/StreamingTest.scala @@ -19,7 +19,7 @@ package org.apache.spark.mllib.stat.test import scala.beans.BeanInfo -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since import org.apache.spark.internal.Logging import org.apache.spark.streaming.api.java.JavaDStream import org.apache.spark.streaming.dstream.DStream @@ -42,7 +42,6 @@ case class BinarySample @Since("1.6.0") ( } /** - * :: Experimental :: * Performs online 2-sample significance testing for a stream of (Boolean, Double) pairs. The * Boolean identifies which sample each observation comes from, and the Double is the numeric value * of the observation. @@ -67,7 +66,6 @@ case class BinarySample @Since("1.6.0") ( * .registerStream(DStream) * }}} */ -@Experimental @Since("1.6.0") class StreamingTest @Since("1.6.0") () extends Logging with Serializable { private var peacePeriod: Int = 0 diff --git a/mllib/src/main/scala/org/apache/spark/mllib/stat/test/TestResult.scala b/mllib/src/main/scala/org/apache/spark/mllib/stat/test/TestResult.scala index 8a29fd39a9..5cfc05a3dd 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/stat/test/TestResult.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/stat/test/TestResult.scala @@ -17,7 +17,7 @@ package org.apache.spark.mllib.stat.test -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since /** * Trait for hypothesis test results. @@ -94,10 +94,8 @@ class ChiSqTestResult private[stat] (override val pValue: Double, } /** - * :: Experimental :: * Object containing the test results for the Kolmogorov-Smirnov test. */ -@Experimental @Since("1.5.0") class KolmogorovSmirnovTestResult private[stat] ( @Since("1.5.0") override val pValue: Double, @@ -113,10 +111,8 @@ class KolmogorovSmirnovTestResult private[stat] ( } /** - * :: Experimental :: * Object containing the test results for streaming testing. */ -@Experimental @Since("1.6.0") private[stat] class StreamingTestResult @Since("1.6.0") ( @Since("1.6.0") override val pValue: Double, 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 index 853c7319ec..2436ce4086 100644 --- 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 @@ -17,14 +17,12 @@ package org.apache.spark.mllib.tree.configuration -import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.annotation.Since /** - * :: Experimental :: * Enum to select the algorithm for the decision tree */ @Since("1.0.0") -@Experimental object Algo extends Enumeration { @Since("1.0.0") type Algo = Value 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 index 3a731f45d6..d4448da9ee 100644 --- 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 +17,12 @@ package org.apache.spark.mllib.tree.impurity -import org.apache.spark.annotation.{DeveloperApi, Experimental, Since} +import org.apache.spark.annotation.{DeveloperApi, Since} /** - * :: Experimental :: * Class for calculating entropy during multiclass classification. */ @Since("1.0.0") -@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 index 7730c0a8c1..22e70278a6 100644 --- 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 @@ -17,16 +17,14 @@ package org.apache.spark.mllib.tree.impurity -import org.apache.spark.annotation.{DeveloperApi, Experimental, Since} +import org.apache.spark.annotation.{DeveloperApi, Since} /** - * :: Experimental :: * Class for calculating the * [[http://en.wikipedia.org/wiki/Decision_tree_learning#Gini_impurity Gini impurity]] * during multiclass classification. */ @Since("1.0.0") -@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 index 65f0163ec6..a5bdc2c6d2 100644 --- 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 @@ -17,17 +17,15 @@ package org.apache.spark.mllib.tree.impurity -import org.apache.spark.annotation.{DeveloperApi, Experimental, Since} +import org.apache.spark.annotation.{DeveloperApi, Since} /** - * :: Experimental :: * Trait for calculating information gain. * This trait is used for * (a) setting the impurity parameter in [[org.apache.spark.mllib.tree.configuration.Strategy]] * (b) calculating impurity values from sufficient statistics. */ @Since("1.0.0") -@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 index 2423516123..c9bf0db4de 100644 --- 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 @@ -17,14 +17,12 @@ package org.apache.spark.mllib.tree.impurity -import org.apache.spark.annotation.{DeveloperApi, Experimental, Since} +import org.apache.spark.annotation.{DeveloperApi, Since} /** - * :: Experimental :: * Class for calculating variance during regression */ @Since("1.0.0") -@Experimental object Variance extends Impurity { /** |